Marta Estrela , Pedro Lopes Ferreira , Fátima Roque , Maria Teresa Herdeiro
{"title":"“Simplification, decentralization, proximity” – A critical analysis of the digital health framework in Portugal through expert interviews","authors":"Marta Estrela , Pedro Lopes Ferreira , Fátima Roque , Maria Teresa Herdeiro","doi":"10.1016/j.ijmedinf.2025.105962","DOIUrl":"10.1016/j.ijmedinf.2025.105962","url":null,"abstract":"<div><h3>Introduction</h3><div>The implementation of digital health tools and services encounters policy and governance challenges tied to a complex web of stakeholders and influencing factors. This study seeks analyse the digital health framework in Portugal, focusing on digital health policies and interventions.</div></div><div><h3>Methods</h3><div>Through a multifaceted approach, this study included the conduction of expert interviews, and an extensive assessment of publicly available official documents, thus allowing a thorough analysis of the national digital health framework. To consolidate all the information gathered, a SWOT analysis was subsequently performed.</div></div><div><h3>Results</h3><div>Eight experts involved with digital health in Portugal were interviewed. Seven key themes were identified and discussed alongside the data extracted from document analysis: 1) the digital health context in Portugal; 2) digital health services, tools, and infrastructure in Portugal: strengths and limitations; 3) budget and resources allocation towards digital health in Portugal; 4) digital health development in Portugal: current status and necessary steps; 5) Digital health accessibility and digital health literacy in Portugal; 6) COVID-19 pandemic and its impact on digital [health] tools usage; and 7) comparison of the digital health framework with other countries: lessons to learn.</div></div><div><h3>Discussion</h3><div>As digital health has gained momentum in Portugal over the years, it is crucial to enhance governance and transparency, connect digital infrastructures, and promote data availability. These measures, along with a well-defined strategic vision, are essential for cultivating a robust digital health ecosystem.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105962"},"PeriodicalIF":3.7,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916748","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}
Maeve Brin , Claudia Michaels , Patrick Veihman , Olivia R. Wood , Joseph Abua , Emma Sophia Kay , D.Scott Batey , Rebecca Schnall
{"title":"Acceptability and perceived usefulness of the CHAMPS intervention for improving medication adherence among people with HIV in Alabama and New York","authors":"Maeve Brin , Claudia Michaels , Patrick Veihman , Olivia R. Wood , Joseph Abua , Emma Sophia Kay , D.Scott Batey , Rebecca Schnall","doi":"10.1016/j.ijmedinf.2025.105959","DOIUrl":"10.1016/j.ijmedinf.2025.105959","url":null,"abstract":"<div><h3>Background</h3><div>Antiretroviral therapy allows people with HIV to manage the disease as a chronic illness rather than a fatal diagnosis as regular adherence can lead to viral suppression. It is estimated, however, that less than two-thirds of people with HIV in the United States sustain viral suppression. Community Health Workers and mHealth to Improve Viral Suppression (CHAMPS) is useful for improving and personalizing care and may help promote medication adherence among people with HIV.</div></div><div><h3>Objective</h3><div>We aimed to understand acceptability and perceived usefulness of the CHAMPS intervention.</div></div><div><h3>Methods</h3><div>In-depth interviews were carried out with a total of 42 intervention participants from the RCT of the CHAMPS intervention versus standard of care on ART adherence and viral suppression among PWH, which enrolled participants between May 2021 and May 2023 in the NYC and Birmingham, AL areas, to obtain feedback on the CHAMPS intervention, a combination of CHW sessions, and the CleverCap app and device. Interviews were transcribed and coded using a codebook guided by the Unified Theory of Acceptance and Use of Technology framework.</div></div><div><h3>Results</h3><div>Participants ranged from 19 to 65 years old with a mean of 47 years. Most participants (62 %) identified as cisgender female, 33 % as cisgender male, 2 % as transgender male, and 2 % as transgender female. Participants believed the CleverCap app and device and CHW sessions were useful for medication adherence and, consequently, reducing viral load. Participants identified varying levels of difficulty with using the intervention, and varying levels of comfort with using the intervention in public settings. Overall, participants felt they could integrate the intervention into their daily lives and that it was instrumental in achieving improved health status and quality of life.</div></div><div><h3>Conclusion</h3><div>Despite some complexities associated with use of the intervention, participants overwhelmingly demonstrated interest in and were pleased with the CleverCap app and device and CHW sessions for improvement of viral load and overall health status. Positive feedback during the interviews supports future testing of the CHAMPS mHealth and CHW intervention.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105959"},"PeriodicalIF":3.7,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923991","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}
Dan Luo , Xiaolan Ye , Hongying Zhao , Bin Yao , Wentong Liu , Xiaobo Xu
{"title":"Reducing proton pump inhibitors overuse with an advisory, risk-based, context-aware electronic alert system: A controlled interrupted time series analysis","authors":"Dan Luo , Xiaolan Ye , Hongying Zhao , Bin Yao , Wentong Liu , Xiaobo Xu","doi":"10.1016/j.ijmedinf.2025.105960","DOIUrl":"10.1016/j.ijmedinf.2025.105960","url":null,"abstract":"<div><h3>Background</h3><div>Proton pump inhibitors (PPI) are frequently overprescribed despite guidelines recommending cautious use. Electronic alert systems have shown potential in improving prescribing practices, but their effectiveness varies. This study evaluates a novel electronic alert system designed to reduce perioperative PPI overuse by leveraging real-time, patient-specific clinical data.</div></div><div><h3>Methods</h3><div>A retrospective controlled interrupted time series analysis was conducted from February 2015 to October 2021 in a tertiary care hospital. The intervention group comprised patients undergoing internal fixation surgeries in the orthopedic department, while the control group included patients receiving appendectomies in the general surgery department. A novel electronic alert system was integrated into the computerized physician order entry system, providing risk assessments and advisory alerts for intravenous PPI prescriptions. The system operated from July 2019 to November 2020. Key outcomes measured every two weeks included Defined Daily Doses (DDD) and Days of Therapy (DOT) per patient, prescription rates, and proportions of high-dose and alert-triggering orders.</div></div><div><h3>Results</h3><div>The study included 8,303 patients in the intervention group and 5,728 in the control group. Post-implementation, the intervention group showed a significant decrease in DDD per patient (β = -1.21, p = 0.003) and DOT per patient (β = -0.698, p = 0.011), primarily due to reduced intravenous administration. Prescription rates for PPI decreased significantly (OR = 0.710, p = 0.002), and there was a reduction in high-dose prescriptions (OR = 0.243, p < 0.001). While consumption metrics remained sustained after alert deactivation, quality indicators showed partial rebounds but remained improved compared to baseline.</div></div><div><h3>Conclusions</h3><div>The advisory, risk-based, context-aware electronic alert system effectively reduced PPI overuse and improved prescribing quality in a surgical department. The differential impact post-intervention, with more durable effects on consumption metrics than on prescribing quality, suggests a certain degree of sustainability in prescribing behaviors. Implementing advisory, context- aware electronic alerts may offer a scalable solution for optimizing medication use in healthcare settings.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"202 ","pages":"Article 105960"},"PeriodicalIF":3.7,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937318","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}
Yanqiu Li , Zhuojun Li , Jinze Li , Long Liu , Yao Liu , Bingbing Zhu , Ke shi , Yu Lu , Yongqi Li , Xuanwei Zeng , Ying Feng , Xianbo Wang
{"title":"The actual performance of large language models in providing liver cirrhosis-related information: A comparative study","authors":"Yanqiu Li , Zhuojun Li , Jinze Li , Long Liu , Yao Liu , Bingbing Zhu , Ke shi , Yu Lu , Yongqi Li , Xuanwei Zeng , Ying Feng , Xianbo Wang","doi":"10.1016/j.ijmedinf.2025.105961","DOIUrl":"10.1016/j.ijmedinf.2025.105961","url":null,"abstract":"<div><h3>Objective</h3><div>With the increasing prevalence of large language models (LLMs) in the medical field, patients are increasingly turning to advanced online resources for information related to liver cirrhosis due to its long-term management processes. Therefore, a comprehensive evaluation of real-world performance of LLMs in these specialized medical areas is necessary.</div></div><div><h3>Methods</h3><div>This study evaluates the performance of four mainstream LLMs (ChatGPT-4o, Claude-3.5 Sonnet, Gemini-1.5 Pro, and Llama-3.1) in answering 39 questions related to liver cirrhosis. The information quality, readability and accuracy were assessed using Ensuring Quality Information for Patients tool, Flesch-Kincaid metrics and consensus scoring. The simplification and their self-correction ability of LLMs were also assessed.</div></div><div><h3>Results</h3><div>Significant performance differences were observed among the models. Gemini scored highest in providing high-quality information. While the readability of all four LLMs was generally low, requiring a college-level reading comprehension ability, they exhibited strong capabilities in simplifying complex information. ChatGPT performed best in terms of accuracy, with a “Good” rating of 80%, higher than Claude (72%), Gemini (49%), and Llama (64%). All models received high scores for comprehensiveness. Each of the four LLMs demonstrated some degree of self-correction ability, improving the accuracy of initial answers with simple prompts. ChatGPT’s and Llama’s accuracy improved by 100%, Claude’s by 50% and Gemini’s by 67%.</div></div><div><h3>Conclusion</h3><div>LLMs demonstrate excellent performance in generating health information related to liver cirrhosis, yet they exhibit differences in answer quality, readability and accuracy. Future research should enhance their value in healthcare, ultimately achieving reliable, accessible and patient-centered medical information dissemination.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105961"},"PeriodicalIF":3.7,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143912439","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":"SupportPrim CDSS: A clinical decision support system architecture based on microservices for non-specific musculoskeletal disorders","authors":"Amar Jaiswal , Mohit Kumar , Ingebrigt Meisingset","doi":"10.1016/j.ijmedinf.2025.105919","DOIUrl":"10.1016/j.ijmedinf.2025.105919","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Non-specific musculoskeletal disorders (MSDs) pose significant challenges in primary care due to ambiguous symptoms and diverse etiologies. This research presents the SupportPrim clinical decision support system (CDSS), an innovative approach that combines case-based reasoning (CBR) with a scalable microservice framework, aiming to improve personalized treatment and clinical decision processes in MSD care.</div></div><div><h3>Methods</h3><div>The SupportPrim CDSS is engineered using a modular microservice architecture designed for scalability, reliability, and seamless clinical integration. Subjective patient-reported questionnaires and demographic data are processed through an optimized CBR engine that retrieves precedent cases to inform current clinical decisions. The system leverages rigorous evaluation through iterative experiments and a randomized controlled trial (RCT) in Norwegian primary care, thereby assessing its usability, clinical utility, and operational performance.</div></div><div><h3>Results</h3><div>The system demonstrates high reliability, characterized by negligible downtime and a mean case retrieval response time of 0.18 seconds. Clinicians reported favorable user interactions, emphasizing the system's ability to facilitate shared decision making and personalized care. While the SupportPrim study intentionally maintained a static casebase, the system possesses the ability to incorporate active learning to boost adaptability and precision. Extensive validation and verification from associated studies confirm considerable performance of both the CBR engine and the CDSS.</div></div><div><h3>Conclusion</h3><div>The SupportPrim CDSS effectively leverages CBR within a microservice-based framework to aid clinicians in delivering evidence-based, personalized patient care for patients with non-specific MSDs. Its robust design, coupled with comprehensive verification and validation across multiple associated studies, underscores its potential for broader healthcare applications and improved clinical decision support.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105919"},"PeriodicalIF":3.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143912438","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}
Bader Alshoumr , Jwaher A. Almulhem , Khulud Alkadi , Lujain Aljarallah , Lobna A. Aljuffali , Raniah N. Aldekhyyel
{"title":"Identifying and prioritizing competencies for health informatics master’s graduates to support the health sector transformation program in Saudi Arabia","authors":"Bader Alshoumr , Jwaher A. Almulhem , Khulud Alkadi , Lujain Aljarallah , Lobna A. Aljuffali , Raniah N. Aldekhyyel","doi":"10.1016/j.ijmedinf.2025.105944","DOIUrl":"10.1016/j.ijmedinf.2025.105944","url":null,"abstract":"<div><h3>Background</h3><div>The 2030 Health Sector Transformation Program (HSTP) in Saudi Arabia includes digital health as one of its objectives. To achieve this transformation a knowledgeable and skillful workforce is needed. No research identifies the specific health informatics competencies needed to support HSTP’s objectives. Our study aims to identify and prioritize key competencies for health informatics master’s graduates needed to support Saudi Arabia’s digital health transformation strategies for 2030.</div></div><div><h3>Methods</h3><div>A series of semi-structured interviews were conducted with 17 health informatics experts in Saudi Arabia, identified through LinkedIn, with over 10 years of experience working on large-scale national projects. Interviewees were conducted in August and September of 2024. Experts ranked competencies based on their priority and alignment with HSTP’s digital transformation goals. The competencies were drawn from of the International Medical Informatics Association (IMIA) international recommendations in biomedical and health informatics (BMHI) educational framework, which served as the gold standard.</div></div><div><h3>Results</h3><div>A total of 37 competencies were ranked as high priority, 38 as moderate priority, and 5 as neutral. The top high-priority competencies for health informatics master’s graduates included change management, patient safety, data and information analysis, system security, business alignment, ethics, security and privacy, and leadership. The management science and social and behavioral domains were identified as the most critical for developing health informatics curricula and professional training programs. Two new competencies were identified: innovation, and emerging digital health technologies.</div></div><div><h3>Conclusion</h3><div>The findings reflect the changes that the healthcare system in the country is experiencing specifically related to data and digitalization as identified by the 2030 HSTP. There needs to be more standardized educational programs focused on the competencies needed for the workforce to contribute to the digital health transformation plans. These findings can serve as a standard guide in revising or establishing BMHI educational programs.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105944"},"PeriodicalIF":3.7,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906815","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}
Abubakar Sadiq Bouda Abdulai , Jean Storm , Michael Ehrlich
{"title":"“I don’t know”: An uncertainty-aware machine learning model for predicting patient disposition at emergency department triage","authors":"Abubakar Sadiq Bouda Abdulai , Jean Storm , Michael Ehrlich","doi":"10.1016/j.ijmedinf.2025.105957","DOIUrl":"10.1016/j.ijmedinf.2025.105957","url":null,"abstract":"<div><h3>Background</h3><div>Machine learning (ML) models are widely used for predicting patient disposition at emergency department (ED) triage. However, these models generate predictions regardless of the level of uncertainty, potentially leading to overconfident outputs that can compromise clinical decision-making.</div></div><div><h3>Objective</h3><div>To develop a conformal prediction model for ED triage that provides uncertainty-aware patient disposition predictions.</div></div><div><h3>Methods</h3><div>This retrospective study analyzed 560,486 adult ED visits (March 2014 – July 2017) from one academic and two community hospitals. An extreme gradient boosting (XGBoost) model was trained, validated, and conformalized to introduce a “Don’t know” prediction for high-uncertainty cases. The model was tested on a random sample of 56,000 ED cases.</div></div><div><h3>Results</h3><div>The standard XGBoost model achieved an AUC of 0.9307 (95% CI: 0.9285 – 0.9329), with sensitivity of 0.72 and specificity of 0.94. With conformal prediction at a lower confidence threshold of 60%, the model indicated “Don’t know” in 4.9% of cases while returning sensitivity and specificity values of 0.74 and 0.95, respectively. As confidence thresholds increased, the model returned more “Don’t know” predictions and fewer misclassifications. At 90% confidence, the model returned “Don’t know” in 34.5% of cases while returning sensitivity and specificity values of 0.88 and 0.99, respectively. This trade-off highlights a balance between model confidence and prediction accuracy<strong>.</strong></div></div><div><h3>Conclusion</h3><div>Incorporating uncertainty-awareness in ML models improves reliability in ED triage. By acknowledging uncertainty, clinicians receive more interpretable insights, reducing the risk of overconfident predictions and enhancing patient safety.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105957"},"PeriodicalIF":3.7,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899274","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}
Ling Chen , Ching-Po Lin , Chi-Hua Chung , Jason Jiunshiou Lee
{"title":"Using longitudinal data and deep learning models to enhance resource allocation in home-based medical care","authors":"Ling Chen , Ching-Po Lin , Chi-Hua Chung , Jason Jiunshiou Lee","doi":"10.1016/j.ijmedinf.2025.105953","DOIUrl":"10.1016/j.ijmedinf.2025.105953","url":null,"abstract":"<div><h3>Background</h3><div>The aging population is driving increased healthcare demands and costs, prompting the need for effective home healthcare programs. Accurate patient assessment is essential for optimizing resource allocation and tailoring services.</div></div><div><h3>Objective</h3><div>This retrospective study explores the application of artificial intelligence (AI) in predicting home medical care stages to enhance care delivery.</div></div><div><h3>Methods</h3><div>Data from Taipei City Hospital (2015–2021) included inpatient, outpatient, and home medical care records. Three deep learning (DL) models—Transformer encoder-based, long short-term memory (LSTM), and gated recurrent unit (GRU)—were compared with three baseline machine learning (ML) models. Models were trained on 3, 5, and 10 consecutive visits for binary and multiclass classification. Performance was evaluated using accuracy, precision, recall, and the area under the receiver operating characteristic curve (AUC).</div></div><div><h3>Results</h3><div>The study included 4,343 patients with a mean age of 85.04 ± 11.47 years. While models trained on 10 visits generally exhibited higher performance, data from 5 visits were sufficient for accurate predictions. With five visits, the LSTM model achieved the highest AUC (0.908) for distinguishing between the absence (S0) and presence (S1–S3) of home medical care. Meanwhile, the Transformer achieved the best AUC (0.86) for classifying S0–S3, with individual stage AUCs of 0.90, 0.82, 0.81, and 0.94 for S0, S1, S2, and S3, respectively.</div></div><div><h3>Conclusions</h3><div>AI deep learning models show strong potential for accurately predicting home medical care stages. The best-performing model could be a promising tool for healthcare professionals to optimize resource allocation in home medical care settings.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105953"},"PeriodicalIF":3.7,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879188","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}
Wan-Yin Kuo , Chien-Cheng Huang , Chung-Feng Liu , Mei-I Sung , Chien-Chin Hsu , Hung-Jung Lin , Shih-Bin Su , How-Ran Guo
{"title":"Utilizing machine learning for predicting mortality in patients with heat-related illness who visited the emergency department","authors":"Wan-Yin Kuo , Chien-Cheng Huang , Chung-Feng Liu , Mei-I Sung , Chien-Chin Hsu , Hung-Jung Lin , Shih-Bin Su , How-Ran Guo","doi":"10.1016/j.ijmedinf.2025.105951","DOIUrl":"10.1016/j.ijmedinf.2025.105951","url":null,"abstract":"<div><h3>Background</h3><div>In the context of climate change and global warming, heat-related illness (HRI) is anticipated to escalate and become a major concern. Patients with severe HRI primarily present to the emergency department (ED), but there are no prediction tools for mortality in HRI patients who visit ED. The objective of this study was to use machine learning approaches to establish prediction models for mortality in patients with HRI who visit ED.</div></div><div><h3>Methods</h3><div>We included all patients aged 20 and above with a final diagnosis of HRI who visited the EDs of three hospitals (Chi Mei Medical Center, Chi Mei Hospital Liouying, and Chi Mei Hospital Chiali) between January 2010 and October 2021. Patients who had transferred to other hospitals or had insufficient data were excluded. A total of 11 predictive feature variables were used in the algorithms. The primary outcome was in-hospital mortality or impending death discharge. We used machine learning algorithms including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), Multilayer Perceptron (MLP), and eXtreme Gradient Boosting (XGBoost) to establish prediction models for mortality in such patients. Accuracy, sensitivity, specificity, and area under curve (AUC) were used as indicators to evaluate the performance of prediction models.</div></div><div><h3>Results</h3><div>Out of the 820 HRI patients included in the analysis, 1.5% had mortality. All six prediction models had a high AUC, ranging from 0.825 to 0.991, and LightGBM which included peripheral oxygen saturation (SpO<sub>2)</sub> and Glasgow Coma Scale (GCS) score on arrival as the two main features had the highest AUC. The accuracy, sensitivity, and specificity of LightGBM were 0.976, 1.000 and 0.975, respectively.</div></div><div><h3>Conclusion</h3><div>Machine learning-based prediction models are promising tools in accurately predicting mortality in HRI patients who present to the ED.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105951"},"PeriodicalIF":3.7,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899275","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}
Mohsen Askar, Beate Hennie Garcia, Kristian Svendsen
{"title":"Exploring Multimorbidity Patterns in older hospitalized Norwegian patients using Network Analysis modularity","authors":"Mohsen Askar, Beate Hennie Garcia, Kristian Svendsen","doi":"10.1016/j.ijmedinf.2025.105954","DOIUrl":"10.1016/j.ijmedinf.2025.105954","url":null,"abstract":"<div><h3>Background</h3><div>Understanding Multimorbidity Patterns (MPs) is crucial for planning healthcare interventions, allocating resources, and improving patients’ outcomes.</div></div><div><h3>Objective</h3><div>We aim to demonstrate the use of Network Analysis (NA) to explore the MPs in hospitalized Norwegian older patients.</div></div><div><h3>Methods</h3><div>We utilized data from the Norwegian Patient Registry (NPR) of all admissions between 2017 and 2019. The study population included patients ≥ 65 years old with two or more different conditions. Multimorbidity was defined as the co-occurrence of two or more associated chronic conditions. Chronic conditions were identified using the Chronic Condition Indicator Refined (CCIR) list. The association between chronic conditions was determined by calculating Relative Risk (RR) and Phi-correlation to detect pairs of conditions that co-occur beyond chance. A multimorbidity network was created, and MPs were detected using Louvain method for community detection. We suggested a clinical interpretation for these MPs.</div></div><div><h3>Results</h3><div>A total of 539 chronic conditions were used to create a multimorbidity network revealing several MPs. These modules included patterns of vision and hearing disorders, cardiorenal syndrome, metabolic and cardiovascular disorders, respiratory disorders, endocrine and skin conditions, autoimmune and musculoskeletal disorders, as well as mental and behavioral disorders. Using NA centrality measures, we identified the most influential conditions in each module. An interactive network and sunburst graphs for each module are publicly available.</div></div><div><h3>Conclusion</h3><div>The study demonstrates the use of NA modularity detection in identifying MPs. The findings highlight the complex interaction of chronic conditions in the elderly and the potential of NA methodology in exploring these relationships.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"201 ","pages":"Article 105954"},"PeriodicalIF":3.7,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143882255","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}