Journal of Medical Internet Research最新文献

{"title":"AI Predictive Model of Mortality and Intensive Care Unit Admission in the COVID-19 Pandemic: Retrospective Population Cohort Study of 12,000 Patients.","authors":"Jose Manuel Ruiz Giardin, Óscar Garnica, Nieves Mesa Plaza, Juan Víctor SanMartín López, Ana Farfán Sedano, Elena Madroñal Cerezo, Miguel Ángel Duarte Millán, Aida Izquierdo Martínez, Luis Rivas, Marta Rivilla, Alejandro Morales Ortega, Begoña Frutos Pérez, Cristina De Ancos Aracil, Ruth Calderón, Guillermo Soria Fernandez, Jorge Marrero Francés, David Bernal Bello, Jose Ángel Satué Bartolomé, María Toledano Macías, Sara Piedrabuena García, Marta Guerrero Santillán, Rafael Cristóbal, Belen Mora, Laura Velázquez Ríos, Vanesa García de Viedma, Paula Cuenca Ruiz, Ibone Ayala Larrañaga, Lorena Carpintero, Celia Lara, Alvaro Ricardo Llerena, Virginia García Bermúdez, Gema Delgado Cárdenas, Paloma Pardo Rovira, Elena Tejero Sánchez, Maria Jesús Domínguez García, Carolina Mariño, Cristina Bravo, Ana Ontañon, Mario García, Jose Ignacio Hidalgo Pérez, Santiago Prieto Menchero, Natalia González Pereira, Sonia Gonzalo Pascua, Jorge Tarancón Rey, Luis Antonio Lechuga Suárez","doi":"10.2196/70674","DOIUrl":"10.2196/70674","url":null,"abstract":"<p><strong>Background: </strong>One of the main challenges with COVID-19 has been that although there are known factors associated with a worse prognosis, clinicians have been unable to predict which patients, with similar risk factors, will die or require intensive care unit (ICU) care.</p><p><strong>Objective: </strong>This study aimed to develop a personalized artificial intelligence model to predict the patient risk of mortality and ICU admission related to SARS-CoV-2 infection during the initial medical evaluation before any kind of treatment.</p><p><strong>Methods: </strong>It is a population-based, observational, retrospective study covering from February 1, 2020, to January 24, 2023, with different circulating SARS-CoV-2 viruses, vaccinated status, and reinfections. It includes patients attended by the reference hospital in Fuenlabrada (Madrid, Spain). The models used the random forest technique, Shapley Additive Explanations method, and processing with Python (version 3.10.0; Python Software Foundation) and scikit-learn (version 1.3.0). The models were applied to different epidemic SARS-CoV-2 infection waves. Data were collected from 11,975 patients (4998 hospitalized and 6737 discharged). Predictive models were built with records from 4758 patients and validated with 6977 patients after evaluation in the emergency department. Variables recorded were age, sex, place of birth, clinical data, laboratory results, vaccination status, and radiologic data at admission.</p><p><strong>Results: </strong>The best mortality predictor achieved an area under the receiver operating characteristic curve (AUC) of 0.92, sensitivity of 0.89, specificity of 0.82, positive predictive value (PPV) of 0.35, and mean negative predictive value (NPV) of 0.98. The ICU admission predictor had an AUC of 0.89, sensitivity of 0.75, specificity of 0.88, PPV of 0.37, and NPV of 0.98. During validation, the mortality model exhibited good performance for the nonhospitalized group, achieving an AUC of 0.95, sensitivity of 0.88, specificity of 0.98, PPV of 0.21, and NPV of 0.99, predicting the death of 30 of 34 patients who were not hospitalized. For the hospitalized patients, the mortality model achieved an AUC of 0.85, sensitivity of 0.86, specificity of 0.74, PPV of 0.24, and NPV of 0.98. The model for predicting ICU admission had an AUC of 0.82, sensitivity of 1.00, specificity of 0.59, PPV of 0.05, and NPV of 1.00. The models' metrics presented stability along all pandemic waves. Key mortality predictors included age, Charlson value, and tachypnea. The worse prognosis was linked to high values in urea, erythrocyte distribution width, oxygen demand, creatinine, procalcitonin, lactate dehydrogenase, heart failure, D-dimer, oncological and hematological diseases, neutrophil, and heart rate. A better prognosis was linked to higher values of lymphocytes and systolic and diastolic blood pressures. Partial or no vaccination provided less protection than full vaccination.</p><","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e70674"},"PeriodicalIF":5.8,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144608590","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":"Sleep Quality as a Mediator of Internet Gaming Disorder and Executive Dysfunction in Adolescents: Cross-Sectional Questionnaire Study.","authors":"Michoel L Moshel, Wayne Warburton, Rainer Thomasius, Kerstin Paschke","doi":"10.2196/68571","DOIUrl":"10.2196/68571","url":null,"abstract":"<p><strong>Background: </strong>Internet gaming disorder (IGD) has been associated with impairments in executive functioning, particularly inattention and impulsivity. Sleep quality has separately been linked to both gaming behavior and cognitive performance, yet its role as a mediating factor in this relationship is underexplored.</p><p><strong>Objective: </strong>This study aimed to determine whether sleep quality mediates the relationship between IGD symptoms and executive dysfunction in adolescents, specifically focusing on the domains of inattention and hyperactivity or impulsivity. A reverse mediation model was also tested to explore the bidirectional nature of these relationships.</p><p><strong>Methods: </strong>A representative sample of 1000 adolescents (539/1000, 53.9% males), aged between 12 and 17 years (mean 14.52, SD 1.64), completed validated self-report measures of IGD symptoms, executive dysfunction, and sleep quality. Structural equation modeling was used to test direct and indirect effects with age and gender included as covariates.</p><p><strong>Results: </strong>Of the sample, 2.4% (24/1000) met criteria for IGD (875/1000, 87.5% males), and 22.6% (226/1000) met criteria for chronic sleep reduction. Among those with IGD, 54.2% (542/1000) also experienced chronic sleep reduction. In model A (IGD → Sleep → Executive Dysfunction), IGD symptoms were associated with poorer sleep quality (a=0.32, 95% CI 0.19-0.44), which in turn were associated with greater executive dysfunction (b=0.05, 95% CI 0.01-0.10). The indirect effect was significant (a×b=0.02, 95% CI 0.01-0.04), and sleep quality was a partial mediator. In the reverse model (model B), executive dysfunction was associated with poorer sleep quality (a=0.15, 95% CI 0.06-0.25), which subsequently was associated with higher IGD symptoms (b=0.11, 95% CI 0.07-0.16); indirect effect a×b=0.02, 95% CI 0.01-0.04. Simple slope analysis showed that IGD symptoms were associated only with executive dysfunction at average or poor levels of sleep quality. At higher levels of sleep quality, this relationship was no longer significant.</p><p><strong>Conclusions: </strong>The results of this study suggest that sleep quality may be an important intermediary mechanism by which IGD might contribute to executive dysfunction and provide a basis for the development and implementation of strategies that target sleep issues in IGD. Prospective longitudinal research is needed to examine the directionality of the relationships between IGD, sleep quality, and executive dysfunction longitudinally.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e68571"},"PeriodicalIF":5.8,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12266305/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600723","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":"Effectiveness of Gamified Teaching in Disaster Nursing Education for Health Care Workers: Systematic Review.","authors":"Shiyi Bai, HuiJuan Zeng, Qianmei Zhong, Lulu Cao, Mei He","doi":"10.2196/74955","DOIUrl":"10.2196/74955","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;With the continuous advancement of medical technology and the frequent occurrence of disaster events, the training of health care workers in disaster nursing has become increasingly significant. However, traditional training methods often struggle to engage learners' interest and enthusiasm, making it challenging to simulate emergencies in real-life scenarios effectively. Gamification, as an innovative pedagogical approach that enhances the enjoyment and practicality of learning through the incorporation of game elements, has garnered considerable attention in the realm of disaster nursing education for health care workers in recent years. This review systematically evaluates its effectiveness and explores its advantages in improving training outcomes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This review aims to evaluate the effectiveness of gamified teaching methodologies in disaster nursing education and to identify the outcome of 16 indicators used in existing studies.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This study was conducted following the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines, using the PICO-SD framework (Population, Intervention, Control, Outcome, Study Design) to establish the inclusion criteria. The researchers systematically searched 8 databases on February 10, 2025, including the Cochrane Library, PubMed, CINAHL (EBSCO), Embase, Web of Science, CNKI, Wanfang, and SCOPUS. Ultimately, 16 quasi-experimental studies investigating the application of gamified teaching in disaster nursing education were included in the analysis. For randomized controlled trials (RCTs), the Cochrane Risk of Bias Assessment Tool (RoB 2.0) was used for quality assessment; for quasi-experimental studies, the Joanna Briggs Institute Risk of Bias Tool for Non-Randomized Intervention Studies was used for methodological quality evaluation. Given the heterogeneity of study designs and the diversity of study indicators, this study used a narrative synthesis to integrate the findings.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The studies included in this review comprised 1 RCT and 15 quasi-experimental designs. Six gamified formats exhibited positive outcomes. The effectiveness of these formats was assessed through various metrics, including theoretical knowledge (14 studies), practical skills (11 studies), learner satisfaction (9 studies), knowledge retention (4 studies), and self-efficacy (2 studies). All formats demonstrated improvements in knowledge and skills, with high levels of satisfaction reported. However, data on long-term retention were limited.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Gamification teaching methods have shown significant potential to enhance core competencies such as emergency response, decision-making, and teamwork in disaster nursing education and have been effective in reinforcing learning engagement through elements such as cooperation, competition, scoring, and scenario simulation.","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e74955"},"PeriodicalIF":5.8,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12266611/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600721","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":"Artificial Intelligence-Enabled Facial Privacy Protection for Ocular Diagnosis: Development and Validation Study.","authors":"Haizhu Tan, Hongyu Chen, Zhenmao Wang, Mingguang He, Chiyu Wei, Lei Sun, Xueqin Wang, Danli Shi, Chengcheng Huang, Anping Guo","doi":"10.2196/66873","DOIUrl":"10.2196/66873","url":null,"abstract":"<p><strong>Background: </strong>Facial biometric data, while valuable for clinical applications, poses substantial privacy and security risks.</p><p><strong>Objective: </strong>This paper aims to address the privacy and security concerns related to facial biometric data and support auxiliary diagnoses, in pursuit of which we developed Digital FaceDefender, an artificial intelligence-driven privacy safeguard solution.</p><p><strong>Methods: </strong>We constructed a diverse set of digitally synthesized Asian face avatars representing both sexes, spanning ages 5 to 85 years in 10-year increments, using 70,000 facial images and 13,061 Asian face images. Landmark data were separately extracted from both patient and avatar images. Affine transformations ensured spatial alignment, followed by color correction and Gaussian blur to enhance fusion quality. For auxiliary diagnosis, we established 95% CIs for pixel distances within the eye region on a cohort of 1163 individuals, serving as diagnostic benchmarks. Reidentification risk was assessed using the ArcFace model, applied to 2500 images reconstructed via Detailed Expression Capture and Animation (DECA). Finally, Cohen Kappa analyses (n=114) was applied to assess agreement between diagnostic benchmarks and ophthalmologists' evaluations.</p><p><strong>Results: </strong>Compared to the DM method, Digital FaceDefender significantly reduced facial similarity scores (FDface vs raw images: 0.31; FLAME_FDface vs raw images: 0.09) and achieved zero Rank-1 accuracy in Pose #2-#3 and Pose #2-#5, with near-zero accuracy in Pose #4 (0.02) and Pose #5 (0.04), confirming lower reidentification risk. Cohen Kappa analysis demonstrated moderate agreement between our benchmarks and ophthalmologists' assessments for the left eye (κ=0.37) and right eye (κ=0.45; both P<.001), validating diagnostic reliability of the benchmarks. Furthermore, the user-friendly Digital FaceDefender platform has been established and is readily accessible for use.</p><p><strong>Conclusions: </strong>In summary, Digital FaceDefender effectively balances privacy protection and diagnostic use.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e66873"},"PeriodicalIF":5.8,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12266301/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600718","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":"Impact of News Portrayals of Physicians as Vulnerable on the Public's Evaluation and Trust in Physicians Under Different Involvement Levels: Quantitative Study.","authors":"Qiwei Li, Jie Zhou","doi":"10.2196/67947","DOIUrl":"https://doi.org/10.2196/67947","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;News portrayals of physicians, especially in China, often depict them as vulnerable-overworked, with inadequate compensation, or as victims of violence. These portrayals may send mixed signals to the public, yet their impact remains underexplored. Understanding their impact is essential for informing media strategies and improving physician-patient relationships.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study investigated how portrayals of physicians as vulnerable influence public evaluations of their competence, warmth, morality, and overall trust and considered the moderating effects of involvement (ie, hospital visit frequency).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Four studies were conducted. Study 1 (N=492) examined the effects of daily exposure to vulnerable portrayals, and study 2 (N=710) experimentally exposed participants to vulnerable portrayals to directly investigate the causal relationship between exposure and evaluations with involvement as a hypothesized moderator. Study 3 (N=565) manipulated situational involvement using an imagination task, whereas study 4 (N=436) embedded involvement-enhancing content into news articles to improve ecological validity.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Study 1 revealed that among individuals with low or moderate involvement, greater exposure to vulnerable physician portrayals in everyday life predicted more favorable overall evaluations of physicians (low involvement: B=0.11 and P=.04; moderate involvement: B=0.20 and P&lt;.001). No significant effect was found among high-involvement individuals (P&gt;.68 in all cases), suggesting an inverted U-shaped moderating effect of involvement. Study 2 supported this pattern-vulnerable portrayals had no significant impact among individuals with low or high involvement (t&lt;sub&gt;702&lt;/sub&gt;&lt;0.49 in all cases; P&gt;.15 in all cases) but had marginally positive effects on individuals with moderate involvement (t&lt;sub&gt;702&lt;/sub&gt;=1.67; P=.10; d=0.26). Notably, individuals with superhigh involvement (ie, those in hospital settings) evaluated physicians more negatively following vulnerable portrayals (t&lt;sub&gt;702&lt;/sub&gt;=2.49; P=.01; d=0.44). Given that nearly 80% of the general population reports low to moderate hospital visits, which is the positive moderating effect range for involvement, studies 3 and 4 targeted this group and tested whether manipulated situational involvement could enhance the effects of vulnerable portrayals. In studies 3a and 3b, participants in the high-situational involvement condition evaluated physicians more positively in the vulnerable portrayal group than in the control group (3a: t&lt;sub&gt;401&lt;/sub&gt;=2.71, P=.007, d=0.37; 3b: t&lt;sub&gt;154&lt;/sub&gt;=3.48, P&lt;.001, d=0.93), with no effects under low-involvement conditions. Study 4 confirmed that involvement-enhancing vulnerable portrayals elicited more favorable evaluations compared to the control group (t&lt;sub&gt;433&lt;/sub&gt;=3.14; P=.002; d=0.37). Across all 4 studies, overall evaluation significan","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e67947"},"PeriodicalIF":5.8,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600722","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":"Analyzing Public Google Search Interest in Measles Within Canada: Identifying Key Moments for Targeted Risk Communication.","authors":"Mohammad Jokar, Diego Nobrega","doi":"10.2196/75025","DOIUrl":"10.2196/75025","url":null,"abstract":"<p><strong>Unlabelled: </strong>We analyzed Google Trends data on measles-related searches in Canada from January 1 to May 21, 2025; web, news, and YouTube search trends increased significantly across provinces (all P values were <.05), aligning with rising case numbers. Our findings emphasize the importance of timely, targeted risk communication for enhancing public awareness and responses during this outbreak.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e75025"},"PeriodicalIF":5.8,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12266579/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600717","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":"Association Between COVID-19 During Pregnancy and Preterm Birth by Trimester of Infection: Retrospective Cohort Study Using Large-Scale Social Media Data.","authors":"Ari Z Klein, Shriya Kunatharaju, Su Golder, Lisa D Levine, Jane C Figueiredo, Graciela Gonzalez-Hernandez","doi":"10.2196/66097","DOIUrl":"10.2196/66097","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Preterm birth, defined as birth at &lt;37 weeks of gestation, is the leading cause of neonatal death globally and the second leading cause of infant mortality in the United States. There is mounting evidence that COVID-19 infection during pregnancy is associated with an increased risk of preterm birth; however, data remain limited by trimester of infection. The ability to study COVID-19 infection during the earlier stages of pregnancy has been limited by available sources of data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The objective of this study was to use self-reports in large-scale social media data to assess the association between the trimester of COVID-19 infection and preterm birth.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In this retrospective cohort study, we used natural language processing and machine learning, followed by manual validation, to identify self-reports of pregnancy on Twitter and to search these users' collection of publicly available tweets for self-reports of COVID-19 infection during pregnancy and, subsequently, a preterm birth or term birth outcome. Among the users who reported their pregnancy on Twitter, we also identified a 1:1 age-matched control group, consisting of users with a due date before January 1, 2020-that is, without COVID-19 infection during pregnancy. We calculated the odds ratios (ORs) with 95% CIs to compare the frequency of preterm birth for pregnancies with and without COVID-19 infection and by the timing of infection: first trimester (1-13 weeks), second trimester (14-27 weeks), or third trimester (28-36 weeks).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Through August 2022, we identified 298 Twitter users who reported COVID-19 infection during pregnancy, a preterm birth or term birth outcome, and maternal age: 94 (31.5%) with first-trimester infection, 110 (36.9%) with second-trimester infection, and 95 (31.9%) with third-trimester infection. In total, 26 (8.8%) of these 298 users reported preterm birth: 8 (8.5%) with first-trimester infection, 7 (6.4%) with second-trimester infection, and 12 (12.6%) with third-trimester infection. In the 1:1 age-matched control group, 13 (4.4%) of the 298 users reported preterm birth. Overall, the odds of preterm birth were significantly higher for pregnancies with COVID-19 infection compared to those without (OR 2.08, 95% CI 1.06-4.28; P=.046). In particular, the odds of preterm birth were significantly higher for pregnancies with COVID-19 infection during the third trimester (OR 3.16, 95% CI 1.36-7.29; P=.007). The odds of preterm birth were not significantly higher for pregnancies with COVID-19 infection during the first trimester (OR 2.05, 95% CI 0.78-5.08; P=.12) or second trimester (OR 1.50, 95% CI 0.54-3.82; P=.44) compared to those without infection.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Based on self-reports in large-scale social media data, the results of our study suggest that COVID-19 infection particularly during the third trimester is associated ","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e66097"},"PeriodicalIF":5.8,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12266298/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600719","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":"Developing a Framework for Online Review-Based Health Care Service Quality Assessment: Text-Mining Study.","authors":"Xue Zhang, Jianshan Sun, Xin Li, Yezheng Liu, Chenwei Li","doi":"10.2196/66141","DOIUrl":"10.2196/66141","url":null,"abstract":"<p><strong>Background: </strong>With the development of online health care platforms, patient reviews have become an important source for assessing medical service quality. However, the critical aspects of quality dimensions in textual reviews remain largely unexplored.</p><p><strong>Objective: </strong>This study aims to establish a comprehensive medical service quality assessment framework by leveraging online review data. Such a framework would support large service providers, such as online platforms, to assess the quality of many doctors efficiently.</p><p><strong>Methods: </strong>We adopted a text-mining approach with theory-driven topic extraction from online reviews to develop a service quality assessment framework. The framework is based on topic and sentiment classification methods. We conducted an empirical analysis to assess the validity of the framework. Specifically, we examined if patients' sentiments regarding our extracted dimensions affect demand (number of consultation requests) due to quality signals reflected in these dimensions.</p><p><strong>Results: </strong>We develop a 5-dimensional health care service quality framework (HSQ-5D model). In the empirical study, patient demand is affected by these dimensions, including expertise (coefficient=1.12; P<.001), service delivery process (coefficient=5.60; P<.001), attitude (coefficient=0.82; P<.001), empathy (coefficient=2.65; P<.001), and outcome (coefficient=0.26; P<.001; through patients' perceived quality from reviews). The 5 dimensions can explain 85.52% of the variance in patient demand, while all information from online reviews can explain 85.67%. The results show the validity and the potential practical value of the proposed HSQ-5D model.</p><p><strong>Conclusions: </strong>This study explores how online reviews can be used to evaluate health care services, offering significant implications for health care management. Theoretically, we extend existing service quality frameworks by integrating text-mining analysis of online reviews, thereby enhancing the understanding of service quality assessment in the digital health context. Practically, the framework can allow health care platforms to identify and reveal doctors' service quality to reduce patients' information asymmetry and strengthen patient-provider relationships, ultimately contributing to a more effective and patient-centered health care system.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e66141"},"PeriodicalIF":5.8,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12266612/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600720","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: Using Large Language Models to Detect Depression From User-Generated Diary Text Data as a Novel Approach in Digital Mental Health Screening: Instrument Validation Study.","authors":"Daun Shin, Hyoseung Kim, Seunghwan Lee, Younhee Cho, Whanbo Jung","doi":"10.2196/79198","DOIUrl":"https://doi.org/10.2196/79198","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.2196/54617.].</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e79198"},"PeriodicalIF":5.8,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144591460","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":"School-Based Online Surveillance of Youth: Systematic Search and Content Analysis of Surveillance Company Websites.","authors":"Alison O'Daffer, Wendy Liu, Cinnamon S Bloss","doi":"10.2196/71998","DOIUrl":"10.2196/71998","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;School-based online surveillance of students has been widely adopted by middle and high school administrators over the past decade. Little is known about the technology companies that provide these services or the benefits and harms of the technology for students. Understanding what information online surveillance companies monitor and collect about students, how they do it, and if and how they facilitate appropriate intervention fills a crucial gap for parents, youth, researchers, and policy makers.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The two goals of this study were to (1) comprehensively identify school-based online surveillance companies currently in operation, and (2) collate and analyze company-described surveillance services, monitoring processes, and features provided.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We systematically searched GovSpend and EdSurge's Education Technology (EdTech) Index to identify school-based online surveillance companies offering social media monitoring, student communications monitoring, or online monitoring. We extracted publicly available information from company websites and conducted a systematic content analysis of the websites identified. Two coders independently evaluated all company websites and discussed the findings to reach 100% consensus regarding website data labeling.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Our systematic search identified 14 school-based online surveillance companies. Content analysis revealed that most of these companies facilitate school administrators' access to students' digital behavior, well beyond monitoring during school hours and on school-provided devices. Specifically, almost all companies reported conducting monitoring of students at school, but 86% (12/14) of companies reported also conducting monitoring 24/7 outside of school and 7% (1/14) reported conducting monitoring outside of school at school administrator-specified locations. Most online surveillance companies reported using artificial intelligence to conduct automated flagging of student activity (10/14, 71%), and less than half of the companies (6/14, 43%) reported having a secondary human review team. Further, 14% (2/14) of companies reported providing crisis responses via company staff, including contacting law enforcement at their discretion.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study is the first detailed assessment of the school-based online surveillance industry and reveals that student monitoring technology can be characterized as heavy-handed. Findings suggest that students who only have school-provided devices are more heavily surveilled and that historically marginalized students may be at a higher risk of being flagged due to algorithmic bias. The dearth of research on efficacy and the notable lack of transparency about how surveillance services work indicate that increased oversight by policy makers of this industry may be warranted. Dissemination of our findings can improve pare","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e71998"},"PeriodicalIF":5.8,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12262101/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144591462","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}