JMIR Formative Research最新文献

{"title":"Feasibility, Acceptability, and Appropriateness of an 8-Week Supervised Aerobic Exercise Intervention for Adults With Epilepsy: Pilot Randomized Controlled Trial.","authors":"Sydney Churchill, Jeni Lansing, Angelique Brellenthin, Alison Phillips, Elizabeth Stegemöller, Jacob Meyer","doi":"10.2196/97392","DOIUrl":"10.2196/97392","url":null,"abstract":"<p><strong>Background: </strong>Epilepsy affects multiple dimensions of health. Exercise may serve as a nonpharmacological strategy to improve health outcomes among adults with epilepsy; however, translating this potential into effective and scalable interventions remains challenging. Before advancing to efficacy trials, early-stage research is needed to establish whether exercise interventions are feasible, acceptable, and appropriate for this population.</p><p><strong>Objective: </strong>This study aimed to evaluate the feasibility, acceptability, and appropriateness of an 8-week supervised aerobic exercise intervention for adults with epilepsy, guided by the Obesity-Related Behavioral Intervention Trials (ORBIT) model.</p><p><strong>Methods: </strong>Adults with epilepsy aged 18-65 years were recruited between April 2024 and December 2024 and randomized to either a supervised aerobic exercise intervention (n=4) or a control group (n=2). The exercise group completed an 8-week supervised aerobic exercise program consisting of 50-minute sessions performed 3 days per week. The intervention incorporated behavior change techniques, including goal setting, action planning, habit formation, and commitment contracts to support exercise adherence. Process feasibility outcomes included recruitment, retention, adherence, survey completion, protocol compliance, and safety. Self-reported feasibility, acceptability, and appropriateness were assessed using the Feasibility of Intervention Measure, Acceptability of Intervention Measure, and Intervention Appropriateness Measure.</p><p><strong>Results: </strong>Overall, 34 individuals expressed interest in the study, 25 completed the screening survey, 10 were preliminarily eligible, and 6 were enrolled in the study over 8 months. Recruitment was low, with a recruitment rate of 0.75 participants per month and enrollment achievement of 16.7% of the target sample (target n=36). Retention and adherence were 100%. All exercise participants completed 24/24 sessions, with 100% weekly survey completion. Protocol compliance was high. No seizures occurred during exercise sessions. Mean scores for self-reported feasibility, acceptability, and appropriateness were high (>4 out of 5).</p><p><strong>Conclusions: </strong>The results of this Phase IIb pilot study suggest that a supervised aerobic exercise intervention for adults with epilepsy is feasible, acceptable, and appropriate to implement among participants who enroll. Recruitment remains the primary challenge to progressing this line of research and may represent a broader field-level barrier. Future trials should focus on improving how adults with epilepsy are reached and engaged in exercise research while preserving intervention strategies that support strong engagement among those who enroll.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e97392"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149147919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Human-in-the-Loop Suicide Risk Detection and Clinical Escalation in a Generative AI Mental Health Chatbot: Prospective Implementation Study.","authors":"Suzette Glasner, Darcy Michero, Matthew Stewart","doi":"10.2196/106118","DOIUrl":"https://doi.org/10.2196/106118","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Mental illness is the leading cause of disability worldwide, affecting more than one billion individuals, and suicide accounts for 720,000 to 800,000 deaths annually. While AI-native mental health chatbots have the potential to fill a sizable gap between treatment need and workforce capacity, their rapid proliferation has outpaced the development of scalable procedures to identify, detect, and respond to suicidal ideation. Despite AI best practice recommendations to incorporate human oversight for safety monitoring and intervention, studies of procedures for human clinical oversight and crisis response are scarce.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To implement a human-in-the-loop suicide risk screening, detection, and clinical escalation protocol in a generative AI mental health chatbot.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In an implementation study of a human-in-the-loop suicide risk detection and escalation protocol, adults were recruited online to participate in a single-arm trial of an AI-native mental health chatbot. Participants completed a pre-treatment screening using the Patient Health Questionnaire-9 (PHQ-9). In Phase 1, individuals who endorsed suicidal ideation were escalated to a human clinician for further assessment, safety planning and provision of referral resources, as appropriate. In Phase 2, escalation was triggered by either PHQ-9 responses or detection of spontaneous disclosure of implicit or explicit suicidality in conversational AI interactions. In both phases, the Ask Suicide-Screening Questionnaire (ASQ) guided human-led assessment and risk stratification. Prevalence of suicidal ideation was assessed, along with the rate of successful human outreach, time from suicidality risk detection to human outreach and results of risk stratification evaluation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In Phase 1, 624 participants completed suicide screening, of whom 81 (13.0%) endorsed PHQ-9 item 9 (score &gt;1). Outreach was initiated a mean of 11.2 minutes after the alert (SD=13.2; range 1-54 minutes). A clinician successfully reached 25/81 participants (30.9%). In Phase 2, 650 participants completed screening, of whom 133 (20.5%) screened positive at baseline. Across the 30 day post-baseline observation period, 284 risk-alert events were generated among 172 participants (26.5%), including 50 conversational suicidal ideation events. Clinicians successfully contacted 73/172 participants (42.4%). Time from risk detection to clinician outreach initiation was an average of 11.5 minutes (SD 11.7; range 1-58 minutes).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Proactive, universal suicide risk screening and conversational detection using a human-in-the-loop protocol can be operationally implemented for individuals utilizing a Generative AI mental health chatbot. A subgroup of those who were responsive to human clinical outreach described the approach as acceptable and helpful. Given that contact and clinical assessment were no","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149148239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Order System Redesign in Emergency-to-Intensive Care Unit Admissions: Prospective Observational Study.","authors":"Ding-Kuo Chien, Wei Hung Chang, Chih Wei Ten, Jung-Mei Tsai, Li-Kuo Kuo, Shih-Yi Lee","doi":"10.2196/88230","DOIUrl":"10.2196/88230","url":null,"abstract":"<p><strong>Background: </strong>Emergency-to-intensive care unit (ICU) admissions are high-stakes transitions in care, where delays or documentation errors can compromise patient safety and disrupt operational efficiency. Although digital order systems can support these workflows, traditional platforms often lack real-time traceability and structured input logic, leaving them vulnerable to duplicate submissions, lost orders, and misaligned ICU bed reservations.</p><p><strong>Objective: </strong>The study aimed to examine whether an updated digital order system was associated with differences in emergency-to-ICU admission workflows, including order validity, documentation-error frequencies, and ICU reservation alignment, compared with those of the traditional platform.</p><p><strong>Methods: </strong>We conducted a single-center retrospective historical-control formative evaluation of emergency-to-ICU admissions processed through traditional (2023) and updated (2024) digital order systems at a tertiary medical center. Prospectively generated system log and ICU-reservation data were analyzed to quantify order validity, error subtypes (duplicate, lost, and tracking), and admission-to-reservation alignment. Proportions were compared using chi-square tests, with risk ratios (RRs) and absolute differences in proportions reported. Statistical significance was defined as <i>P</i><.05.</p><p><strong>Results: </strong>The updated system was associated with higher admission-order validity (54.1%-75.4%; RR 1.39, 95% CI 1.25-1.54; <i>P</i><.001) and lower erroneous-order frequency (45.9%-24.6%; RR 0.54, 95% CI 0.44-0.66; <i>P</i><.001). Duplicate and lost orders declined, whereas tracking-error frequency showed no meaningful change. ICU reservation alignment also differed, with the admission-to-reservation ratio rising from 0.68 to 0.78 (RR 0.88, 95% CI 0.77-0.99; <i>P</i>=.03).</p><p><strong>Conclusions: </strong>The updated digital order system was associated with more consistent emergency-to-ICU workflow patterns, including higher order validity, fewer documentation errors, and closer alignment between admission intent and ICU reservations. These findings are consistent with literature on structured electronic order systems, digital-workflow standardization, and timestamp integrity, and they highlight the potential value of structured, timestamp-driven digital infrastructures in supporting more reliable high-acuity workflows. Further evaluation using time-motion analysis, interaction-log metrics, or mixed methods assessment is warranted to examine the robustness and generalizability of these patterns.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e88230"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652527/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149148337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Etiology, Clinical Features, and Outcomes of Acute Poisoning Among Children at a Provincial Pediatric Hospital in Vietnam: Retrospective Descriptive Study.","authors":"Cao Thanh Vu, Tien Dat Pham, Anh Tuyet Bui, Huy Quan Dam, Van Hung Lanh, Pak Chhengpay, Thi Hoa Luu, Thi Thuyet Luong, Thi Thu Huyen Pham, Minh Manh To, Van Lap Khuc","doi":"10.2196/97091","DOIUrl":"10.2196/97091","url":null,"abstract":"<p><strong>Background: </strong>Acute poisoning in children remains a significant cause of emergency admission and is largely preventable. Its epidemiological profile varies across settings according to age, household environment, and locally available toxic agents. Understanding the patterns, management, and outcomes of pediatric poisoning is important for improving prevention and clinical care.</p><p><strong>Objective: </strong>This study aimed to characterize the demographic and exposure patterns, treatment practices, and in-hospital outcomes of acute poisoning among children treated at a provincial pediatric hospital in Vietnam.</p><p><strong>Methods: </strong>We conducted a hospital-based retrospective descriptive study of children aged <16 years treated for acute poisoning at Thai Binh Pediatric Hospital, Vietnam, from January 1, 2023, to December 31, 2025. Hospital records were screened using prespecified eligibility criteria. Data included age, sex, time from poisoning to hospital presentation, exposure location and intent, route and agent of poisoning, recorded treatment measures, and in-hospital outcomes. Analyses were descriptive, with variable-specific denominators used when data were missing.</p><p><strong>Results: </strong>Of the 326 records identified, 276 were included in the final analysis. Children aged 1 to 5 years accounted for the largest proportion (n=151, 54.7%), and 53.6% (n=148) were male. Time from poisoning to hospital presentation was not reported for 12.3% (n=34) of the children; 67.4% (n=186) presented to the hospital within 6 hours after poisoning. Poisoning occurred mainly at home (n=266, 96.4%) and was predominantly unintentional (n=265, 96%). All 11 intentional poisonings occurred in children aged >10 years. Ingestion was the main route of exposure (n=220, 79.7% documented exposure routes). Chemical substances, medications, and food were prominent agent groups among the classifiable agents reported in the dataset. Intravenous fluids were recorded in 80.4% (n=222) of children, gastric lavage in 26.1% (n=72), and single-dose activated charcoal in 24.3% (n=67). Overall, 97.5% (n=269) of children were discharged from the study hospital and 2.5% (n=7) were transferred to a national hospital. Final outcomes after transfer were unavailable. No deaths occurred at the study hospital.</p><p><strong>Conclusions: </strong>Pediatric acute poisoning treated at this provincial hospital mainly affected young children and most often resulted from unintentional exposure in the home. The study identifies locally relevant exposure patterns that can guide household prevention and age-specific risk reduction. Most children were discharged from the study hospital, but final outcomes were unavailable for transferred patients; therefore, the findings should not be interpreted as demonstrating uniformly favorable outcomes or the appropriateness of specific treatments.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e97091"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13651977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149147916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-Physician Areas in Japan: Typological Classification Based on Regional Demographic Characteristics.","authors":"Takashi Kuwayama, Kazuhiko Kotani","doi":"10.2196/101570","DOIUrl":"10.2196/101570","url":null,"abstract":"<p><strong>Background: </strong>Across Japan, there are \"non-physician areas\" where medical institutions are not present and health care access is difficult. Although these areas are defined as a single administrative category, they may vary according to regional demographic characteristics. Understanding this possible heterogeneity may be important for developing more context-sensitive strategies to improve health care accessibility.</p><p><strong>Objective: </strong>This study examined whether non-physician areas can be classified based on regional demographic characteristics using an unsupervised machine learning model.</p><p><strong>Methods: </strong>A total of 590 non-physician areas were identified from the national survey conducted by the Ministry of Health, Labour and Welfare of Japan (2019). Data on regional demographic characteristics were also obtained. After <i>z</i> score standardization, k-means clustering was used for classification. The optimal number of clusters was determined using silhouette scores. The data on non-physician areas were divided into training (354/590, 60.0% areas) and validation (236/590, 40.0% areas) datasets. The reproducibility of the cluster structure was evaluated using Jensen-Shannon distance and chi-square tests, and principal component analysis (PCA) was used to examine the overall structure of the clusters.</p><p><strong>Results: </strong>The optimal number of clusters was 3 (silhouette score=0.266), indicating that non-physician areas could be classified into 3 types. The cluster distributions of the training and validation datasets were consistent (Jensen-Shannon distance=0.017; <i>P</i>=.76), supporting the reproducibility of the cluster structure. The PCA suggested that differences among non-physician areas could be interpreted along 2 axes, including population age structure and settlement size. The 3 clusters represented younger, intermediate, and older types, characterized by differences in demographic and settlement characteristics.</p><p><strong>Conclusions: </strong>The present study demonstrated that administratively defined non-physician areas in Japan are not uniform and can be classified into 3 demographically distinct types. The typology may provide a framework for understanding differences not captured by the current administrative designation and for considering more context-sensitive health care strategies.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e101570"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652521/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149147747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feasibility and Methodological Consideration of Using Wearable Devices to Examine the Relationship Between Sleep and Balance: Case Report With 2 College Students.","authors":"Yuan Li, Hongwu Wang, Raghuveer Chandrashekhar, Jordan Major, Mahek Chandna, Stefanie C Bodison","doi":"10.2196/93019","DOIUrl":"10.2196/93019","url":null,"abstract":"<p><strong>Unlabelled: </strong>This exploratory case study primarily examined the feasibility of using consumer-grade wearable devices for longitudinal sleep tracking and observed descriptive visual trends between sleep patterns and balance performance. Two college students participated over 4 months. Participant 1 used an Apple Watch Series 5 and an OURA ring; participant 2 used a Fitbit Charge 5 and an OURA ring. Data were collected continuously alongside daily sleep diaries and monthly sensory organization test (SOT) balance assessments. As a primary feasibility outcome, missing data rates were initially high (up to 75.2%) but improved significantly after implementing structured weekly check-ins, dropping to 14.1% and 20.3% for the wrist devices, 9.4% and 25% for the OURA rings, and 0% and 6.25% for the sleep diaries in the optimized phase. Wearables showed varying concordance with sleep diaries for time in bed (TIB), with the Apple Watch showing the least bias (-0.6 min) and the Fitbit and OURA overestimating TIB. While devices showed excellent within-participant agreement for total sleep time (intraclass correlation coefficient=0.97-0.99), agreement was poor for specific sleep stages. Regarding secondary exploratory observations, descriptive visual trends showed that fluctuations in sleep timing and duration coincided with changes in SOT visual subscale scores. In conclusion, consumer wearables are feasible for long-term sleep monitoring when supported by active compliance protocols. While sleep consistency was visually patterned alongside postural stability, these balance findings are strictly exploratory, hypothesis-generating, and not generalizable due to the small sample size and potential practice effects from repeated testing.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e93019"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652396/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149147953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Individualized Therapy Optimization for Type 2 Diabetes: Retrospective Study of Model Development, Internal Validation, and Physician Evaluation.","authors":"Arina Lozhkina, Camillo Dario Piazza, Zeina Gabr, Maurice Rupp, David Herzig, Lia Bally, Andre Jaun","doi":"10.2196/92877","DOIUrl":"10.2196/92877","url":null,"abstract":"<p><strong>Background: </strong>Type 2 diabetes is a widespread chronic condition in which blood glucose and body weight management constitute essential therapeutic targets. Emerging technologies have the potential to aid complex therapeutic pharmacotherapy choices that are optimally tailored to individual needs.</p><p><strong>Objective: </strong>In this study, we developed and evaluated an AI model combining guidelines with clinical features and continuous glucose monitoring (CGM) to optimize therapeutic decision-making.</p><p><strong>Methods: </strong>Therapeutic guidelines were first encoded using a rule-based model and trained on a feed-forward neural network to predict the probability of therapeutic success for individual treatment recommendations. This approach relied on real-world evidence from a specialist diabetes outpatient clinic, using historical clinical data generated between 2009 and 2023. We used data from 533 patients with a diagnosis of type 2 diabetes and complete baseline data for weight and hemoglobin A_1c within relevant therapy windows, resulting in a total of 853 treatment regimens. Transfer learning was used to optimize for glucose-lowering therapies that led to successful treatment outcomes, defined as an absolute 0.3% reduction in hemoglobin A_1c (when it is over 6.5%) without weight gain in patients with a BMI over 28 kg/m². Recommendations that deviated from the guidelines were described using Shapley values and tested in digital twins for statistical significance. Four CGM-derived glucose-insulin response dynamic factors served as additional biomarkers.</p><p><strong>Results: </strong>Dual glycemic and weight targets were achieved in actual clinical practice in 51.2% (131/256) of cases, increasing to 54% (20/37) when clinical guidelines were followed. After selecting outcomes in the test set that followed individualized recommendations, this increased further to 58% (21/36) when using only phenotypic markers and to 65% (22/34) when adding CGM-derived dynamic factors.</p><p><strong>Conclusions: </strong>Tested on the limited number of patients available, our findings show that our AI model was associated with improved retrospective outcomes compared to the guidelines in complex type 2 diabetes cases by integrating multiple data sources, drawing on experiential clinical insights, and selecting treatments most likely to meet each patient's clinical targets for glucose and weight control. Future research is needed with a larger dataset.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e92877"},"PeriodicalIF":2.4,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652385/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149148216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using App Store Reviews to Explore User Experiences and Perceptions of Mental Health Mobile Apps: Qualitative Study.","authors":"Rachana Talekar, Israel Arevalo, Blanca Macareno, Whitney Garney","doi":"10.2196/97517","DOIUrl":"10.2196/97517","url":null,"abstract":"<p><strong>Background: </strong>With the rise of digital health, mental health apps (MHapps) have become an increasingly popular tool in the self-management of depression, anxiety, and stress. Star ratings are often used as indicators of app quality to guide selection. However, ratings do not fully capture if the MHapp's features, usability, or design elements exhibit the heterogeneous real-life user experiences. Instead, examining the patterns of engagement and app usage can highlight whether high ratings reflect diverse user needs.</p><p><strong>Objective: </strong>This study aimed to examine user experience of top-rated depression and anxiety apps to assess if user perceptions, as reported in app reviews, align with star ratings.</p><p><strong>Methods: </strong>To identify relevant mobile apps, we used a systematic search strategy that mimicked a typical user's journey and applied search terms related to depression, anxiety, and stress management. Apps were screened using a predefined inclusion criteria that guided the identification of the 5 most highly rated MHapps, yielding approximately 750 user reviews across all apps. Reviews were analyzed using hybrid inductive and deductive coding techniques, with codes generated iteratively to capture the spectrum of user perceptions and experiences. Codes were then clustered, leading to theme generation that provided a deeper understanding of user experiences.</p><p><strong>Results: </strong>User experiences demonstrated a complex interplay between perceived benefits and frustration. Users valued ease of navigation, convenience, accessibility, and low-effort features that allowed easier entry to self-management of mental health. Users expressed their affinity toward specific app features and desire for the addition of new features that could further support their mental wellness. However, limited or restrictive features due to paywall, in-app advertisement placement, and functionality issues resulting from technical issues or bugs garnered substantial criticism.</p><p><strong>Conclusions: </strong>This study highlights the complexity of user perceptions influencing experience with self-management MHapps. Despite high star ratings, app usability elicited paradoxical responses and showed multiple overlapping themes, showcasing features that may support some users but hinder others. The results emphasize that star ratings alone are insufficient to showcase if a MHapp meets user needs. Continued improvement in app design such as interface usability, feature development, and pricing transparency is needed to meet the diverse needs of users for better engagement and satisfaction.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e97517"},"PeriodicalIF":2.4,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13648948/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Remote Identification of APOE-ε4 Carrier Status in Cognitively Normal Adults via Speech Acoustics: Cross-Sectional Observational Study.","authors":"Maryam Tavakoli, Mehrdad Dadgostar, Jordan R Green, David H Salat, Steven E Arnold, Kathryn P Connaghan, Brian Richburg, Nelson V Barnett, Mariam Tkeshelashvili, Marziye Eshghi","doi":"10.2196/89830","DOIUrl":"10.2196/89830","url":null,"abstract":"<p><strong>Background: </strong>Apolipoprotein E ε4 (APOE-ε4), the strongest genetic risk factor for late-onset Alzheimer disease (AD), is associated with early neuromotor vulnerability that may precede measurable cognitive decline. Because speech integrates fine neuromotor processes, acoustic analysis could offer a sensitive, noninvasive marker of preclinical effects.</p><p><strong>Objective: </strong>This study aims to determine if speech acoustics distinguish cognitively normal APOE-ε4 carriers from noncarriers, and to assess which speech tasks provide optimal classification performance.</p><p><strong>Methods: </strong>In this cross-sectional observational study, 80 cognitively normal adults aged 41 to 89 years (22 APOE-ε4 carriers and 58 noncarriers) completed sustained phonation, oral diadochokinetic syllable repetition, passage reading, and spontaneous-speech tasks. Speech samples were collected remotely using participants' personal devices and processed to extract 88 acoustic features from the extended Geneva Minimalistic Acoustic Parameter Set. Task-specific random forest classifiers were developed to distinguish APOE-ε4 carriers from noncarriers. A genetic algorithm was used to select informative features, and model performance was evaluated using leave-one-participant-out cross-validation. Performance metrics included balanced accuracy, accuracy, precision, sensitivity, specificity, F₁-score, and receiver operating characteristic area under the curve (ROC-AUC).</p><p><strong>Results: </strong>Spontaneous speech produced the strongest classification performance, with balanced accuracy of 0.84, accuracy of 0.89, sensitivity of 0.73, specificity of 0.95, F₁-score of 0.78, and ROC-AUC of 0.75. Performance was lower for sustained phonation (F₁-score=0.69), diadochokinetic syllable repetition (F₁-score =0.70 for /ba/ and 0.64 for /pa/), and passage reading (F₁-score=0.61). Combining recordings across tasks reduced performance (F₁-score=0.53), indicating that task-specific acoustic patterns were more informative than pooled data.</p><p><strong>Conclusions: </strong>Automated analysis of task-specific acoustic speech features, particularly spontaneous speech, internally distinguished cognitively normal APOE-ε4 carriers from noncarriers. These findings support further validation of speech acoustics as a low-burden digital biomarker of preclinical AD risk and suggest that spontaneous-speech tasks may be especially well suited for future remote and longitudinal assessment.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e89830"},"PeriodicalIF":2.4,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Physical Activity Intervention for High-Risk Mothers Whose Children Play Sports: Qualitative Analysis of Exit Interviews From Two Pilot Studies.","authors":"Sugandha K Gupta-Louis, Belinda O'Hagan, Naomi Raisman, Gabriel Prieto, Michael C Onu, Bess H Marcus, Tayla von Ash","doi":"10.2196/87120","DOIUrl":"10.2196/87120","url":null,"abstract":"<p><strong>Background: </strong>Mothers, especially those with low socioeconomic status and minoritized identities, encounter barriers to participating in physical activity (PA), a behavior that improves health outcomes. Moms on the Move (MOMs) is a community-based and theory-informed intervention developed to address the PA barriers endorsed by low-income Black and Hispanic mothers. This intervention offered in-person group PA sessions led by a female fitness instructor and held during children's sports practices. The MOMs intervention was piloted in 2022 and 2023; the intervention in 2023 was longer (8-weeks, vs 6-weeks) and included goal-setting calls and written materials.</p><p><strong>Objective: </strong>This study examined the qualitative data from exit interviews of both pilot studies to explore participants' engagement and satisfaction with the intervention. We also sought to identify perceived benefits and barriers to participation, in addition to recommendations for future interventions.</p><p><strong>Methods: </strong>Exit interviews of 19 participants who had enrolled in at least 1 MOMs pilot study were analyzed with directed content analysis. Interviews were approximately 16 minutes on average. Social Cognitive Theory (SCT) and the Transtheoretical Model (TTM) were incorporated as theoretical frameworks for data coding and analysis.</p><p><strong>Results: </strong>Around half the participants identified as Black or Hispanic and reported an annual household income of ≤US $40,000. Participants were generally satisfied with the intervention, noting benefits including increased motivation to maintain PA beyond the duration of the intervention. Barriers included scheduling conflicts and inclement weather. Three theory-consistent themes framed participants' evaluation of intervention success: accountability, accessibility, and ability. Accountability referred to support from the in-person group that facilitated motivation. Accessibility was described as the appreciation for resources provided by the intervention, including the provision of exercise equipment. Finally, participants discussed how their shared identity with other participants increased their sense of ability (or self-efficacy) to engage in PA. This was especially true for participants who described little to no engagement in PA prior to the intervention.</p><p><strong>Conclusions: </strong>To our knowledge, the MOMs intervention is the first of its kind: it delivers an in-person group PA intervention to high-risk mothers and women caregivers of children during their children's sports practices. Findings from this study support the intervention's delivery and integration to improve health behaviors, including PA, among mothers with intersectional and marginalized identities from the perspective of participants.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"10 ","pages":"e87120"},"PeriodicalIF":2.4,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13649072/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149136799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}