Effect of a Structured Multilevel Telehealth Service on Hospital Admissions and Mortality During COVID-19 in a Resource-Limited Region in Brazil: Retrospective Cohort Study.

BACKGROUND: The COVID-19 pandemic represented a great stimulus for the adoption of telehealth and many initiatives in this field have emerged worldwide. However, despite this massive growth, data addressing the effectiveness of telehealth with respect to clinical outcomes remain scarce. OBJECTIVE: The aim of this study was to evaluate the impact of the adoption of a structured multilevel telehealth service on hospital admissions during the acute illness course and the mortality of adult patients with flu syndrome in the context of the COVID-19 pandemic. METHODS: A retrospective cohort study was performed in two Brazilian cities where a public COVID-19 telehealth service (TeleCOVID-MG) was deployed. TeleCOVID-MG was a structured multilevel telehealth service, including (1) first response and risk stratification through a chatbot software or phone call center, (2) teleconsultations with nurses and medical doctors, and (3) a telemonitoring system. For this analysis, we included data of adult patients registered in the Flu Syndrome notification databases who were diagnosed with flu syndrome between June 1, 2020, and May 31, 2021. The exposed group comprised patients with flu syndrome who used TeleCOVID-MG at least once during the illness course and the control group comprised patients who did not use this telehealth service during the respiratory illness course. Sociodemographic characteristics, comorbidities, and clinical outcomes data were extracted from the Brazilian official databases for flu syndrome, Severe Acute Respiratory Syndrome (due to any respiratory virus), and mortality. Models for the clinical outcomes were estimated by logistic regression. RESULTS: The final study population comprised 82,182 adult patients with a valid registry in the Flu Syndrome notification system. When compared to patients who did not use the service (n=67,689, 82.4%), patients supported by TeleCOVID-MG (n=14,493, 17.6%) had a lower chance of hospitalization during the acute respiratory illness course, even after adjusting for sociodemographic characteristics and underlying medical conditions (odds ratio [OR] 0.82, 95% CI 0.71-0.94; P=.005). No difference in mortality was observed between groups (OR 0.99, 95% CI 0.86-1.12; P=.83). CONCLUSIONS: A telehealth service applied on a large scale in a limited-resource region to tackle COVID-19 was related to reduced hospitalizations without increasing the mortality rate. Quality health care using inexpensive and readily available telehealth and digital health tools may be delivered in areas with limited resources and should be considered as a potential and valuable health care strategy. The success of a telehealth initiative relies on a partnership between the involved stakeholders to define the roles and responsibilities; set an alignment between the different modalities and levels of health care; and address the usual drawbacks related to the implementation process, such as infrastructure and accessibility issues.

Acoustic Analysis of Speech for Screening for Suicide Risk: Machine Learning Classifiers for Between- and Within-Person Evaluation of Suicidality.

BACKGROUND: Assessing a patient's suicide risk is challenging for health professionals because it depends on voluntary disclosure by the patient and often has limited resources. The application of novel machine learning approaches to determine suicide risk has clinical utility. OBJECTIVE: This study aimed to investigate cross-sectional and longitudinal approaches to assess suicidality based on acoustic voice features of psychiatric patients using artificial intelligence. METHODS: We collected 348 voice recordings during clinical interviews of 104 patients diagnosed with mood disorders at baseline and 2, 4, 8, and 12 months after recruitment. Suicidality was assessed using the Beck Scale for Suicidal Ideation and suicidal behavior using the Columbia Suicide Severity Rating Scale. The acoustic features of the voice, including temporal, formal, and spectral features, were extracted from the recordings. A between-person classification model that examines the vocal characteristics of individuals cross sectionally to detect individuals at high risk for suicide and a within-person classification model that detects considerable worsening of suicidality based on changes in acoustic features within an individual were developed and compared. Internal validation was performed using 10-fold cross validation of audio data from baseline to 2-month and external validation was performed using data from 2 to 4 months. RESULTS: A combined set of 12 acoustic features and 3 demographic variables (age, sex, and past suicide attempts) were included in the single-layer artificial neural network for the between-person classification model. Furthermore, 13 acoustic features were included in the extreme gradient boosting machine learning algorithm for the within-person model. The between-person classifier was able to detect high suicidality with 69% accuracy (sensitivity 74%, specificity 62%, area under the receiver operating characteristic curve 0.62), whereas the within-person model was able to predict worsening suicidality over 2 months with 79% accuracy (sensitivity 68%, specificity 84%, area under receiver operating characteristic curve 0.67). The second model showed 62% accuracy in predicting increased suicidality in external sets. CONCLUSIONS: Within-person analysis using changes in acoustic features within an individual is a promising approach to detect increased suicidality. Automated analysis of voice can be used to support the real-time assessment of suicide risk in primary care or telemedicine.

Building a Chatbot in a Pandemic.

Easy access to evidence-based information on COVID-19 within an infodemic has been a challenging task. Chatbots have been introduced in times of emergency, when human resources are stretched thin and individuals need a user-centered resource. The World Health Organization Regional Office for Europe and UNICEF (United Nations Children's Fund) Europe and Central Asia came together to build a chatbot, HealthBuddy+, to assist country populations in the region to access accurate COVID-19 information in the local languages, adapted to the country context. Working in close collaboration with thematic technical experts, colleagues and counterparts at the country level allowed the project to be tailored to a diverse range of subtopics. To ensure that HealthBuddy+ was relevant and useful in countries across the region, the 2 regional offices worked closely with their counterparts in country offices, which were essential in partnering with national authorities, engaging communities, promoting the tool, and identifying the most relevant communication channels in which to embed HealthBuddy+. Over the past 2 years, the project has expanded from a web-based chatbot in 7 languages to a multistream, multifunction chatbot available in 16 regional languages, and HealthBuddy+ continues to expand and adjust to meet emerging health emergency needs.

Evaluation of the Rosa Chatbot Providing Genetic Information to Patients at Risk of Hereditary Breast and Ovarian Cancer: Qualitative Interview Study.

BACKGROUND: Genetic testing has become an integrated part of health care for patients with breast or ovarian cancer, and the increasing demand for genetic testing is accompanied by an increasing need for easy access to reliable genetic information for patients. Therefore, we developed a chatbot app (Rosa) that is able to perform humanlike digital conversations about genetic BRCA testing. OBJECTIVE: Before implementing this new information service in daily clinical practice, we wanted to explore 2 aspects of chatbot use: the perceived utility and trust in chatbot technology among healthy patients at risk of hereditary cancer and how interaction with a chatbot regarding sensitive information about hereditary cancer influences patients. METHODS: Overall, 175 healthy individuals at risk of hereditary breast and ovarian cancer were invited to test the chatbot, Rosa, before and after genetic counseling. To secure a varied sample, participants were recruited from all cancer genetic clinics in Norway, and the selection was based on age, gender, and risk of having a BRCA pathogenic variant. Among the 34.9% (61/175) of participants who consented for individual interview, a selected subgroup (16/61, 26%) shared their experience through in-depth interviews via video. The semistructured interviews covered the following topics: usability, perceived usefulness, trust in the information received via the chatbot, how Rosa influenced the user, and thoughts about future use of digital tools in health care. The transcripts were analyzed using the stepwise-deductive inductive approach. RESULTS: The overall finding was that the chatbot was very welcomed by the participants. They appreciated the 24/7 availability wherever they were and the possibility to use it to prepare for genetic counseling and to repeat and ask questions about what had been said afterward. As Rosa was created by health care professionals, they also valued the information they received as being medically correct. Rosa was referred to as being better than Google because it provided specific and reliable answers to their questions. The findings were summed up in 3 concepts: "Anytime, anywhere"; "In addition, not instead"; and "Trustworthy and true." All participants (16/16) denied increased worry after reading about genetic testing and hereditary breast and ovarian cancer in Rosa. CONCLUSIONS: Our results indicate that a genetic information chatbot has the potential to contribute to easy access to uniform information for patients at risk of hereditary breast and ovarian cancer, regardless of geographical location. The 24/7 availability of quality-assured information, tailored to the specific situation, had a reassuring effect on our participants. It was consistent across concepts that Rosa was a tool for preparation and repetition; however, none of the participants (0/16) supported that Rosa could replace genetic counseling if hereditary cancer was confirmed. This indicates that a chatbot can be a well-suited digital companion to genetic counseling.

Multicriteria Decision-Making in Diabetes Management and Decision Support: Systematic Review.

BACKGROUND: Diabetes mellitus prevalence is increasing among adults and children around the world. Diabetes care is complex; examining the diet, type of medication, diabetes recognition, and willingness to use self-management tools are just a few of the challenges faced by diabetes clinicians who should make decisions about them. Making the appropriate decisions will reduce the cost of treatment, decrease the mortality rate of diabetes, and improve the life quality of patients with diabetes. Effective decision-making is within the realm of multicriteria decision-making (MCDM) techniques. OBJECTIVE: The central objective of this study is to evaluate the effectiveness and applicability of MCDM methods and then introduce a novel categorization framework for their use in this field. METHODS: The literature search was focused on publications from 2003 to 2023. Finally, by applying the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) method, 63 articles were selected and examined. RESULTS: The findings reveal that the use of MCDM methods in diabetes research can be categorized into 6 distinct groups: the selection of diabetes medications (19 publications), diabetes diagnosis (12 publications), meal recommendations (8 publications), diabetes management (14 publications), diabetes complication (7 publications), and estimation of diabetes prevalence (3 publications). CONCLUSIONS: Our review showed a significant portion of the MCDM literature on diabetes. The research highlights the benefits of using MCDM techniques, which are practical and effective for a variety of diabetes challenges.

Artificial intelligence-enabled tools in cardiovascular medicine: A survey of current use, perceptions, and challenges.

Background: Numerous artificial intelligence (AI)-enabled tools for cardiovascular diseases have been published, with a high impact on public health. However, few have been adopted into, or have meaningfully affected, routine clinical care. Objective: To evaluate current awareness, perceptions, and clinical use of AI-enabled digital health tools for patients with cardiovascular disease, and challenges to adoption. Methods: This mixed-methods study included interviews with 12 cardiologists and 8 health information technology (IT) administrators, and a follow-on survey of 90 cardiologists and 30 IT administrators. Results: We identified 5 major challenges: (1) limited knowledge, (2) insufficient usability, (3) cost constraints, (4) poor electronic health record interoperability, and (5) lack of trust. A minority of cardiologists were using AI tools; more were prepared to implement AI tools, but their sophistication level varied greatly. Conclusion: Most respondents believe in the potential of AI-enabled tools to improve care quality and efficiency, but they identified several fundamental barriers to wide-scale adoption.

Use of smartphone application versus written titration charts for basal insulin titration in adults with type 2 diabetes and suboptimal glycaemic control (My Dose Coach): multicentre, open-label, parallel, randomised controlled trial.

Background: The majority of people with type 2 diabetes who require insulin therapy use only basal insulin in combination with other anti-diabetic agents. We tested whether using a smartphone application to titrate insulin could improve glycaemic control in people with type 2 diabetes who use basal insulin. Methods: This was a 12-week, multicentre, open-label, parallel, randomised controlled trial conducted in 36 diabetes practices in Germany. Eligible participants had type 2 diabetes, a BMI ≥25.0 kg/m2, were on basal insulin therapy or were initiating basal insulin therapy, and had suboptimal glycaemic control (HbA1c >7.5%; 58.5 mmol/mol). Block randomisation with 1:1 allocation was performed centrally. Participants in the intervention group titrated their basal insulin dose using a smartphone application (My Dose Coach) for 12 weeks. Control group participants titrated their basal insulin dose according to a written titration chart. The primary outcome was the baseline-adjusted change in HbA1c at 12 weeks. The intention-to-treat analysis included all randomised participants. Results: Between 13 July 2021 and 21 March 2022, 251 study participants were randomly assigned (control group: n = 123; intervention group: n = 128), and 236 completed the follow-up phase (control group: n = 119; intervention group: n = 117). Regarding the HbA1c a model-based adjusted between-group difference of -0.31% (95% CI: 0.01%-0.69%; p = 0.0388) in favour of the intervention group was observed. There were 30 adverse events reported: 16 in the control group, 14 in the intervention group. Of these, 15 adverse events were serious. No event was considered to be related to the investigational device. Interpretation: Study results suggest that utilizing this digital health smartphone application for basal insulin titration may have resulted in a comparatively greater reduction in HbA1c levels among individuals with type 2 diabetes, as compared to basal insulin titration guided by a written titration schedule. No negative effect on safety outcomes was observed. Funding: Sanofi-Aventis Deutschland GmbH.

Using Decision Trees as an Expert System for Clinical Decision Support for COVID-19.

COVID-19 has impacted billions of people and health care systems globally. However, there is currently no publicly available chatbot for patients and care providers to determine the potential severity of a COVID-19 infection or the possible biological system responses and comorbidities that can contribute to the development of severe cases of COVID-19. This preliminary investigation assesses this lack of a COVID-19 case-by-case chatbot into consideration when building a decision tree with binary classification that was stratified by age and body system, viral infection, comorbidities, and any manifestations. After reviewing the relevant literature, a decision tree was constructed using a suite of tools to build a stratified framework for a chatbot application and interaction with users. A total of 212 nodes were established that were stratified from lung to heart conditions along body systems, medical conditions, comorbidities, and relevant manifestations described in the literature. This resulted in a possible 63,360 scenarios, offering a method toward understanding the data needed to validate the decision tree and highlighting the complicated nature of severe cases of COVID-19. The decision tree confirms that stratification of the viral infection with the body system while incorporating comorbidities and manifestations strengthens the framework. Despite limitations of a viable clinical decision tree for COVID-19 cases, this prototype application provides insight into the type of data required for effective decision support.

Public Use of the "Your COVID Recovery" Website Designed to Help Individuals Manage Their COVID-19 Recovery: Observational Study.

BACKGROUND: At the start of the COVID-19 pandemic, unprecedented pressure was placed on health care services globally. An opportunity to alleviate this pressure was to introduce a digital health platform that provided COVID-19-related advice and helped individuals understand and manage their COVID-19 symptoms. Therefore, in July 2020, the Your COVID Recovery website was launched by the National Health Service of England with the aim of creating a practical tool that provides advice and support to individuals recovering from COVID-19. The website includes information on many of the key COVID-19 symptoms. To date, public use of the Your COVID Recovery website and user behavior remain unknown. However, this information is likely to afford insight into the impact of the website and most commonly experienced COVID-19 symptoms. OBJECTIVE: This study aimed to evaluate public use of the Your COVID Recovery website, a digital health platform that provides support to individuals recovering from COVID-19, and determine user behavior during its first year of operation. METHODS: Google Analytics software that was integrated into the Your COVID Recovery website was used to assess website use and user behavior between July 31, 2020, and July 31, 2021. Variables that were tracked included the number of users, user country of residence, traffic source, number of page views, number of session views, and mean session duration. User data were compared to COVID-19 case data downloaded from the UK government's website. RESULTS: During the study period, 2,062,394 users accessed the Your COVID Recovery website. The majority of users were located in the United Kingdom (1,265,061/2,062,394, 61.30%) and accessed the website via a search engine (1,443,057/2,062,394, 69.97%). The number of daily website users (n=15,298) peaked on January 18, 2021, during the second wave of COVID-19 in the United Kingdom. The most frequently visited pages after the home page were for the following COVID-19 symptoms: Cough (n=550,190, 12.17%), Fatigue (n=432,421, 9.56%), Musculoskeletal pain (n=406,859, 9.00%), Taste and smell (n=270,599, 5.98%), and Breathlessness (n=203,136, 4.49%). The average session duration was 1 minute 13 seconds. CONCLUSIONS: A large cohort of individuals actively sought help with their COVID-19 recovery from the website, championing the potential of this tool to target an unmet health care need. User behavior demonstrated that individuals were primarily seeking advice on how to relieve and manage COVID-19 symptoms, especially symptoms of cough, fatigue, and musculoskeletal pain. COVID-19 rehabilitation programs should use the results of this study to ensure that the program content meets the needs of the post-COVID-19 population.

Health Outcomes Following Engagement With a Digital Health Tool Among People With Prediabetes and Type 2 Diabetes: Prospective Evaluation Study.

BACKGROUND: Diabetes is a worldwide chronic condition causing morbidity and mortality, with a growing economic burden on health care systems. Complications from poorly controlled diabetes are associated with increased socioeconomic costs and reduced quality of life. Smartphones have become an influential platform, providing feasible tools such as health apps to deliver tailored support to enhance the ability of patients with diabetes for self-management. Gro Health is a National Health Service division X-certified digital health tool used to deliver educational and monitoring support to facilitate the development of skills and practices for maintaining good health. OBJECTIVE: This study aims to assess self-reported outcomes of the Gro Health app among users with diabetes and prediabetes and identify the factors that determine engagement with the digital health tool. METHODS: This was a service evaluation of self-reported data collected prospectively by the developers of the Gro Health app. The EQ-5D questionnaire is a standardized tool used to measure health status for clinical and economic appraisal. Gro Health users completed the EQ-5D at baseline and 6 months after using the app. Users provided informed consent for the use of their anonymized data for research purposes. EQ-5D index scores and visual analogue scale (VAS) scores were calculated at baseline and 6 months for individuals with prediabetes and type 2 diabetes. Descriptive statistics and multiple-regression models were used to assess changes in the outcome measures and determine factors that affected engagement with the digital tool. RESULTS: A total of 84% (1767/2114) of Gro Health participants completed EQ-5D at baseline and 6 months. EQ-5D index scores are average values that reflect people's preferences about their health state (1=full health and 0=moribund). There was a significant and clinically meaningful increase in mean EQ-5D index scores among app users between baseline (0.746, SD 0.23) and follow-up (0.792, SD 0.22; P<.001). The greatest change was observed in the mean VAS score, with a percentage change of 18.3% improvement (61.7, SD 18.1 at baseline; 73.0, SD 18.8 at follow-up; P<.001). Baseline EQ-5D index scores, age, and completion of educational modules were associated with significant changes in the follow-up EQ-5D index scores, with baseline EQ-5D index scores, race and ethnicity, and completion of educational modules being significantly associated with app engagement (P<.001). CONCLUSIONS: This study provides evidence of a significant positive effect on self-reported quality of life among people living with type 2 diabetes engaging with a digital health intervention. The improvements, as demonstrated by the EQ-5D questionnaire, are facilitated through access to education and monitoring support tools within the app. This provides an opportunity for health care professionals to incorporate National Health Service-certified digital tools, such as Gro Health, as part of the holistic management of people living with diabetes.

Developing and Evaluating a Measure of the Willingness to Use Pandemic-Related mHealth Tools Using National Probability Samples in the United States: Quantitative Psychometric Analyses and Tests of Sociodemographic Group Differences.

BACKGROUND: There are no psychometrically validated measures of the willingness to engage in public health screening and prevention efforts, particularly mobile health (mHealth)-based tracking, that can be adapted to future crises post-COVID-19. OBJECTIVE: The psychometric properties of a novel measure of the willingness to participate in pandemic-related screening and tracking, including the willingness to use pandemic-related mHealth tools, were tested. METHODS: Data were from a cross-sectional, national probability survey deployed in 3 cross-sectional stages several weeks apart to adult residents of the United States (N=6475; stage 1 n=2190, 33.82%; stage 2 n=2238, 34.56%; and stage 3 n=2047, 31.62%) from the AmeriSpeak probability-based research panel covering approximately 97% of the US household population. Five items asked about the willingness to use mHealth tools for COVID-19-related screening and tracking and provide biological specimens for COVID-19 testing. RESULTS: In the first, exploratory sample, 3 of 5 items loaded onto 1 underlying factor, the willingness to use pandemic-related mHealth tools, based on exploratory factor analysis (EFA). A 2-factor solution, including the 3-item factor, fit the data (root mean square error of approximation [RMSEA]=0.038, comparative fit index [CFI]=1.000, standardized root mean square residual [SRMR]=0.005), and the factor loadings for the 3 items ranged from 0.849 to 0.893. In the second, validation sample, the reliability of the 3-item measure was high (Cronbach α=.90), and 1 underlying factor for the 3 items was confirmed using confirmatory factor analysis (CFA): RMSEA=0, CFI=1.000, SRMR=0 (a saturated model); factor loadings ranged from 1.000 to 0.962. The factor was independently associated with COVID-19-preventive behaviors (eg, "worn a face mask": r=0.313, SE=0.041, P<.001; "kept a 6-foot distance from those outside my household": r=0.282, SE=0.050, P<.001) and the willingness to provide biological specimens for COVID-19 testing (ie, swab to cheek or nose: r=0.709, SE=0.017, P<.001; small blood draw: r=0.684, SE=0.019, P<.001). In the third, multiple-group sample, the measure was invariant, or measured the same thing in the same way (ie, difference in CFI [ΔCFI]<0.010 across all grouping categories), across age groups, gender, racial/ethnic groups, education levels, US geographic region, and population density (ie, rural, suburban, urban). When repeated across different samples, factor-analytic findings were essentially the same. Additionally, there were mean differences (ΔM) in the willingness to use mHealth tools across samples, mainly based on race or ethnicity and population density. For example, in SD units, suburban (ΔM=-0.30, SE=0.13, P=.001) and urban (ΔM=-0.42, SE=0.12, P<.001) adults showed less willingness to use mHealth tools than rural adults in the third sample collected on May 30-June 8, 2020, but no differences were detected in the first sample collected on April 20-26, 2020. CONCLUSIONS: Findings showed that the screener is psychometrically valid. It can also be adapted to future public health crises. Racial and ethnic minority adults showed a greater willingness to use mHealth tools than White adults. Rural adults showed more mHealth willingness than suburban and urban adults. Findings have implications for public health screening and tracking and understanding digital health inequities, including lack of uptake.

Assessment of a Digital Symptom Checker Tool's Accuracy in Suggesting Reproductive Health Conditions: Clinical Vignettes Study.

BACKGROUND: Reproductive health conditions such as endometriosis, uterine fibroids, and polycystic ovary syndrome (PCOS) affect a large proportion of women and people who menstruate worldwide. Prevalence estimates for these conditions range from 5% to 40% of women of reproductive age. Long diagnostic delays, up to 12 years, are common and contribute to health complications and increased health care costs. Symptom checker apps provide users with information and tools to better understand their symptoms and thus have the potential to reduce the time to diagnosis for reproductive health conditions. OBJECTIVE: This study aimed to evaluate the agreement between clinicians and 3 symptom checkers (developed by Flo Health UK Limited) in assessing symptoms of endometriosis, uterine fibroids, and PCOS using vignettes. We also aimed to present a robust example of vignette case creation, review, and classification in the context of predeployment testing and validation of digital health symptom checker tools. METHODS: Independent general practitioners were recruited to create clinical case vignettes of simulated users for the purpose of testing each condition symptom checker; vignettes created for each condition contained a mixture of condition-positive and condition-negative outcomes. A second panel of general practitioners then reviewed, approved, and modified (if necessary) each vignette. A third group of general practitioners reviewed each vignette case and designated a final classification. Vignettes were then entered into the symptom checkers by a fourth, different group of general practitioners. The outcomes of each symptom checker were then compared with the final classification of each vignette to produce accuracy metrics including percent agreement, sensitivity, specificity, positive predictive value, and negative predictive value. RESULTS: A total of 24 cases were created per condition. Overall, exact matches between the vignette general practitioner classification and the symptom checker outcome were 83% (n=20) for endometriosis, 83% (n=20) for uterine fibroids, and 88% (n=21) for PCOS. For each symptom checker, sensitivity was reported as 81.8% for endometriosis, 84.6% for uterine fibroids, and 100% for PCOS; specificity was reported as 84.6% for endometriosis, 81.8% for uterine fibroids, and 75% for PCOS; positive predictive value was reported as 81.8% for endometriosis, 84.6% for uterine fibroids, 80% for PCOS; and negative predictive value was reported as 84.6% for endometriosis, 81.8% for uterine fibroids, and 100% for PCOS. CONCLUSIONS: The single-condition symptom checkers have high levels of agreement with general practitioner classification for endometriosis, uterine fibroids, and PCOS. Given long delays in diagnosis for many reproductive health conditions, which lead to increased medical costs and potential health complications for individuals and health care providers, innovative health apps and symptom checkers hold the potential to improve care pathways.

An mHealth App (eSkinHealth) for Detecting and Managing Skin Diseases in Resource-Limited Settings: Mixed Methods Pilot Study.

BACKGROUND: In sub-Saharan Africa, the disease burden from skin diseases, including skin-related neglected tropical diseases (skin NTDs), is extremely high. These diseases often are overlooked due to limited access to health care stemming from, for example, remote geographical locations and a lack of experts. To address these gaps, we developed a mobile health app, eSkinHealth, which is a field-adapted platform to serve as a portable electronic patient chart and for teledermatology. OBJECTIVE: The purpose of the study is to evaluate the usability and effectiveness of the app in rural Côte d'Ivoire for diagnosing and managing skin NTDs and other skin diseases. METHODS: A 2-arm trial with local health care providers and patients with skin diseases was implemented over a 3-month period. The providers were assigned to an intervention receiving the eSkinHealth app or control with usual care. Four nurses and 8 community health care workers participated in each arm. The training was provided on the use of the app to the intervention arm only, while both arms were trained on skin diseases. For the usability study, we evaluated our approach with the System Usability Scale (SUS) and in-depth interviews. For the effectiveness study, our primary outcome was to evaluate the detection and management of 5 skin NTDs as our targeted diseases, namely, Buruli ulcer, leprosy, lymphatic filariasis, scabies, and yaws, using the eSkinHealth app. Procedures of our methods were reviewed and approved by the institutional review board of the Ministry of Health and by Tulane University. RESULTS: The mean age of our participants (providers) was 40.5 and 42.5 years for the intervention and control arms, respectively, and all were male (n=24). The average SUS scores taken from the intervention arm at baseline, the midpoint (6 weeks), and the end of study (12 weeks) were 72.3 (SD 11.5), 72.3 (SD 12.4), and 86.3 (SD 10.8), respectively. All participants interviewed, including 4 dermatologists and program managers, were satisfied with the app. Especially community health care workers felt empowered by being equipped with the tool. A total of 79 cases of skin NTDs were reported in the intervention arm as compared to 17 cases in the control arm (P=.002). Besides the skin NTDs, more skin diseases and conditions were reported from the control than from the intervention arm (P<.001). However, 100 cases (66%) were not given any particular diagnosis in the control arm and were documented only as a "dermatosis." In the intervention arm, 151 cases (72.9%) were diagnosed within the eSkinHealth platform, and the remaining were diagnosed on-site by dermatologists. CONCLUSIONS: The study provided evidence for the usability and effectiveness of the eSkinHealth app embedded into our surveillance approach to improve the detection and management of skin NTDs and other skin diseases in Côte d'Ivoire and, furthermore, is expected to contribute to knowledge on mobile health approaches in the control of skin diseases in resource-limited settings. TRIAL REGISTRATION: ClinicalTrials.gov NCT05300399; https://clinicaltrials.gov/ct2/show/NCT05300399.

Patient Perceptions of e-Visits: Qualitative Study of Older Adults to Inform Health System Implementation.

BACKGROUND: Electronic visits (e-visits) are billable, asynchronous patient-initiated messages that require at least five minutes of medical decision-making by a provider. Unequal use of patient portal tools like e-visits by certain patient populations may worsen health disparities. To date, no study has attempted to qualitatively assess perceptions of e-visits in older adults. OBJECTIVE: In this qualitative study, we aimed to understand patient perceptions of e-visits, including their perceived utility, barriers to use, and care implications, with a focus on vulnerable patient groups. METHODS: We conducted a qualitative study using in-depth structured individual interviews with patients from diverse backgrounds to assess their knowledge and perceptions surrounding e-visits as compared with unbilled portal messages and other visit types. We used content analysis to analyze interview data. RESULTS: We conducted 20 interviews, all in adults older than 65 years. We identified 4 overarching coding categories or themes. First, participants were generally accepting of the concept of e-visits and willing to try them. Second, nearly two-thirds of the participants voiced a preference for synchronous communication. Third, participants had specific concerns about the name "e-visit" and when to choose this type of visit in the patient portal. Fourth, some participants indicated discomfort using or accessing technology for e-visits. Financial barriers to the use of e-visits was not a common theme. CONCLUSIONS: Our findings suggest that older adults are generally accepting of the concept of e-visits, but uptake may be limited due to their preference for synchronous communication. We identified several opportunities to improve e-visit implementation.

Answering Hospital Caregivers' Questions at Any Time: Proof-of-Concept Study of an Artificial Intelligence-Based Chatbot in a French Hospital.

BACKGROUND: Access to accurate information in health care is a key point for caregivers to avoid medication errors, especially with the reorganization of staff and drug circuits during health crises such as the COVID­19 pandemic. It is, therefore, the role of the hospital pharmacy to answer caregivers' questions. Some may require the expertise of a pharmacist, some should be answered by pharmacy technicians, but others are simple and redundant, and automated responses may be provided. OBJECTIVE: We aimed at developing and implementing a chatbot to answer questions from hospital caregivers about drugs and pharmacy organization 24 hours a day and to evaluate this tool. METHODS: The ADDIE (Analysis, Design, Development, Implementation, and Evaluation) model was used by a multiprofessional team composed of 3 hospital pharmacists, 2 members of the Innovation and Transformation Department, and the IT service provider. Based on an analysis of the caregivers' needs about drugs and pharmacy organization, we designed and developed a chatbot. The tool was then evaluated before its implementation into the hospital intranet. Its relevance and conversations with testers were monitored via the IT provider's back office. RESULTS: Needs analysis with 5 hospital pharmacists and 33 caregivers from 5 health services allowed us to identify 7 themes about drugs and pharmacy organization (such as opening hours and specific prescriptions). After a year of chatbot design and development, the test version obtained good evaluation scores: its speed was rated 8.2 out of 10, usability 8.1 out of 10, and appearance 7.5 out of 10. Testers were generally satisfied (70%) and were hoping for the content to be enhanced. CONCLUSIONS: The chatbot seems to be a relevant tool for hospital caregivers, helping them obtain reliable and verified information they need on drugs and pharmacy organization. In the context of significant mobility of nursing staff during the health crisis due to the COVID-19 pandemic, the chatbot could be a suitable tool for transmitting relevant information related to drug circuits or specific procedures. To our knowledge, this is the first time that such a tool has been designed for caregivers. Its development further continued by means of tests conducted with other users such as pharmacy technicians and via the integration of additional data before the implementation on the 2 hospital sites.

Validation of an Electronic Visual Analog Scale App for Pain Evaluation in Children and Adolescents With Symptomatic Hypermobility: Cross-sectional Study.

BACKGROUND: Rapid advances in mobile apps for clinical data collection for pain evaluation have resulted in more efficient data handling and analysis than traditional paper-based approaches. As paper-based visual analogue scale (p-VAS) scores are commonly used to assess pain levels, new emerging apps need to be validated prior to clinical application with symptomatic children and adolescents. OBJECTIVE: This study aimed to assess the validity and reliability of an electronic visual analogue scale (e-VAS) method via a mobile health (mHealth) App in children and adolescents diagnosed with hypermobility spectrum disorder/hypermobile Ehlers-Danlos syndrome (HSD/HEDS) in comparison with the traditional p-VAS. METHODS: Children diagnosed with HSD/HEDS aged 5-18 years were recruited from a sports medicine center in Sydney (New South Wales, Australia). Consenting participants assigned in random order to the e-VAS and p-VAS platforms were asked to indicate their current lower limb pain level and completed pain assessment e-VAS or p-VAS at one time point. Instrument agreement between the 2 methods was determined from the intraclass correlation coefficient (ICC) and through Bland-Altman analysis. RESULTS: In total, 43 children with HSD/HEDS aged 11 (SD 3.8) years were recruited and completed this study. The difference between the 2 VAS platforms of median values was 0.20. Bland-Altman analysis revealed a difference of 0.19 (SD 0.95) with limits of agreement ranging -1.67 to 2.04. An ICC of 0.87 (95% CI 0.78-0.93) indicated good reliability. CONCLUSIONS: These findings suggest that the e-VAS mHealth App is a validated tool and a feasible method of collecting pain recording scores when compared with the traditional paper format in children and adolescents with HSD/HEDS. The e-VAS App can be reliably used for pediatric pain evaluation, and it could potentially be introduced into daily clinical practice to improve real-time symptom monitoring. Further research is warranted to investigate the usage of the app for remote support in real clinical settings.

Understanding Mental Health Apps for Youth: Focus Group Study With Latinx Youth.

BACKGROUND: An increasing number of mental health apps (MHapps) are being developed for youth. In addition, youth are high users of both technologies and MHapps. However, little is known about their perspectives on MHapps. MHapps might be particularly well suited to reach the youth underserved by traditional mental health resources, and incorporating their perspectives is especially critical to ensure such tools are useful to them. OBJECTIVE: The goal of this study was to develop and pilot a process for eliciting youth perspectives on MHapps in a structured and collaborative way. We also sought to generate learnings on the perspectives of Latinx youth on MHapps and their use in ways that might facilitate discovery, activation, or engagement in MHapps, especially in Latinx populations. METHODS: We created a series of focus groups consisting of 5 sessions. The groups introduced different categories of MHapps (cognitive behavioral therapy apps, mindfulness apps, and miscellaneous apps). Within each category, we selected 4 MHapps that participants chose to use for a week and provided feedback through both between-session and in-session activities. We recruited 5 youths ranging in age from 15 to 21 (mean 18, SD 2.2) years. All the participants identified as Hispanic or Latinx. After completing all 5 focus groups, the participants completed a brief questionnaire to gather their impressions of the apps they had used. RESULTS: Our focus group methodology collected detailed and diverse information about youth perspectives on MHapps. However, we did identify some aspects of our methods that were less successful at engaging the youth, such as our between-session activities. The Latinx youth in our study wanted apps that were accessible, relatable, youth centric, and simple and could be integrated with their offline lives. We also found that the mindfulness apps were viewed most favorably but that the miscellaneous and cognitive behavioral therapy apps were viewed as more impactful. CONCLUSIONS: Eliciting youth feedback on MHapps is critical if these apps are going to serve a role in supporting their mental health and well-being. We refined a process for collecting feedback from the youth and identified factors that were important to a set of Latinx youth. Future work could be broader, that is, recruit larger samples of more diverse youth, or deeper, that is, collect more information from each youth around interests, needs, barriers, or facilitators or better understand the various impacts of MHapps by using qualitative and quantitative measures. Nevertheless, this study advances the formative understanding of how the youth, particularly Latinx youth, might be viewing these tools.

Digital Screening and Automated Resource Identification System to Address COVID-19-Related Behavioral Health Disparities: Feasibility Study.

BACKGROUND: Digital mental health (DMH) tools use technology (eg, websites and mobile apps) to conveniently deliver mental health resources to users in real time, reducing access barriers. Underserved communities facing health care provider shortages and limited mental health resources may benefit from DMH tools, as these tools can help improve access to resources. OBJECTIVE: This study described the development and feasibility evaluation of the Emotional Needs Evaluation and Resource Guide for You (ENERGY) System, a DMH tool to meet the mental health and resource needs of youth and their families developed in the context of the COVID-19 pandemic. The ENERGY System offers a brief assessment of resource needs; problem-solving capabilities; and symptoms of depression, anxiety, trauma, and alcohol and substance use followed by automated, personalized feedback based on the participant's responses. METHODS: Individuals aged ≥15 years were recruited through community partners, community events, targeted electronic health record messages, and social media. Participants completed screening questions to establish eligibility, entered demographic information, and completed the ENERGY System assessment. Based on the participant's responses, the ENERGY System immediately delivered digital resources tailored to their identified areas of need (eg, relaxation). A subset of participants also voluntarily completed the following: COVID-19 Exposure and Family Impact Survey (CEFIS) or COVID-19 Exposure and Family Impact Survey Adolescent and Young Adult Version (CEFIS-AYA); resource needs assessment; and feedback on their experience using the ENERGY System. If resource needs (eg, housing and food insecurity) were endorsed, lists of local resources were provided. RESULTS: A total of 212 individuals accessed the ENERGY System link, of which 96 (45.3%) completed the screening tool and 86 (40.6%) received resources. Participant responses on the mental health screening questions triggered on average 2.04 (SD 1.94) intervention domains. Behavioral Activation/Increasing Activities was the most frequently launched intervention domain (56%, 54/96), and domains related to alcohol or substance use were the least frequent (4%, 4/96). The most frequently requested support areas were finances (33%, 32/96), transportation (26%, 25/96), and food (24%, 23/96). The CEFIS and CEFIS-AYA indicated higher than average impacts from the pandemic (ie, average scores >2.5). Participants were satisfied with the ENERGY System overall (65%, 39/60) as well as the length of time it took to answer the questions (90%, 54/60), which they found easy to answer (87%, 52/60). CONCLUSIONS: This study provided initial support for the feasibility of the ENERGY System, a DMH tool capable of screening for resource and mental health needs and providing automated, personalized, and free resources and techniques to meet the identified needs. Future studies should seek direct feedback from community members to further improve the ENERGY System and its dissemination to encourage use.

Equity and Accessibility of Washington State's COVID-19 Digital Exposure Notification Tool (WA Notify): Survey and Listening Sessions Among Community Leaders.

BACKGROUND: In November 2020, WA Notify, Washington State's COVID-19 digital exposure notification tool, was launched statewide to mitigate ongoing COVID-19 transmission. WA Notify uses the Bluetooth proximity-triggered, Google/Apple Exposure Notification Express framework to distribute notifications to users who have added or activated this tool on their smartphones. This smartphone-based tool relies on sufficient population-level activation to be effective; however, little is known about its adoption among communities disproportionately impacted by the COVID-19 pandemic or what barriers might limit its adoption and use among diverse populations. OBJECTIVE: We sought to (1) conduct a formative exploration of equity-related issues that may influence the access, adoption, and use of WA Notify, as perceived by community leaders of populations disproportionately impacted by the COVID-19 pandemic; and (2) generate recommendations for promoting the equitable access to and impact of this novel intervention for these communities. METHODS: We used a 2-step data collection process to gather the perspectives of community leaders across Washington regarding the launch and implementation of WA Notify in their communities. A web-based, brief, and informational survey measured the perceptions of the community-level familiarity and effectiveness of WA Notify at slowing the spread of COVID-19 and identified potential barriers and concerns to accessing and adopting WA Notify (n=17). Semistructured listening sessions were conducted to expand upon survey findings and explore the community-level awareness, barriers, facilitators, and concerns related to activating WA Notify in greater depth (n=13). RESULTS: Our findings overlap considerably with those from previous mobile health equity studies. Digital literacy, trust, information accessibility, and misinformation were highlighted as key determinants of the adoption and use of WA Notify. Although WA Notify does not track users or share data, community leaders expressed concerns about security, data sharing, and personal privacy, which were cited as outweighing the potential benefits to adoption. Both the survey and informational sessions indicated low community-level awareness of WA Notify. Community leaders recommended the following approaches to improve engagement: tailoring informational materials for low-literacy levels, providing technology navigation, describing more clearly that WA Notify can help the community, and using trusted messengers who are already engaged with the communities to communicate about WA Notify. CONCLUSIONS: As digital public health tools, such as WA Notify, emerge to address public health problems, understanding the key determinants of adoption and incorporating equity-focused recommendations into the development, implementation, and communication efforts around these tools will be instrumental to their adoption, use, and retention.

Identifying Risk Factors, Patient-Reported Experience and Outcome Measures, and Data Capture Tools for an Individualized Pain Prediction Tool in Pediatrics: Focus Group Study.

BACKGROUND: The perioperative period is a data-rich environment with potential for innovation through digital health tools and predictive analytics to optimize patients' health with targeted prehabilitation. Although some risk factors for postoperative pain following pediatric surgery are already known, the systematic use of preoperative information to guide personalized interventions is not yet widespread in clinical practice. OBJECTIVE: Our long-term goal is to reduce the incidence of persistent postsurgical pain (PPSP) and long-term opioid use in children by developing personalized pain risk prediction models that can guide clinicians and families to identify targeted prehabilitation strategies. To develop such a system, our first objective was to identify risk factors, outcomes, and relevant experience measures, as well as data collection tools, for a future data collection and risk modeling study. METHODS: This study used a patient-oriented research methodology, leveraging parental/caregiver and clinician expertise. We conducted virtual focus groups with participants recruited at a tertiary pediatric hospital; each session lasted approximately 1 hour and was composed of clinicians or family members (people with lived surgical experience and parents of children who had recently undergone a procedure requiring general anesthesia) or both. Data were analyzed thematically to identify potential risk factors for pain, as well as relevant patient-reported experience and outcome measures (PREMs and PROMs, respectively) that can be used to evaluate the progress of postoperative recovery at home. This guidance was combined with a targeted literature review to select tools to collect risk factor and outcome information for implementation in a future study. RESULTS: In total, 22 participants (n=12, 55%, clinicians and n=10, 45%, family members) attended 10 focus group sessions; participants included 12 (55%) of 22 persons identifying as female, and 12 (55%) were under 50 years of age. Thematic analysis identified 5 key domains: (1) demographic risk factors, including both child and family characteristics; (2) psychosocial risk factors, including anxiety, depression, and medical phobias; (3) clinical risk factors, including length of hospital stay, procedure type, medications, and pre-existing conditions; (4) PREMs, including patient and family satisfaction with care; and (5) PROMs, including nausea and vomiting, functional recovery, and return to normal activities of daily living. Participants further suggested desirable functional requirements, including use of standardized and validated tools, and longitudinal data collection, as well as delivery modes, including electronic, parent proxy, and self-reporting, that can be used to capture these metrics, both in the hospital and following discharge. Established PREM/PROM questionnaires, pain-catastrophizing scales (PCSs), and substance use questionnaires for adolescents were subsequently selected for our proposed data collection platform. CONCLUSIONS: This study established 5 key data domains for identifying pain risk factors and evaluating postoperative recovery at home, as well as the functional requirements and delivery modes of selected tools with which to capture these metrics both in the hospital and after discharge. These tools have been implemented to generate data for the development of personalized pain risk prediction models.