Journal of Medical Internet Research最新文献

{"title":"Improving Hand Hygiene Skills Using Virtual Reality: Quasi-Experimental Study.","authors":"José Mira, Mery González, Carolina Villalba, Laura Guerra, Yesid Ramirez-Moya, Jazmín Hernández, Olga Moya, Luis Pineda, Clara Pérez-Esteve","doi":"10.2196/78882","DOIUrl":"https://doi.org/10.2196/78882","url":null,"abstract":"<p><strong>Background: </strong>Hand hygiene is a critical strategy for preventing health care-associated infections (HAIs) and reducing health care costs. However, adherence remains low, particularly among health care assistants (HCAs) and informal caregivers (ICs), who often lack formal training. Virtual reality (VR) delivers standardized, immersive practice with active learning and real-time feedback. It has shown favorable effects on skill execution and acceptability in training paramedics and caregivers. To our knowledge, VR has not been systematically applied to train World Health Organization (WHO)-aligned hand hygiene techniques. Given its portability and suitability for brief, repeatable drills, VR is a plausible solution to upskill HCAs and ICs in both hospital and home-care settings.</p><p><strong>Objective: </strong>This study aims to assess the immediate training effectiveness and implementation feasibility of a brief VR-based hand hygiene program for HCAs and ICs in Colombia. We quantified pre-post changes in correct execution (primary outcome), timing, errors, and knowledge. Success was defined a priori as achieving ≥75% correct execution after training, consistent with adherence levels associated with HAI reductions when embedded in WHO-aligned bundles in prior studies.</p><p><strong>Methods: </strong>In this quasi-experimental, one-group pretest-posttest study, 215 participants (94 HCAs, 121 ICs) completed up to three 15-minute VR training sessions with real-time feedback on hand hygiene technique following the WHO recommendations for hand hygiene. Data were collected at baseline (pre) and immediately after the VR intervention (post). Variables assessed included correct execution (primary; binary), error counts, timing adequacy, knowledge assessment, and acceptability.</p><p><strong>Results: </strong>Correct hand hygiene performance increased from 26.6% to 97.9% among HCAs (95% CI 92.6-99.4; P<.001) and from 9.9% to 95.9% among ICs (95% CI 90.7-98.2; P<.001), with paired odds ratios of 34.5 (95% CI 8.46-140.72) and 21.8 (95% CI 8.90-53.43), respectively. Wide intervals were driven by the very small number who performed worse after training. Timing adequacy improved significantly in both groups, reaching 46.6 (SD 6.7) and 48 (SD 6.6) seconds, respectively (P<.001). Common errors, such as insufficient fingertip coverage and incomplete thumb cleaning, were reduced to near 0 (P<.001). Knowledge scores also improved significantly in both groups, and VR training was rated as \"very useful\" or \"extremely useful\" for skill acquisition.</p><p><strong>Conclusions: </strong>VR training significantly improved hand hygiene technique and knowledge. The high acceptance rates observed suggest that these technologies can effectively enhance infection prevention skills in undertrained populations, supporting broader adoption in health care education. Because this brief, portable, and highly acceptable intervention can be embedded in routine onboard","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e78882"},"PeriodicalIF":6.0,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145244522","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":"The Role of Data in Public Health and Health Innovation: Perspectives on Social Determinants of Health, Community-Based Data Approaches, and AI.","authors":"Kaakpema Yelpaala, Michael Christopher Gibbons, Ines Maria Vigil, Jennifer Leaño, Terika McCall, Ijeoma Opara, Anne Zink, Marcella Nunez-Smith, Bhramar Mukherjee, Megan Ranney","doi":"10.2196/78794","DOIUrl":"10.2196/78794","url":null,"abstract":"<p><strong>Unlabelled: </strong>Public health is undergoing profound transformation driven by data from the global health sector and related fields. To address systemic health disparities, scholars and health practitioners are increasingly applying a data equity lens, an approach that has become even more urgent as the United States faces the erosion of public health data infrastructure. This paper summarizes insights from an April 2024 convening by the Yale School of Public Health-The Role of Data in Public Health Equity and Innovation-with intersectoral stakeholders from academia, government (local, state, and federal), health care, and private industry. The convening included keynote presentations and roundtables regarding the depiction of social determinants of health in data; effects of artificial intelligence (AI) on health data equity; and community-based models for data, providing a framework for cross-cutting discussions. Through a narrative synthesis, themes were identified and synthesized from systematically gathered information from presentations and roundtables. This process led to a set of actionable, cross-cutting recommendations to guide inclusive and impactful data practices for policymakers, public health professionals, and health innovators across diverse contexts: (1) enable big data and interoperability connecting social determinants of health and health outcomes; (2) include diverse, nontechnical voices in AI and health discussions; (3) fund research on data equity and AI in health sciences; (4) modernize the Health Insurance Portability and Accountability Act (HIPAA) with new guidelines for AI and big data; and (5) research and conceptual frameworks are needed to elucidate interconnections between data equity and health equity.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e78794"},"PeriodicalIF":6.0,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12505398/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145251440","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":"Clinical and Economic Outcomes Associated With Musculoskeletal Care in an Integrated Advanced Primary Care Model: Controlled Cohort Analysis.","authors":"Courtenay J Stewart, Dena M Bravata, Michael T Nelson, Esha Datta, Raj Behal","doi":"10.2196/76794","DOIUrl":"https://doi.org/10.2196/76794","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Health care costs in the United States are skyrocketing, with commercial spending increasing 7.7% between 2022 and 2023. Musculoskeletal conditions affect more than one-third of US adults and account for over US $300 billion in total medical spending, more than any other chronic condition. Employers bear a disproportionate burden of these costs, both because they pay for the care of employees and their families with musculoskeletal conditions and because musculoskeletal pain is the second leading cause of workplace absenteeism, accounting for approximately 290 million lost workdays annually. Tele-physical therapy (TPT) solutions can be an effective alternative to in-person physical therapy (PT) and, especially when provided early in the course of care, have the potential to reduce employer-sponsored health care spending.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;We sought to evaluate the effects of a proactive musculoskeletal treatment approach-TPT integrated into advanced primary care-on patient access, changes in functional status, and employer cost.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We performed a retrospective analysis of participants (&gt;13 years old) seen by TPT integrated with primary care compared to a risk-adjusted, nationally matched cohort of patients receiving PT. The studied intervention had five key elements: (1) a multidisciplinary team, (2) a musculoskeletal toolkit for primary care physicians, (3) a peer-to-peer musculoskeletal expert opinion portal, (4) a shared technology platform, and (5) musculoskeletal educational rounds. We collected participants' access to both primary care and PT and compared participants' functional status at baseline and at the end of their course of PT to risk-adjusted Focus on Therapeutic Outcomes controls, providers' assessments of participants' progress with PT, participants' satisfaction with their TPT, and costs of care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;We evaluated 1563 participants whose average age was 42.8 (SD 10.4) years. Of these, 586 (37.5%) identified as female, 574 (36.7%) as White, 182 (11.6%) as Asian, and 19 (1.2%) as Black or African American. Their presenting complaints included shoulder pain (282/1563, 18%), knee pain (250/1563, 16%), and low back pain (187/1563, 11.96%). The mean time to TPT appointment was 7.6 (SD 5) days. On average, TPT patients required 5.4 (SD 2.7) visits to symptom resolution, compared to 6.5 (SD 5.5) visits for controls (a 17% reduction) and 10.3 (SD 1.55) predicted visits from risk-adjusted benchmarks, resulting in US $193 to US $1411 in savings per injury per patient. Recovery, defined as patients either meeting, mostly meeting, or on track to meet expectations, was achieved for 461/473 (97.5%) participants for whom it was assessed. Overall participant satisfaction was high, with a net promoter score for PTs of 97.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;TPT integrated with advanced primary care was associated with greater functional improve","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e76794"},"PeriodicalIF":6.0,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145244481","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":"Evaluating Large Language Models and Retrieval-Augmented Generation Enhancement for Delivering Guideline-Adherent Nutrition Information for Cardiovascular Disease Prevention: Cross-Sectional Study.","authors":"Vijaya Parameswaran, Jenna Bernard, Alec Bernard, Neil Deo, Sean Tsung, Kalle Lyytinen, Christopher Sharp, Fatima Rodriguez, David J Maron, Rajesh Dash","doi":"10.2196/78625","DOIUrl":"https://doi.org/10.2196/78625","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Cardiovascular disease (CVD) remains the leading cause of death worldwide, yet many web-based sources on cardiovascular (CV) health are inaccessible. Large language models (LLMs) are increasingly used for health-related inquiries and offer an opportunity to produce accessible and scalable CV health information. However, because these models are trained on heterogeneous data, including unverified user-generated content, the quality and reliability of food and nutrition information on CVD prevention remain uncertain. Recent studies have examined LLM use in various health care applications, but their effectiveness for providing nutrition information remains understudied. Although retrieval-augmented generation (RAG) frameworks have been shown to enhance LLM consistency and accuracy, their use in delivering nutrition information for CVD prevention requires further evaluation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To evaluate the effectiveness of off-the-shelf and RAG-enhanced LLMs in delivering guideline-adherent nutrition information for CVD prevention, we assessed 3 off-the-shelf models (ChatGPT-4o, Perplexity, and Llama 3-70B) and a Llama 3-70B+RAG model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We curated 30 nutrition questions that comprehensively addressed CVD prevention. These were approved by a registered dietitian providing preventive cardiology services at an academic medical center and were posed 3 times to each model. We developed a 15,074-word knowledge bank incorporating the American Heart Association's 2021 dietary guidelines and related website content to enhance Meta's Llama 3-70B model using RAG. The model received this and a few-shot prompt as context, included citations in a Context Source section, and used vector similarity to align responses with guideline content, with the temperature parameter set to 0.5 to enhance consistency. Model responses were evaluated by 3 expert reviewers against benchmark CV guidelines for appropriateness, reliability, readability, harm, and guideline adherence. Mean scores were compared using ANOVA, with statistical significance set at P&lt;.05. Interrater agreement was measured using the Cohen κ coefficient, and readability was estimated using the Flesch-Kincaid readability score.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The Llama 3+RAG model scored higher than the Perplexity, GPT-4o, and Llama 3 models on reliability, appropriateness, guideline adherence, and readability and showed no harm. The Cohen κ coefficient (κ&gt;70%; P&lt;.001) indicated high reviewer agreement.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The Llama 3+RAG model outperformed the off-the-shelf models across all measures with no evidence of harm, although the responses were less readable due to technical language. The off-the-shelf models scored lower on all measures and produced some harmful responses. These findings highlight the limitations of off-the-shelf models and demonstrate that RAG system integration can enhance LLM performa","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e78625"},"PeriodicalIF":6.0,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145244524","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":"Sensorized Motor and Cognitive Dual Task Framework for Dementia Diagnosis: Preliminary Insights From a Cross-Sectional Study.","authors":"Gianmaria Mancioppi, Erika Rovini, Laura Fiorini, Radia Zeghari, Auriane Gros, Valeria Manera, Philippe Robert, Filippo Cavallo","doi":"10.2196/64255","DOIUrl":"https://doi.org/10.2196/64255","url":null,"abstract":"<p><strong>Background: </strong>This study explores the use of novel motor and cognitive dual task (MCDT) approaches, based on upper limb motor function (ULMF) and lower limb motor function (LLMF), to discern individuals with mild cognitive impairment (MCI) or subjective cognitive impairment (SCI) from older adults who are cognitively healthy (OA).</p><p><strong>Objective: </strong>The study objectives encompass (1) the exploration of alternatives to the traditional walking MCDT; (2) the examination of various ULMF and LLMF MCDT modalities, incorporating different exercises with varying motor difficulties; and eventually, (3) the assessment of OA in comparison with people with MCI and SCI to acquire more nuanced insights into different stages of the diseases.</p><p><strong>Methods: </strong>The upper and lower limb motor performances of 44 older adults were evaluated using a wearable inertial system during 5 MCDTs comprising 2 ULMF tasks (forefinger tapping [FTAP] and thumb-forefinger tapping [THFF]) and 2 LLMF tasks (toe tapping heel pin [TTHP] and heel tapping toe pin [HTTP]). The gold standard for MCDT, 10-meter walking (GAIT), was included. We incorporated 5 pooled indices based on MCDTs, demographic data, and clinical scores into logistic regression models.</p><p><strong>Results: </strong>In 2-class classification models (MCI vs OA), HTTP showed the highest accuracy, at 93%; TTHP and TTHF models reached 89% accuracy; and FTAP and GAIT achieved 85% accuracy in distinguishing between the 2 groups of participants. In 3-class classification models (MCI vs SCI vs OA), transitioning from FTAP to THFF improved participant characterization by +5%. TTHP outperformed HTTP by +9%. Furthermore, models effectively identified individuals with MCI, with HTTP achieving 76% recall and TTHP achieving 88% recall.</p><p><strong>Conclusions: </strong>This study emphasizes the potential of an integrated, sensorized MCDT framework that combines a broader theoretical foundation and task selection with neuropsychological and behavioral data. This approach can enhance our understanding of dementia and provide clinicians with valuable diagnostic tools. Although these tasks demonstrated ease and efficiency, validation in subsequent clinical studies is necessary.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e64255"},"PeriodicalIF":6.0,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145238792","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":"Effectiveness and Costs of Participant Recruitment Strategies to a Web-Based Population Cohort: Observational Study.","authors":"Hannah Milbourn, Archie Campbell, Fiona Clark, Elly Darrah, Robin Flaig, Liz Kirby, Daniel L McCartney, Isla Mitchell, Sarah Robertson, Anne Richmond, Rosie Tatham, Zhuoni Xiao, Kerim McAteer, Caroline Hayward, Riccardo E Marioni, Andrew M McIntosh, David J Porteous, Heather C Whalley, Cathie L M Sudlow","doi":"10.2196/75116","DOIUrl":"10.2196/75116","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Recruitment to population-based health studies remains challenging, with difficulties meeting target participant numbers, biosample returns, and achieving a representative sample. Few studies provide evaluations of traditional and web-based recruitment methods particularly for studies with broad inclusion criteria and extended recruitment periods. Generation Scotland (GS) is a family-based cohort study that initiated a new wave of recruitment in 2022 using web-based data collection and remote saliva sampling (for genotyping). Here, we provide an overview of recruitment strategies used by GS over the first 18 months of new recruitment, highlighting which proved most effective and cost-efficient in order to inform future research.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study evaluated recruitment strategies using four main outcomes: (1) absolute recruitment numbers, (2) sociodemographic representativeness, (3) biosample return rate, and (4) cost per participant.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Between May 2022 and December 2023, recruitment was undertaken via snowball recruitment (through friends and family of existing volunteers), invitations to those who participated in a previous survey (CovidLife: the GS COVID-19 impact survey), and Scotland-wide recruitment through social media (including sponsored Meta-advertisements), news media, and TV advertisement. The method of recruitment was self-reported in the baseline questionnaire. We present absolute recruitment numbers and sociodemographic characteristics by recruitment method and evaluate the saliva sample return rate by recruitment strategy using chi-square tests. The overall cost and cost per participant were calculated for each method.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In total, 7889 new participants joined the cohort over this period. Recruitment sources by contribution were social media (n=2436, 30.9%), survey responder invitations (n=2049, 26.0%), TV advertising (n=367, 17.3%), snowball (n=891, 11.3%), news media (n=747, 9.5%), and other methods or unknown (n=399, 5.0%). More females signed up than males (5570/7889, 70.5% female). To date, 83.5% (6543/7836) of participants returned their postal saliva sample, which also varied by demographic factors (3485/3851, 90.5% older than 60 years vs 471/662, 71.1% aged 16-34 years). Average cost per participant across all recruitment strategies was £13.52 (US $16.82). Previous survey recontacting was the most cost-effective (£0.37 [US $0.46]), followed by social media (£14.78 [US $18.39]), while TV advertisement recruitment was the most expensive per recruit (£33.67 [US $41.89]).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study highlights both the challenges and the opportunities in large web-based cohort recruitment. Overall, social media advertising has been the most cost-effective and easily sustained strategy for recruitment over the reported recruitment period. We note that different strategies resulted in successful","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e75116"},"PeriodicalIF":6.0,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12500226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145238778","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":"Internet Use and Perceived Stress: Longitudinal Observational Study Combining Web Tracking Data with Questionnaires.","authors":"Mohammad Belal, Nguyen Luong, Talayeh Aledavood, Juhi Kulshrestha","doi":"10.2196/78775","DOIUrl":"https://doi.org/10.2196/78775","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;In today's digital era, the internet plays a pervasive role in our lives, influencing everyday activities such as communication, work, and leisure. This online engagement intertwines with offline experiences, shaping individuals' overall well-being. Despite its significance, existing research often falls short in capturing the relationship between internet use and wellbeing, relying primarily on isolated studies and self-reported data. One major contributor to deteriorated wellbeing is stress. While some research has examined the relationship between internet use and stress, both positive and negative associations have been reported.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;Our primary goal in this work is to identify the associations between an individual's internet use and their stress.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a seven-month longitudinal study. We combined fine-grained URL-level web browsing traces of 1490 German internet users with their sociodemographics and monthly measures of stress. Further, we developed a conceptual framework that allows us to simultaneously explore different contextual dimensions, including how, where, when, and by whom the internet is used. We applied linear mixed models to examine these associations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Our analysis revealed several associations between internet use and stress, varying by context. Increased time spent on social media, online shopping, and gaming platforms was associated with higher stress. For example, the time spent by individuals on shopping-related internet use (aggregated over the 30 days before their stress was measured via questionnaires) was positively associated with stress on both mobile (β = 0.04, CI = [0.00-0.08], P = .035) and desktop devices (β = 0.03, CI = [-0.00-0.06], P = .090). In contrast, time spent on productivity or news websites was associated with lower stress. Specifically, in the last 30 days of mobile usage, productivity-related use showed a negative association with stress (β = -0.03, CI = [-0.06- -0.00], P = .042). Additionally, in the last two days of data, news usage was negatively associated with stress on both mobile (β = -0.54, CI = [-1.08-0.00], P = .048) and desktop devices (β = -0.50, CI = [-0.90- -0.11], P = .012). Further analysis showed that total time spent online (β = 0.01, CI = [0.00-0.02], P &lt; .001), social-media usage (β = 0.02, CI = [0.00-0.03], P = .021), and gaming usage (β = 0.01, CI = [0.00-0.02], P = .021) were all positively associated with stress in high-stress (PSS &gt; 26) individuals on mobile devices.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The findings indicate that internet use is associated with stress, and these associations differ across various usage contexts. In the future, the behavioral markers we identified can pave the way for designing individualized tools for people to self-monitor and self-moderate their online behaviors to enhance their well-being, reducing the burde","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":" ","pages":""},"PeriodicalIF":6.0,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145238885","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":"Deep Learning Algorithms in the Diagnosis of Basal Cell Carcinoma Using Dermatoscopy: Systematic Review and Meta-Analysis.","authors":"Huasheng Liu, Guangqian Shang, Qianqian Shan","doi":"10.2196/73541","DOIUrl":"https://doi.org/10.2196/73541","url":null,"abstract":"<p><strong>Background: </strong>In recent years, deep learning algorithms based on dermatoscopy have shown great potential in diagnosing basal cell carcinoma (BCC). However, the diagnostic performance of deep learning algorithms remains controversial.</p><p><strong>Objective: </strong>This meta-analysis evaluates the diagnostic performance of deep learning algorithms based on dermatoscopy in detecting BCC.</p><p><strong>Methods: </strong>An extensive search in PubMed, Embase, and Web of Science databases was conducted to locate pertinent studies published until November 4, 2024. This meta-analysis included articles that reported the diagnostic performance of deep learning algorithms based on dermatoscopy for detecting BCC. The quality and risk of bias in the included studies were assessed using the modified Quality Assessment of Diagnostic Accuracy Studies 2 tool. A bivariate random-effects model was used to calculate the pooled sensitivity and specificity, both with 95% CIs.</p><p><strong>Results: </strong>Of the 1941 studies identified, 15 (0.77%) were included (internal validation sets of 32,069 patients or images; external validation sets of 200 patients or images). For dermatoscopy-based deep learning algorithms, the pooled sensitivity, specificity, and area under the curve (AUC) were 0.96 (95% CI 0.93-0.98), 0.98 (95% CI 0.96-0.99), and 0.99 (95% CI 0.98-1.00). For dermatologists' diagnoses, the sensitivity, specificity, and AUC were 0.75 (95% CI 0.66-0.82), 0.97 (95% CI 0.95-0.98), and 0.96 (95% CI 0.94-0.98). The results showed that dermatoscopy-based deep learning algorithms had a higher AUC than dermatologists' performance when using internal validation datasets (z=2.63; P=.008).</p><p><strong>Conclusions: </strong>This meta-analysis suggests that deep learning algorithms based on dermatoscopy exhibit strong diagnostic performance for detecting BCC. However, the retrospective design of many included studies and variations in reference standards may restrict the generalizability of these findings. The models evaluated in the included studies generally showed improved performance over that of dermatologists in classifying dermatoscopic images of BCC using internal validation datasets, highlighting their potential to support future diagnoses. However, performance on internal validation datasets does not necessarily translate well to external validation datasets. Additional external validation of these results is necessary to enhance the application of deep learning in dermatological diagnostics.</p><p><strong>Trial registration: </strong>PROSPERO International Prospective Register of Systematic Reviews CRD42025633947; https://www.crd.york.ac.uk/PROSPERO/view/CRD42025633947.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e73541"},"PeriodicalIF":6.0,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145225141","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":"Gender Differences in Psychosocial Pathways to Depression and Anxiety: Cross-Sectional and Bayesian Causal Network Study.","authors":"Han Zhang, Ye Xia, Peicai Fu, Cun Li, Ke Shi, Yuan Yang","doi":"10.2196/76913","DOIUrl":"10.2196/76913","url":null,"abstract":"<p><strong>Background: </strong>Depression and anxiety are widespread disorders with documented gender differences in symptom progression and associated psychosocial factors. However, the complex interrelationships between childhood trauma, self-esteem, social support, emotion regulation, and their gender-specific impacts on the development of depression and anxiety remain unclear.</p><p><strong>Objective: </strong>The objective of this study was to investigate the network structures of depression, anxiety, and psychosocial factors and to examine the pathways contributing to the development of depression and anxiety, with a focus on gender-specific differences.</p><p><strong>Methods: </strong>This study included 6105 participants from across China, collecting their sociodemographic characteristics and psychological scale data. Cross-sectional network analysis was used to explore the complex relationships between depression, anxiety, insomnia, somatic symptoms, childhood trauma, self-esteem, social support, and emotional regulation. Subsequently, Bayesian network analysis was used to infer potential causal pathways. Gender differences in the network structures were specifically examined.</p><p><strong>Results: </strong>Network analysis revealed strong associations among depression, anxiety, insomnia, and somatic symptoms. Network strength centrality exhibited the highest stability across overall networks (CS-C=0.75), with high predictability for depression (R²=72.4%) and anxiety (R²=64%), supporting the robustness of the model. The network structure invariance test between male and female participants was significant (P=.001). Furthermore, the Bayesian network analysis showed gender-specific symptom progression, where anxiety preceded depression in male participants, while depression preceded anxiety in female participants (with edges retained in nearly 100% of bootstrap samples). Self-esteem, social support, and insomnia were central nodes in female participants, whereas emotion regulation was more influential in male participants. Additionally, childhood trauma influenced depression or anxiety indirectly through self-esteem and social support in both male and female participants.</p><p><strong>Conclusions: </strong>This study presents a novel application of network analyses to delineate distinct gender-specific pathways in the development of depression and anxiety. The findings underscore insomnia, self-esteem, and social support as intervention targets for women and emotion regulation for men. Findings support gender-sensitive mental health strategies and emphasize the need for longitudinal validation.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e76913"},"PeriodicalIF":6.0,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12494359/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145225085","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 Smartphone App (WExercise) to Promote Physical Activity Among Cancer Survivors: Randomized Controlled Trial.","authors":"Denise Shuk Ting Cheung, Tiffany Wan Han Kwok, Sam Liu, Ryan E Rhodes, Pui Hing Chau, Chi-Leung Chiang, Anne Wing-Mui Lee, Chia-Chin Lin","doi":"10.2196/75839","DOIUrl":"10.2196/75839","url":null,"abstract":"<p><strong>Background: </strong>Cancer survivors face unique health challenges that may be addressed through physical activity (PA) interventions. Technology-based tools provide innovative, resource-efficient alternatives to traditional approaches, delivering PA interventions.</p><p><strong>Objective: </strong>This study aimed to examine the effectiveness of a smartphone app (WExercise) in promoting PA among cancer survivors.</p><p><strong>Methods: </strong>This study was an assessor-blind, 2-arm randomized controlled trial. The intervention group used WExercise, which consisted of automated weekly lessons developed based on the multi-process action control (M-PAC) framework. The control group received written PA recommendations. Ninety-eight physically inactive cancer survivors who had completed curative treatment were recruited from an oncology clinic and the community. Outcomes included exercise behavior (primary), exercise capacity, quality of life, and M-PAC constructs.</p><p><strong>Results: </strong>The majority (81/98, 82.7%) of participants remained in the study. The proportion of participants completing at least 75% of lessons was 69.44%. For exercise behavior, mixed findings were identified: the intervention group had a significantly greater increase in self-reported moderate-to-vigorous PA compared to the control group at postintervention (mean difference in change 89.02 minutes, 95% CI 34.87-143.16) and 3 months postintervention (mean difference in change 49.37 minutes, 95% CI 8.63-90.10; group × time interaction; P=.003), while no significant effect on ActiGraph-measured moderate-to-vigorous PA was observed at postintervention (mean difference in change -8.54 minutes, 95% CI -36.19 to 19.11) and 3 months postintervention (mean difference in change 2.56 minutes, 95% CI -27.29 to 32.41; group × time interaction; P=.74). WExercise was also effective in increasing cancer survivors' exercise capacity but not their quality of life or M-PAC constructs.</p><p><strong>Conclusions: </strong>WExercise demonstrated a significant effect on increasing self-reported PA, but this was not corroborated with ActiGraph-measured PA. The application may be a useful addition for clinicians aiming to promote physical activity in people with cancer.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e75839"},"PeriodicalIF":6.0,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12494186/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145225512","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}