JMIR Formative Research最新文献

{"title":"Implementation of Fully Automated AI-Integrated System for Body Composition Assessment on Computed Tomography for Opportunistic Sarcopenia Screening: Multicenter Prospective Study.","authors":"Bushra Urooj, Yousun Ko, Seongwon Na, In-One Kim, Eun-Hee Lee, Seon Cho, Heeryeol Jeong, Seungwoo Khang, Jeongjin Lee, Kyung Won Kim","doi":"10.2196/69940","DOIUrl":"10.2196/69940","url":null,"abstract":"<p><strong>Background: </strong>Opportunistic computed tomography (CT) screening for the evaluation of sarcopenia and myosteatosis has been gaining emphasis. A fully automated artificial intelligence (AI)-integrated system for body composition assessment on CT scans is a prerequisite for effective opportunistic screening. However, no study has evaluated the implementation of fully automated AI systems for opportunistic screening in real-world clinical practice for routine health check-ups.</p><p><strong>Objective: </strong>The aim of this study is to evaluate the performance and clinical utility of a fully automated AI-integrated system for body composition assessment on opportunistic CT during routine health check-ups.</p><p><strong>Methods: </strong>This prospective multicenter study included 537 patients who underwent routine health check-ups across 3 institutions. Our AI algorithm models are composed of selecting L3 slice and segmenting muscle and fat area in an end-to-end manner. The AI models were integrated into the Picture Archiving and Communication System (PACS) at each institution. Technical success rate, processing time, and segmentation accuracy in Dice similarity coefficient were assessed. Body composition metrics were analyzed across age and sex groups.</p><p><strong>Results: </strong>The fully automated AI-integrated system successfully retrieved anonymized CT images from the PACS, performed L3 selection and segmentation, and provided body composition metrics, including muscle quality maps and muscle age. The technical success rate was 100% without any failed cases requiring manual adjustment. The mean processing time from CT acquisition to report generation was 4.12 seconds. Segmentation accuracy comparing AI results and human expert results was 97.4%. Significant age-related declines in skeletal muscle area and normal-attenuation muscle area were observed, alongside increases in low-attenuation muscle area and intramuscular adipose tissue.</p><p><strong>Conclusions: </strong>Implementation of the fully automated AI-integrated system significantly enhanced opportunistic sarcopenia screening, achieving excellent technical success and high segmentation accuracy without manual intervention. This system has the potential to transform routine health check-ups by providing rapid and accurate assessments of body composition.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e69940"},"PeriodicalIF":2.0,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12413142/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145006146","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":"Quality and Reliability of Adolescent Sexuality Education on Chinese Video Platforms: Sentiment-Topic Analysis and Cross-Sectional Study.","authors":"Lan Wang, Xiantao Shu, Jianmei Huang, Weiqian Yan, Duo Zhao","doi":"10.2196/77100","DOIUrl":"10.2196/77100","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Adolescence is a critical period for lifelong health, which makes access to accurate and comprehensive sexuality education essential. As video platforms become a primary source of information for adolescents, the quality of their content significantly impacts their physical and mental health.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to evaluate the quality, reliability, understandability, and actionability of adolescent sexuality education videos on major Chinese platforms (Bilibili, TikTok or Douyin, and Kwai), analyze associated user comment sentiment and topics, identify predictors of quality and reliability, and provide recommendations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A cross-sectional analysis was conducted (April 2025) on the top 100 comprehensively ranked comprehensive sexuality education videos (N=300 total) retrieved from each platform using the keyword (\"adolescent sexuality education\"). Videos were assessed using the Global Quality Score, modified DISCERN, and Patient Education Materials Assessment Tool (PEMAT-U/A), with interrater reliability assessed via Cohen κ. A corpus of over 49,000 user comments underwent sentiment analysis (fine-tuned RoBERTa) and topic modeling (BERTopic, yielding 29 topics grouped into 6 themes). Statistical analyses included Kruskal-Wallis H tests, Spearman correlations, and stepwise linear regressions (SPSS [version 27.0]; P&lt;.05).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Video quality and reliability were moderate on Bilibili and TikTok but generally poor on Kwai. Content from verified sources (physicians, educators, and institutional media) demonstrated superior quality and stability compared to highly variable content from individual media (the predominant source type, especially on Kwai; 87/100, 87%). Paradoxically, Kwai exhibited the highest user engagement despite the lowest quality scores. Understandability (PEMAT-U) was consistently the strongest positive predictor for both quality (Global Quality Score, final model adjusted R&lt;sup&gt;2&lt;/sup&gt;=0.383, β=0.485) and reliability (modified DISCERN, final model adjusted R&lt;sup&gt;2&lt;/sup&gt;=0.209, β=0.319). Actionability (PEMAT-A) and video duration were also significant positive predictors. Understandability scores (PEMAT-U) were generally high (approximately 69%), while actionability scores (PEMAT-A) were moderate to low (33%-50%). Sentiment analysis revealed that comments were predominantly neutral (35,372/49,680, 71.2%), with negative comments (9141/49,680, 18.4%) significantly outweighing positive ones (5167/49,680, 10.4%). Key discussion themes identified included sources of knowledge acquisition, sexual safety and prevention, physiology, and sexual health and practices.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;While online video platforms offer accessible channels for adolescent sexuality education in China, the current content is often of moderate-to-poor quality, with questionable reliability and limited actionability. Understandab","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e77100"},"PeriodicalIF":2.0,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12449667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145000649","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":"The Moderating Effect of Atypical Events on the Relationship Between Heart Rate and Stress in Medical Residents Working in an Intensive Care Unit: Longitudinal, Observational Daily Diary Study.","authors":"Ruibei Li, Ujjwal Pasupulety, Wellington Chang, Adam C Frank","doi":"10.2196/67822","DOIUrl":"10.2196/67822","url":null,"abstract":"<p><strong>Background: </strong>Residency is a critical period in a physician's training, characterized by significant physical, cognitive, and emotional demands that make residents highly susceptible to stress and associated negative health outcomes. While physiological signals such as heart rate have been explored as potential biomarkers of stress, their predictive utility in high-stress environments such as the intensive care unit (ICU) remains inconclusive, especially when factoring in atypical events that can further exacerbate resident stress levels.</p><p><strong>Objective: </strong>This study aimed to investigate the relationship between daily average heart rate (AHR) and perceived stress among ICU residents and examine the moderating effect of atypical events on this relationship.</p><p><strong>Methods: </strong>The TILES (Tracking Individual Performance With Sensors)-2019 dataset collected longitudinal data from 44 ICU residents who provided daily self-reported stress ratings and wore a Fitbit device to track physiological data over a 3-week period. The main predictor variables were AHR and the occurrence of atypical events (both work and life related and daily hassles). The primary outcome was the level of perceived stress measured on a 7-point Likert scale. Linear mixed models were used to analyze the relationship between AHR and stress, accounting for within-subject and between-subject variance. Interaction effects between AHR and atypical events were also examined.</p><p><strong>Results: </strong>The analysis revealed a significant positive association between AHR and perceived stress (β=0.032; P=.04) on standard days. However, this relationship was attenuated by the presence of negative atypical events (β=-0.076; P=.02). We further analyzed whether the severity of negative atypical events had an additional moderating effect but found no statistical significance.</p><p><strong>Conclusions: </strong>AHR is a potential physiological marker for perceived stress in ICU residents, but its effect is moderated by negative atypical events. Future research should replicate these findings in more diverse cohorts, assess their generalizability to broader populations, and control for additional confounding variables. Incorporating negative atypical events into stress assessment could lead to more accurate and context-sensitive interpretations of physiological data.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e67822"},"PeriodicalIF":2.0,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12449669/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145006155","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":"The Feasibility and Acceptability of an App-Based Intervention Aimed at Improving Maternal Health Literacy Regarding Infant Play and Development: Mixed Methods Study.","authors":"Fiona Bennin, Shane A Norris, Alessandra Prioreschi","doi":"10.2196/76517","DOIUrl":"10.2196/76517","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Allowing infants access to unstructured, unrestricted play in their home environment is imperative for increasing healthy movement behaviors and, therefore, developmental outcomes. Interventions should equip mothers to provide opportunities for infant play as early as possible. Evaluating such interventions is necessary to understand the feasibility for scale-up and implementation in specific contexts. Furthermore, the appropriateness and relevance of standardized outcome measures in different ethnic and socioeconomic contexts should be determined to ensure validity.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to (1) test the feasibility and acceptability of an intervention aimed at improving maternal health literacy regarding infant play and development and (2) determine participants' understanding of the study outcome questionnaires.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This mixed methods study was nested within the Play Love and You (PLAY) study, a randomized controlled trial (PACTR202202747620052) designed to promote infant development. Mothers assigned to the PLAY study intervention arm at 6 months post partum (n=68) received telephone or in-person check-ins and assessments every 2 months and health literacy intervention content and resources (videos and infographics) delivered via a mobile app every week. Feasibility was assessed by monitoring appointment attendance (adherence) and frequency of access to the content via the app. Acceptability was explored using a questionnaire and 2 participant focus group discussions (FGDs) at the end of the study (12 months post partum). The FGDs also included questions exploring the participants' understanding of the 4 study outcome measure questionnaires administered at both 6 and 12 months.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In total, 68 participants were enrolled in the study at 6 months, of whom 17 (25%) attended the FGDs (n=8, 47% in FGD 1 and n=9, 53% in FGD 2). A total of 79% (49/62) of the participants completed the acceptability questionnaire. The health literacy content was found to be highly acceptable based on qualitative and quantitative data. Most acceptability questions had 98% (48/49) positive answers. Participants enjoyed learning about active infant play and developmental milestones and how to make recycled toys. Over 80% of participants (62/68, 91%) attended the 12-month exit appointment. Most of the participants (47/62, 76%) could access the intervention content over the 12 months of the PLAY study, and of those, 60% (28/47) looked at content more than once a week, and 11% (5/47) did so every day. Less than a quarter (10/47, 21%) only looked at the content sporadically. Access was impacted by technical difficulties attributed to using inconsistent external service providers.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study was found to be acceptable to participants and feasible in this setting. The high acceptability of the intervention content and belief ","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e76517"},"PeriodicalIF":2.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12447011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144992408","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":"Race and Ethnicity in Facebook Images and Text: Thematic Analysis.","authors":"Shaniece Criss, Sarah M Gonzales, Heran Mane, Katrina Makres, Dalmondeh D Nayreau, Vaishnavi Bharadwaj, Hannah G Kim, Thu T Nguyen","doi":"10.2196/62713","DOIUrl":"10.2196/62713","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Social media platforms, such as Facebook, provide a dynamic public space where users of various racial and ethnic backgrounds share content related to identity, politics, and other social issues. These platforms allow racially minoritized groups to both challenge racial silencing and express cultural pride. At the same time, they expose users to racism and stereotypes that can negatively affect their mental and physical health through psychosocial stress. Given the rise of multimodal communication, it is essential to study both images and text to fully understand how race and ethnicity are discussed in digital spaces.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This exploratory, descriptive study aimed to investigate how people discuss race and ethnicity on Facebook and specifically examine themes related to cultural pride, solidarity, racism, antiracism, and politics using qualitative content analysis of race- and ethnicity-related Facebook posts with images and text. These themes reflect how individuals construct identity, engage with other social identities, and navigate sociopolitical discourse in digital spaces.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a qualitative content analysis using a hybrid inductive-deductive approach. A total of 500 multimodal Facebook posts were randomly sampled using CrowdTangle, with 100 posts from each year between 2019 and 2023. Each post included both image and text and contained at least 1 race- or ethnicity-related keyword. Posts were uploaded to GitHub for storage and to Label Studio for coding. An iteratively developed codebook guided the analysis, focusing on representations of race and ethnicity, the continuum of race-related discourse, and topical content. All posts were double coded until an 80% interrater agreement was reached. The remaining discrepancies were resolved through coder consensus to ensure reliability and consistency. Themes were solidified through thematic analysis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Across 500 Facebook posts from 2019 to 2023, nearly one-third lacked clear racial specificity, with 19.8% (99/500) unrelated to race and 11.2% (56/500) mentioning no specific racial or ethnic group. Among the identified groups, Hispanic, multiracial, and immigrant communities were the most frequently referenced. Common themes included US politics, cultural pride, racism and stereotypes, and antiracism. Political content was the most crosscutting theme, while cultural pride and racism-related discourse varied by group. Antiracism posts reflected the national response to racial justice movements. These findings highlight the nuanced and evolving nature of race-related discourse on social media.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;It can be complicated to interpret image-based posts because of the subtle ways in which an image may reference race and ethnicity but does not explicitly mention it, or when there is a contradiction in the ideas portrayed in the image versus th","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e62713"},"PeriodicalIF":2.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12447004/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144992455","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":"Interaction of Long Working Hours and Sense of Coherence on Objective Total Sleep Time: Cross-Sectional Study From the SLEPT Study.","authors":"Kei Muroi, Emi Morita, Sumire Matsumoto, Asuka Ishihara, Sumi Hasegawa, Mami Ishitsuka, Daisuke Hori, Shorato Doki, Tsukasa Takahashi, Shin-Ichiro Sasahara, Takashi Kanbayashi, Masashi Yanagisawa, Makoto Satoh, Ichiyo Matsuzaki","doi":"10.2196/73784","DOIUrl":"10.2196/73784","url":null,"abstract":"<p><strong>Background: </strong>Long working hours are a significant risk factor for reduced sleep duration among workers. Sense of coherence (SOC), a dispositional orientation that enhances resilience to daily stressors, may serve as a protective factor for sleep duration under work-related stress. However, previous studies examining SOC and sleep duration have relied on subjective measures, which may be subject to recall bias. The interaction between long working hours and SOC on objective sleep duration has not been previously investigated.</p><p><strong>Objective: </strong>This study aimed to investigate the interaction between SOC and long working hours on objectively measured total sleep time (TST) among Japanese workers. We hypothesized that individuals with higher SOC would demonstrate less susceptibility to sleep reduction associated with long working hours compared to those with lower SOC.</p><p><strong>Methods: </strong>A cross-sectional survey was conducted from 2016 to 2017 as part of the Sleep Epidemiology Project at the University of Tsukuba (SLEPT) study among workers in Japan. The 13-item Sense of Coherence scale (SOC-13) was administered to assess participants' SOC levels, and weekly working hours were self-reported. TST was objectively measured using actigraphy devices worn continuously for 1 week. Long working hours were defined as ≥50 hours per week. Multiple regression analysis was performed with TST as the dependent variable, including long working hours, SOC-13, and their interaction term as independent variables. Simple slope analysis was conducted to examine the interaction effect at different SOC levels of ±1 SD from the mean.</p><p><strong>Results: </strong>A total of 540 workers were included in the final analysis. The study population had a mean age of 43.2 years, with 41.1% female participants. Mean TST was 322.0 (SD 58.0) minutes, and mean SOC score was 58.3 (SD 11.9). Long working hours were reported by 304 (56.3%) participants. Multiple regression analysis revealed a significant main effect of long working hours on reduced TST (β=-.115, P=.023), with workers in the long hours group sleeping 13.5 minutes less per night. Importantly, a significant interaction between long working hours and SOC was observed (β=.147, P=.026), indicating that SOC moderated the relationship between long working hours and sleep duration. Simple slope analysis demonstrated that at low SOC levels (-1 SD), long working hours were significantly associated with reduced TST (β=-24.7, P=.0015).</p><p><strong>Conclusions: </strong>Workers with lower SOC experienced significantly greater sleep reduction when working long hours, while those with higher SOC maintained relatively stable sleep duration despite extended work schedules. These findings suggest that interventions aimed at enhancing SOC may be effective in protecting workers' sleep health, particularly for those unable to reduce their working hours.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e73784"},"PeriodicalIF":2.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12407221/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144992475","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":"Web-Based Video Platforms as Sources of Information on Body Image Dissatisfaction in Adolescents: Content and Quality Analysis of a Cross-Sectional Study.","authors":"Li Liu, Jianning Yang, Fengmei Tan, Huan Luo, Yanhua Chen, Xiaolei Zhao","doi":"10.2196/71652","DOIUrl":"10.2196/71652","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Body image dissatisfaction among children and adolescents is a significant public health concern and is associated with numerous physical and mental problems. Social media platforms, including TikTok, BiliBili, and YouTube, have become popular sources of health information. However, the quality and reliability of content related to body image dissatisfaction have not been comprehensively evaluated.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The primary goal of this study was to examine the quality and reliability of videos related to body image dissatisfaction on TikTok, BiliBili, and YouTube.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The keywords \"body image dissatisfaction\" were searched on YouTube, TikTok, and BiliBili in November 2024. Videos were collected based on platform-specific sort filters, including the filter of \"Most liked\" on TikTok and the filter of \"Most viewed\" on BiliBili and YouTube. The top 100 videos on each platform were reviewed and screened in the study. After excluding videos that were (1) not in English or Chinese, (2) duplicates, (3) irrelevant, (4) no audio or visual, (5) contained advertisements, and (6) with a Global Quality Scale (GQS) score of 1, the final sample consisted of 64 videos, which formed the basis of our research and subsequent findings. Two reviewers (LL and JNY) screened, selected, extracted data, and evaluated all videos using the GQS, the Modified DISCERN (mDISCERN) scores, and the Modified Journal of the American Medical Association (mJAMA) benchmark criteria. Statistical analysis was performed using SPSS (version 28.0; IBM Corp).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In total, 64 videos were analyzed in the study, including 20 from TikTok, 13 from BiliBili, and 31 from YouTube. The median duration of the involved videos was 3.01 (IQR 1.00-5.94) minutes on TikTok, 3.52 (IQR 2.36-5.63) minutes on BiliBili, and 4.86 (IQR 3.10-6.93) minutes on YouTube. Compared with the other 2 platforms, BiliBili videos received higher likes and more comments. The majority of the videos (n=40, 62%) were uploaded by self-media. The quality of the videos on YouTube shows the highest overall scores. Videos uploaded by professional authors had significantly higher GQS, mDISCERN, and mJAMA scores compared to those uploaded by nonprofessionals. There was no significant correlation between video quality and the number of views or likes. However, the number of views and likes were significantly positively correlated. Furthermore, a significant correlation was found between the mJAMA, mDISCERN, and GQS scores.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Web-based video platforms have become an important source for adolescents to access health information. However, the lack of a significant correlation between video quality and the number of likes and comments poses a challenge for users seeking reliable health information. It is suggested that the quality of the videos on health information would be taken into consideration i","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e71652"},"PeriodicalIF":2.0,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12439227/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145069590","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":"Recognizing Skateboard and Kickboard Commuting Behaviors Using Activity Trackers: Feasibility Study Using Machine Learning Approaches.","authors":"Nathanael Aubert-Kato, Hitomi Hatori, Arisa Orihara, Takashi Nakagata, Yuji Ohta, Julien Tripette","doi":"10.2196/71969","DOIUrl":"https://doi.org/10.2196/71969","url":null,"abstract":"<p><strong>Background: </strong>Active commuting, such as skateboarding and kickboarding, is gaining popularity as an alternative to traditional modes of transportation such as walking and cycling. However, current activity trackers and smartphones, which rely on accelerometer data, are primarily designed to recognize symmetrical locomotive activities (eg, walking and running) and may struggle to accurately identify the unique push-push-glide motion patterns of skateboarding and kickboarding.</p><p><strong>Objective: </strong>The primary objective of this study was to evaluate the feasibility of classifying skateboard and kickboard commuting behaviors using data from wearable sensors and smartphones. A secondary objective was to identify the most important sensor-derived features for accurate activity recognition.</p><p><strong>Methods: </strong>Ten participants (4 women and 6 men; aged 12-55 y) performed 9 activities, including skateboarding, kickboarding, walking, running, bicycling, ascending stairs, descending stairs, sitting, and standing. Data were collected using wearable sensors (accelerometer, gyroscope, and barometer) placed on the wrist and the hip, as well as in the pocket to replicate the sensing characteristics of commercial activity trackers and smartphones. The signal processing approach included the extraction of 211 features from 10- and 20-second sliding windows. Random forest classifiers were trained to perform multiclass and binary classifications, including distinguishing skateboarding and kickboarding from other activities.</p><p><strong>Results: </strong>Wrist-worn sensor configurations achieved the highest balanced accuracies for multiclass classification (range 84%-88%). Skateboarding and kickboarding were identified with high sensitivity, ranging from 93% to 99% and 97% to 99%, respectively. Hip and pocket sensor configurations showed lower performance, particularly in distinguishing skateboarding (range 49%-58% sensitivity) from kickboarding (78% sensitivity). Binary classification models grouping skateboarding and kickboarding into a push-push-glide superclass achieved high accuracies (range 91%-95%). Key features for classification included low- and high-frequency accelerometer signals, as well as roll-pitch-yaw angles.</p><p><strong>Conclusions: </strong>This study demonstrates the feasibility of recognizing skateboard and kickboard commuting behaviors using wearable sensors, particularly wrist-worn devices. While hip and pocket sensors showed limitations in differentiating these activities, the broader push-push-glide classification achieved acceptable accuracy, suggesting its potential for integration into activity tracker software. Future research should explore sensor fusion approaches to further enhance recognition performance and address the question of energy expenditure estimation.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e71969"},"PeriodicalIF":2.0,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12396795/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144954936","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":"Medical Information Provided by Transgender and Gender-Diverse Content Creators on YouTube: Descriptive Content Analysis.","authors":"Lydia Bliss, Qianqian Zhao, Irene Chao, Oliver L Haimson, Ellen Selkie","doi":"10.2196/75787","DOIUrl":"https://doi.org/10.2196/75787","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Transgender and gender-diverse (TGD) individuals frequently turn to social media to find community, express their identities, and access essential information. These platforms are easily accessible to TGD people and enable health information-seeking in anonymous, identity-affirming spaces outside of traditional health care systems. As a result, social media has become a critical source of health information on topics like gender-affirming care for TGD individuals, specifically for TGD youth. YouTube, one of the most widely used social media platforms, is especially popular for its long-form videos made by content creators who have built dedicated followings on the platform. Among them are TGD content creators, many of whom make content documenting their medical transition and gender identity journey and provide general information about TGD topics. TGD creator content therefore makes YouTube an important platform for health education for TGD individuals.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to describe the health-related content shared by TGD content creators on YouTube. Specifically, we characterize the medical topics addressed, the frameworks used to discuss these topics, and the valence of creators' health care experiences.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A descriptive content analysis was performed on 2485 videos posted by 42 self-identified TGD YouTube content creators. Videos were systematically evaluated for mentions of gender-affirming care and other health-related topics. We also examined whether creators framed medical information using personal narratives or an informational approach and if they characterized their medical experiences as positive, negative, or neutral.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Most videos (n=1724, 69.4%) created by TGD content creators did not include discussions related to gender identity or transitioning. However, among the videos that did address gender identity (n=761, 30.6%), mentions of medical topics were prevalent (n=554, 72.8%). Of videos that discussed medical topics, gender-affirming surgeries (n=356, 64.3%) and hormone replacement therapy (n=307, 55.4%) were the most frequently discussed. Other commonly discussed medical topics included mental health (n=131, 23.6%) and sexual health (n=96, 17.3%). Videos covering medical topics primarily centered on personal experiences (n=411, 74.2%), with content creators often characterizing these experiences positively (n=224, 73.2%).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study highlights the breadth of health-related information shared by TGD content creators on YouTube. Our findings underscore the role of long-form video content on YouTube as an educational resource for TGD people, offering health information that is both easy to access and grounded in lived experience. Clinicians can use these findings to better understand the health information that their TGD clients are likely to encounter online, fostering mor","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e75787"},"PeriodicalIF":2.0,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12396793/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144954960","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":"Designing Digital Mental Health Interventions to Meet the Needs of Older Adolescents: Qualitative Interview and Group Discussion Study.","authors":"Rachel Kornfield, Sarah Alexandra Popowski, Emily Tack, Jack Svoboda, Miguel Herrera, Theresa Nguyen, Ashley Arehart Knapp, David Curtis Mohr, Jonah Meyerhoff","doi":"10.2196/68950","DOIUrl":"10.2196/68950","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Anxiety and depression are common in adolescents, but adolescents are often uninterested in formal mental health treatments or are unable to access them. Digital interventions can be delivered at scale to bridge critical gaps in mental health care but must address the needs and preferences of adolescents.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to conduct qualitative research involving adolescents aged 18 years to inform both the design of digital mental health interventions for adolescents broadly and new features and refinements to incorporate in an automated SMS text messaging intervention, Small Steps SMS, that was originally designed for young adults.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We recruited non-treatment-engaged older adolescents who were aged 18 years, lived in the United States, and had experienced depression or anxiety. In total, 12 participants were recruited through social media advertising and online self-screeners hosted by Mental Health America, a mental health advocacy organization. For 24 days, participants answered researcher prompts and engaged with one another in an asynchronous online discussion group, with a new discussion prompt released every 3 days. In parallel, partway through the discussion group, participants received interactive messages from Small Steps SMS, an automated SMS text messaging intervention that delivers daily dialogues supporting mental health self-management. Questions in the discussion group pertained to mental health challenges, help-seeking attitudes, perceptions of Small Steps SMS, and ways the program and other digital mental health interventions could meet the needs of older adolescents. A subset of participants (n=4, 33%) also completed interviews to elaborate on their responses. Thematic analysis was applied to transcripts of the discussion group and interviews to characterize user needs and design priorities when making Small Steps SMS and similar interventions available to adolescents.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Participants reported factors that contributed to their experience of mental health symptoms, including the transition from adolescence to adulthood, fears that the world is unstable and their futures are uncertain, and ineffective use of social media to cope with symptoms. Participants were proud of their generation's mental health acceptance but also observed a generational divide in mental health stigma and literacy that could impede seeking help from parents and other adults. Participants appreciated that Small Steps SMS allowed them to pursue mental health self-management conveniently and independently. They suggested that the program and similar interventions address adolescent-specific challenges and facilitate intergenerational communication about mental health. They also recommended possible ways to increase engagement through peer-to-peer communication, gamification, and greater explanation of self-management strategies.&lt;/p&gt;&lt;p","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e68950"},"PeriodicalIF":2.0,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12432472/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144955179","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}