Journal of Medical Systems最新文献

{"title":"Infection Spread and Outbreaks Support with Spatial-Temporal Visualization Tool for Hospitals.","authors":"Denisse Kim, Bernardo Canovas-Segura, Manuel Campos, Sergio Aleman Belando, Jose M Juarez","doi":"10.1007/s10916-025-02219-7","DOIUrl":"10.1007/s10916-025-02219-7","url":null,"abstract":"<p><p>Hospital-acquired infections (HAIs), especially those caused by multidrug-resistant bacteria, represent a critical challenge, increasing healthcare costs, hospital stays, and mortality rates. Monitoring HAIs requires integrating spatial-temporal data from patient records and microbiology results. However, current manual methods are time-consuming and error-prone. Although temporal factors are often considered, spatial patient distribution and hospital topological factors are frequently overlooked. Interactive information visualization provides a solution, combining diverse data sources to enhance understanding of spatial-temporal relationships. We aim to develop OBViz, an interactive visual tool employing spatial-temporal visualization techniques to analyze infection spread and hospital epidemic situations over time. Four user tasks relevant in HAIs control were defined, focusing on spatial-temporal pathogen localization and identifying outbreak origins. Using Unity 3D and C#, along with a simulated dataset of hospitalized patients experiencing an infection spread, we developed a visual interactive tool that integrates 3D hospital visualization for patients' individual monitoring, 2D visualization for tracking epidemiological indicators, and tabular view for detailed information. A user study with 14 healthcare personnel evaluated its usability, usefulness and interpretability. Interactivity and animations accurately depicted movements and infection processes, while known charts facilitated temporal understanding. Despite room for improvement in patient tracking (57.14% success rate), OBViz demonstrated strong potential for decision-making (91.43% success rate), healthcare education, and integration into clinical workflows (Post-Study System Usability Questionnaire result: 1.85). The tool's interactive spatial visualization and clear time control were preferred over more abstract methods, highlighting its utility in hospital epidemic analysis.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"85"},"PeriodicalIF":3.5,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12176923/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144326040","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":"Correction: Innovative Technologies for Smarter and Efficient Operating Room Scheduling.","authors":"Valentina Bellini, Tania Domenichetti, Elena Giovanna Bignami","doi":"10.1007/s10916-025-02193-0","DOIUrl":"https://doi.org/10.1007/s10916-025-02193-0","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"84"},"PeriodicalIF":3.5,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317093","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":"From Conflict to Care - Telemedicine Utilization During Wartime: A Retrospective Cohort Study.","authors":"Sarah Sberro-Cohen, Moriah E Ellen","doi":"10.1007/s10916-025-02220-0","DOIUrl":"10.1007/s10916-025-02220-0","url":null,"abstract":"<p><strong>Background: </strong>Armed conflict poses severe challenges to healthcare delivery, requiring rapid adaptation. This study evaluates how telemedicine enabled continuity of care during the October 7, 2023, war in Israel, and assess regional and service-specific utilization patterns in relation to conflict intensity.</p><p><strong>Methods: </strong>A retrospective cohort study of 7.19 million healthcare interactions from an Israeli HMO covering one-third of Israel's population. The study compared three periods: (T0) the first month of the war, (T1) the month before, and (T2) the same period last year. Interactions included visits and inquiries in primary care, secondary care, mental health, and allied health services. Data were categorized by service type and geographic conflict zones. Chi-square tests and effect sizes assessed trends.</p><p><strong>Results: </strong>Telemedicine utilization increased significantly during the war, especially in primary conflict zones (13-20%, p < 0.01). Remote consultations in mental health tripled (10-30%, p < 0.01), and nutrition services reached the highest telemedicine adoption (27-52%, p < 0.01). Family medicine, pediatrics, and gynecology also showed significant increases. Digital inquiries surged in family medicine but declined in pediatrics.</p><p><strong>Conclusion: </strong>This study offers timely insights into telemedicine's role in maintaining access during armed conflict within a digitally advanced system. By examining service utilization across medical domains and conflict zones, it highlights how remote care supports system adaptability in crises. Notably, patient satisfaction remained high, suggesting telemedicine preserved access and perceived care quality. Findings may inform digital health planning to strengthen continuity, equity, and resilience in future emergencies.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"83"},"PeriodicalIF":3.5,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12174172/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144317094","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 for Chronic Disease Screening in Latin America and the Caribbean: The Diagnostic Potential of Digital Health.","authors":"Wagner Rios-Garcia, Fontana Sofía, Sashenka Silva-Jiménez, Daniel Banegas-Báez, Alondra A Rios-Garcia","doi":"10.1007/s10916-025-02218-8","DOIUrl":"https://doi.org/10.1007/s10916-025-02218-8","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"82"},"PeriodicalIF":3.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144302226","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":"A Meta-Analysis of the Diagnostic Test Accuracy of Artificial Intelligence for Predicting Emergency Department Revisits.","authors":"Kuang-Ming Kuo, Wen-Shiann Wu, Chao Sheng Chang","doi":"10.1007/s10916-025-02210-2","DOIUrl":"10.1007/s10916-025-02210-2","url":null,"abstract":"<p><p>The revisit of the emergency department (ED) is a key indicator of emergency care quality. Various strategies have been proposed to reduce ED revisits, including the use of artificial intelligence (AI) models for prediction. However, AI model performance varies significantly, and its true predictive capability remains unclear. To address these gaps, the primary purpose of this study is to evaluate the performance of AI in predicting ED revisits through a meta-analysis. Specifically, this study aims to (1) Quantitatively assess the predictive performance of AI in ED revisit prediction and (2) Identify covariates contributing to between-study heterogeneity. A systematic search was conducted on December 31, 2024, across multiple electronic databases, including Scopus, SpringerLink, ScienceDirect, PubMed, Wiley, Sage, and Google Scholar, to identify relevant studies meeting the following criteria: (1) Utilized machine learning, deep learning, or artificial intelligence techniques to predict patient return visits to the ED, (2) Written in English, and (3) Peer-reviewed. Diagnostic accuracy was assessed using pooled sensitivity, specificity, and area under receiver operating characteristic curve (AUROC), while subgroup analysis explored factors contributing to heterogeneity. This meta-analysis included 20 articles, comprising 27 AI models. The summary estimates for ED revisit prediction were as follows: (1) Sensitivity: 0.56 (95% Confidence Interval [CI]: 0.44-0.67), (2) Specificity: 0.92 (95% CI: 0.86-0.96), and (3) AUROC: 0.81 (95% CI: 0.71-0.88). Subgroup analysis identified nationality, missing value-handling strategies, and specific disease samples as potential contributors to between-study heterogeneity. Future research should focus on improving missing value processing and using specific disease samples to enhance model reliability.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"81"},"PeriodicalIF":3.5,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144302225","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":"Large Language Models and the Analyses of Adherence to Reporting Guidelines in Systematic Reviews and Overviews of Reviews (PRISMA 2020 and PRIOR).","authors":"Diego A Forero, Sandra E Abreu, Blanca E Tovar, Marilyn H Oermann","doi":"10.1007/s10916-025-02212-0","DOIUrl":"10.1007/s10916-025-02212-0","url":null,"abstract":"<p><p>In the context of Evidence-Based Practice (EBP), Systematic Reviews (SRs), Meta-Analyses (MAs) and overview of reviews have become cornerstones for the synthesis of research findings. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 and Preferred Reporting Items for Overviews of Reviews (PRIOR) statements have become major reporting guidelines for SRs/MAs and for overviews of reviews, respectively. In recent years, advances in Generative Artificial Intelligence (genAI) have been proposed as a potential major paradigm shift in scientific research. The main aim of this research was to examine the performance of four LLMs for the analysis of adherence to PRISMA 2020 and PRIOR, in a sample of 20 SRs and 20 overviews of reviews. We tested the free versions of four commonly used LLMs: ChatGPT (GPT-4o), DeepSeek (V3), Gemini (2.0 Flash) and Qwen (2.5 Max). Adherence to PRISMA 2020 and PRIOR was compared with scores defined previously by human experts, using several statistical tests. In our results, all the four LLMs showed a low performance for the analysis of adherence to PRISMA 2020, overestimating the percentage of adherence (from 23 to 30%). For PRIOR, the LLMs presented lower differences in the estimation of adherence (from 6 to 14%) and ChatGPT showed a performance similar to human experts. This is the first report of the performance of four commonly used LLMs for the analysis of adherence to PRISMA 2020 and PRIOR. Future studies of adherence to other reporting guidelines will be helpful in health sciences research.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"80"},"PeriodicalIF":3.5,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162794/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144275136","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) Facts Labels: An Innovative Disclosure Tool Promoting Patient-Centric Transparency in Healthcare AI Systems.","authors":"Katrina A Bramstedt","doi":"10.1007/s10916-025-02216-w","DOIUrl":"https://doi.org/10.1007/s10916-025-02216-w","url":null,"abstract":"<p><p>In the field of healthcare, artificial intelligence (AI)-assisted solutions can be viewed with anxiety or apprehension, thus transparency and trust-building are essential. AI is often invisible (and potentially undisclosed) to users, violating the ethical principle of transparency -- particularly with respect to informed disclosure. This Brief Technical Report describes the creation of a novel, patient-centric prototype AI transparency tool (AI Facts Label) using the United States Drug Facts Label as a model. The prototype was then populated with lay language in the context of a hypothetical AI-assisted wearable medical device. Using lay language amid a defined graphic template that could be globally harmonized, the AI Facts Label is a communication tool that honors the ethical principle of transparency and could potentially aid readers (patients and healthcare workers) in understanding the use of AI in a specific product. AI Facts Labels have the potential to be used globally (adapted to local language) in clinical research settings as well as commercial settings as a transparency tool that discloses when a system is AI-assisted. AI Facts Labels could also be used as a communication tool in other settings such as general consumer electronics (e.g., televisions, household appliances, mobile phones) and non-healthcare apps.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"78"},"PeriodicalIF":3.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144266345","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":"Preparing Tomorrow's Physicians: The Case for Machine Learning in Medical Education.","authors":"Julian Michael Burwell","doi":"10.1007/s10916-025-02214-y","DOIUrl":"10.1007/s10916-025-02214-y","url":null,"abstract":"<p><p>Machine learning should be integrated into medical curricula to prepare physicians-in-training for 21st-century practice conditions. This comment proposes practical implementation strategies that build upon existing educational frameworks by drawing parallels to traditional statistical methods. By incorporating these skills through a phased approach, medical education can fulfill its duty to the public by preparing future physicians to effectively evaluate emergent technology, identify potential sources of bias, and better serve patients.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"79"},"PeriodicalIF":3.5,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144266346","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":"SHAP-Driven Feature Analysis Approach for Epileptic Seizure Prediction.","authors":"Mohsin Hasan, Wenjuan Wu, Xufeng Zhao","doi":"10.1007/s10916-025-02211-1","DOIUrl":"https://doi.org/10.1007/s10916-025-02211-1","url":null,"abstract":"<p><p>Predicting epileptic seizures presents a substantial difficulty in healthcare, with considerable implications for enhancing patient outcomes and quality of life. This paper presents an explainable artificial intelligence (AI) that integrates a one-dimensional convolutional neural network (1D-CNN) with SHapley Additive exPlanations (SHAP). The approach facilitates precise and interpretable seizure prediction utilising electroencephalography (EEG) inputs. The suggested 1D-CNN model with SHAP attains superior performance, exhibiting an accuracy of 98.14% and an F1-score of 98.30% with feature-level explainability and high clinical insight using the CHB-MIT dataset. Through the computation and aggregation of SHAP values across time, we identified the most significant EEG channels, specifically \"P7-O1\" and \"P3-O1\", as essential for seizure detection. This transparency is crucial for building practitioners' trust and acceptance of the use of artificial intelligence-based solutions in the clinical domain. The technique can readily operate within portable EEG structures and hospital monitoring systems, triggering real-time alerts to patients. The outcome provides a timely intervention that could include anything from medication adjustments to responses in emergencies, preventing potential injury and improving safety. So, SHAP not only explains the model's predictions, but it also check and improve how much it relies on certain features, which makes it more reliable. Additionally, SHAP's interpretability aids physicians in understanding why the model arrived at its conclusions, increasing trust in the predictions and encouraging its extensive utilisation in diagnostic processes.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"77"},"PeriodicalIF":3.5,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144258222","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":"User Engagement with A Multimodal Conversational Agent for Self-Care and Chronic Disease Management: A Retrospective Analysis.","authors":"Selahattin Colakoglu, Mustafa Durmus, Zeynep Pelin Polat, Asli Yildiz, Emre Sezgin","doi":"10.1007/s10916-025-02202-2","DOIUrl":"10.1007/s10916-025-02202-2","url":null,"abstract":"<p><strong>Introduction: </strong>Understanding user engagement with conversational agents is key to their sustainable use in mobile health and improving patient outcomes. This retrospective study analyzed interactions with a multimodal conversational agent in the Albert Health app to identify usage patterns and barriers to long-term engagement in self-care and chronic disease management.</p><p><strong>Methods: </strong>We retrospectively analyzed interactions from 24,537 users of a Turkish-language mobile health app (between January 1, 2022, and December 31, 2023). Interactions with the app's multimodal conversational agent (voice and text) were categorized by demographics, interaction type, and engagement mode. Descriptive statistics summarized patterns, while Mann-Whitney U, Chi-square, and logistic regression identified group differences and predictors of sustainable engagement.</p><p><strong>Results: </strong>Most users were female (56%) and aged 30-45 (44%). The majority (92%) used general health programs, with only 8% in disease-specific ones. Common interaction types included health information (32%), small talk (20%), and clinical parameter logging (16%; e.g., blood pressure). Voice use was frequent in fallback (80%; unclear/ out-of-scope input), small talk (64%), and medication tasks (53%), while screen input was more common for clinical logging (61%) and health queries (59%). Engagement peaked in the first week and declined after 10 days. Sustainable engagement was associated with disease-specific program use (OR = 0.67, 95%CI: 0.60-0.74, p < 0.001), greater voice interaction (OR = 1.005, 95%CI: 1.004-1.006, p < 0.001), and a balanced mix of clinical and non-clinical use (OR = 1.56, 95%CI: 1.43-1.70, p < 0.05).</p><p><strong>Conclusions: </strong>This study highlights user preferences for voice interaction and health information access when using a multimodal conversational agent. The high rate of single-session users (58%) points to barriers to sustainable engagement, emphasizing the need for better user experience strategies.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"76"},"PeriodicalIF":3.5,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12148993/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144248289","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}