JMIR mHealth and uHealth最新文献

{"title":"Mobile AI-Assisted Oral Lesion Triage for Community Oral Cancer Screening: Prospective Field Evaluation Study.","authors":"Hao-Yun Liu, Yu-Cheng Huang, Si-Wei Chen, Ling-Ying Wei, Cheng-Ying Chou, Jang-Jaer Lee, Shyh-Jye Chen, Chien-Chang Lee","doi":"10.2196/101721","DOIUrl":"10.2196/101721","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI)-based tools for oral cancer screening have shown promising performance in curated or retrospective image datasets, although such evidence may not fully reflect performance in real-world mobile community screening workflows. In remote or resource-limited settings, intraoral images are often acquired by trained non-specialist personnel under variable field conditions, making workflow-integrated image quality assurance, risk stratification, and expert oversight essential for human-supervised AI-assisted screening.</p><p><strong>Objective: </strong>This study aimed to evaluate the prospective field performance of a parameter-locked, mobile AI-assisted oral lesion triage system embedded within a human-supervised routine community oral cancer screening workflow.</p><p><strong>Methods: </strong>We conducted a prospective community-based field evaluation in eastern Taiwan from June 17 to December 31, 2025. Trained non-specialist personnel acquired standard white-light intraoral images using handheld mobile devices during routine oral cancer screening activities. The AI system incorporated on-site image quality assessment and lesion-level risk stratification into green, yellow, and red triage categories. Images that remained technically inadequate after repeated acquisition attempts were classified as ungradable and excluded from performance analysis. Three board-certified oral and maxillofacial specialists established an operational clinical reference standard through structured image review and consensus adjudication. The primary outcome was lesion-level identification of high-risk lesions requiring specialist referral, defined as red versus non-red triage. Diagnostic performance was estimated with Wilson 95% confidence intervals; precision-recall performance and pre-consensus inter-rater agreement among specialists were also assessed.</p><p><strong>Results: </strong>Among 602 screened participants, 4283 interpretable intraoral images were included in expert adjudication and lesion-level analysis. The AI system flagged 68 red lesions; 12 were confirmed as high risk by expert adjudication, and 4 additional high-risk lesions were identified during expert review, yielding 16 high-risk events for the primary red-triage analysis. For high-risk lesion identification, sensitivity was 75.0% (95% CI 50.5%-89.8%) and positive predictive value was 17.6% (95% CI 10.4%-28.4%); specificity, negative predictive value, and accuracy were 98.6%, 99.9%, and 98.5%, respectively. ROC-AUC values were 0.957 for red, 0.931 for yellow, and 0.964 for green triage; precision-recall analysis showed PR-AUC values of 0.8235 for red, 0.9052 for yellow, and 0.9476 for green triage. Pre-consensus specialist agreement was high, with a Fleiss' kappa of 0.921 and a Gwet's AC1 of 0.981.</p><p><strong>Conclusions: </strong>A parameter-locked mobile AI-assisted oral lesion triage system was feasibly integrated into a real-world com","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":" ","pages":""},"PeriodicalIF":6.3,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148850692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Immediate and Sustained Improvements in Mood and Stress Associated With Yuna, an AI-Powered Digital Mental Health Intervention: Real-World Retrospective Study.","authors":"Kelsey McAlister, Courtney Jewell, Chad Stecher, Jennifer Huberty","doi":"10.2196/94070","DOIUrl":"10.2196/94070","url":null,"abstract":"<p><strong>Background: </strong>AI-powered digital mental health interventions (DMHIs) are a promising approach to address barriers to traditional mental health care. However, real-world evidence of their immediate and sustained benefits remains limited.</p><p><strong>Objective: </strong>The purpose of this real-world, retrospective study is to explore patterns of perceived mood and stress change associated with the use of Yuna, an AI-powered DMHI. We aimed to (1) describe user demographics and session characteristics, (2) quantify the magnitude of mood and stress change within sessions and over time with continued Yuna use, and (3) identify session-level factors associated with changes in mood and stress.</p><p><strong>Methods: </strong>Adult Yuna users (aged ≥18 y) who initiated at least one session with the Yuna app were included in this study. Users self-reported mood and stress on Visual Analog Scales (VASs; range 0-1) before and after sessions. Linear mixed effects models were used to explore the immediate, within-session improvements in mood and stress, and the sustained, between-session changes in symptoms of mood and stress. Linear mixed effects models were also used to examine session-level predictors of within-session improvements, including baseline symptom severity, session duration, total number of unique therapeutic approaches used, safety guardrail activation, and gender.</p><p><strong>Results: </strong>A total of 5549 real-world users were included (2901/5549, 52.3% female; mean sessions 3.44, SD 9.83). Users demonstrated significant, immediate within-session improvements in both mood (<i>d</i>=0.55) and stress (<i>d</i>=0.56), with sensitivity analyses yielding consistent results. Between-session analyses revealed gradual improvements in baseline mood (<i>d</i>=-0.009) and stress (d=-0.011). Baseline symptom severity was the strongest predictor of immediate, within-session change (mood: β=.118, SE 0.003; <i>P</i><.001; stress: β=.131, SE 0.004; <i>P</i><.001), followed by session duration (mood: β=.027, SE 0.003; <i>P</i>=.003; stress: β=.029, SE 0.003; <i>P</i><.001). A greater number of unique therapeutic approaches used was associated with smaller improvements in both outcomes (mood: β=-0.007, SE 0.003; <i>P</i>=.043; stress: β=-0.011, SE 0.003; <i>P</i>=.002).</p><p><strong>Conclusions: </strong>Use of Yuna, an AI-powered DMHI, was associated with perceived within-session improvements in mood and stress, with preliminary evidence of gradual improvements in mood and stress across repeated sessions. However, the absence of a control group and potential selection bias preclude causal conclusions. These findings offer promising, real-world evidence for AI-powered DMHIs as accessible, on-demand support tools. Prospective, controlled designs are needed to establish causal effects and evaluate the sustainability of observed improvements.</p>","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e94070"},"PeriodicalIF":6.3,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13505972/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148818589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feasibility and Preliminary Efficacy of a \"Sit Less\" Program Leveraging Fitbit Tracking and Tailored Text Messages in Cardiometabolic Disease: Findings From 2 Parallel Randomized Controlled Trials in Coronary Artery Disease and Type 2 Diabetes.","authors":"Chorong Park, Mary S Dietrich, Britta Larsen, Lindsay S Mayberry, Abigail Doyle, Soojung Ahn, Jason Jean, Kevin Maquiling, Mulubrhan F Mogos, James M Muchira, Shelagh Mulvaney","doi":"10.2196/56497","DOIUrl":"10.2196/56497","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Individuals with cardiometabolic disease typically average 10 to 14 hours of daily sedentary time, which increases the risk of cardiovascular disease.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to evaluate the feasibility, acceptability, and preliminary efficacy of a \"Sit Less\" program in reducing sedentary behavior in people with cardiometabolic disease.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Participants with cardiovascular disease or type 2 diabetes underwent separate randomization into the Sit Less intervention or the control group. Sit Less included 1 in-person counseling session, a Fitbit, a smart water bottle, and tailored weekly text messages for 12 weeks. Control group participants received the American Heart Association's \"Answers by Heart\" booklet. Sedentary behavior was measured using the activPAL for 7 days at baseline and postintervention. The secondary outcomes included physical activity, cardiometabolic biomarkers, continuous glucose monitoring metrics, and psychological factors. Generalized linear models estimated adjusted between-group differences, controlling for baseline values, cohort, cohort×group interaction, and leisure-time exercise.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Of the 37 randomized participants, 35 (95%) completed the study (Sit Less: n=17, 48.6%; and control: n=18, 51.4%). Of the 35 participants who completed the study, 62% (n=21) were men, the median age was 67 (54-72) years, and their baseline sedentary time was approximately 10.4 hours per day. Sit Less participants demonstrated high adherence, including a text response rate of 81% and a median Fitbit wear time of 15 hours per day on 6.8 days per week, and 15 (88%) of 17 participants reported satisfaction with the program. Compared with the control group, Sit Less participants showed greater reductions in total sedentary time (adjusted mean difference -17.3 min/d, 95% CI -63 to 28; &lt;i&gt;P&lt;/i&gt;=.45) and prolonged sedentary time of &gt;30 minutes (-39.5 min/d, 95% CI -100 to 21; &lt;i&gt;P&lt;/i&gt;=.20) and &gt;60 minutes (-49.9 min/d, 95% CI -102 to 2; &lt;i&gt;P&lt;/i&gt;=.06) and increases in sit-to-stand transitions (4.2 per day, 95% CI -2 to 10; &lt;i&gt;P&lt;/i&gt;=.13), although none were statistically significant. Hemoglobin A&lt;sub&gt;1c&lt;/sub&gt; was lower in the Sit Less group than in the control group (adjusted mean difference -0.4%, 95% CI -0.8 to -0.1; &lt;i&gt;P&lt;/i&gt;=.04). Continuous glucose monitoring outcomes, including mean glucose (-6.0 mg/dL, 95% CI -14.9 to 2.8; &lt;i&gt;P&lt;/i&gt;=.18) and time in range (2.1%, 95% CI -4.8 to 9.1; &lt;i&gt;P&lt;/i&gt;=.54), were not statistically significant but demonstrated similar directional changes. Other cardiometabolic biomarkers, physical activity, and psychological outcomes were not significantly different, except for lower self-efficacy for moderate physical activity in the Sit Less group (-0.6, 95% CI -1.1 to -0.2; &lt;i&gt;P&lt;/i&gt;=.003).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The Sit Less intervention was feasible and acceptable and showed possible improvements","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e56497"},"PeriodicalIF":6.3,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13505886/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148818571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanical Contact Conditions in Wearable Reflectance Photoplethysmography: Scoping Review.","authors":"Chenxi Yang, Jiahang Xie, Zifei He, Jianqing Li, Chengyu Liu","doi":"10.2196/99333","DOIUrl":"10.2196/99333","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Cardiovascular diseases remain a major global health burden, highlighting the need for long-term physiological monitoring. Photoplethysmography (PPG) is widely used in wearable devices for noninvasive monitoring of heart rate (HR), rhythm, and oxygen saturation in mobile health (mHealth) apps. However, the reliability of wearable reflectance PPG depends on sensing conditions, including sensor-skin contact force and pressure.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This scoping review maps how contact force and contact pressure have been defined, controlled, measured, represented, and reported in wearable or wearable-relevant reflectance PPG studies; characterizes the reported signal-, waveform-, feature-, and task-level responses under different contact conditions; and identifies methodological and evidence gaps.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A comprehensive literature search was conducted in PubMed, IEEE Xplore, Scopus (Elsevier), and Web of Science Core Collection (Clarivate) from database inception to June 1, 2026. Studies were eligible if they addressed contact force or contact pressure in wearable or wearable-relevant reflectance PPG and reported measurement approaches, measurement sites and device configurations, force or pressure representation, or PPG responses across signal quality, waveform and feature characteristics, and downstream physiological estimation. Database filters were applied, where available, to restrict results to English-language publications. Search results were imported into EndNote for deduplication. Database searches were supplemented by reference-list screening. After screening, 53 reports were sought for retrieval; 1 was not retrieved, 52 were assessed at full text, and 21 studies met the inclusion criteria.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The 21 included studies showed substantial heterogeneity, with sample sizes ranging from single-participant experiments to a wrist PPG dataset including 1142 participants. Most human studies recruited healthy volunteers, whereas some used public datasets or tissue-vessel phantoms, and 1 combined theoretical modeling with human-participant validation. The mapped evidence identified contact force and contact pressure as important measurement conditions in wearable reflectance PPG. Across the included studies, different contact conditions were associated with changes in alternating current/direct current components, amplitude- and morphology-related features, derivative-based indices, wavelength-dependent responses, and fiducial-point detection. Several studies also examined downstream physiological tasks, including HR, oxygen saturation, pulse transit or arrival time, blood pressure-related estimates, and HR variability.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The evidence mapped in this scoping review supports a multilevel conceptual pathway in wearable reflectance PPG, in which mechanical conditions at the sensor-skin interface are associated with changes ","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e99333"},"PeriodicalIF":6.3,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13550977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148813030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Mobile Virtual Reality-Based Intervention for Stress Reduction Among Young Adults: Pilot Randomized Controlled Trial.","authors":"Houlin Hong, Matthew R Lootens, Rebecca Bachman, Luis David Olivera Leon, Ann F Dunlap, Emilio Goldenhersch, Nicolas Rosencovich, Cristian Waitman, Katarzyna E Wyka, Terry T-K Huang","doi":"10.2196/83438","DOIUrl":"10.2196/83438","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Young adults experience disproportionately high levels of stress, creating significant health challenges. This demographic often underuses traditional stress management methods due to perceived ineffectiveness, inconvenience, or stigma. Given these challenges, mobile virtual reality (VR) offers a novel, engaging, and accessible alternative stress management tool that may be more appealing to young adults.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This pilot randomized controlled trial (RCT) evaluated the preliminary effects of MindCo Relief (MR), a mobile VR-based stress management app, accompanied by online coaching, on perceived stress, resilience, anxiety, depressive symptoms, and quality of life (QoL).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Young adults aged 18 to 29 years were recruited to participate in the study. A total of 70 participants with moderate-to-high stress levels at baseline were randomized to an intervention (n=34) group and a control (n=36) group. Moderate-to-high stress was defined as a sum score of 14 or more on the Perceived Stress Scale-10 (PSS-10). The intervention group completed an 8-week VR mindfulness program with access to in-person coaching, while the control group received no intervention. The primary outcome was self-reported perceived stress (PSS-10). Secondary measures included resilience (measured by the Connor-Davidson Resilience Scale-2), anxiety (measured by the Generalized Anxiety Disorder-7 scale), depressive symptoms (measured by the Patient Health Questionnaire-9), and QoL (measured by the General Well-Being Schedule). Primary analyses used linear mixed-effects models to assess the intervention effect over the 8-week study period. Secondary analyses examined whether the percentage of program modules completed and the number of coaching sessions attended were associated with changes in the primary and secondary outcomes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The mean age of the participants was 23 (SD 3.41) years, and they were predominantly female (n=52, 74%), students (n=46, 66%), and insured (n=63, 90%). No significant differences were observed between the intervention and control groups in terms of sex (P=.89), student status (P=.56), insurance status (P=.68), race and ethnicity (P=.18), or age (P=.32). Linear mixed-effects models showed a significant interaction between time and intervention, with the intervention group showing greater reductions in stress (β=-3.84, SE 1.37; P=.007), anxiety (β=-3.21, SE 0.97; P=.002), and depressive symptoms (β=-3.13, SE 1.13; P=.007) and a greater increase in QoL (β=9.99, SE 2.92; P=.001). No significant interaction was found for resilience (β=0.83, SE 0.43; P=.06). In the secondary analyses, neither the percentage of modules completed nor the number of coaching sessions attended was significantly associated with changes in the primary or secondary outcomes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study provided preliminary evidence that mobile VR can ","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e83438"},"PeriodicalIF":6.3,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13545530/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148793317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of Self-Guided Digital Mindfulness Interventions on the Mental Health of Health Care Workers: Systematic Review and Meta-Analysis of Randomized Controlled Trials.","authors":"Natsu Sasaki, Akiomi Inoue, Mako Iida, Kazuhiro Watanabe, Yuka Kobayashi, Asuka Sakuraya, Hisashi Eguchi, Kanami Tsuno, Yu Komase, Yasumasa Otsuka, Mai Iwanaga, Reiko Inoue, Kazuto Kuribayashi, Ayako Hino, Hiroki Asaoka, Satoru Kanamori, Yuta Inagawa, Takenori Yamauchi, Hiroki Ikeda, Go Muto, Rika Kato, Takuro Okuyama, Naomichi Tani, Noriko Kojimahara, Takeshi Ebara, Akihito Shimazu, Akizumi Tsutsumi, Norito Kawakami, Kotaro Imamura","doi":"10.2196/74272","DOIUrl":"10.2196/74272","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Mindfulness interventions are considered an effective strategy for preventing mental health problems among health care workers (HCWs). While prior reviews have often included facilitator-guided or multicomponent interventions, it is unclear whether self-guided digital mindfulness interventions can also be effective without professional or in-person support.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This systematic review aimed to investigate the effects of self-guided digital mindfulness interventions on the mental health and well-being of HCWs.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This work was conducted as part of the DeLiGHT project. We searched electronic databases, including PubMed (MEDLINE), Embase, Cochrane CENTRAL, PsycINFO, PsycARTICLES, and the Japan Medical Abstract Society database, from inception in 2010 to July 25, 2023. To ensure timeliness, we performed an updated search on December 27, 2025. Database searching yielded 37,851 abstracts and 145 studies that examined the effectiveness of digital health interventions for workers in the initial 2023 screen. In the present study, we limited the included studies to those that met the following criteria: randomized controlled trials (RCTs) using self-guided digital mindfulness interventions (eg, smartphone apps or web-based programs) delivered without face-to-face or professional support compared to waiting list controls or usual care among HCWs. The updated search in 2025 yielded 6328 additional records, of which 11 studies were examined. Study quality was assessed using the Cochrane Risk of Bias tool, with meta-analyses conducted using a random-effects model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 9 RCTs with 3088 participants were included in the final analysis. The study populations were diverse, covering North America, Europe, Oceania, and Asia. Interventions were delivered via various digital platforms, including commercial mindfulness apps (n=3), social networking service tools (n=3), and web-based programs (n=3), with an average duration of 6.17 weeks (range: 1.5-18 wk). Five studies assessed outcomes only postintervention, and 4 included short-term follow-up (4-12 wk); no long-term effects were evaluated. The meta-analysis showed a significant beneficial effect on depression (standardized mean difference [SMD]=-0.44, 95% CI -0.88 to -0.00; &lt;i&gt;P&lt;/i&gt;=.049), anxiety (SMD=-0.29, 95% CI -0.51 to -0.06; &lt;i&gt;P&lt;/i&gt;=.011), perceived stress (SMD=-0.42, 95% CI -0.77 to -0.06; &lt;i&gt;P&lt;/i&gt;=.02), and well-being (SMD=0.20, 95% CI 0.09 to 0.30; &lt;i&gt;P&lt;/i&gt;&lt;.001) immediately postintervention. The adherence rates reported across studies were highly variable, ranging from 19% to 56%. According to the Cochrane Risk of Bias tool, most studies were rated as having some concerns or a high risk of bias. The certainty of evidence included in the analysis ranged from \"Low\" to \"Very Low.\"&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Overall, low to very low certainty evidence suggests that self-gui","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e74272"},"PeriodicalIF":6.3,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13494152/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148793294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mobile Health in Home-Based Palliative Care: Realist Review of Contextual Factors and Mechanisms Influencing Outcomes.","authors":"Nuhamin Tekle Gebre, Oladayo Afolabi, Nahla Gafer, Kennedy Bashan Nkhoma, Nicola Ayers, Charlotte Hanlon, Richard Harding","doi":"10.2196/80321","DOIUrl":"10.2196/80321","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The increasing prevalence of chronic illness presents a significant global health challenge due to growing end-of-life suffering. Palliative care is now an essential health service under Universal Health Coverage. Its integration into primary health care and use of mobile health (mHealth) have been recommended to improve access.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to synthesize evidence on how mHealth interventions in home-based palliative care work, for whom, and in what context.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This realist review identified global evidence relevant to mHealth interventions for home-based palliative care through searches of 9 electronic databases (ie, MEDLINE, Embase, PsycINFO, Global Health, CINAHL, Web of Science, Cochrane Database of Systematic Reviews, Scopus, and Global Index Medicus), and forward citation tracking of included articles conducted in March 2026. The review followed the 5 key stages of a realist review: scoping the literature to assess what is important about the context of mHealth intervention in home-based palliative care and what mechanisms might be important in how such interventions result in their intended outcomes; articulating the underlying program theory and refining the review scope through consultation with international palliative care experts; conducting iterative searches for and appraisal of relevant evidence; extracting data; and narratively synthesizing the data, prioritized by relevance and rigor to generate conclusions and recommendations. The Framework of Complexity in Palliative Care Context, adapted from Bronfenbrenner's Ecological Systems Theory, was applied to examine the contextual influences and interactions among factors within the multilayered system. Context-mechanism-outcome configurations were developed and iteratively tested to refine the program theory for mHealth in home-based palliative care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 4134 records were identified, of which 422 (10.21%) articles were retained for full-text screening, and 126 (3.05%) studies were included in the final synthesis. The contextual factors and mechanisms that positively influence the intended outcomes include (1) alleviating concerns and mitigating perceived threats about mHealth's suitability in palliative care through proper orientation for patients and carers, along with clear guidelines for health care professionals; (2) minimizing infrastructural and technological barriers through user-friendly designs and investment in sustainable models of mHealth for home-based palliative care; (3) engaging diverse stakeholders to ensure mHealth aligns with priority health care needs, user preferences, and the operations of implementing organizations and the wider health care system; (4) streamlining health management information systems through interoperable mHealth systems implemented at different levels of care; (5) enabling access to and regular communicati","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e80321"},"PeriodicalIF":6.3,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13475790/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148764812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of Mobile Health Technologies to Prevent Unintentional Childhood Injuries: Scoping Review.","authors":"Huan Wang, Fengjiao Pu, Dongjun Jing, Hangcheng Liu, Miao Li, Xixi Li","doi":"10.2196/94038","DOIUrl":"10.2196/94038","url":null,"abstract":"<p><strong>Background: </strong>Unintentional childhood injuries represent a major public health issue affecting the lives and health of children worldwide, with the risk and injury type dynamically changing with age and developmental stage. To effectively prevent unintentional injuries, intervention measures must be adjusted based on actual circumstances and kept up to date in real time. Mobile health (mHealth) technologies can meet this need, but their specific functions and intervention methods remain unclear at present.</p><p><strong>Objective: </strong>This study aimed to conduct a scoping review of research on the application of mHealth technologies in the prevention and emergency management of unintentional injuries among children, with a focus on identifying the types of mHealth technologies used, intervention contents, and outcome measures, thereby providing a reference for related studies.</p><p><strong>Methods: </strong>We systematically searched 5 databases-PubMed, Web of Science, Embase, Cochrane Library, and CINAHL-from their inception to December 31, 2025. Data extraction and synthesis were performed on the included studies.</p><p><strong>Results: </strong>Of 1085 articles, 15 (1.3%) met the inclusion criteria, and 1 additional reference was added during full-text review. Thus, 16 studies were included. The included studies comprised 9 (56.2%) randomized controlled trials, 2 (12.5%) quasi-experimental studies, 3 (18.8%) mixed methods studies, 1 (6.2%) qualitative study, and 1 (6.2%) descriptive study. mHealth technologies included apps, WeChat, mobile-based e-learning programs, and virtual reality combined with wearable devices. Their functions included health education, interactive communication, monitoring and reminders, behavioral training, questionnaires and record-keeping, and emergency response. Outcome measures included the incidence of unintentional injuries among children; knowledge, attitudes, and behaviors regarding injuries; other psychological and social indicators; and usability of mHealth technology.</p><p><strong>Conclusions: </strong>mHealth technologies have shown some progress in reducing unintentional injuries among children. Content based on this technology has demonstrated positive effects in reducing injury incidence, enhancing caregivers' awareness, and improving related attitudes and behavioral capabilities. However, only 2 mobile apps are currently available to the public. Future research should optimize the functional design of mHealth, strengthen sustainability, explore long-term implementation methods, and conduct large-scale, long-term studies to further evaluate its impact on the incidence of unintentional injuries among children.</p><p><strong>Trial registration: </strong>Open Science Framework 8QPR6; https://osf.io/8qpr6.</p>","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e94038"},"PeriodicalIF":6.3,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13525362/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148761059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Short-Term Effects of an mHealth Intervention on Healthy Behaviors and Cardiometabolic Health in Sedentary Employees: Quasi-Experimental Study.","authors":"Yun-Ping Lin, Shu-Hua Lu, Kwo-Chen Lee, Wei-Fen Ma, Ya-Fang Ho, Wen-Chun Liao, Hui-Ting Yang, OiSaeng Hong","doi":"10.2196/106593","DOIUrl":"10.2196/106593","url":null,"abstract":"","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e106593"},"PeriodicalIF":6.3,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13475937/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148764987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Assessment of Free-Living Physical Behaviors and Activity Intensity Using Dual-Wearable Multitask Learning: Development and Evaluation Study From the Multicenter WEALTH Project.","authors":"Luis Sigcha, Annika Swenne, Grainne Hayes, Jitka Kuhnova, Richard Cimler, Steriani Elavsky, Tomas Vetrovsky, Léopold Fezeu Kamedjie, Jérôme Bouchan, Jean-Michel Oppert, Janas Harrington, Greet Cardon, Antje Hebestreit, Alan Donnelly, Pepijn Van de Ven, Christoph Buck","doi":"10.2196/94302","DOIUrl":"10.2196/94302","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Accurate assessment of physical behaviors (PBs) and activity intensity is essential for public health research and digital health monitoring. Wearable accelerometers combined with machine learning (ML) or deep learning (DL) enable objective behavior assessment, but most existing models are trained on laboratory data, limiting generalizability to free-living conditions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to develop and evaluate multitask ML and DL models for PB classification across 7 categories (sitting, standing, walking, running, sports, cycling, and lying) and activity intensity categories (AIC) across 3 levels (sedentary, light, and moderate-to-vigorous physical activity) using thigh-worn (activPAL) and waist-worn (ActiGraph) wearable accelerometers. A second objective was to compare model-derived estimates of daily time spent in PB and AIC across single- and dual-sensor (activPAL + ActiGraph) configurations, and to evaluate agreement between the best-performing model and corresponding estimates obtained from the proprietary activPAL classification of real-world everyday activities (CREA) algorithm using free-living data collected over a 9-day monitoring period.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Data were obtained from 590 adults in the multicenter WEALTH study (627 recruited) and included up to 9 days of concurrent activPAL and ActiGraph free-living recordings. Sparse accelerometer-labeled data were obtained using ecological momentary assessment and refined by retaining instances with ≥75% agreement with the CREA algorithm. Resulting labeled data of 583 participants were used to develop ML models for single-sensor (activPAL or ActiGraph) and combined (dual-sensor) configurations. A random forest (RF) model using engineered features and a multihead convolutional neural network (MH-CNN) were trained within a multitask learning framework to jointly predict PB (task 1) and AIC (task 2) using a subject-independent hold-out split. The test subset (n=87) was used to estimate daily time spent in PB and AIC over 9 days, which were compared with CREA-derived estimates using Pearson coefficients and intraclass correlation coefficients (ICCs).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The dual-sensor configuration consistently outperformed single-sensor models. For PB classification, the MH-CNN achieved the highest performance (&lt;i&gt;F&lt;/i&gt;&lt;sub&gt;1&lt;/sub&gt;-score=0.750). For AIC, the RF model performed best (&lt;i&gt;F&lt;/i&gt;&lt;sub&gt;1&lt;/sub&gt;-score=0.741). Dual-sensor free-living estimates showed epidemiologically plausible distributions across the 24-hour period, including sitting 37% (538/1440 min), lying 34% (496/1440 min), walking 9% (131/1440 min), and moderate-to-vigorous physical activity (MVPA) 2% (31/1440 min). Agreement with CREA was strongest for standing, walking, and cycling (&lt;i&gt;r&lt;/i&gt;≥0.86; ICC ≥0.72), while lying showed modest reliability (ICC=0.48). For AIC, agreement was highest for light physical activity (LPA) and MVPA (IC","PeriodicalId":14756,"journal":{"name":"JMIR mHealth and uHealth","volume":"14 ","pages":"e94302"},"PeriodicalIF":6.3,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13481161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148793258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}