JMIR Medical Informatics最新文献

{"title":"Genotype Distribution and Migration Patterns of Hepatitis C Virus in Shandong Province, China: Molecular Epidemiology and Phylogenetic Study.","authors":"Lin Lin, Guoyong Wang, Lianzheng Hao, Tingbin Yan","doi":"10.2196/60207","DOIUrl":"10.2196/60207","url":null,"abstract":"<p><strong>Background: </strong>Hepatitis C virus (HCV) remains a significant public health concern in China, particularly in Shandong Province, where detailed molecular epidemiological data are limited. HCV exhibits substantial genetic diversity, and understanding its genotype distribution and transmission dynamics is critical for developing effective control strategies.</p><p><strong>Objective: </strong>This study aimed to investigate the genetic diversity, geographic dissemination, and evolutionary history of HCV genotypes in Shandong Province, China, using molecular techniques and phylogenetic methods.</p><p><strong>Methods: </strong>A total of 320 HCV-positive serum samples were collected from multiple hospitals across Shandong Province between 2013 and 2021. HCV RNA was extracted and amplified targeting the 5' untranslated region (UTR), Core, and NS5B regions. Sequencing was conducted, and genotypes were determined using the National Center for Biotechnology Information's Basic Local Alignment Search Tool (NCBI BLAST). Phylogenetic trees were constructed using maximum likelihood methods with the general time reversible with Gamma-distributed rate variation among sites [(GTR)+Gamma model]. The temporal and geographic evolution of the major subtypes (1b and 2a) was analyzed using Bayesian Markov chain Monte Carlo (MCMC) methods implemented in Bayesian Evolutionary Analysis Sampling Trees (BEAST). The Bayesian skyline plot (BSP) was used to infer population dynamics and estimate the time to the most recent common ancestor (tMRCA).</p><p><strong>Results: </strong>Genotypes 1b (n=165) and 2a (n=131) were identified as the predominant subtypes, with a small number of genotypes 3b, 6a, 6k, and potential recombinant strains also detected. Phylogenetic analysis revealed distinct evolutionary clustering of 1b and 2a strains, suggesting multiple diffusion events within the province. The tMRCA of subtypes 1b and 2a were estimated to be 1957 and 1979, respectively. Bayesian skyline analysis showed that both subtypes experienced long-term population stability, followed by a rapid expansion period between 2014 and 2019 (1b) and 2014 to 2016 (2a), respectively. The analysis also identified key transmission hubs such as Jinan, Liaocheng, Tai'an, and Dezhou, indicating city-level variations in HCV spread.</p><p><strong>Conclusions: </strong>This study provides data-supported insights into the genotypic landscape and evolutionary patterns of HCV in Shandong Province. The identification of dominant subtypes, potential recombinant strains, and regional transmission pathways enhances our understanding of local HCV epidemiology. These findings have implications for public health policy, resource allocation, and targeted treatment strategies. The integration of molecular epidemiology and phylogenetics offers a valuable model for infectious disease surveillance and control in similar settings.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e60207"},"PeriodicalIF":3.8,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12360734/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144876986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-Driven Integrated System for Burn Depth Prediction With Electronic Medical Records: Algorithm Development and Validation.","authors":"Md Masudur Rahman, Mohamed El Masry, Surya C Gnyawali, Yexiang Xue, Gayle Gordillo, Juan P Wachs","doi":"10.2196/68366","DOIUrl":"10.2196/68366","url":null,"abstract":"<p><strong>Background: </strong>Burn injuries represent a significant clinical challenge due to the complexity of accurately assessing burn depth, which directly influences the course of treatment and patient outcomes. Traditional diagnostic methods primarily rely on visual inspection by experienced burn surgeons. Studies report diagnostic accuracies of around 76% for experts, dropping to nearly 50% for less experienced clinicians. Such inaccuracies can result in suboptimal clinical decisions-delaying vital surgical interventions in severe cases or initiating unnecessary treatments for superficial burns. This diagnostic variability not only compromises patient care but also strains health care resources and increases the likelihood of adverse outcomes. Hence, a more consistent and precise approach to burn classification is urgently needed.</p><p><strong>Objective: </strong>The objective is to determine whether a multimodal integrated artificial intelligence (AI) system for accurate classification of burn depth can preserve diagnostic accuracy and provide an important resource when used as part of the electronic medical record (EMR).</p><p><strong>Methods: </strong>This study used a novel multimodal AI system, integrating digital photographs and ultrasound tissue Doppler imaging (TDI) data to accurately assess burn depth. These imaging modalities were accessed and processed through an EMR system, enabling real-time data retrieval and AI-assisted evaluation. TDI was instrumental in evaluating the biomechanical properties of subcutaneous tissues, using color-coded images to identify burn-induced changes in tissue stiffness and elasticity. The collected imaging data were uploaded to the EMR system (DrChrono), where they were processed by a vision-language model built on GPT-4 architecture. This model received expert-formulated prompts describing how to interpret both digital and TDI images, guiding the AI in making explainable classifications.</p><p><strong>Results: </strong>This study evaluated whether a multimodal AI classifier, designed to identify first-, second-, and third-degree burns, could be effectively applied to imaging data stored within an EMR system. The classifier achieved an overall accuracy of 84.38%, significantly surpassing human performance benchmarks typically cited in the literature. This highlights the potential of the AI model to serve as a robust clinical decision support tool, especially in settings lacking highly specialized expertise. In addition to accuracy, the classifier demonstrated strong performance across multiple evaluation metrics. The classifier's ability to distinguish between burn severities was further validated by the area under the receiver operating characteristic: 0.97 for first-degree, 0.96 for second-degree, and a perfect 1.00 for third-degree burns, each with narrow 95% CIs.</p><p><strong>Conclusions: </strong>The storage of multimodal imaging data within the EMR, along with the ability for post hoc ana","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e68366"},"PeriodicalIF":3.8,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12356521/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144859891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Co-Opetition Strategies of Superior and Subordinate Hospitals for Integration of Electronic Health Records Within the Medical Consortiums in China Based on Two-Party Evolutionary Game Theory: Mixed Methods Study.","authors":"Shenghu Tian, Rong Jiang, Jianfeng Yao, Yu Chen","doi":"10.2196/70866","DOIUrl":"10.2196/70866","url":null,"abstract":"<p><strong>Background: </strong>Medical consortiums take the integration of electronic health records (EHR) as a breakthrough point and the construction of an integrated medical service system as the ultimate goal. However, their establishment has disrupted the balance between the original medical order and interest patterns. While promoting active cooperation among hospitals, it has also intensified active competition between them.</p><p><strong>Objective: </strong>This study aimed to explore the internal evolution mechanism of the co-opetition strategies adopted by the superior and subordinate hospitals in the medical consortiums, providing a theoretical foundation and policy reference for achieving EHR integration.</p><p><strong>Methods: </strong>On the basis of analyzing the structure of the main players in the co-opetition game and their game motivations, we established an evolutionary game model, analyzed the impact mechanism of key parameters, simulated the dynamic evolution process of the co-opetition strategies using MATLAB (MathWorks), and finally proposed actionable policy recommendations.</p><p><strong>Results: </strong>The results indicate that three factors positively promote EHR integration: (1) EHR complementarity, (2) hospitals' willingness and ability to use EHR, and (3) the average revenue per unit of EHR. Conversely, the investment cost per unit of resources hinders EHR integration. Neither the original income of hospitals nor the stock of EHR significantly affects the evolution direction of the game system.</p><p><strong>Conclusions: </strong>Medical consortiums should actively involve all levels and different types of medical institutions, and continuously improve hospitals' willingness and ability to use EHR through training, assistance, support, and sinking of medical resources, etc. The government should establish a reward and punishment system, optimize the operation and supervision mechanism of medical consortiums, and monitor and punish opportunism behaviors such as \"free-riding.\" It is also crucial to strengthen the construction of hospital informatization infrastructure and improve the technical, content, and sharing standards for EHR construction. In addition, designing reward and punishment mechanisms as well as cost accounting based on \"unit EHR resources\" is also of great significance for promoting the EHR integration.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e70866"},"PeriodicalIF":3.8,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12352793/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144857160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of Large Language Models in Complex Clinical Cases: Cross-Sectional Evaluation Study.","authors":"Yuanheng Huang, Guozhen Yang, Yahui Shen, Huiguo Chen, Weibin Wu, Xiaojun Li, Yonghui Wu, Kai Zhang, Jiannan Xu, Jian Zhang","doi":"10.2196/73941","DOIUrl":"https://doi.org/10.2196/73941","url":null,"abstract":"<p><strong>Background: </strong>Large language models (LLMs) have made significant advancements in natural language processing (NLP) and are gradually showing potential for application in the medical field. However, LLMs still face challenges in medicine.</p><p><strong>Objective: </strong>This study aims to evaluate the efficiency, accuracy, and cost of LLMs in handling complex medical cases and to assess their potential and applicability as tools for clinical decision support.</p><p><strong>Methods: </strong>We selected cases from the database of the Department of Cardiothoracic Surgery, the Third Affiliated Hospital of Sun Yat-sen University (2021-2024), and conducted a multidimensional preliminary evaluation of the latest LLMs in clinical decision-making for complex cases. The evaluation included measuring the time taken for the LLMs to generate decision recommendations, Likert scores, and calculating decision costs to assess the execution efficiency, accuracy, and cost-effectiveness of the models.</p><p><strong>Results: </strong>A total of 80 complex cases were included in this study, and the performance of multiple LLMs in clinical decision-making was evaluated. Experts required 33.60 minutes on average (95% CI 32.57-34.63), far longer than any LLM. GPTo1 (0.71, 95% CI 0.67-0.74), GPT4o (0.88, 95% CI 0.83-0.92), and Deepseek (0.94, 95% CI 0.90-0.96) all finished under a minute without statistical differences. Although Kimi, Gemini, LLaMa3-8B, and LLaMa3-70B took 1.02-3.20 minutes, they were still faster than experts. In terms of decision accuracy, Deepseek-R1 had the highest accuracy (mean Likert score=4.19), with no significant difference compared to GPTo1 (P=.699), and both performed significantly better than GPT4o, Kimi, Gemini, LLaMa3-70B, and LLaMa3-8B (P<.001). Deepseek-R1 and GPTo1 demonstrated the lowest hallucination rates-6/80 (8%) and 5/80 (6%), respectively-significantly outperforming GPT-4o (7/80, 9%), Kimi (10/80, 12%), and the Gemini and LLaMa3 models, which exhibited substantially higher rates ranging from 13/80 (16%) to 25/80 (31%). Regarding decision costs, all LLMs showed significantly lower costs than the Multidisciplinary Team, with open-source models such as Deepseek-R1 offering a zero direct cost advantage.</p><p><strong>Conclusions: </strong>GPTo1 and Deepseek-R1 show strong clinical potential, boosting efficiency, maintaining accuracy, and reducing costs. GPT4o and Kimi performed moderately, indicating suitability for broader clinical tasks. Further research is needed to validate LLaMa3 series and Gemini in clinical decision.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e73941"},"PeriodicalIF":3.8,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145240413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bridging Global Frameworks and Local Practice: Quantitative Evaluation of Electronic Health Record Safety in Kuwait's Public Hospitals.","authors":"Anwar AlHussainan, Dari Alhuwail","doi":"10.2196/70782","DOIUrl":"10.2196/70782","url":null,"abstract":"<p><strong>Background: </strong>Electronic health records (EHRs) play a critical role in today's health care by enhancing data management, improving workflows, and supporting clinical decision-making. However, EHR implementation introduces technical and clinical challenges that can compromise patient safety. The Safety Assurance Factors for Electronic Health Record Resilience guides, developed by the Office of the National Coordinator for Health Information Technology, provide a structured framework for evaluating and optimizing EHR safety practices. Despite extensive research on EHR safety in developed countries, little is known about its implementation in regions with differing health care systems, such as Kuwait.</p><p><strong>Objective: </strong>This study aims to examine the EHR safety across hospitals in the State of Kuwait via (1) conducting a proactive risk assessment examining current safety practices and (2) proposing recommendations to improve EHR safety practices.</p><p><strong>Methods: </strong>A quantitative approach was used to evaluate EHR safety practices in 6 public hospitals. Multidisciplinary teams completed the Safety Assurance Factors for Electronic Health Record Resilience self-assessment questionnaire, scoring their implementation status of 165 recommended practices as \"fully,\" \"partially,\" or \"not\" implemented across 9 Safety Assurance Factors for Electronic Health Record Resilience guides. Data were analyzed to calculate the percentage of \"fully implemented\" recommended practices for each hospital, guide, and EHR safety domain. Standard deviations were calculated to assess data variability, and comparative analysis was conducted to identify implementation patterns.</p><p><strong>Results: </strong>The findings revealed significant variability in the implementation of recommended safety practices, with an average of 53% rated as \"fully implemented\" across hospitals. Infrastructure-focused guides, such as system configuration (77%) and system interfaces (80%), had the highest implementation rates, while clinical process guides, such as clinician communication (25%), scored the lowest. Among the 9 guides, 16 recommended practices were unanimously rated as \"fully implemented,\" while 8 were predominantly rated as \"not implemented.\" The high-priority guide showed notable variability, with implementation rates ranging from 17% to 89% across hospitals. Hospitals with longer EHR adoption periods tended to perform better, though hospital size and implementation type showed inconsistent effects on safety practices scores.</p><p><strong>Conclusions: </strong>The study highlights variability in EHR safety practice implementation across Kuwait's public hospitals, with stronger performance in technical domains and gaps in clinical processes. By applying the Safety Assurance Factors for EHR Resilience guides in a non-US context, the study offers a foundational understanding of EHR safety implementation in Kuwait's public health care syst","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e70782"},"PeriodicalIF":3.8,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144857159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the Role of Large Language Models Between ChatGPT and DeepSeek in Asthma Education for Bilingual Individuals: Comparative Study.","authors":"Yaxin Liu, Fangfei Yu, Xiaofei Zhang, Xiaohan Tong, Kui Li, Weikuan Gu, Baiquan Yu","doi":"10.2196/65365","DOIUrl":"10.2196/65365","url":null,"abstract":"<p><strong>Background: </strong>Asthma is a chronic inflammatory airway disease requiring long-term management. Artificial intelligence (AI)-driven tools such as large language models (LLMs) hold potential for enhancing patient education, especially for multilingual populations. However, comparative assessments of LLMs in disease-specific, bilingual health communication are limited.</p><p><strong>Objective: </strong>This study aimed to evaluate and compare the performance of two advanced LLMs-ChatGPT-4o (OpenAI) and DeepSeek-v3 (DeepSeek AI)-in providing bilingual (English and Chinese) education for patients with asthma, focusing on accuracy, completeness, clinical relevance, and language adaptability.</p><p><strong>Methods: </strong>A total of 53 asthma-related questions were collected from real patient inquiries across 8 clinical domains. Each question was posed in both English and Chinese to ChatGPT-4o and DeepSeek-v3. Responses were evaluated using a 7D clinical quality framework (eg, completeness, consensus consistency, and reasoning ability) adapted from Google Health. Three respiratory clinicians performed blinded scoring evaluations. Descriptive statistics and Wilcoxon signed-rank tests were applied to compare performance across domains and against theoretical maximums.</p><p><strong>Results: </strong>Both models demonstrated high overall quality in generating bilingual educational content. DeepSeek-v3 outperformed ChatGPT-4o in completeness and currency, particularly in treatment-related knowledge and symptom interpretation. ChatGPT-4o showed advantages in clarity and accessibility. In English responses, ChatGPT achieved perfect scores across 5 domains, but scored lower in clinical features (mean 3.78, SD 0.16; P=.02), treatment (mean 3.90, SD 0.05; P=.03), and differential diagnosis (mean 3.83, SD 0.29; P=.08).</p><p><strong>Conclusions: </strong>ChatGPT-4o and DeepSeek-v3 each offer distinct strengths for bilingual asthma education. While ChatGPT is more suitable for general health education due to its expressive clarity, DeepSeek provides more up-to-date and comprehensive clinical content. Both models can serve as effective supplementary tools for patient self-management but cannot replace professional medical advice. Future AI health care systems should enhance clinical reasoning, ensure guideline currency, and integrate human oversight to optimize safety and accuracy.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e65365"},"PeriodicalIF":3.8,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12349887/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144849925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 (AI) and Emergency Medicine: Balancing Opportunities and Challenges.","authors":"Félix Amiot, Benoit Potier","doi":"10.2196/70903","DOIUrl":"10.2196/70903","url":null,"abstract":"<p><strong>Unlabelled: </strong>Artificial intelligence (AI), particularly large language models (LLMs) such as ChatGPT, has rapidly evolved and is reshaping various fields, including clinical medicine. Emergency medicine stands to benefit from AI's capacity for high-volume data processing, workflow optimization, and clinical decision support. However, important challenges exist, ranging from model \"hallucinations\" and data bias to questions of interpretability, liability, and ethical use in high-stake environments. This updated viewpoint provides a structured overview of AI's current capabilities in emergency medicine, highlights real-world applications, and explores concerns regarding regulatory requirements, safety standards, and transparency (explainable AI). We discuss the potential risks and limitations of LLMs, including their performance in rare or atypical presentations common in the emergency department and potential biases that could disproportionately affect vulnerable populations. We also address the regulatory landscape, particularly the liability for AI-driven decisions, and emphasize the need for clear guidelines and human oversight. Ultimately, AI holds enormous promise for improving patient care and resource management in emergency medicine; however, ensuring safety, fairness, and accountability remains vital.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e70903"},"PeriodicalIF":3.8,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12349885/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144849915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardiorenal Interorgan Assessment via a Novel Clustering Method Using Dynamic Time Warping on Electrocardiogram: Model Development and Validation Study.","authors":"Sally Zhao, Zhan Ye, Bhavna Adhin, Matti Vuori, Jari Laukkanen, Sudeshna Fisch","doi":"10.2196/73353","DOIUrl":"10.2196/73353","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The heart and kidneys have vital functions in the human body that reciprocally influence each other physiologically. Pathological changes in 1 organ can damage the other. Epidemiologic studies show that greater than 50% of patients with heart failure (HF) have preserved ejection fraction (HFpEF). Additionally, 1 in 6 patients identified as having chronic kidney disease (CKD) also has HF. Thus, it is important to be able to predict and identify the cardiorenal relationship between HFpEF and CKD.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;Creating an electrocardiogram (ECG)-enabled model that stratifies suspected patients with HFpEF would help identify CKD-enriched HFpEF clusters and phenogroups. Simultaneously, a minimal set of significant ECG features derived from the stratification model would aid precision medicine and practical diagnoses due to being more accessible and widely readable than a large set of clinical inputs. Furthermore, the validation of the existing cardiorenal relationship using this ECG-enabled model may lead to better biological understanding.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Using unsupervised clustering on all extractable ECG features from FinnGen, patients with an indication of HFpEF (filtered by left ventricular ejection fraction [LVEF] values ≥50% and N-terminal pro B-type natriuretic peptide [NT-proBNP] values &gt;450 pg/mL) were categorized into different phenogroups and analyzed for CKD risk. After isolating significant predictive ECG features, unsupervised clustering and risk analysis were performed again to demonstrate the efficacy of using a minimal set of features for phenogrouping. These clusters were then compared to clusters formed using dynamic time warping (DTW) on raw ECG time series electrical signals. Afterward, these clusters were analyzed for CKD enrichment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The PR interval and QRS duration stood out as significant features and were used as the minimal feature set. After generating and comparing clusters (k-means with all extracted ECG features, k-means with a minimal feature set, and DTW with full lead II ECG waveform), the DTW-generated clusters were most stable. ANOVA analysis also showed that several HFpEF clusters exhibited a deviation of CKD risk from baseline, allowing for further trajectory analysis. Specifically, the creatinine levels (a proxy for CKD) of several DTW-created clusters showed significant differences from the average. Based on the Jaccard score, the DTW clusters also showed the greatest alignment to baseline comparison clusters created by clustering on creatinine. In comparison, the other 2 sets of clusters (created by all extracted ECG features and the minimal set) performed similarly.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This project validates both the known cardiorenal relationship between HFpEF and CKD and the importance of the PR interval and QRS duration. After exploring the use of ECG data for patient clustering and stratifi","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e73353"},"PeriodicalIF":3.8,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12342687/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144838698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dolodoc, an App to Leverage Self-Management of Chronic Pain: Design, Development, and Implementation Report.","authors":"Frederic Ehrler, Julie Guebey, Jessica Rochat, Laetitia Gosetto, Benno Rehberg, Christian Lovis, Aude Molinard-Chenu","doi":"10.2196/71597","DOIUrl":"10.2196/71597","url":null,"abstract":"<p><strong>Background: </strong>Chronic pain affects approximately 19% of the European population and presents major challenges, both in terms of individual impact and the economic burden on health care systems. While clinical expertise remains essential, patient empowerment through self-management tools has become a key component in the long-term management of chronic pain.</p><p><strong>Objective: </strong>This report describes the development and implementation of Dolodoc, a mobile app designed to support patients with chronic pain in monitoring and managing their condition.</p><p><strong>Methods: </strong>Developed by a research and development team at the University Hospitals of Geneva, Dolodoc enables users to track their pain across 7 dimensions of daily life. A digital coach provides personalized guidance, drawing from a corpus of over 80 evidence-based recommendations elaborated by clinical experts. The project was conducted over 4 years with the early involvement of stakeholders, including pain specialists and end users, to ensure alignment with user needs. Emphasis was placed on both the scientific validity and accessibility of the recommendations.</p><p><strong>Results: </strong>The project was completed on time and within budget. The app was made freely available to patients identified as likely to benefit. However, a notable limitation is the absence of predefined key performance indicators to assess the impact of the intervention quantitatively.</p><p><strong>Conclusions: </strong>This implementation report illustrates how mobile technology can be leveraged in a university hospital context to address the needs of patients with chronic pain and promote self-management. Early and sustained collaboration with stakeholders was instrumental in aligning the solution with both clinical evidence and user expectations.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e71597"},"PeriodicalIF":3.8,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12334107/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144805367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Current Landscape and Future Directions Regarding Generative Large Language Models in Stroke Care: Scoping Review.","authors":"XingCe Zhu, Wei Dai, Richard Evans, Xueyu Geng, Aruhan Mu, Zhiyong Liu","doi":"10.2196/76636","DOIUrl":"10.2196/76636","url":null,"abstract":"<p><strong>Background: </strong>Stroke has a major impact on global health, causing long-term disability and straining health care resources. Generative large language models (gLLMs) have emerged as promising tools to help address these challenges, but their applications and reported performance in stroke care require comprehensive mapping and synthesis.</p><p><strong>Objective: </strong>The aim of this scoping review was to consolidate a fragmented evidence base and examine the current landscape, shortcomings, and future directions in the design, reporting, and evaluation of gLLM-based interventions in stroke care.</p><p><strong>Methods: </strong>In this scoping review, which adhered to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines and the Population, Concept, and Context (PCC) framework, we searched 6 major scientific databases in December 2024 for gLLM-based interventions across the stroke care pathway, mapping their key characteristics and outcomes.</p><p><strong>Results: </strong>A total of 25 studies met the predefined eligibility criteria and were included for analysis. Retrospective designs predominated (n=16, 64%). Key applications of gLLMs included clinical decision-making support (n=10, 40%), administrative assistance (n=9, 36%), direct patient interaction (n=5, 20%), and automated literature review (n=1, 4%). Implementations mainly used generative pretrained transformer models accessed through task-prompted chat interfaces. In total, 5 key challenges were identified from the included studies during the implementation of gLLM-based interventions: ensuring factual alignment, maintaining system robustness, enhancing interpretability, optimizing efficiency, and facilitating clinical adoption.</p><p><strong>Conclusions: </strong>The application of gLLMs in stroke care, while promising, remains relatively new, with most interventions reflecting early-stage or relatively simple implementations. Against this backdrop, critical gaps in research and clinical translation persist. To support the development of clinically impactful and trustworthy applications, we propose an actionable framework that prioritizes real-world evidence, mandates transparent technical reporting, broadens evaluation beyond output accuracy, strengthens validation of advanced task adaptation strategies, and investigates mechanisms for safe and effective human-gLLM interaction.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e76636"},"PeriodicalIF":3.8,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12371286/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144801054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}