@Article{info:doi/10.2196/15236, author="Zelkowitz, Phyllis and Miner, Skye and O'Connell, Siobhan and Robins, Stephanie", title="An mHealth App Designed for Fertility Patients: From Conception to Pilot Testing", journal="iproc", year="2019", month="Oct", day="4", volume="5", number="1", pages="e15236", keywords="infertility", keywords="mobile health (mHealth)", keywords="online information", keywords="peer support", abstract="Background: Infertility is a distressing chronic condition affecting one in six couples; many of them seek to achieve a pregnancy via assisted reproductive technologies. Online resources for information and support are a mainstay of the self-help strategies of fertility patients. Patients seek explanations online about their diagnoses and treatment options, and hope to connect with others who have lived through a diagnosis of infertility. However, medical information found online is often inaccurate or hard to understand. Importantly, online forums that might provide social support are seldom monitored, allowing for the dissemination of potentially misleading information. In this study we describe the development of an mHealth app, Infotility, designed to provide evidence-based reproductive health information and a monitored message board to provide social support to users. Objective: The objective was to describe the steps involved in the production of an mHealth app created specifically for fertility patients. Methods: Our team followed guidelines established for the development of complex health interventions. To evaluate the existing online information sources, we assessed web-based information on infertility using standardized tools for readability, suitability and quality. To determine our stakeholders' perspectives on what content to include in the app, a needs assessment survey was conducted in a sample of 289 male and 370 female fertility patients and 127 health care providers at clinics in Montreal and Toronto. A comprehensive review of the literature on the medical and psychosocial aspects of infertility was undertaken; summaries were then reviewed for accuracy and pertinence by patients, clinicians, researchers and professionals in the field of fertility. A technology partner was hired to create a user-friendly mobile app that contained the informational summaries, with separate portals for men and women, leading to content specifically curated for the user's interests. There was also a closed discussion platform, ``Connect'', monitored by 18 previous or current fertility patients. Peer monitors underwent one-on-one training and received an instructional manual created to assist with responding to forum messages from participants. Between November 2018 and April 2019, the app was pilot tested in a sample of 72 male and 187 female fertility patients to assess feasibility of recruitment, acceptability, and user satisfaction. Results: Initial results show that men and women appreciated Infotility. The most popular sections included information on modifiable lifestyle risks (eg, diet, exercise, environment), and medical and psychosocial information. Men preferentially visited pages about lifestyle factors whereas the most common pages visited by women related to medical information. Importantly, the ``Connect'' social network logged 39 open forum conversations with 258 total posts, as well as 14 private messages. Both men and women lurked and posted on the board; women posted more often than men. Conclusions: The design of a mobile health app for fertility patients should consider user experience and design along with the quality and accessibility of information. A fertility mHealth app should provide access to monitored social support through the interface and consider how to effectively tailor information to men and women. ", doi="10.2196/15236", url="http://www.iproc.org/2019/1/e15236/" } @Article{info:doi/10.2196/16305, author="Biernat, Lisa and Milliren, E. Carly and Rauen, Jon and Lindsay, Bill and Weaver, Betsy and Smith, Todd", title="Improving Orthopedic Care Delivery Through Digital Engagement", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e16305", keywords="mobile technology", keywords="patient activation", keywords="patient education", keywords="digital engagement", abstract="Background: Patient activation has been hypothesized to improve medical and surgical outcomes by increasing patient involvement in the care plan. We tested this hypothesis by utilizing a patient activation tool in a population of adults having total hip or total knee replacement. We hypothesized that patient activation would be associated with increased discharge to home as opposed to a skilled nursing facility, reduced hospital length of stay, decreased inpatient readmissions, and decreased emergency department (ED) visits. Objective: Using an email patient activation tool, we sought to increase patients' involvement in their care before and after total joint replacement. Outcomes examined included day of surgery cancellation, length of hospital stay, discharge to home vs discharge to a skilled nursing facility, any ED visit within 30 days of discharge, and any inpatient readmission within 30 days of discharge Methods: This was a quasi-experimental design comparing Jan-Jun 2017 to Jan-Jun 2018. We instituted an email patient activation tool for all patients with total knee or total hip replacement surgery beginning in January 2018. This tool was integrated with the electronic medical record system during the six month study period and patients could opt out at anytime if they desired. The tool was designed to prepare patients both educationally and emotionally for their operation with multiple easy-to-read emails starting from the time they were scheduled for surgery through six months postop. Percent of emails opened and clicked were used as measures of engagement for the intervention participants. Results: Of the 2,027 TJR patients included, 720 were hip patients and 1,307 were knee patients. Pre- and postintervention groups were similar in gender and age. For hip replacement patients, length of stay was nearly 1/4 day lower in the postintervention group ($\beta$=-0.23; P=.001) after adjusting for gender, age and insurance; ED visits were lower among the postintervention group (OR=0.45; P=.05) after adjusting for gender, age and insurance; and postintervention patients were less likely to have day of surgery cancellation, any revisit (ED or readmission), and were more likely to be discharged home. However, these associations did not reach statistical significance. Conclusions: Among patients who received the intervention, higher engagement was significantly associated with positive changes in almost all outcomes. Use of the digital patient activation tool demonstrated significant savings in length of stay and reduced ED visits among hip replacement patients. Although just under 50\% of patients in the intervention group were enrolled to use the tool, these findings were still significant even when non-participants were included in the postintervention group. ", doi="10.2196/16305", url="http://www.iproc.org/2019/1/e16305/" } @Article{info:doi/10.2196/16298, author="Devoe, Connor and Fischer, Nils and Hale, Tim and Derakhshani, Neda and Atif, Mursal and Gabbidon, Harriett and Cagliero, Enrico and McDonnell, Marie and Jethwani, Kamal", title="Pilot Study of a Prototype Integrated Diabetes Management System and the Relationship of Use to Diabetes Management Behaviors and HbA1c Among Type 2 Diabetes Patients", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e16298", keywords="health behavior", keywords="type 2 diabetes mellitus", keywords="digital health", keywords="mobile app", keywords="IDM", keywords="patient engagement", abstract="Background: Type 2 diabetes (T2D) is the seventh leading cause of death (2017) in the United States, and by 2030 it is estimated that it will affect 439 million globally. Effective glycemic control can be challenging for patients. A tool to guide patients' in their self-management behaviors and share this data with their physician may improve insulin adherence leading to lower HbA1c. We examined an integrated diabetes management (IDM) system that utilizes a Bluetooth-enabled insulin event capture device, a Bluetooth-enabled glucometer, and an Android smartphone app. IDM data can be viewed by clinicians in the electronic medical record (EMR). Objective: The primary aim of this study is to describe how app use is related to insulin adherence, blood glucose measurements, meal snapshots, and step count. Secondarily, we assessed the impact on HbA1c levels over a 3- and 6-month period. Methods: Thirty-five participants were enrolled from Boston-area hospitals in this single-arm pilot study. Use of the IDM system was defined as the number of days per week participants logged into the app and moved past the home screen. Three app use groups were created: low app use (0.33-2.46 days per week), medium app use (2.54-5.08 days per week), and high app use (>5.4 days per week). Adherence to insulin, blood glucose measurements, and meal snapshots were defined as a ratio of actual weekly events recorded by participants' app use divided by their physician's recommendation. Step count was defined as the total weekly steps for each participant. Daily app-generated data on app use and indicators of diabetes management were collected. HbA1c levels were assessed via blood test at enrollment, 3-months, and 6-months. Using a hierarchical linear mixed model, we examined changes in outcome measures while accounting for random intercepts and slopes to control for variation in individual outcomes over the study. Results: Overall app use (average unique days using the app per week) declined from 6.19 days to 3.00 days (at 1 and 24 weeks, respectively). Participants with high app use had significant improvement in bolus and basal insulin adherence per week (0.009 P=.041 [95\% CI 0.0004 to 0.018] and 0.016 P<.001 [95\% CI 0.0079 to 0.023], respectively), but participants had no significant improvements in blood glucose and meal snapshot adherence or absolute step count. HbA1c significantly decreased per week (coefficient --0.025 [95\% CI --0.044 to --0.007], P=.007) with an overall change of 0.6. Participants with high app use significantly improved their HbA1c per week (--0.037 P=.016 [--0.066 to --0.0067]) compared to participants with medium and low app use, yielding a total improvement of 0.88 over 24 weeks. Conclusions: Results show that bolus and basal insulin may have increased with higher app use. HbA1c significantly improved over the course of the study, along with significantly greater improvement in HbA1c among participants with higher app use compared to participants in the middle or low app use groups. This study is not designed or intended to evaluate efficacy but provides results to guide the future design and development of this prototype IDM system. ", doi="10.2196/16298", url="http://www.iproc.org/2019/1/e16298/" } @Article{info:doi/10.2196/16256, author="Polanco, Nicole and Palacholla, Ramya and Noor, Tasmia and Oh, Jung-Taek", title="Evaluating the Usability and Acceptability of the HARP Mobile App", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e16256", keywords="mobile app", keywords="health", keywords="home care", abstract="Background: Studies show that good communication between doctors and patients and among all caregivers who interface with patients directly results in better clinical outcomes, reduced costs, greater patient satisfaction, and lower rates of physician burnout. The main purpose of this pilot study was to test the acceptability and usability of a mobile phone app (HARP), an app designed to improve communication and data collection among nonclinical care givers such as home health aides and case managers of patients who receive care at home. The home health aides collected information on patient's mood, energy, medication adherence, potential falls and appetite level for the day. This information is summarized in postvisit, weekly and final discharge summary reports via an online dashboard and sent to the patient's case manager at different time points. We assessed the usability and acceptability of the HARP mobile app. Objective: This is a quality improvement pilot project geared towards assessing the usability and acceptability of a mobile app developed to facilitate patient data collection by trained home health aides who work together on a regular basis to provide home-based care to discrete subpopulations of patients. Methods: Four home health aides were recruited from Partners Healthcare at Home to use the app to collect data on at least 12 patients. Eligible patients received care from 1 of the 4 home health aides for at least 23 days and scheduled to have at least 5 home visits during this time. Each of the patients were followed for a minimum of 23 days and a maximum 60 days in which home health aides collected patient data using the app. Postvisit reports, weekly reports and discharge summary reports were shared with the patient's case managers. Data collection included acceptability and satisfaction data from all home health aides and case managers via surveys. A subgroup of 2 case managers and 2 home health aides participated in semistructured interviews. Results: 9 have completed the project to date, 5 patients dropped out due to discharge from Partners Healthcare at Home care. The interim data included is from 8 case managers and 4 home health aides who provide care to one or more of the 9 patients who completed the project. Most case managers (75\%) found postvisit and weekly reports useful and 87\% found tracking mood and energy helpful. About 75\% felt tracking appetite and falls via the HARP app helpful. Almost all case managers (87\%), agreed that integrating a tool like the HARP app to the EMR would help them provide better care to their patients. Three out of four home health aides (75\%) felt that the app easy to use or learn about once they received instructions and were willing to consider using the app in their workflow. Conclusions: Acceptability and usability of HARP app was considerably high among case managers. The acceptability of the app varied among home health aides, some found information useful and believed the app has potential to help personalize patient care. Future research would require exploring other patient information that is useful to all staff involved in the clinical workflow and increase adoption of tool in clinical settings. Such tools could potentially reduce clinician burnout and improve patient outcomes. ", doi="10.2196/16256", url="http://www.iproc.org/2019/1/e16256/" } @Article{info:doi/10.2196/16250, author="Polanco, Nicole and Odametey, Sharon and Derakhshani, Neda and Khachaturian, Mark and Devoe, Connor and Jethwani, Kamal and Kakarmath, Sujay", title="Evaluating the Accuracy of the VitalWellness Device", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e16250", keywords="personal tracking", keywords="vital signs", keywords="blood pressure", keywords="heart rate", keywords="home monitoring", abstract="Background: Wellness devices for health tracking have gained popularity in recent years. Additionally, portable and readily accessible wellness devices have several advantages when compared to traditional medical devices found in clinical environments The VitalWellness device is a portable wellness device that can potentially aide vital sign measuring for those interested in tracking their health. Objective: In this diagnostic accuracy study, we evaluated the performance of the VitalWellness device, a wireless, compact, non-invasive device that measures four vital signs (blood pressure (BP), heart rate (HR), respiratory rate (RR), and body temperature using the index finger and forehead. Methods: Volunteers age ?18 years were enrolled to provide blood pressure (BP), heart rate (HR), respiratory rate (RR), and body temperature. We recruited participants with vital signs that fell within and outside of the normal physiological range. A sub-group of eligible participants were asked to undergo an exercise test, aerobic step test and/or a paced breathing test to analyze the VitalWellness device's performance on vital signs outside of the normal physiological ranges for HR and RR. Vital signs measurements were collected with the VitalWellness device and FDA-approved reference devices. Mean, standard deviation, mean difference, standard deviation of difference, standard error of mean difference, and correlation coefficients were calculated for measurements collected; these measurements were plotted on a scatter plot and a Bland-Altman plot. Sensitivity analyses were performed to evaluate the performance of the VitalWellness device by gender, skin color, finger size, and in the presence of artifacts. Results: 265 volunteers enrolled in the study and 2 withdrew before study completion. Majority of the volunteers were female (62\%), predominately white (63\%), graduated from college or post college (67\%), and employed (59\%). There was a moderately strong linear relationship between VitalWellness BP and reference BP (r=0.7, P<.05) and VitalWellness RR and reference RR measurements (r=0.7, P<.05). The VitalWellness HR readings were significantly in line with the reference HR readings (r=0.9, P<.05). There was a weaker linear relationship between VitalWellness temperature and reference temperature (r=0.3, P<.05). There were no differences in performance of the VitalWellness device by gender, skin color or in the presence of artifacts. Finger size was associated with differential performance for RR. Conclusions: Overall, the VitalWellness device performed well in taking BP, HR, and RR when compared to FDA-approved reference devices and has potential serve as a wellness device. To test adaptability and acceptability, future research may evaluate user's interactions and experiences with the VitalWellness device at home. In addition, the next phase of the study will evaluate transmitting vital sign information from the VitalWellness device to an online secured database where information can be shared with HCPs within seconds of measurement. ", doi="10.2196/16250", url="http://www.iproc.org/2019/1/e16250/" } @Article{info:doi/10.2196/16230, author="Du, Yan and Lewis, Brittney and Lopez, Katrina and Li, Chengdong and White, Carole and Seshadri, Sudha and Wang, Jing", title="Developing a Comprehensive Model for Improving Quality of Life in Individuals with Alzheimer Disease and Related Dementia and Their Informal Caregivers: Qualitative Study of AZL Forum Data", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e16230", keywords="qualitative study", keywords="quality of life", keywords="model", keywords="Alzheimer disease and related dementias", keywords="informal caregivers", keywords="forum", abstract="Background: It is estimated that more than five million Americans are living with Alzheimer disease and related dementia (ADRD), and the population of people living with the disease is expected to triple by 2060. Most care for persons living with ADRD is provided by informal caregivers. However, current strategies to improve the quality of life for both people living with ADRD and their informal caregivers are not optimal, especially from a comprehensive approach. Social media and online forums have become increasingly popular tools for ADRD caregivers to manage the burden of caregiving. Objective: This study was to 1) explore informal caregivers' discussion topics by analyzing the caregiver online forum data, and 2) develop a comprehensive model based on their discussion topics, with the aim to improve quality of life for both persons living with ADRD and their informal caregivers. Methods: Publicly available peer interactions of 4102 registered users, with 96\% self-claimed as informal caregivers (67\% as a child of a person with dementia, 13\% as a partner/spouse, and 7\% as a relative) on the Alzheimer's Association ALZ Connected Caregivers Forum were extracted in January 2019 using computer programming. A total of 40,798 postings were collected. All authors agreed to use a triangular model to serve as the predetermined three major themes to categorize all codes. The three major themes were factors of caregivers, factors of individuals with ADRD, and factors of care context. Inductive coding was used to derive in vivo codes from the data, and the codes were further refined throughout the coding process. Two researchers independently coded postings until saturation was reached. Discrepancies were discussed among the two researchers to reach consensus. A third senior researcher's opinion was referred to whenever necessary. Results: For factors of caregivers, the most frequent subthemes were perceived caregiver burden, caregiver's life balance, caregiving strategies, communication, expectations, personal health issues, poor relationship, and ineffective coping. Subthemes of factors of individuals with ADRD included changes in abilities and capacities, commodities, behaviors, health conditions, daily living function, disengagement, and ineffective coping. Lastly, for factors of care context, the most frequent themes were family support, financial support, informational support, professional support, length of care provided, living arrangement, activities and stimulation, patient health care coordination, unexpected situations, communication, and physical environment. One theme under one of the triangular factors may influence another theme under another triangular factor and vice versa. Conclusions: By analyzing the discussions of informal caregivers on ALZ online forum, we found that taking care of a loved one with ADRD is challenging for informal caregivers. The challenges may affect the quality of life for both caregivers and the caregiver recipients; factors of care recipients, caregivers, and the care context interactively affect perceived challenges of caregivers. This study has identified a comprehensive model which may be used to help improve quality of life for both informal caregivers and people living with ADRD. Our next step is to use these manually determined codes to analyze all extracted postings via machine learning to improve this model. ", doi="10.2196/16230", url="http://www.iproc.org/2019/1/e16230/" } @Article{info:doi/10.2196/16200, author="Bane, Sunetra", title="Incorporation of Potential User Feedback to Inform the Design of a Prototype Integrated Diabetes Management System", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e16200", keywords="diabetes mellitus, type 2", keywords="human-centered design", keywords="user research", keywords="product design", abstract="Background: Type 2 diabetes (T2D) is a complex and burdensome chronic disease. Most patients, including uncontrolled (HbA1c >7\%) patients, only see their Health Care Provider (HCP) once every three months. Thus, a tremendous amount of patient self-management is required outside the clinic to maintain blood glucose (BG) levels within a healthy range and prevent worsening of the disease. Additionally, HCP's overseeing diabetes care often rely on patient self-report and lack key data about how well the patient is managing the condition. We hypothesized that the development of an Integrated Diabetes Management (IDM) system which helps patients better track their BG, insulin and diet would support patient self-management. By sharing a data summary with HCPs through an EMR-integrated, web-based portal, the patient's HCP could would have access to data to help inform treatment decisions and patient education strategies to improve outcomes. Objective: The goal of this design research was to better understand how an IDM platform might support patient self-management and care, and, based on this data, create a prioritized list of requirements for a prototype of the system. Methods: We used one-hour, semi-structured, in-person interviews and observations with HCPs (n=18) and T2D patients (n=14, recruited via HCP referral). Interview and observation data (via summary notes and transcripts) were analyzed, coding for pain points and workflows. Personas and journey-maps of patients and clinicians were created to inform product design. Pain points and unmet needs were categorized by task and informed the design of features in the IDM system. High fidelity paper prototypes of the solution were tested with HCPs and patients to gather feedback on design options. Results: HCPs interviewed ranged from MDs (n=4), NPs (n=7), RNs (n=3), CDEs/RDs (n=2) and health coaches (n=2). For HCPs, tasks along the patient journey consist of diagnosis, training, titration, follow-up, and long-term maintenance. Titration and follow-up are the most resource intensive, with the largest number of tasks falling to RNs and NPs. Key HCPs needs included a way to better track patients' behaviors and a way to illustrate the relationship between diet, physical activity and BG/insulin readings to educate patients, improving communication between the patient and their HCP. Patient demographics were predominantly male (57\%), between 50-59 years old (36\%), high-school educated (57\%), and split 50/50 between Android and iOS users. Fifty percent of patients had been diagnosed 1-5 years prior to interview, and 58\% only used long-acting insulin. Patients had the greatest need for help with self-management of their T2D, including reminders and automatic logging of BG and insulin dose, simplified meal and exercise logging, and the ability to share this information with their HCPs. Conclusions: Design research with T2D patients and HCPs was critical to inform the design of a prototype IDM system. User feedback was incorporated to generate an IDM system which included a patient mobile application, BT-connected insulin event capture device, BT-glucose meter, daily meal log, physical activity tracker, and an HCP clinical portal. ", doi="10.2196/16200", url="http://www.iproc.org/2019/1/e16200/" } @Article{info:doi/10.2196/15273, author="Goodman, Georgia and O'Cleirigh, Conall and Mayer, H. Kenneth and Boyer, W. Edward and Rosen, K. Rochelle and Chai, R. Peter", title="Attitudes and Response to a Smartphone-Based Digital Pill Intervention to Enhance PrEP Adherence Among Men Who Have Sex With Men With Stimulant Use", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15273", keywords="focus groups", keywords="HIV", keywords="medication adherence", keywords="prep", keywords="MSM", abstract="Background: Digital pills contain a radiofrequency emitter and gelatin capsule that over-encapsulate a study medication. The radiofrequency emitter, activated by the chloride ion gradient in the stomach, transmits a signal to a wearable Reader device following ingestion. The Reader relays ingestion data to a smartphone app and cloud-based server, allowing for real-time verification of ingestion events and adherence measurement. Digitized pre-exposure prophylaxis (PrEP) may improve outcomes in populations with suboptimal adherence related to substance use. Stimulant use is particularly prevalent among men who have sex with men (MSM) and is associated with increased HIV risk behavior and transmission. We conducted seven focus groups with MSM who use stimulants (N=16) to inform the development of PrEPsteps, a novel smartphone-based adherence intervention respondent to data from digitized PrEP and designed to augment adherence. Objective: To inform the specification of the design, content, and delivery of the smartphone-based PrEPsteps adherence system via focus groups with HIV-negative MSM who use stimulants. Methods: Seven focus groups were conducted with HIV-negative MSM reporting stimulant use (eg, cocaine, methamphetamine) in the past six months. Participants self-reported medical history, substance use and sexual activity. Focus groups explored responses to digital pill technology, willingness and barriers to use, content and timing of adherence messaging, and three intervention components: (1) abbreviated cognitive behavioral therapy (CBT) adherence counseling (LifeSteps); (2) contingent reinforcement/corrective feedback; and (3) substance use-related Screening, Brief Intervention and Referral to Treatment (SBIRT). Focus groups were transcribed and analyzed using applied thematic analysis. Results: Sixteen individuals participated in focus groups. All were male; age ranged from 24 to 63 (mean 39.9, SD 14.1) and most self-identified as gay (N=13). Participants were primarily non-Hispanic or Latino (N=12); 10 identified as white, two as black, and four as multiracial. Most had at least a college degree (N=14). Twelve participants were taking PrEP, 5 of whom reported missed doses in the past two weeks. Number of sexual partners in the past three months ranged from 1 to 200 (M=28.1; SD=50.9). Fifteen participants reported using stimulants during the last 30 days. Participants viewed digital pills as a tool to enhance PrEP adherence and accountability. They expressed a willingness to use the digital pill and identified physicians, family members, and partners as people with whom they would share adherence data. The Reader was viewed as the most difficult technological component to use, although participants also described the device as itself an adherence reminder. Participants identified customizability as a valuable aspect of the technology; message and reminder content, structure, and scheduling were all considered customizable. With regard to the intervention, participants were accepting of and willing to interact with corrective feedback messages linked to a brief CBT LifeSteps booster session. Conclusions: PrEPsteps, a smartphone-based adherence intervention, was viewed as acceptable by HIV-negative MSM who use stimulants. Individuals perceived corrective feedback notifications to be the most helpful component of the system, and expressed a strong preference for customizability across the intervention. ", doi="10.2196/15273", url="http://www.iproc.org/2019/1/e15273/" } @Article{info:doi/10.2196/15270, author="Bishop, Natalie and Kakkar, Sarthak and Garg, Shashank and Pfau, Andy and Burgo, Melody and Jaffe, Cera and Patel, Shrawan and Rogers, Jason and Fasihuddin, Farah and Sharma, Virender and Greenwald, David and Smith, Michael and Sands, Bruce and Solad, Yauheni and Laine, Loren and Masoud, Amir and Sidhu, Kiran and Atreja, Ashish", title="Impact of Automated Digital Navigation Program on Bowel Preparation Quality and Patient Satisfaction for Colonoscopy: A Comparative Study Across Multiple Sites", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15270", keywords="endoscopy", keywords="digital medicine", abstract="Background: Nearly 1 in 5 patients suffers from inadequate or poor bowel preparation in advance of a colonoscopy. Prior studies have shown that this leads to a decrease in adenoma detection rate, increased time spent in completing efficiency in endoscopy suite, as well as an overall increase in cost of care from 13-20\%. With the shift to value-based care in the American healthcare system, there is an urgent need for solutions that can automate pre-procedure guidance and post-procedure follow up. Objective: As part of the American Gastroenterology Association digital transformation network, we sought to automate and improve pre-procedure navigation for colonoscopy using connected health technologies (specifically digital navigation). At Arizona Center for Digestive Health (AZCDH), we assessed the impact of digital navigation on bowel preparation quality, patient engagement, and patient satisfaction. We also sought to assess the reproducibility of outcomes seen at AZCDH at additional sites that have implemented digital navigation for endoscopic procedures as part of the American Gastroenterology Association network, including Yale New Haven Hospital (YNHH) and three Mount Sinai Hospital locations. Methods: At AZCDH, we compared two cohorts of patients (usual care versus digital navigation) scheduled for colonoscopy. The digital navigation cohort received usual care in addition to time based messages and education content pathways on smartphones and delivered through Rx.Health's digital medicine platform. Bowel preparation quality was then assessed, as well as patient satisfaction with the digital navigation intervention. Patient engagement and satisfaction were then compared with initial data from other sites within the network. Results: Of the 217 patients prescribed the digital navigation program at AZCDH, 93 completed the procedure to date and had bowel preparation results documented in the electronic endoscopic record system. After implementing the digital navigation program the rate of aborted procedures decreased from 2.2\% at baseline to 1.07\%. In a follow up survey, 93\% of respondents ``strongly agreed'' or ``agreed'' that the digital navigation program was helpful in preparing for their colonoscopy. At other locations to date, 433 patients have been prescribed the pathway at YNHH along with 213 patients at Mount Sinai locations. One hundred percent and 94\% of respondents ``strongly agreed'' or ``agreed'' that the digital navigation program was helpful in preparing for their procedure at YNHH and Mount Sinai locations, respectively. Conclusions: Our single-site study at AZCDH paved the way to implementing digital navigation pathways at YNHH and Mount Sinai endoscopy locations by demonstrating that colonoscopy instructions are well received by patients, can reduce the rate of aborted procedures and can result in higher patient satisfaction as well as a higher quality of bowel preparation. Further, patient engagement rates and satisfaction with the program was consistent at all sites across the US where the digital navigation program has been implemented. In the future, we plan to report on patient outcomes (including reduction in no shows, poor bowel preparation) to allow benchmarking on a national scale. ", doi="10.2196/15270", url="http://www.iproc.org/2019/1/e15270/" } @Article{info:doi/10.2196/15259, author="Shi, Galen and Shah, Pavan and Canares, Therese and Zimmer-Galler, Ingrid", title="Improving the Pediatric Hospital Experience Using Telepresence Robotics", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15259", keywords="affect", keywords="asessment", keywords="children and adolescents", keywords="mood", keywords="survey", keywords="telemedicine", abstract="Background: In a hospital setting, pediatric patients miss out on routine stress coping mechanisms, such as normative play, socialization, and exploration. Previous work has established that a lack of healthy coping mechanisms negatively impacts the psychosocial development and well-being of hospitalized children. To help alleviate the stress of hospitalization, we created a novel, normative play robotics program that utilizes telepresence technology to give children live, virtual tours of museums and cultural attractions. Objective: The objective was to 1) demonstrate feasibility, and 2) assess quality and impact on mood of telepresence tours as a new normative play intervention. Methods: A prospective, cross-sectional study was conducted on inpatients at the Johns Hopkins Children's Center and the University of Maryland Children's Hospital from the ages of 3 to 19. Subjects were selected through convenience sampling by Child Life Specialists. The intervention consisted of a 30-minute session in which a volunteer: 1) remotely connected a laptop in the hospital room to a telepresence robot at the Maryland Science Center or the National Aquarium; 2) introduced the child to their venue tour guide and taught the child how to drive the robot, and 3) facilitated a tour in conjunction with the venue tour guide on site with the robot. Feasibility was assessed by the rate of completed tours. Quality of the experience and mood were evaluated with surveys answered with a 5 or 7-point Likert scale. Surveys were administered in 2 phases: phase 1 evaluated quality of the experience after the tour, and phase 2 included the phase 1 survey plus mood assessment before and after the tour. The two-tailed Wilcoxon signed-rank test was used to determine statistical significance in difference in mood before and after the tour. Verbal consent was obtained from patient guardians and assent was obtained from the patient. Results: 77 tours were conducted with pediatric inpatients, and no tours were terminated due to technical difficulty. Out of 77 children, 68 completed surveys. In phase 1 (n=40) participants' average age was 7.8 years. On average, patients rated their overall experience a 4.8/5, ease of driving 4.1/5, ease of communicating with other guests at the venues a 4.3/5, and their tour guides a 4.7/5. In phase 2 (n=37), average age was 10.1 years. Children's self-reported mood improved from pre-visit (3.7/5) to post visit (4.4/5) (P<.001). Additionally, patients rated their overall ease of driving 5.8/7, ease of communicating with other guests at the venues 5.3/7, and their tour guides 6.8/7. Conclusions: Patients reported positive assessments of their overall experience, ease of driving, communication with tour guides and guests at the venues, and elevated mood after the tour. This study demonstrates that telepresence tours are a feasible and enjoyable intervention for hospitalized pediatric patients, and significantly improve mood. This unique program adds to existing child life specialist strategies by allowing children to engage in normative behaviors outside of the hospital. This novel use of telepresence robotics as a normative play intervention warrants future studies to further characterize the improvement in mood and impact on the patient's overall hospital satisfaction. ", doi="10.2196/15259", url="http://www.iproc.org/2019/1/e15259/" } @Article{info:doi/10.2196/15258, author="Dixon, Ronald and Zisser, Howard and Barleen, Nathan and Layne, Jennifer and Moloney, Daniel and Majithia, Amit and Riff, Josh", title="Participation in a Virtual Diabetes Clinic Improves Glycemic Control in Adults with Type 2 Diabetes", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15258", keywords="blood glucose", keywords="mobile health (mHealth)", keywords="telehealth", keywords="telemedicine", keywords="type 2 diabetes mellitus", abstract="Background: Telemedicine for people with type 2 diabetes (T2D) has the potential to positively impact self-management behaviors and improve health outcomes. The Onduo Virtual Diabetes Clinic (VDC) is a comprehensive telehealth program for people with T2D that combines mobile app technology, remote personalized lifestyle coaching from certified diabetes educators and health coaches, connected devices including blood glucose meters and continuous glucose monitoring systems, and clinical support from board certified endocrinologists. Objective: To describe the VDC care delivery model and present preliminary data on change in glycemic control in program participants with up to 6 months of follow-up. Methods: Adults ?18 years of age with T2D and who were members of sponsoring health plans and employers throughout the US were eligible to participate. Those who elected to enroll downloaded the VDC app to their smartphone, provided demographic and clinical information, completed an onboarding survey, and were mailed a self-management kit that included a connected blood glucose meter, test strips and a home glycosylated hemoglobin (HbA1c) testing kit. Participants interacted with their care team primarily through the VDC app, with occasional phone calls, and by synchronous video consultations with endocrinologists, as clinically appropriate. Change in glycemic control in participants who completed a baseline survey from February 2018 through December 31, 2018, with an initial HbA1c measurement within 30 days of enrollment and a follow-up measurement between 90 and 180 days after baseline was analyzed. Results: Participants (n=740) were (mean {\textpm} SD): 53.8 {\textpm} 8.8 years of age, 62\% female, BMI 35.6 {\textpm} 8.5, initial HbA1c 7.7\% {\textpm} 1.8, 31.0\% were on insulin and 25.9\% were on sulfonylureas at baseline, and 30.0\% lived in a rural area. HbA1c decreased significantly by 2.3\% {\textpm} 1.9, 0.7\% {\textpm} 1.0 and 0.2\% {\textpm} 0.8 across the baseline categories of >9.0\%, 8.0\% to 9.0\% and 7.0\% to <8.0\%, respectively (all P<.001). Within these categories, HbA1c improved in 91.9\%, 77.3\% and 63.5\% of participants. For the group with an initial HbA1c >9.0\%, HbA1c decreased from 10.7\% {\textpm} 1.4 to 8.3\% {\textpm} 1.5, and when stratified by HbA1c ?8.0\% the mean decrease in HbA1c was 1.5\%, from 9.5\% {\textpm} 1.5 to 8.0\% {\textpm} 1.3, with 84.5\% of participants demonstrating improvement. Participants with an initial HbA1c <7.0\% who were meeting treatment targets at baseline, HbA1c 6.3\% {\textpm} 0.4, continued to maintain this level of glycemic control at follow-up, HbA1c 6.4\% {\textpm} 0.6 (ns). Conclusions: Participation in the VDC was associated with a significant improvement in HbA1c in adults with T2D who were not meeting treatment targets, with the greatest improvement observed in those with an initial HbA1c >9.0\%. Importantly, the majority of program participants experienced an improvement in glycemic control. Our findings suggest that the VDC program is an effective approach to support individuals with T2D and their clinicians in diabetes management between office visits. ", doi="10.2196/15258", url="http://www.iproc.org/2019/1/e15258/" } @Article{info:doi/10.2196/15248, author="Molefi, Tsholofelo", title="Development of an Accident and Emergency Triage Mobile App Using Open Data Kit", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15248", keywords="clinical decision support systems", keywords="computerized triage", keywords="emergency department", keywords="mobile app", keywords="decision-making", keywords="mHealth", abstract="Background: The process of triaging is performed as an effective solution to balance limited resources against high patient volumes, based on an assessment of the patient's medical condition and the application of an established patient categorization protocol. In Princess Marina Hospital (PMH), a national referral government hospital in the capital city of Botswana, the Princess Marina Hospital Accident and Emergency Centre Triage Scale (PATS) has been in use since 2010. Because the rules of these triage scales are very well defined, these protocols have been shown to be amenable to translation into computer algorithms. Thus, clinical decision support systems (CDSSs) that can assist with information management to support clinicians' decision-making abilities can be developed, leading to improved healthcare quality and patient safety. Objective: This study aims to determine the feasibility of development of a mobile triage app based on the adult PATS using Open Data kit (ODK) open source software to be used as a CDSS on smartphones and tablet computers for correct patient categorization. Methods: A user-centered design approach was used in designing the app, with participants recruited from the staff at the Accident and Emergency Department (A\&E) at PMH. Forty clinical vignettes were used in the evaluation of the performance of the app as compared to the paper-based system currently in use with the emergency physician at PMH providing the gold standard categorization of these vignettes. Usability testing was also performed. Results: The app scored 90\% (n=36) of the vignettes correctly, as compared to the paper-based system which scored 82.5\% (n=33) of the vignettes correctly. Both systems achieved an over-triage score of 7.5\% with an equal number of vignettes over-triaged (n=3). The results of the chi-square test indicate that the difference in triage scores between the paper-based system and the mobile app is statistically significant at P=.001 in favour of the ODK app. An overall positive outcome was also achieved in the usability test with ease of use and speed of triage determined to be the most recurring themes in the user feedback survey. While the app does not require an internet connection for triaging patients, a reliable wireless internet connection is required to upload data to the server for viewing by medical officers and physicians in real time, and this can be provided by the hospital as part of the Botswana government eHealth strategy. Additionally, the app developed in this research allows for data collection up to the point of triage categorization, meaning that a separate form would be required for capturing the rest of the information on the PMH A\&E triage form. Conclusions: The triage app developed in this research was found to determine the triage category of patient vignettes more accurately than the traditional paper-based system based on PATS triage guidelines with good results obtained in usability testing. Future work includes use of the app developed in this research in a live setting involving real patients in the A\&E in PMH. ", doi="10.2196/15248", url="http://www.iproc.org/2019/1/e15248/" } @Article{info:doi/10.2196/15245, author="Hoffman, Jennifer and Burke, Lori and Kay, Cheryl and Hlavaty, Rachel and Thompson-Wood, Jennifer and O'Dell, Danyelle", title="Standardizing Postpartum Discharge Instructions With an Educational Video: A Quality Improvement Project", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15245", keywords="education technology", keywords="pregnancy", keywords="women's health", abstract="Background: The World Health Organization (WHO) estimates that, in the United States, 1200 women annually experience perinatal events that prove fatal and 60,000 suffer complications that are near-fatal. Postpartum morbidity and mortality may be decreased by explicit patient education. At our institution, the maternal discharge education process was varied among providers. Of the available literature, most focus on maternal knowledge of pediatric concerns with a limited amount of studies looking at maternal postpartum health. Objective: The objective of this quality improvement project is to standardize postpartum education with the use of a postpartum education video available on a bedside tablet in order to improve maternal perception and knowledge of postpartum warning signs. Methods: This prospective cohort study was designed using a patient survey which was administered to evaluate the effectiveness of the maternal discharge education procedures in our institution. The baseline results were reviewed by a team of physicians and nurses. A 10-question survey was provided to patients following the birth of their first baby about maternal warning signs and complications after discharge from the hospital. A standardized discharge education video was created using information from ACOG and AWHONN. The video was made accessible on bedside tablet devices. Patients were able to indicate understanding or request clarification on the devices after review of the materials, and this was communicated from the tablets to the electronic health record. All postpartum nurses were trained on the video content and how to operate the tablets. Survey responses were collected via bedside tablets following implementation of the video and were compared with the baseline results. Educational information was available to patients after discharge from the hospital via a patient portal. Results: Twenty-nine women were surveyed prior to implementation of the standardized educational video available on bedside tablets. After implementation, 50 women were surveyed. Comparison of the survey responses showed there was an increase in patient-reported knowledge and understanding in all 10 questions on the survey. Of those, 4 areas were statistically significant with P values <.05: when to call 911 (82.8\% before and 98\% after), when to call your doctor (75.9\% before and 98.0\% after), heavy vaginal bleeding (62.1\% before and 87.8\% after), and symptoms of acute blood loss (51.7\% before and 83.7\% after). Conclusions: The implementation of a postpartum education video available to patients on bedside tablets improved and standardized workflow for routine postpartum care and discharge processes. Survey questions regarding patient knowledge and perception of when to call 911, when to call your doctor, heavy bleeding, and signs of acute blood loss were all noted to be statistically significant. The improved perception of postpartum warning signs after the educational video appears to be beneficial in patient education at this high volume OB institution. The establishment of this platform for education became a model for education in other hospital units using bedside tablets. The use of a multidisciplinary team to review, revise, and standardize the postpartum education program at our institution was well received and supported by nurses, providers, and ultimately patients. ", doi="10.2196/15245", url="http://www.iproc.org/2019/1/e15245/" } @Article{info:doi/10.2196/15239, author="Franco, Gabala and Ndibaisa, Juliet and Slivia, Namumbya", title="Women Mobile Lifeline Channel Is a Key Stimulant of MCH Services Use in Resource Constrained Settings: A Success Story of Women Health Channel Uganda", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15239", abstract="Background: Uganda has made progress in recent decades; however, the country still ranks among the top 10 countries in the world with high maternal, newborn, and child mortality rates. 336 women in every 100000 live births die due to preventable pregnancy related causes (under-five mortality rate 64/1000 live births; infant mortality rate 43/1000 live births; and neonatal mortality rate 27/1000 live births). Despite the growing global focus on reaching the last mile that necessitates the development of mHealth tools that best reach, empower, and mobilize the last mile women to seek and utilize critical and life-saving health care services as a vehicle for accelerating reduction of maternal and child deaths, mHealth tools in Uganda continue to limit focus on reporting and trucking of health indicators. Objective: MIRA Channel is a single-window app with multiple channels on prenatal care, child immunization, newborn care, and family planning with the objective to improve maternal and child health outcomes in rural and resource-constrained settings. The app delivers information to women through interactive edutainment tools that builds on their knowledge, thus creating awareness on critical health issues and preempt timely use of MCH services. Methods: Women Health Channel Uganda piloted the Women Mobile Lifeline Channel app in 15 public health facilities in Jinja district, Uganda, and particularly targeted pregnant women. A systematic review of records, particularly the health facility ANC register, was done to estimate the facility clientele size. Purposive random sampling was used to arrive at the survey sample. Two contact midwives and 5 VHTs were selected, trained, and given a connected mobile device at each of the implementing health facilities. Recruitment of women on the platform was done by VHTs using connected phones at community level, and 3489 pregnant women were studied for 16 months. Data was collected at baseline and at end line. Results: Both at baseline and at end line, information on knowledge as well as usage of key MCH services was collected. All women had heard of ANC and the recommended place of delivery; however, only 59\% at baseline had knowledge of the exact recommended number of ANC visits as opposed to 94\% at end line. At baseline, 36\% of women reported to have attended ANC 4 or more times at the most recent pregnancy as opposed to 82\% at end line, while 63\% of women at baseline reported to have given birth in a health facility for the previous pregnancy as opposed to 94\% at end line. Sven neonatal deaths were reported in the cohort at baseline as opposed to 0 maternal deaths and 1 neonatal death at end line. Conclusions: The pilot showed that one critical determinant of use of MCH services is the overall client knowledge and the perceived available support mechanism in the face of challenges. mHealth tools ought to expand focus to include stimulation of two-way mobile-based interactions that reinforce behavior change and preempt use as such. The Women Mobile Lifeline Channel that Women Health Channel is implementing offers lenses for Uganda and other countries to walk towards meaningful ICT integration in health. ", doi="10.2196/15239", url="http://www.iproc.org/2019/1/e15239/" } @Article{info:doi/10.2196/15237, author="Ukponu, Winifred and Shallangwa, Joy and Adamu, Helen and Mohammed, Amina and Ihueze, Adachioma and Ibrahim, Ramat and Olawepo, Olatayo and Yashe, Rimamdeyati and Njoku, Kingsley and Niyang, Mercy and Gobir, Bola", title="Outcomes of Mobile Reporting to Enhance Disease Surveillance in 632 Districts of 29 States in Nigeria", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15237", abstract="Background: Optimal disease surveillance provides opportunities for identifying outbreaks early and intervening to reduce their spread and impact. The availability of mobile phone technologies have improved communication across the world and now serves as an effective system for frontline healthcare workers to gather and disseminate data that can inform actions at country and program levels. In Nigeria, with an estimated population of over 200 million people spread across a wide land mass area of 923,763 km2, surveillance for diseases will require innovative strategies with penetrative abilities to the lowest levels of healthcare to achieve desired outcomes. Objective: The objective was to describe the outcomes of reporting using mobile technology to enhance surveillance. Methods: An SMS-based reporting tool was developed which conforms to the nationally approved weekly reporting format for IDSR 002 diseases. A total of nine diseases and public health events are reported weekly by 774 Disease Surveillance and Notification Officers (DSNOs) at the Districts. On reporting days (Tuesdays), the DSNOs receive a reminder via SMS to send in their reports, which is shortly followed by the reporting template. The DSNOs enter the weekly data for their respective data and send via SMS. The data is received nationally at the Nigeria Centre for Disease Control (NCDC) where staff provide oversight function on reports coming in by states. The team monitor reporting through visualization monitoring boards and respond to wrongly sent reports by calling up the DSNO. Collated reports by states are shared with the State Supervisory Teams on nationally approved Excel sheets which bypasses the cumbersome nature of direct data entry on the Excel sheets. Reports are validated by the state before the final version of the Excel sheets are shared with the NCDC. Completeness, timeliness of data, and alert threshold of reported cases were used to monitor the reporting process for 52 weeks in 2018. Results: A total of 32,864 reports were expected in 2018 with 1 report sent weekly from each of the 632 districts of 29 states. The benchmark for timely reports is 80\% and completeness of reports is 90\% as indicated in the Integrated Disease Surveillance and Response (IDSR) Technical Guidelines. Average completeness was 90\% with 97\% noted in February and 57\% in November. An average of 93\% of reports were sent in a timely manner with timeliness of 89\% observed in in June and July and 96\% observed in January, February, and December. All 29 states reported in a timely manner and 2 states sent in complete reports consistently for 52 weeks. This system provided real-time alerts for priority diseases that were above established thresholds highlighting the start of various outbreaks reported in the year. Conclusions: During the year, there was a marked improvement in disease surveillance and notification despite periods of low completeness of reports observed. Instituting into mobile systems, processing for feedback, and improvement will further support the system among healthcare workers. Leveraging on the ease of how mobile phones have become part of everyday human life, disease surveillance methods can be enhanced and used on mobile phones ", doi="10.2196/15237", url="http://www.iproc.org/2019/1/e15237/" } @Article{info:doi/10.2196/15235, author="Ihekweazu, Chikwe and Ossai, Paulinus and Nnaji, Robinson and Osigwe, Ugochukwu and Ngozi, Mba", title="Interoperability of Surveillance Data Collection Tools (District Health Information System 2 and District Vaccine Data Management Tools) in Enugu State, Nigeria, From 2015-2018", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15235", keywords="surveillance evalluation", keywords="qualitative study", keywords="data tools", abstract="Background: Over the years, Nigeria has used District Vaccine Data Management Tool (DVDMT) for surveillance data collection including routine immunization. In 2012, Nigeria adopted District Health Information Software (DHIS2), a Java driving online real-time tool for data collection. In 2015, Enugu State commenced the use of DHIS2 alongside the traditional DVDMT as surveillance data capturing tools. Objective: The objective was to carry out an evaluation of the two surveillance data tools to assess surveillance attributes, interoperability, effect in decision making, and preference of use. Methods: We quantitatively and qualitatively assessed surveillance attributes of Enugu State's DHIS2 and DVDMT from 2015 to 2018 using adapted CDC guidelines (2001). We administered semi-structured questionnaires to all 17 local immunization officers from the 17 local government areas (districts) to assess surveillance attributes. We carried out desk review at all levels, key informants done with 6 purposefully selected stakeholders, and focused group discussion carried out with 6 randomly selected heads of surveillance at local governments areas. We recorded proportions, interoperability, effect in decision making, and preference of use. Results: Average completeness of data is 100\% in both DHIS2 and DVDMT systems (target 90\%). Eligibility is 100\% in DHIS2 and 85\% in DVDMT (target 80\%). Timeliness of reporting is 100\% and 80\% in DHIS2 and DVDMT, respectively (target 80\%). All stakeholders accepted both tools and agreed that they are simple and flexible. In addition to collection of all data recorded by DVDMT, DHIS2 captures vaccine utilization. Data collection and transmission of DVDMT and DHIS2 are carried out by the same surveillance personnel at health facility and local government area levels. Apart from vaccine utilization both tools can complement each other in case of missed data as they record the same thing. All key informants opined that it is double work managing the two tools and also agreed that DHIS2 is better than DVDMT in decision making because it has features for data visualization and real-time reporting. The focused group discussion agreed that both tools are good, although DVDMT is easier to work with as DHIS2 requires computer proficiency of current users alongside hardware management of the Java-enabled phones used in data capture and transmission. However, they also agreed that DHIS2 usage is less time consuming and opined they will prefer to use DHIS2 as the only data capturing tool in Enugu State if proper capacity building is done. Conclusions: The DHIS2 and DVDMT surveillance data tools in Enugu State is meeting all its targets based on surveillance attributes, though DHIS2 provides better quality data. There is a good understanding and synergy in operation of the two systems in all levels and intermittently data from both tools can be compared. DHIS2 can enable prompt decision making than DVDMT as data can be assessed and visualized in real time. Surveillance officers prefer the use of DHIS2 as the only surveillance tool in Enugu State, although proficiency is a challenge. We recommended a gradual phase out of DVDMT for data capturing in Enugu State, while capacity building of users for DHIS2 should be addressed. ", doi="10.2196/15235", url="http://www.iproc.org/2019/1/e15235/" } @Article{info:doi/10.2196/15231, author="Sezgin, Emre and Militello, Lisa and Huang, Yungui and Lin, Simon", title="Look to the Future and SMILE: Feasibility of Interactive Voice Assistant Technology to Support Maternal Infant Health", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15231", keywords="behavioral health", keywords="interactive voice response", keywords="mobile health", keywords="mothers", keywords="pregnancy", keywords="self care", keywords="self-management", abstract="Background: Both maternal and infant mortality rates serve as indicators of population health and are unacceptably high worldwide. Voice assistant (VA) technologies present a potential new modality to support maternal child health. We developed an interactive VA intervention app (SMILE) to deliver brief, maternal-infant education and management skills (eg, perinatal care, stress management, breast feeding, infant-care) using evidence-based content. Objective: The objective was to understand the feasibility and usability of an interactive VA intervention to support maternal and infant health among a group of pregnant women. Methods: We employed a mixed methods study design. Pregnant women were recruited via email and word of mouth. Participants completed a baseline demographic and technology-use survey and were asked to use the intervention over the course of two weeks. Postintervention, participants were invited to participate in an individual or group interview. Interviews were conducted to elicit feedback regarding thoughts and attitudes towards VA technology to support the health of mothers and infants. Descriptive analysis was used to summarize quantitative data (ie, survey responses, app logs) and thematic analysis was used for qualitative data (ie, transcriptions of voice recordings collected from SMILE, transcriptions of follow-up interviews). Results: Out of 46 respondents, 19 participants were consented, completed baseline surveys and used SMILE. Approximately 63\% (n=12) of participants participated in exit interviews. The sample was predominantly 25-34 years old (n=16, 84\%), part of a two-parent household (n=19, 100\%), white (n=15, 79\%), and pregnant with their first child (n=12, 63\%). Nine participants (47.4\%) reported that they practice stress management, and favorable stress-management activities were mainly comprised of exercise activities, yoga, and outdoor activities without technology involvement. Over half of the participants reported using technology to support pregnancy self-management (n=10, 53\%). However, participants preferred mobile apps for education and self-management support during pregnancy and relied on the Internet to access health-related information. More than half of participants reported using default VAs on their phone (n=11, 58\%) and on smart speakers (n=10, 53\%). Yet, VA technology was mainly reported as being used for basic tasks, such as setting a timer or reminder, checking the weather, turning on/off the lights, or playing music. Postintervention, participants verbalized that VA technology was a potential medium for receiving health information, pregnancy-related information, and could be a strategy to engage other family members in the process. Major concerns revolved around security, privacy, trust, and concerns regarding interacting via voice when in public. Conclusions: Although this research is limited by the small and predominantly white sample size, this research represents one of the first studies to explore perceptions and attitudes towards VA to promote maternal-infant health. As VA technology increases in popularity, adoption and utility to support health and well-being among pregnant women is nascent. While VA technology offers some benefits (eg, reduce literacy barriers, hands-free), familiarity and trust of nonvoice digital health tools (eg, mobile apps, Web-based content) remain important in supporting maternal-child health. Digital health solutions that incorporate multiple platforms (eg, mobile apps, Internet, voice) warrant further exploration to optimize support for maternal child health. ", doi="10.2196/15231", url="https://www.iproc.org/2019/1/e15231" } @Article{info:doi/10.2196/15229, author="Sack, Jordan and Reid, Todd and Schlossberg, Eric and Hashemi, Nikroo", title="A Smartphone App for Patients With End-Stage Liver Disease Can Detect Behavioral Changes That Predict Liver-Related Events", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15229", keywords="app", keywords="smartphone", keywords="cirrhosis", abstract="Background: Patients with end-stage liver disease have significant morbidity and mortality. The 90-day readmission rate for these patients is up to 53\% at a cost of \$4.45 billion annually. Healthcare delivery for these patients is often fragmented and inadequate. Smartphone-based remote health monitoring may reduce hospitalizations by earlier detection of premonitory warning signs associated with liver-related complications. Hepatic encephalopathy which is a common cause of hospitalization and sleep disturbance and subtle/sub-clinical behavioral changes are early warning signs. Objective: In this pilot study of patients with end-stage liver disease, we assessed the feasibility of our smartphone app to detect physiologic and behavioral changes during the 7 days prior to liver-related hospitalizations or urgent visits. Methods: This is a prospective multicenter pilot study of patients with end-stage liver disease who were enrolled at three academic centers to receive our smartphone app for a 180-day period. English speaking patients age ?18 years who receive liver care at one of the study sites, do not actively use alcohol or drugs, have had a liver-related complication in the previous 3 months (ascites, hepatic encephalopathy, variceal bleeding, bacterial peritonitis), and own an Android smartphone with internet connectivity were eligible. The smartphone app solicits emotions daily and collects passive data on activity, sleep, and social interactions. Patients received monthly in-app questions about how many liver-related events they had over the preceding month. Surveys on sociodemographic characteristics and health status were collected at baseline, 90 days, and 180 days. Clinical data on liver-related hospitalizations or urgent visits (``events'') were collected prospectively through chart review. Smartphone data on activity, sleep, social interactions, and emotions were analyzed during the 7-day period preceding a liver event and compared to the average over the study period. Statistical analyses were performed with Mann-Whitney U test. Results: An interim analysis of the 40 enrolled patients who met all eligibility criteria found that 15 patients had 27 liver-related events during the study period. These patients were predominantly men with a median age of 56 years. 61\% of these patients responded to the monthly in-app question about hospitalizations and did so with 100\% accuracy. In the 7-day period prior to the event, these patients had more sleep disturbances and changes in activity score (P=.04; P=.04). There was no statistically significant difference in social scores during the 7-day period prior to the event. Emoji selection among this group was too small for analysis. Conclusions: The interim analysis of this pilot study suggests that passive data collected from our smartphone app can detect behavioral changes that could be used to predict liver-related events. Specifically, significant changes in smartphone activity and sleep disturbances were identified during the 7-day period prior to a liver-related event. Smartphone-based remote health monitoring appears to be feasible in this patient population and has the potential to reduce hospitalizations through early detection of early warning signs. ", doi="10.2196/15229", url="http://www.iproc.org/2019/1/e15229/" } @Article{info:doi/10.2196/15227, author="Kelly, Lara and Zalkikar, Dattatray Akshay and Armstrong, G. John", title="Evaluation of the Adoption of a Connected Device to Monitor and improve patient's adherence and persistence to therapy using real-world data", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15227", keywords="adherence", keywords="persistence", keywords="connected health", keywords="digital tools", keywords="adoption", keywords="patient-centric design", abstract="Background: The HealthBeaconTM is a smart sharps bin for patients who self-inject medications at home. It is digitally connected and programmed with a patient's medication schedule and uses customized reminders to help them start and stay on track with their medication. The HealthBeacon device was launched in May 2015; since then, it has been used by 8000+ patients and has tracked 250,000+ injections across 11 markets. The HealthBeacon is designed to be passive. The patient is not asked to do anything; the device captures the act of disposal which is a highly accurate method for measuring drug adherence. Several studies on the adoption of self-tracking devices have found that the percentages of people who stopped using their device within relative short-term follow up periods may vary between 33-75\%. A behavioral analysis was completed to determine if the patient-centric design of HealthBeacon technology can overcome barriers to patient adoption and improve persistence to therapy. Objective: The objective was to evaluate the adoption of a connected device to monitor and improve patient adherence and persistence to therapy. Methods: For the purpose of the study the patients were classified into two categories. 1) If all conditions outlined below were met, the patient ``adopted'' the technology: A) Patient consented to support program; B) HealthBeacon was delivered and established in the home; C) Patient utilized the technology correctly; D) Technology successfully tracked injections and communicated with HealthBeacon platform; E) Patient remains on HealthBeacon achieving high persistence to medication or continued until treatment completion. 2) If any of the following circumstances arose, the patient was considered as ``rejected'' as they failed to adopt the technology: A) Upon introduction to HealthBeacon the patient requested a regular sharps bin; B) Patient never disposed an injection into the HealthBeacon; C) Patient has not interacted with the device for 90+ days; D) Patient accepted the HealthBeacon initially but returned it for reasons other than their treatment ending Results: Data were measured over a 24-month period from May 2017 to May 2019 for the 756 patients were involved in the study; 584 (77\%) of the patients adopted the technology and 172 (23\%) rejected it. Of the patients that adopted, 478 (82\%) continue to utilize the technology and 106 (18\%) are no longer active. The reason for stopping was associated with their treatment ending rather than an adoption issue. Of the 172 patients (23\%) rejected the technology, 26 (15\%) requested a standard sharps bin after receiving the introduction; 45 (26\%) accepted the HealthBeacon but never disposed an injection into it; 86 (50\%) used the HealthBeacon initially but had not interacted with it for 90+ days; 2 (1\%) rejected it due to a technical issue; and 13 (8\%) accepted it initially but reported that they prefer to manage adherence on their own. Conclusions: With almost 80\% of patients adopting the technology, and 82\% of the adopters persisting, this study demonstrates that patient-centered design that deploys passive adherence monitoring can overcome barriers to adoption of technology. ", doi="10.2196/15227", url="http://www.iproc.org/2019/1/e15227/" } @Article{info:doi/10.2196/15225, author="Masculo, Felipe and op den Buijs, Jorn and Simons, Mariana and Harma, Aki", title="Natural Language Processing of Medical Alert Service Notes Reveals Reasons for Emergency Admissions", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15225", keywords="data visualization", keywords="natural language processing", keywords="text data mining", abstract="Background: A Personal Emergency Response Service (PERS) enables an aging population to receive help quickly when an emergency situation occurs. The reasons that trigger a PERS alert are varied, including a sudden worsening of a chronic condition, a fall, or other injury. Every PERS case is documented by the response center using a combination of structured variables and free text notes. The text notes, in particular, contain a wealth of information in case of an incident such as contextual information, details about the situation, symptoms and more. Analysis of these notes at a population level could provide insight into the various situations that cause PERS medical alerts. Objective: The objectives of this study were to (1) develop methods to enable the large-scale analysis of text notes from a PERS response center, and (2) to apply these methods to a large dataset and gain insight into the different situations that cause medical alerts. Methods: More than 2.5 million deidentified PERS case text notes were used to train a document embedding model (ie, a deep learning Recurrent Neural Network [RNN] that takes the medical alert text note as input and produces a corresponding fixed length vector representation as output). We applied this model to 100,000 PERS text notes related to medical incidents that resulted in emergency department admission. Finally, we used t-SNE, a nonlinear dimensionality reduction method, to visualize the vector representation of the text notes in 2D as part of a graphical user interface that enabled interactive exploration of the dataset and visual analytics. Results: Visual analysis of the vectors revealed the existence of several well-separated clusters of incidents such as fall, stroke/numbness, seizure, breathing problems, chest pain, and nausea, each of them related to the emergency situation encountered by the patient as recorded in an existing structured variable. In addition, subclusters were identified within each cluster which grouped cases based on additional features extracted from the PERS text notes and not available in the existing structured variables. For example, the incidents labeled as falls (n=37,842) were split into several subclusters corresponding to falls with bone fracture (n=1437), falls with bleeding (n=4137), falls caused by dizziness (n=519), etc. Conclusions: The combination of state-of-the-art natural language processing, deep learning, and visualization techniques enables the large-scale analysis of medical alert text notes. This analysis demonstrates that, in addition to falls alerts, the PERS service is broadly used to signal for help in situations often related to underlying chronic conditions and acute symptoms such as respiratory distress, chest pain, diabetic reaction, etc. Moreover, the proposed techniques enable the extraction of structured information related to the medical alert from unstructured text with minimal human supervision. This structured information could be used, for example, to track trends over time, to generate concise medical alert summaries, and to create predictive models for desired outcomes. ", doi="10.2196/15225", url="http://www.iproc.org/2019/1/e15225/" } @Article{info:doi/10.2196/15207, author="Bradley, Dani and Cobb, Christina and Wolfberg, Adam", title="Digital Tools Fill a Gap in Mental Health Screening and Support, Particularly for Women Lacking Strong Social Networks", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15207", keywords="digital screening", keywords="mental health", keywords="reproductive health", keywords="digital support", abstract="Background: Roughly 11\% of women suffer from postpartum depression nationwide; however, many believe the condition to be widely underreported, in part due to inadequate screening and stigma associated with the condition. Social support networks can help to prevent or mitigate symptoms related to postpartum depression. Single mothers tend to suffer from this condition at a higher rate than married women as they tend to have weaker social networks compared to married women. Objective: The primary objective ws to determine whether gaps exist in mental health screening and whether digital screening tools can help to fill these gaps. The secondary objective ws to determine whether digitally delivered support proves to be more or less beneficial to subsets of women, namely based on their marital status. Methods: A survey about mental health history, support, experience with mental health screeners, and characteristics of social networks was sent by email to users of the Ovia Fertility, Ovia Pregnancy, and Ovia Parenting mobile apps. Respondents were all 18 years of age or older and living in the United States. The study was granted exemption by our institutional review board. Results: Of the 2016 respondents, 39\% reported that they were never screened by their healthcare provider for mental health conditions (26\% of women with children and 52\% of women without children). Among women who reported never being screened by a healthcare provider, 17\% reported that they have completed at least one of the screeners (PHQ-9 or Edinburgh Postnatal Depression Scale [EPDS]) in an Ovia mobile app. Of the 2016 respondents, 86\% reported being married or in a domestic partnership. Among the single respondents, 32\% reported either having children, being pregnant, or currently trying to conceive. More single women who have children, are pregnant, or are actively trying to conceive reported that they would feel most supported by a mobile appl (namely, one of Ovia Health's three mobile apps) and to seek treatment for mental health concerns compared to married women (19\% compared to 14\% of married women; P=.03). Additionally, single women who have children, are pregnant, or are actively trying to conceive reported more often than married women that they feel their mental health is best supported by a mobile appl (16\% compared to 10\% of married women; P=.007). However, both groups of women selected their healthcare provider and their friends/family as the first and second ranking support systems for both seeking mental health treatment and for mental health related support, with the mobile app ranking last. Conclusions: Screening for mental health conditions during the reproductive health journey is lacking. Digital solutions that deliver clinically validated screening tools help to screen women who are missed in a clinical setting. Women who report being single throughout parenting, pregnancy, or while trying to conceive find more value in mobile app--provided mental health support compared to married women. These findings highlight two gaps that digital technologies, like Ovia Health, can fill: low mental health screening rates during reproductive years and suboptimal social systems. ", doi="10.2196/15207", url="http://www.iproc.org/2019/1/e15207/" } @Article{info:doi/10.2196/15203, author="Polanco, Nicole and Odametey, Sharon and Derakhshani, Neda and Khachaturian, Mark and Devoe, Connor and Jethwani, Kamal and Kakarmath, Sujay", title="Evaluating the Accuracy of an Integrated Vital Sign Measurement Wellness Device", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15203", keywords="wellness device", keywords="vital signs monitoring", keywords="cuffless blood pressure monitor", keywords="patient-centric", keywords="blood pressure", keywords="heart rate", keywords="health tracking", abstract="Background: Wellness devices for health tracking have gained popularity in recent years. Additionally, portable and readily accessible wellness devices have several advantages when compared to traditional medical devices found in clinical environments. Building tools for patients to manage their health independently may benefit their health in the long run by improving health care providers' (HCPs) awareness of their patients' health information outside of the clinic. Increased access to portable wellness devices that track vital signs may increase how patients and HCPs track and monitor chronic conditions which can improve health outcomes. The VitalWellness is a portable wellness device that can potentially aid vital sign measuring for those interested in tracking their health. Objective: In this diagnostic accuracy study, we evaluated the clinical performance of the VitalWellness, a wireless, compact, non-invasive device that measures four vital signs using the index finger and forehead against reference vital signs devices used in the hospital setting. Methods: Volunteers age ?18 years were enrolled to provide blood pressure (BP), heart rate (HR), respiratory rate (RR), and body temperature. We recruited volunteers with vital signs that fell within and outside of the normal physiological range, depending on the measurements they consented to undergo. A subgroup of eligible volunteers were asked to undergo an exercise test, aerobic step test and/or a paced breathing test to analyze the VitalWellness device's performance on vital signs outside of the normal physiological ranges for HR and RR. Vital signs measurements were collected with the VitalWellness device and FDA-approved reference devices. Mean, standard deviation, mean difference, standard deviation of difference, standard error of mean difference, and correlation coefficients were calculated for measurements collected; these measurements were plotted on a scatter plot and a Bland-Altman plot. Sensitivity analyses were performed to evaluate the performance of the VitalWellness device by gender, skin color, finger size, and in the presence of artifacts. Results: We enrolled 265 volunteers in the study and 2 withdrew before study completion. The majority of volunteers were female (62\%), predominately white (63\%), graduated from college or post college (67\%), and employed (59\%). There was a moderately strong linear relationship between VitalWellness BP and reference BP (r=0.7, P<.05) and bewteen VitalWellness RR and reference RR measurements (r=0.7, P<.05). The VitalWellness HR readings were significantly in line with the reference HR readings (r=0.9, P<.05). There was a weaker linear relationship between VitalWellness temperature and reference temperature (r=0.3, P<.05). There were no differences in performance of the VitalWellness device by gender, skin color or in the presence of artifacts. Finger size was associated with differential performance for RR. Conclusions: Overall, the VitalWellness device performed well in taking BP, HR and RR when compared to FDA-approved reference devices and has potential serve as a wellness device. To test adaptability and acceptability, future research may evaluate user's interactions and experiences with the VitalWellness device at home. In addition, the next phase of the study will evaluate transmitting vital sign information from the VitalWellness device to an online secured database where information can be shared with HCPs within seconds of measurement. ", doi="10.2196/15203", url="http://www.iproc.org/2019/1/e15203/" } @Article{info:doi/10.2196/15197, author="Rogers, Jason and Fasihuddin, Farah and Black, Morgan and Kann, Rebecca and Mei, Shelly and McLaughlin, Jonathan and Atreja, Ashish", title="Developing and Implementing a Digital Navigation Program to Improve Outcomes for Medicare Bundle Patients Undergoing Joint Replacement Surgery", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15197", keywords="mHealth", keywords="mobile health (mHealth)", keywords="patient empowerment", keywords="patient monitoring", abstract="Background: Evidence-based patient education and consistent, timely communication is key to ensuring good outcomes among joint replacement patients. Mount Sinai Hospital (MSH) participates in the mandatory CMS bundle for comprehensive joint replacement (CJR). MSH's bundled payment strategy focuses on the development of a standardized model of care, built around evidence-based best practices to achieve the triple aims of strengthening population health while controlling cost and improving the quality of care. MSH launched a comprehensive digital navigation program (DNP) to guide joint replacement patients and their caregivers through pre-surgical preparation and recovery. Objective: The objective was to improve the quality of care for joint replacement patients through creation of a digital navigation program specifically tailored to Medicare patients (age 65+) across the continuum of care. Methods: Mount Sinai App Lab, in collaboration with the Department of Orthopedics, developed three digital therapeutic modules that were delivered through the RxUniverse Digital Medicine platform (Rx.Health, NY). These automated messages, programmed to send at specific times, included exercise instructions, medication reminders, and suggestions for how to prepare the home for optimal recovery. Messages specifically targeted key patient outcomes: length of stay, readmissions, ambulation on postoperative day 0, and discharge disposition. Staff ``prescribed'' each module to patients to ensure that engagement aligned with their process of care. Results: Clinicians, patients, and their caregivers were receptive to the DNP. Patients showed a high rate of engagement, clicking links to educational content 873 times, and patients called their case manager or surgeon's office to clarify their next steps when prompted. After 9 months, clinical outcomes for the digital navigation program were compared to other Medicare patients who had not received it. DNP patients had significantly shorter length of stay than their peers (2.81 vs 4.31 days). They also had a lower readmission rate (1.9\% vs 2.9\%) as well as a higher rate of discharge to home (87.8\% vs 64.3\%) and were more likely to ambulate on the day of surgery (47.9\% vs 33.3\%). Twenty patients responded to an end-of-program survey about their experience; 18 patients (90\%) agreed that the program was helpful with the process of their total joint replacement surgery, 2 patients neither agreed nor disagreed (10\%), and 0 patients disagreed. When asked about their satisfaction with the message volume, 19 patients answered ``yes, this was the perfect number,'' (95\%) and 1 patient answered ``no, I want fewer messages'' (5\%). Patient qualitative feedback was very positive. Patients reported, ``Texts reassured me and helped me along with my progress and recovery,'' and ``Good support. Thank you.'' A third said, ``The texting program serves as a great reminder as what to do and when.'' Conclusions: The CJR DNP provided a direct, automated channel to educate and support patients at each stage of care. It demonstrated that digital navigation technology can be used even among non-digital native populations. It resulted in a significantly reduced length of stay and hospital readmissions among participating patients. Next steps include scaling the program across the health system and adding Spanish-language support. Similar programs are now being implemented for other surgical and disease use cases. ", doi="10.2196/15197", url="http://www.iproc.org/2019/1/e15197/" } @Article{info:doi/10.2196/15193, author="Wandy, Tiffany and Kiritsy, Michael and Durand, Daniel", title="Improving Patient Access to Diabetic Retinopathy Screening Through Telemedicine", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15193", abstract="Background: The LifeBridge Health (LBH) Accountable Care Organization (ACO) serves approximately 20,000 Medicare beneficiaries, many of whom have type I or type II diabetes. Diabetic retinopathy (DR) screening is extremely important in helping to preserve patient's eyesight and overall functional status. However, like many other organizations, LBH has struggled with low compliance rates for DR screening. As result, LBH searched for a solution to improve DR screening care and improve ACO quality and financial performance. Objective: LifeBridge sought a telemedicine diagnostic solution that was easy for our physicians and clinic teams to use that would enable improved management of patients with diabetes. A pilot was initiated at three large primary care practice locations in the last quarter of 2017. Two of the locations received table top cameras, while the other location received a more mobile, hand held unit. Working with a dedicated LBH IRIS team, the practices created and implemented workflows, documented processes, and instilled best practices. Methods: We used a pre-post test design to measure whether implementation of this tool enabled providers to better meet the diabetic retinopathy screening measure. We included the final months of 2017 in the preperiod to account for any operational changes required to implement the new workflow. Manual chart abstraction of patients seen in the previous 4/6 weeks who were eligible to determine the proportion of patients who met the measure. This was done quarterly in every primary care practice throughout the organization. One of the three practice sites was changed halfway through 2018 and switched to another; however, both practices were included in the analysis. We also compared the number of diabetes patients in the populations of each of the four practices. A two sample z test with a P value of .05 was used to test for statistical significance. Results: As of April 2019, 810 patients were screened for diabetic retinopathy. Of these, 33.1\% (282 patients) were diagnosed with pathology. Approximately 15.6\% (n=133) were diagnosed with DR. We also identified 87 patients who are considered ``IRIS saves'' patients who had pathology identified that was serious enough to put them at imminent risk of losing their sight. For all patients requiring follow up, direct referrals were made to our in-network ophthalmologists at Krieger Eye Institute for treatment that these patients would not have otherwise received. Statistical comparison of DR screening performance of practices pre and post implementation showed mean screening rates of 38.5\% and 47.2\%, respectively, with P=.01. Conclusions: IRIS screenings allowed our primary care providers to provide more comprehensive care to patients with diabetes, eliminating the need for additional office visits. Having IRIS available in the practice was able to demonstrably improve performance in the diabetic retinopathy screening measure. As a result, primary care providerss with IRIS helped facilitate access to care, thus making it easier for patients make better choices related to their health outcomes. We hope to further use the data to study HbA1c control, medication adherence, and cost/utilization in those diagnosed with retinopathy compared to those with a negative screening. ", doi="10.2196/15193", url="http://www.iproc.org/2019/1/e15193/" } @Article{info:doi/10.2196/15181, author="Kuperman, Gilad and Baldwin-Medsker, Abigail and Rozenshteyn, Margarita and Zablocki, Melissa and Perry, Claire and Dhami, Amandeep and Simon, Brett and Daly, Robert and Chiu, Ophelia Yeneat", title="Remote Monitoring and Management of High-Risk Patients Being Started on Antineoplastic Treatment", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15181", keywords="cancer", abstract="Background: Suboptimal management of cancer-related symptoms can lead to potentially preventable emergency department visits. Early detection and management of these symptoms leads to improved patient outcomes. The goal of this program is to capture symptom data on a daily cadence from patients beginning started on antineoplastic treatment and make these data available to staff who would intervene with the aim of mitigating symptom escalation. The aims of this pilot were patient acceptance of automated questionnaires, use of data by clinical staff, and integration of digital tools into workflows. Objective: The objective was development and initial evaluation of a digitally enabled program to monitor and manage symptoms of cancer patients being started on treatment with antineoplastic drugs. Methods: Memorial Sloan Kettering Cancer Center (MSKCC) patients being started on antineoplastic treatment were eligible for inclusion. The technology supporting the program included: (i) a predictive model identifying patients at high risk for emergency department visit in the next 6 months, (ii) a patient portal enabling symptom questionnaires to be sent to enrolled patients, (iii) an internally developed application that allows staff to review and trend symptom data, (iv) ``alerts'' for concerning symptoms that are sent to a dedicated team of oncology registered nurses and nurse practitioners, and (v) a secure messaging platform for communication between staff and patients. The predictive model runs nightly to identify eligible patients. Physicians review the risk information and decide whether to enroll each patient. Enrolled patients receive a daily patient-reported outcome questionnaire to capture symptoms. Alerts are generated based on the patient's response to the symptom questions. The team reviews symptom data and interacts with the patient via phone, secure messaging, or televisits. The team collaborates with the primary oncology team as appropriate. Results: The program went live in October 2018. Fifteen medical oncologists are participating in the pilot. As of June 21, 2019, 302 patients have been evaluated by the predictive model, of which 53 have been high risk and 249 have been low risk. Physicians have enrolled a total of 86 patients. Enrolled patients have completed 4198 out of 7287 symptom questionnaires, for a completion rate of 57.6\%. Of the 4198 questionnaires, 1638 have generated a ``red alert'' (severe) symptom. Over 1200 secure messages have been exchanged between patients and staff. Lessons learned include: (i) patient acceptance of daily questionnaires has been high, (ii) the use of alerts assists the team in proactively managing participating patients, and (iii) patients and caregivers are reporting that they find the program valuable. The pilot demonstrated that daily symptom monitoring through a technology-enabled platform and a dedicated team is feasible and we are examining how the program might be scaled across our organization. Conclusions: Through the use of automated symptom questionnaires and various bidirectional communication channels, remote monitoring and management of symptoms in cancer patients is feasible. This program enables providers at MSKCC to have visibility into patient symptomatology between visits and improves our understanding of the patient's needs. The workflows of the staff monitoring the symptoms and how best to coordinate symptom management across multiple providers are areas of ongoing refinement. ", doi="10.2196/15181", url="http://www.iproc.org/2019/1/e15181/" } @Article{info:doi/10.2196/15173, author="Safioti, Guilherme and Granovsky, Lena and Li, Thomas and Reich, Michael and Cohen, Shahar and Hadar, Yonatan and Pleasants, Roy and Chrystyn, Henry and Hill, Tanisha and DePietro, Michael", title="A Predictive Model for Clinical Asthma Exacerbations Using Albuterol eMDPI (ProAir Digihaler): A Twelve-Week, Open-Label Study", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15173", keywords="asthma", keywords="digital", keywords="inhaler", keywords="predictive", keywords="digital inhaler", keywords="predictive model", keywords="clinical asthma exacerbation", keywords="albuterol", abstract="Background: The ability to identify an impending clinical asthma exacerbation (CAE) would improve asthma action plans and provide opportunities for pre-emptive treatment. Increased use of inhaled rescue medications, such as albuterol, has been observed in the days prior to a CAE, but other potential predictive factors are poorly understood. Approved by the US Food and Drug Administration (FDA) in late 2018, ProAir Digihaler with built-in sensors registers when patients use the inhaler and has been shown previously to accurately measure both peak inspiratory flow and inhalation volume, confirming the device's ability to reliably record objective information on inhaler usage and technique. Objective: Data collected from the ProAir Digihaler provides, for the first time, a more complete picture of patients' use of inhaled medication, and thereby offers an opportunity to develop a predictive model of an impending CAE, and the potential to better implement asthma action plans and facilitate early treatment. Methods: Patients (?18 years old) with exacerbation-prone asthma were recruited to a 12-week, open-label study. Patients used the ProAir Digihaler (albuterol 90 {\textmu}g 1--2 inhalations q4 hours) as needed. The electronic component of Digihaler recorded each use and inhalation variables (peak inspiratory flow, volume inhaled, time to peak flow, and inhalation duration). Data were downloaded from the inhalers and, together with clinical data, subjected to a machine-learning algorithm to develop models predictive of an impending CAE as defined by the need for oral corticosteroids. The generated model was evaluated by receiver operating characteristic (ROC) curve analysis. Results: Three hundred and sixty patients made ?1 valid inhalation from the Digihaler and were included in the analysis. Of these, 64 patients experienced a total of 78 CAEs. The strongest predictive factor during the 5 days before a CAE was the average number of albuterol inhalations per day. The predictive model was strengthened by supplementing these data with other inhalation features collected by Digihaler, including peak inhalation flow, inhalation volume, night-time usage, and trends of these parameters over time. This model predicted an impending exacerbation over the 5 days with a ROC AUC value of 0.75. Conclusions: This study represents, to our knowledge, the first successful attempt to develop a model to predict CAE derived from the use of a rescue medication inhaler device equipped with an integrated sensor and capable of measuring inhalation parameters. The predictive power of the model would benefit from further development with larger populations of asthma patients. ", doi="10.2196/15173", url="http://www.iproc.org/2019/1/e15173/" } @Article{info:doi/10.2196/15157, author="Lynett Ford, Kelsey and Bull, Sheana and Moore, L. Susan and Barrientos Ortiz, Charlene", title="Facilitating User Participation in Digital Health Research: The mHealth Impact Registry", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15157", keywords="registries", keywords="research subject recruitment", keywords="underserved", keywords="user centered design", keywords="user experience evaluation", abstract="Background: The proliferation of technology galvanizes providers, researchers, and entrepreneurs to revolutionize health care and care delivery with diverse audiences. Digital health provides promise in improving health outcomes; however, the pace of technology requires rapid research to remain relevant in the marketplace. User experience (UX) research provides critical information about patient/client preferences while rigorous research trials demonstrate digital health efficacy. Despite the need for such research, the recruitment and enrollment process for digital health research remains time consuming and expensive, particularly when engaging underrepresented populations. Developed in the Colorado School of Public Health, the mHealth Impact Registry is a newly launched platform designed for rapid and responsive recruitment of participants for digital health research studies. While the use of registries in research is robust, the application in digital health research is quite limited. Objective: This poster illustrates the development and testing of the mHealth Impact Registry's Web-based platform, health status survey, mobile app, and participant database to reach underrepresented populations in digital health research. Methods: Formative methods used a user centered approach to document user preferences for Registry design followed by iterative testing to ensure usability and navigability. Results: End-user feedback was captured from multiple stakeholder groups (ie, Patient and Family Research Advisory Panel and mHealth Community Advisory Board) to refine recruitment strategy (ie, letters, video development). A health status survey was developed in both English and Spanish using the online software (ie, Qualtrics) that informs the back-end database. A detailed requirements document outlined technical and functional requirements for the mobile app (ie, iOS and Android) and Web-based platform (ie, Wordpress and Amazon Web Services). Conclusions: Due to the need for rapid, rigorous, and inclusive research in digital health, a registry containing a pool of diverse participants would not only accelerate the recruitment and enrollment process but would also help to improve the reach and engagement of digital health solutions for underrepresented populations. The mHealth Impact Registry would house diverse participants, supporting quick enrollment and active participation in studies for which they are eligible. Improving the accessibility of participants and the speed of enrollment has promise in ensuring digital health solutions are relevant upon dissemination and commercialization. ", doi="10.2196/15157", url="http://www.iproc.org/2019/1/e15157/" } @Article{info:doi/10.2196/15130, author="Bloom, Patricia and Marx, Madeline and Wang, Thomas and Arvind, Ashwini and Ha, Jasmine and Green, Bradley and Richter, James", title="A Smartphone App Is Feasible for Outpatient Cirrhotic Ascites Management", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15130", abstract="Background: Ascites, or accumulation of abdominal free fluid, develops in two-thirds of patients with cirrhosis. Ascites is painful and, if inadequately managed, can lead to life-threatening complications, including spontaneous bacterial peritonitis and kidney failure. Body weight is an effective proxy for ascites volume; therefore, monitoring daily weights is recommended for optimal ascites management. At present, patients with ascites rarely proactively alert providers of significant weight gains, and there are no widely available technologies specifically designed for ascites monitoring. Objective: The objective of this pilot study is to assess the feasibility of a smartphone app to manage outpatient ascites. Methods: In this feasibility study, cirrhotic patients with significant ascites requiring specialist management are identified through an inpatient hepatology consult census and outpatient referrals. Each candidate is sent home with a Bluetooth-connected scale, which transmits weight data to the PGHD Connect Smartphone App, and then via the cloud into the electronic medical record (EMR). Weights are monitored every weekday by study staff and alerts are sent to providers if their patients' weight changes by ?5lbs within a week or from the weight documented at discharge. The primary outcomes are percentage of study enrollment days when weight data was successfully transmitted into the EMR and percentage of weight alerts to which providers responded. Results: Seventy-eight cirrhotic patients were identified as requiring active management of ascites. Of these patients, 8 did not own a smartphone, 23 were encephalopathic, and thus were excluded; another 1 declined to participate, and 3 were consented but subsequently withdrawn due to physical limitation or death prior to hospital discharge. Each patient is enrolled in the program for 28 days. Of the 16 patients currently enrolled, 5 (31\%) are male, mean age is 60.9 years (SD 11.1), 13 (81\%) were enrolled as inpatients, 8 (50\%) have non-alcoholic steatohepatitis cirrhosis, 4 (25\%) alcohol-associated cirrhosis, and 2 (12.5\%) viral cirrhosis. At this interim analysis, transmission of weight data into the EMR has successfully occurred on 70\% of study enrollment days. Patients experienced technology issues during 10\% of days enrolled. Of the total 20 weight alerts to date, 12 (60\%) were triggered by weight loss ?5lb in one week, 7 (35\%) by weight gain ?5lb in one week, and 1 (5\%) by weight gain ?5lb since discharge. Providers responded to 13 (65\%) of the weight alerts within 24 hours. Of the 13 alerts with a provider response, 7 (54\%) were followed by a call or email to the patient to discuss care, 4 (31\%) a scheduled appointment, 4 (31\%) a change in diuretic dosage, 3 (23\%) scheduling for paracentesis (procedure to remove ascites fluid), and 3 (23\%) further laboratory workup. To date, there have been 13 readmissions. Conclusions: On the basis of our interim analysis, we demonstrate feasibility of a martphone app to facilitate ascites management. We report encouraging rates of patient and provider engagement. This innovation shows promise in enabling early intervention and enhancing quality of life in cirrhotic patients. Future studies will investigate the efficacy of mobile health technology to improve outcomes in this population. ", doi="10.2196/15130", url="http://www.iproc.org/2019/1/e15130/" } @Article{info:doi/10.2196/15104, author="Brager, Jenna and Breitenstein, Susan and Budhathoki, Chakra and Gross, Deborah", title="Does Level of Engagement in a Digital Parent Training Program Impact Improvements in Parenting and Child Outcomes?", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15104", keywords="engagement", keywords="metadata", keywords="mobile health (mHealth)", keywords="parent-child relations", keywords="child development", keywords="mobile apps", abstract="Background: Approximately 8\% to 10\% of children younger than 5 years of age experience emotional, behavioral, and social relationship problems. These children are more likely to exhibit poor social interactions, problematic parent--child relationships, and school related setbacks, thus reinforcing the need for early interventions such as parent training programs. The ezParent program is a tablet-based delivery adaptation of the group-based Chicago Parent Program, a program designed to address the needs of families raising young children in urban poverty. The growing interest in and adoption of mHealth has changed the way people receive and seek treatment and the way clinicians deliver care. Despite the usefulness of mHealth apps in helping people manage various aspects of health, people's use of those technologies often lasts only for a short period of time. This suggests a need to delve more deeply into user behaviors. Objective: The purpose of this study was to (1) classify levels of engagement by identifying individual usage of ezParent based on observed user activity (ie, ``metadata'') and (2) examine whether levels of ezParent engagement is associated with changes in parenting and child behavior over time (ie, parenting stress, self-efficacy, warmth, follow through, punishment, child behavior problems and intensity). Methods: This study used a single-group, pre- and posttest design with repeated measures follow-up. Survey measures were collected at baseline (T1), 12 weeks postbaseline (T2) and 24 weeks postbaseline (T3). The study included 92 parents with data collected from two pediatric primary care clinics based in two urban cities with a high proportion of low income and minority families: Chicago, Illinois (cohort 1) and Baltimore, Maryland (cohort 2). Engagement was conceptualized based on total number of modules completed, amount of time spent in the program, and number of skills saved by the parent. Each outcome variable was modeled using a separate mixed-effects model to determine the model of best fit and was analyzed across time and level of engagement. Results: Overall, 78 parents logged in to the ezParent program. The data aggregation resulted in 41 parents categorized as high engagers (cohort 1 n=29; cohort 2 n=12) and 37 parents as low engagers (cohort 1 n=13; cohort 2 n=24). Significant differences were across all outcome variables: parenting stress (P<.05), self-efficacy (P<.05), warmth (P<.05), punishment (P<.05), follow-through (P<.05), child behavior intensity (P<.05), and child behavior problems (P<.05). Although parenting outcomes improved, improvements were not significantly associated with levels of engagement. Conclusions: This study provides insight into engagement of parents participating in a digitally delivered parent training program. Although level of engagement was not associated with improvements in parenting and child outcomes, we were able to systematically identify and test key usage metrics to ope rationalize engagement. This indicates that further study may help researchers identify other usage metrics more indicative of engagement. By exploring usage data, researchers, app developers, and clinicians can better understand how users engage with future tablet-based interventions. ", doi="10.2196/15104", url="http://www.iproc.org/2019/1/e15104/" } @Article{info:doi/10.2196/15091, author="Beck, Adam and Robinson, Caroline", title="The Impact of an Automated Patient Digital Engagement Platform on Revisit Reduction", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15091", abstract="Background: Revisits within 30 days to an emergency department (ED), observation care unit, or inpatient setting following patient discharge continues to be a challenge, especially in urban settings. In addition to the consequences for the patient, these revisits have a negative impact on a health system's finances in a value based care or global budget environment. Objective: The objective was to evaluate the effectiveness of a customized automated digital patient engagement application (GetWell Loop) to prevent 30-day revisits after home discharge from an ED or hospital inpatient setting. Methods: The LifeBridge Health Innovation Team collaborated with the GetWell Network to customize their patient engagement platform (GetWell Loop) with automated check-in questions and resources. An application link was emailed to adult patients discharged home from the ED. A retrospective study of ED visits for patients treated for general medicine and cardiology conditions (accounting for 24\% of our adult ED discharges) between August 1, 2018, and December 31, 2018, was conducted using CRISP, Maryland's state-designated health information exchange. We used this database to identify the index visits that experienced an emergency department visit, inpatient admission, or observation stay at any Maryland facility within 30 days of discharge. We also used data within GetWell Loop to track patient activation and engagement. The primary endpoint was a comparison of ED patients that experienced a 30-day revisit and who did or did not activate their GetWell Loop account. Secondary end points included overall activation rate and the rate of engagement as measured by the number of logins, alerts, and comments generated by patients through the platform. Statistical significance was calculated using the Fisher's exact test with a P<.05. Results: ED discharges who were treated for general medicine conditions (n=787) and activated their GetWell Loop account experienced a 30-day revisit rate of 18.9\% compared to 25.2\% who did not activate their account (P=.06). For patients treated for cardiology conditions (n=722), 10.5\% of patients who activated their GetWell account experienced a 30-day revisit compared to 17.4\% not activating their account (P=.02). During the course of this study, 26\% of patients receiving an invite to use the digital platform activated their account (n=1652) logged in a total of 4006 times, generated 734 alerts, and submitted 297 open ended comments/questions. Conclusions: These results indicate the potential value of digital health platforms to improve 30-day revisit rates. The strongest impact was observed amongst cardiology patients where the revisit rate is 39.8\% lower for patients using GetWell Loop compared to general medicine patients where the relative difference is 25.2\%. The results also indicate patients are willing to utilize a digital platform postdischarge to proactively engage in their own care. We attempted to control for potential selection bias that may impact this analysis given patient adoption and use of a digital platform by looking for differences in the subpopulations who did and did not activate the platform. LifeBridge Health is proving healthcare systems can leverage automated mobile platforms to successfully impact clinical outcomes at scale without compromising customer service and patient experience. ", doi="10.2196/15091", url="http://www.iproc.org/2019/1/e15091/" } @Article{info:doi/10.2196/15090, author="Brager, Jenna and Breitenstein, Susan and Gross, Deborah and Miller, Hailey", title="Low-Income Parents' Perceptions of and Engagement With a Digital Behavioral Training Program: Mixed Methods Study", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15090", keywords="mobile health (mHealth)", keywords="mobile health intervention", keywords="parent-child relations", keywords="digital health", abstract="Background: Parent training is a method for strengthening parenting skill, reducing child behavior problems, and promoting positive parent-child relationships. However, few parents have access to these evidence-based programs. The ezParent program, a tablet-based delivery adaptation of the group-based Chicago Parent Program (CPP), is a parent training program designed to address the needs of families raising young children in urban poverty. There is extensive evidence that positive parenting practices can be a powerful buffer against the negative effects of poverty and adversity and is one of the strongest predictors of children's social and behavioral well-being. Objective: This study aimed to explore (1) parents' perceptions of the benefits and barriers associated with their use of the ezParent program; and (2) the ways in which the ezParent components and perceived usability varied by program use (module completion). Methods: This study uses an explanatory mixed-method design. Data were collected from 92 participants recruited from two pediatric primary care clinics (PPC) based in two urban cities with a high proportion of low income and minority families: Chicago, Illinois (cohort 1) and Baltimore, Maryland (cohort 2). Cohort 1 (n=42) was recruited between October 2013 and June 2014 as part of a randomized controlled tirla. Cohort 2 (n=50) was recruited between May 2017 and July 2017 as part of a single group design. The current report focuses on a subsample from cohorts 1 and 2 who were interviewed about their experiences using the program. To explore parents' perceptions of ezParent (ie, perceived usefulness of content, ease of use, barriers to use, qualities affecting interest, and intention), all participants were invited to participate in an individual interview after the 12th week. Based on degree of module completion, we grouped parents into two user groups: high (completed 4-6 modules) and low (completed 0-3 modules). This cut-off was chosen based on previous data showing that parents who attended at least 50\% of the CPP group sessions reported greater improvements in parenting self-efficacy, use of discipline, and warmth towards their children, as well as fewer child behavior problems. Results: Fifty-nine parents participated in follow-up interview: 32 (54.24\%) from cohort 1 and 27 (45.76\%) from cohort 2. Among those interviewed, 23 (38.9.5\%) parents completed all six modules and 12 parents (20.3\%) completed none of the modules. Specifically, among those interviewed, parents completed an average of 3.73 (SD 2.39) modules compared to an average of 1.79 (SD 2.38) modules completed among those not interviewed. Parents who completed more modules reported more program benefits and those who completed fewer modules reported more barriers. Conclusions: Exploring users' experience with current digital applications, researchers and application developers can better design future tablet-based interventions to be both effective and acceptable by end users. Furthering our understanding of factors associated with engagement will inform more effective tailoring and improvements of mHealth interventions, particularly those targeting vulnerable populations. ", doi="10.2196/15090", url="http://www.iproc.org/2019/1/e15090/" } @Article{info:doi/10.2196/15069, author="Saad, Ezzat and Kamoun, Claire", title="Deployment and Assessment of a Virtual Coaching Platform to Support Healthy Habits and Whole Health for Vulnerable People Living with HIV", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15069", keywords="digital divide", keywords="HIV infections/prevention and control", keywords="psychosocial aspects", abstract="Background: Office of Health and Human Services of Rhode Island (0HHS-RI) provides care to the most vulnerable people in the state living with HIV. While most of their clients achieve viral load suppression, the majority of these individuals still lack the support they need to tackle mental health issues, manage comorbidities, be physically active, and address other social determinants of Health. Digital health technologies have demonstrated value to provide this support and help people manage whole health. Digital platforms can deliver tailored health interventions and improved outcomes for people with HIV. However, this vulnerable population most in need of that support lacks access to current technology and platforms designed to meet their particular needs. Objective: The objective wo design, deploy, and assess an evidence-based digital health platform to support healthy habits and improve outcomes for the target population, TAVIE Red. The platform is the product of two years of patient-centered iterative design and built upon theories of behavioral medicine. The core technology is a clinically-validated virtual nurse app that delivers tailored education to users. On the patient app, clients self-manage health (eg, monitor symptoms and receive treatment reminders), access social services (eg, locate food banks and clinics) and receive evidence-based interventions to promote mental and physical health (eg, decrease stress and increase physical activity). Users receive personalized feedback and rewards that incentivize and engage during each phase of treatment. On the professional portal, case managers can monitor clients remotely, receive actionable insights, and intervene appropriately. Administrators access real-time analytics on health status and delivery of services through a set of customizable dashboards. Methods: Eligible clients received an Android phone preloaded with the app. Case managers received access to the professional platform on a desktop and in some cases, tablet devices to use the app in the field. Three generations of the platform were deployed over a two-year period. Participants completed a survey at baseline and follow-up on paper and digitally through the app. Thus far, 200 people living with HIV have participated in this program along with their case managers. Results: Two years into the project, users are engaged with the app, enjoying it, and benefiting from it. Seventy-seven percent of users actively engage with the app, earning points and progressing through the coaching sessions with 67\% completing self-assessments through the app and most track measures including physical activity, symptoms, and CD4 count and viral load. There was a 5\% increase in viral suppression in this population over two years. Eighty-eight percent of users recommend the app to others. Conclusions: To date, the TAVIE platform is an engaging appealing platform. Users remain on the app over time and report great benefits of use. Formal evaluation of outcomes ongoing. ", doi="10.2196/15069", url="http://www.iproc.org/2019/1/e15069/" } @Article{info:doi/10.2196/15005, author="Hurtado, Suzanne and Simon-Arndt, Cynthia and Dell'Acqua, Renee", title="Acceptability and Short-Term Outcomes Associated With Use of a Prescription Drug Abuse Education Mobile App in a Military Sample", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e15005", keywords="app", keywords="military personnel", keywords="patient education", keywords="prescription drug misuse", abstract="Background: Prescription drug misuse and abuse are serious issues affecting the nation, and military personnel have not been exempt from this problem. However, standards for military personnel in this area are more stringent than those for civilians, and the stakes of even unintentional misuse are higher. For these reasons, it is essential to educate service members about prescription drug misuse and abuse, using a variety of novel approaches. Objective: The objective of this study was to evaluate the acceptability of an educational app and its impact on prescription medication misuse risks among active-duty service members who were currently taking a prescription medication with the potential for misuse. Methods: A randomized controlled trial was conducted to pilot test the app among 80 service members. Participants were randomized to either the app along with treatment as usual (TAU) or just to continue with TAU. Self-report data, collected at pretest and 1-month posttest, included risk of prescription drug misuse, preparedness to talk about prescription drug misuse, knowledge, attitudes, perceived harm, behavioral intentions, medication use, pain, and mental well-being, using a combination of standardized scales and investigator-developed items. In addition, ratings of the app were collected from those in the intervention condition. Results: Preparedness to talk to doctors or leadership about a personal concern related to one's own possible prescription drug misuse increased significantly from pretest to posttest (P=.02). Participants in the intervention condition significantly increased their communication preparedness about a personal concern (P=.01), while those in the TAU condition showed no change (P>.05). In addition, there was a marginally significant interaction between group and time on preparedness to talk to others about their possible misuse (P<.06). No other significant group-by-time interactions were observed for the other outcomes measured. Participants found the app useful (mean3.85), and agreed that they learned new information (mean 3.97), that the app was appropriate for military service members (mean 3.97), and that they would recommend it to fellow service members (mean 3.86; rating scale 1=strongly disagree to 5=strongly agree). Conclusions: The finding that patients using the app felt more prepared to talk to their chain of command or doctor about possible personal prescription drug misuse suggests that the app enhanced their comfort in communicating about prescription drug misuse. One of the goals of the scenarios in the app was to help participants walk through how they would handle a variety of situations related to communicating about prescription drug misuse. Among military personnel, talking to leadership about sensitive issues is often intimidating and uncomfortable, particularly about issues that involve one's own risk, making this shift a rather promising finding. Despite some limitations, and a lack of significant findings among the study's other measures, use of this mobile health tool was associated with a shift toward reducing prescription drug misuse risk in the area of communication, suggesting that it constitutes a valuable addition to the arsenal of multifaceted efforts to decrease prescription drug misuse. ", doi="10.2196/15005", url="" } @Article{info:doi/10.2196/14935, author="Simon-Arndt, Cynthia and Hurtado, Suzanne and Kohen, Casey and Hunter, Michael and Sanchez, Sandra", title="Lessons Learned From Implementing an App-Based Resilience Training Program in a Naval Operational Setting", journal="iproc", year="2019", month="Oct", day="2", volume="5", number="1", pages="e14935", keywords="app", keywords="decision making", keywords="military personnel", keywords="stress", keywords="resilience", abstract="Background: Enhancing resilience and reducing stress are critical to increasing the readiness and performance of military personnel in operational settings. Stress and resilience programs can improve service members' ability to manage their stress during both normal and extreme operational conditions, and have the potential to enhance safety at sea. Implementing an efficient and effective application-based training program in a military setting has unique challenges, including minimizing intrusion on the command's training time and technological considerations (eg, Wi-Fi and Bluetooth technology restrictions). Objective: An enhanced version of a training program called the Stress Resilience Training System (SRTS) was implemented into the operating environment of a naval vessel. The system contains an in-person workshop, regular mentoring in resilience-building techniques, and an iPad-based app used for biofeedback of heart rate variability coherence and training support. This work describes the lessons learned from the implementation process of the app component of the program, based on responses from active duty service members. Methods: Crew members aboard a Navy vessel (N=92) volunteered to participate in the evaluation of the 10-week program. All ship personnel were provided with an initial 2.5-hour workshop, mentorship, and iPads containing the SRTS app to use for the duration of the 10-week program. Participants rated different components of the training, and their app usage during the course of the study was recorded. Results: Participants somewhat agreed that the app was appropriate for military service members (mean 2.51, SD 1.14; response options 0=strongly disagree to 4=strongly agree for all ratings) and were somewhat likely to recommend the app to fellow service members (mean 2.53, SD 1.03). Ratings of the workshop's relevance to military readiness (mean 2.68, SD 0.95) and of the instructors' credibility (mean 3.22, SD 0.92) were higher than ratings of the app. Additionally, usage of the app was low and highly variable (mean 42.26, SD 60.53; range 0 to 312.54 minutes). Anecdotal evidence provided by crewmembers suggested that using the app on an iPad was cumbersome and that the Wi-Fi was often inaccessible, making the iPad a less valuable tool overall. Conclusions: This implementation of the app component of SRTS raised questions regarding the suitability of the technological format for this operational setting. User ratings and participant comments suggested that the technology was not the most successful component of the program. The implementation in the iPad format was not conducive to the operational setting and the inconvenience of this format may have deterred participants from using it in settings where a personal or more compact device may have been more appropriate. Recommendations going forward include making the app component available for use on smartphones operating on both iOS and Android platforms to make it user friendly, accessible, and more engaging, which, in turn, is expected to increase usage and uptake of the program's techniques. Furthermore, incorporating more engaging content, gamification, and tracking and reporting user progress into the overall app may enhance motivation to use more components of the app and increase usage, ultimately enhancing its impact on resilience. ", doi="10.2196/14935", url="http://www.iproc.org/2019/1/e14935/" }