International Journal of Medical Informatics最新文献

{"title":"LLM-powered breast cancer staging from PET/CT reports: a comparative performance study","authors":"Daniel Spitzl ,&nbsp;Markus Mergen ,&nbsp;Rickmer Braren ,&nbsp;Lukas Endrös ,&nbsp;Matthias Eiber ,&nbsp;Lisa Steinhelfer","doi":"10.1016/j.ijmedinf.2025.106053","DOIUrl":"10.1016/j.ijmedinf.2025.106053","url":null,"abstract":"<div><h3>Purpose</h3><div>Imaging reports are crucial in breast cancer management, with the tumor-node-metastasis (TNM) classification serving as a widely used model for assessing disease severity, guiding treatment decisions, and predicting patient outcomes. Large language models (LLMs) offer a potential solution by extracting standardized UICC TNM classifications and the corresponding UICC stage directly from existing PET/CT reports. This approach holds promise to enhance staging accuracy, streamline multidisciplinary discussions, and improve patient outcomes.</div></div><div><h3>Methods</h3><div>Here, we evaluated four LLMs—ChatGPT-4o, DeepSeek V3, Claude 3.5 Sonnet, and Gemini 2.0 Flash—for their capacity to determine TNM staging based on UICC/AJCC breast cancer guidelines. A total of 111 fictitious PET/CT reports were analyzed, and each model’s outputs were measured against expert-generated TNM classifications and stage categorizations.</div></div><div><h3>Results</h3><div>Among the tested models, Claude 3.5 Sonnet demonstrated superior F1 scores of 0.95%, 0.95%, 1.00% and 0.92% for T, N, M classification and UICC stage classification, respectively.</div></div><div><h3>Conclusions</h3><div>These findings underscore the ability of advanced natural language processing (NLP) technologies to support reliable cancer staging, potentially aiding clinicians. Despite the encouraging performance, prospective clinical trials and validation across diverse practice settings remain critical to confirming these preliminary outcomes. Nonetheless, this study highlights the promise of LLM-based systems in reinforcing the accuracy of oncologic workflows and lays the groundwork for broader adoption of AI-driven tools in breast cancer management.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"204 ","pages":"Article 106053"},"PeriodicalIF":3.7,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685660","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":"Towards practical federated learning and evaluation for medical prediction models","authors":"Andrei Kazlouski ,&nbsp;Ileana Montoya Perez ,&nbsp;Faiza Noor ,&nbsp;Mikael Högerman ,&nbsp;Otto Ettala ,&nbsp;Tapio Pahikkala ,&nbsp;Antti Airola","doi":"10.1016/j.ijmedinf.2025.106046","DOIUrl":"10.1016/j.ijmedinf.2025.106046","url":null,"abstract":"<div><div><em>Background</em>: Federated learning (FL) is a rapidly advancing technique that enables collaborative model training while preserving data privacy. This approach is particularly relevant in healthcare, where privacy concerns and regulatory restrictions often prevent centralized data sharing. FL has shown promise in tasks such as disease detection, achieving performance levels comparable to centralized systems. However, its practical usability in real-world applications remains underexplored.</div><div><em>Methods</em>: We evaluate the practical effectiveness of FL in predicting whether patients suspected of prostate cancer require invasive biopsy procedures. The study uses 14 publicly available prostate cancer datasets from 10 countries. We propose and benchmark a novel FL evaluation strategy, Leave-Silo-Out (LSO), which quantifies the performance gap between federated training and free-riding (utilizing the federated model without contributing data). Additionally, we investigate whether locally trained models can outperform multi-hospital FL models. The results are assessed with a focus on improving the diagnosis of local patients.</div><div><em>Results</em>: Our findings reveal that the benefits of FL vary with the amount of locally available annotated data. Hospitals with very small datasets see negligible improvements from FL compared to free-riding. Institutions with moderate datasets may achieve some gains through FL training. However, hospitals with extensive datasets often experience little to no advantage from FL and, in some cases, observe reduced performance compared to local training.</div><div><em>Conclusion</em>: Federated learning shows potential in scenarios with limited data availability. However, its practical applicability is highly context-dependent, influenced by factors such as data availability and specific task requirements.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"204 ","pages":"Article 106046"},"PeriodicalIF":3.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685661","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":"Bridging the digital divide: artificial intelligence as a catalyst for health equity in primary care settings","authors":"Ayokunle Osonuga ,&nbsp;Adewoyin A. Osonuga ,&nbsp;Sandra Chinaza Fidelis ,&nbsp;Gloria C. Osonuga ,&nbsp;Jack Juckes ,&nbsp;David B. Olawade","doi":"10.1016/j.ijmedinf.2025.106051","DOIUrl":"10.1016/j.ijmedinf.2025.106051","url":null,"abstract":"<div><h3>Background</h3><div>Health inequalities remain one of the most pressing challenges in contemporary healthcare, with primary care serving as both a gateway to services and a potential source of disparities. Artificial intelligence (AI) technologies offer unprecedented opportunities to address these inequities through enhanced diagnostic capabilities, improved access to care, and personalised interventions.</div></div><div><h3>Objective</h3><div>This comprehensive narrative review aimed to synthesise current evidence on AI applications in primary care settings, specifically targeting health inequality reduction and identifying both opportunities and barriers for equitable implementation.</div></div><div><h3>Method</h3><div>Following PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) guidelines, we employed a systematic approach to literature identification, selection, and synthesis across seven electronic databases covering literature from 2020 to 2024. Of 1,247 initially identified studies, 89 met inclusion criteria with 52 providing sufficient data quality for evidence synthesis.</div></div><div><h3>Results</h3><div>The review identified promising applications such as AI-powered risk stratification algorithms that improved hypertension control in low-income populations, telemedicine platforms reducing geographic barriers in rural communities, and natural language processing tools facilitating care for non-native speakers. However, significant challenges persist, including algorithmic bias that may perpetuate existing inequities, the digital divide excluding vulnerable populations, and insufficient representation in training datasets. Current evidence suggests that whilst AI holds transformative potential for advancing health equity, successful implementation requires intentional co-design with affected communities, robust bias mitigation strategies, and comprehensive digital literacy programmes.</div></div><div><h3>Conclusion</h3><div>Future research must prioritise equity-centred AI development, longitudinal outcome studies in diverse populations, and policy frameworks ensuring responsible deployment. However, careful consideration of unintended consequences, including potential overdiagnosis, erosion of human clinical judgement, and inadvertent exclusion of vulnerable populations, is essential to prevent AI from exacerbating existing health disparities. The paradigm shift towards equity-first AI design represents a critical opportunity to leverage technology for social justice in healthcare.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"204 ","pages":"Article 106051"},"PeriodicalIF":3.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685656","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":"A multi-task deep sequential neural network for IgA nephropathy Oxford classification and prognosis prediction","authors":"Sai Pan ,&nbsp;Yibing Fu ,&nbsp;Lai Jiang ,&nbsp;Jiaona Liu ,&nbsp;Guangyan Cai ,&nbsp;Wenge Li ,&nbsp;Weicen Liu ,&nbsp;Xiaofei Wang ,&nbsp;Zhong Yin ,&nbsp;Quan Hong ,&nbsp;Jie Wu ,&nbsp;Yong Wang ,&nbsp;Shuwei Duan ,&nbsp;Jingjing Chen ,&nbsp;Pu Chen ,&nbsp;Mai Xu ,&nbsp;Xiangmei Chen","doi":"10.1016/j.ijmedinf.2025.106052","DOIUrl":"10.1016/j.ijmedinf.2025.106052","url":null,"abstract":"<div><h3>Background</h3><div>While deep learning has advanced pathological analysis in IgA nephropathy (IgAN), the lack of integrated models that combine multi-label structural identification, Oxford classification, and prognosis prediction remains a significant clinical challenge.</div></div><div><h3>Methods</h3><div>We developed DeepSNN, a novel deep sequential neural network that serves as a multi-task model trained on multi-center multi-modal renal datasets. The architecture integrates lesion segmentation, glomerular classification, Oxford MEST-C scoring, and prognosis prediction subnets. To ensure interpretability, we conducted visualization experiments and comparative analyses with pathologists’ diagnostic patterns. Pathologist comparisons employed Cohen’s Kappa with blinded re-evaluation of test and validation sets.</div></div><div><h3>Results</h3><div>DeepSNN demonstrated exceptional lesion identification capabilities across the People’s Liberation Army General (PLAG) Hospital dataset (n = 245) and China-Japan Friendship (CJF) Hospital dataset (n = 32), achieving dice coefficients of 0.95 and 0.92, respectively. For Oxford classification, DeepSNN delivered outstanding outcomes with high Kappa values of 0.84, 0.79, 0.87, 0.87, and 0.82 for M, E, S, T, and C scores on the PLAG dataset. Notably, our method outperformed three junior pathologists and achieved comparable performance to senior pathologists across both datasets. During a median follow-up of 47.7 (IQR: 21.9–61.1) months, DeepSNN excelled in prognosis prediction (AUC: 0.810), demonstrating improvement over the International IgA Nephropathy Prediction Tool (IIPT) (AUC: 0.742, ΔAUC = +0.068) in PLAG Hospital dataset (n = 245). Furthermore, visualization maps showed consistent pathological region identification between pathologists and DeepSNN.</div></div><div><h3>Conclusions</h3><div>DeepSNN successfully integrates multiple diagnostic tasks with performance comparable to senior pathologists, demonstrating substantial potential for streamlining IgAN clinical workflows. This innovation addresses critical gaps in automated renal pathology analysis while maintaining clinical interpretability.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"204 ","pages":"Article 106052"},"PeriodicalIF":4.1,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739188","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":"Natural language processing in medical text processing: A scoping literature review","authors":"Luis B. Elvas ,&nbsp;Ana Almeida ,&nbsp;João C. Ferreira","doi":"10.1016/j.ijmedinf.2025.106049","DOIUrl":"10.1016/j.ijmedinf.2025.106049","url":null,"abstract":"<div><h3>Background</h3><div>The exponential growth of digitized medical data has created significant challenges for healthcare professionals, as medical documentation transitions from simple text records to complex, multi-dimensional data structures. Natural Language Processing (NLP), particularly Named Entity Recognition (NER), has emerged as a crucial tool for extracting and categorizing critical information from clinical texts. The development of transformer-based models like BERT and the ability to fine-tune pre-trained AI models have revolutionized the field, offering unprecedented opportunities to enhance the efficient and precise interpretation of medical data across diverse languages and healthcare contexts.</div></div><div><h3>Objective</h3><div>This literature review aimed to analyze recent NLP approaches for medical text processing, examining techniques, performance metrics, and advancements across different languages and healthcare contexts.</div></div><div><h3>Method</h3><div>Following the Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA) methodology, a scoping search was conducted in Scopus and PubMed databases, focusing on studies published between 2019–2024. The review included studies on language model fine-tuning and information extraction in healthcare, with a specific search query designed to capture relevant NLP techniques.</div></div><div><h3>Results</h3><div>Of 67 initial records, 31 studies were ultimately included. Bidirectional Encoder Representations from Transformers (BERT)-based approaches, neural networks, and CRF/LSTM techniques dominated, consistently achieving F1-scores above 85 %. The studies covered multiple languages, with 51.5 % in English, 27.3 % in Chinese, and smaller representations in Italian, German, and Spanish. Hybrid approaches and techniques addressing data privacy and limited labeled data were notably prevalent.</div></div><div><h3>Conclusions</h3><div>The review revealed that modern NLP techniques, particularly BERT-based models and hybrid approaches, show significant promise in medical text processing across different languages. While challenges remain in cross-lingual adaptation and data availability, these technologies demonstrate potential to enhance medical data interpretation and analysis.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"204 ","pages":"Article 106049"},"PeriodicalIF":3.7,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685655","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":"Regression discontinuity in Time: Evaluating the impact of evolving digital health interventions","authors":"Isha Thapa ,&nbsp;Pierre-Amaury Laforcade ,&nbsp;Franziska K. Bishop ,&nbsp;Johannes Ferstad ,&nbsp;Manisha Desai ,&nbsp;David M. Maahs ,&nbsp;Priya Prahalad ,&nbsp;Dessi P. Zaharieva ,&nbsp;David Scheinker ,&nbsp;Ramesh Johari","doi":"10.1016/j.ijmedinf.2025.106050","DOIUrl":"10.1016/j.ijmedinf.2025.106050","url":null,"abstract":"<div><h3>Background</h3><div>Clinics continue to adopt digital health interventions (DHIs) in which algorithms analyze data to help direct patient care. Changes to these algorithms are rarely evaluated rigorously, despite their potential to affect patient outcomes. The regression discontinuity in time (RDT) design may be used to estimate the causal effect of such changes but has received little attention in medical literature.</div></div><div><h3>Methods</h3><div>We conducted a retrospective study of continuous glucose monitor (CGM) data from youth with type 1 diabetes enrolled in the 4T Program from November 2020 to March 2022. In 2020, the clinic used an algorithm that directed patients for provider review based on the number of glucose targets not being met (e.g., time in range (TIR) &lt; 65 %). In September 2021, the clinic adopted a new algorithm that prioritized the review of patients experiencing level 2 hypoglycemia (glucose &lt; 54 mg/dl). We evaluated the validity of the RDT framework in this setting and estimated the impact of this change in directed care on weekly TIR.</div></div><div><h3>Results</h3><div>There were 247 patients with 11,297 weekly TIR observations. Robustness checks supported the validity of the RDT design. Patients with level 2 hypoglycemia were prioritized for review, with no significant change to population-level TIR (−0.2% points; 95% CI:[−4.8, 3.5]).</div></div><div><h3>Conclusions</h3><div>We demonstrate the feasibility of using the RDT framework to estimate the impact of algorithmic changes to a DHI on patient care. As algorithm-directed care increases in clinical practice, this approach can serve as a diagnostic tool to measure how operational changes impact outcomes.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"204 ","pages":"Article 106050"},"PeriodicalIF":3.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713892","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":"Evaluating the efficacy of digital otoscopes in rural pediatric otitis media diagnosis: A comparative study of general practitioners and ENT specialists","authors":"Najmeh Pourshahrokhi ,&nbsp;Somaye Norouzi ,&nbsp;Aliasghar Arabi Mianroodi ,&nbsp;Leila Ahmadian","doi":"10.1016/j.ijmedinf.2025.106042","DOIUrl":"10.1016/j.ijmedinf.2025.106042","url":null,"abstract":"<div><h3>Background</h3><div>Otitis media is a prevalent childhood illness, particularly among specific groups. However, its diagnosis has been of a serious issue, which is exacerbated in underprivileged regions with limited access to Ear, nose and throat specialists. This study aimed to evaluate the agreement between diagnoses of ear diseases made by general practitioners using digital otoscope and standard otoscope, and the diagnoses determined by an otolaryngologist, as the gold standard.</div></div><div><h3>Methods</h3><div>This study examined ear examinations in rural health centers, comparing digital otoscope and standard otoscope, screenings by general practitioners (GPs) with remote digital otoscope evaluations by an ENT specialist. The research involved grading tympanic membranes using the OM-grade scale across three diagnostic groups: GP otoscope, ENT video otoscope, and GP video otoscope. Diagnostic agreement was assessed using Cohen’s kappa coefficient, and both parents/guardians and physicians provided feedback on the examination methods, exploring the potential of telemedicine in remote medical assessments.</div></div><div><h3>Results</h3><div>A total of 82 children, 45 boys and 37 girls, were included in the study from 4 rural health centers. There was a significant agreement (0.90%) between the diagnoses of the ENT specialist and the general practitioner with the video-otoscope examining the patients’ ears. The results of the physician survey showed that the physicians were in complete agreement (100%). The system is easy to use and the video-otoscope can be useful for telemedicine and greater patient interaction. It is worth noting that the results of this study showed a high level of satisfaction (98%) among the parents of the children after exposure.</div></div><div><h3>Conclusion</h3><div>Our findings provide strong evidence that digital video otoscope can enhance the diagnostic accuracy of GPs in detecting ear diseases, especially in settings with limited access to ENT specialists. By facilitating improved visualization, remote consultation, and more efficient referrals, this technology holds promise for empowering primary care providers and expanding the reach of quality ear healthcare. Integration of video otoscope into telemedicine platforms could further support GPs in underserved areas, improving patient outcomes while optimizing healthcare resources.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"204 ","pages":"Article 106042"},"PeriodicalIF":3.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685658","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":"Corrigendum to “Identifying potential medical aid beneficiaries using machine learning: A Korean Nationwide cohort study” [Int. J. Med. Inform. 195 (2025) 105775]","authors":"Junmo Kim ,&nbsp;Su Hyun Park ,&nbsp;Hyesu Lee ,&nbsp;Su Kyoung Lee ,&nbsp;Jihye Kim ,&nbsp;Suhyun Kim ,&nbsp;Yong Jin Kwon ,&nbsp;Kwangsoo Kim","doi":"10.1016/j.ijmedinf.2025.106038","DOIUrl":"10.1016/j.ijmedinf.2025.106038","url":null,"abstract":"","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"203 ","pages":"Article 106038"},"PeriodicalIF":4.1,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144661096","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":"What digital competencies should medical students in China possess in the AI era?","authors":"Jinjuan Chen ,&nbsp;Xiaorong Hou ,&nbsp;Yalan Lv ,&nbsp;Mimi Liu ,&nbsp;Meijie Yang ,&nbsp;Xiaoyu Zhou ,&nbsp;Fei Du ,&nbsp;Jia Yi ,&nbsp;Lingqin Zhang ,&nbsp;Guangying Li","doi":"10.1016/j.ijmedinf.2025.106043","DOIUrl":"10.1016/j.ijmedinf.2025.106043","url":null,"abstract":"<div><h3>Objective</h3><div>With the advancement of the digital society and the extensive application of digital medical technologies, the demand for digital competencies among medical students is becoming increasingly critical. Digital competence of medical students refers to the ability of medical students to effectively select and use digital or intelligent technologies and applications to accomplish their studies, research, and future clinical practice. Currently in China, no digital competency framework for medical students has been established based on clinical practice requirements. Therefore, the study aimes to investigate digital competencies for medical students and provide recommendations for future digital competency training initiatives and framework development.</div></div><div><h3>Methods</h3><div>Focusing on competency theory, we reviewed and analyzed literature related to digital competency. Twenty experts participated in a two-round Delphi method to iteratively refine and correct the indicator items. Finally, the weights of indicators were calculated through the Analytic Hierarchy Process.</div></div><div><h3>Results</h3><div>Twenty experts were invited to participate in two rounds of the Delphi survey, achievinga 100 % response rate in both rounds, with Expert Authority Coefficients of 0.81 and 0.82, indicating the credibility and professional expertise the panelists. Furthermore, Kendall’s consistency coefficient (Kendall’s W) ranged from 0.143 to 0.275 (p &lt; 0.05), indicating that experts reached a consensus on the indicators. The final framework comprises 3 domains, 9 primary indicators, and 27 secondary indicators.</div></div><div><h3>Conclusions</h3><div>A digital competency framework for medical students was developed using the Delphi method. This framework facilitates the self-development of medical students and serves as a reference for the development of digital medical curricula.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"203 ","pages":"Article 106043"},"PeriodicalIF":3.7,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653688","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":"AI in primary care: Comparing ChatGPT and family physicians on patient queries","authors":"Muhammed İnan,&nbsp;Özlem Suvak,&nbsp;Cenk Aypak","doi":"10.1016/j.ijmedinf.2025.106047","DOIUrl":"10.1016/j.ijmedinf.2025.106047","url":null,"abstract":"<div><h3>Objective</h3><div>The integration of artificial intelligence (AI) in medicine has led to growing interest in its applications for primary care. This study evaluates and compares the responses of ChatGPT-4o and family physicians to 200 commonly asked clinical questions in family medicine.</div></div><div><h3>Methods</h3><div>This was a comparative, observational, cross-sectional study was conducted using a dataset of 200 primary care-related questions generated through literature review and expert validation. Three experienced family physicians and ChatGPT-4o independently provided responses. The responses were anonymized and randomly assessed by three independent family medicine experts. Evaluations were based on Likert scales for appropriateness (1–6), accuracy (1–6), comprehensiveness (1–3), and empathy (1–5). Word counts were also recorded.</div></div><div><h3>Results</h3><div>ChatGPT-4o outperformed family physicians across all evaluation metrics (p &lt; 0.01). ChatGPT-4o received higher scores for appropriateness (mean 5.8 ± 0.5 vs. 4.3 ± 1.0), accuracy (5.8 ± 0.5 vs. 4.5 ± 1.1), comprehensiveness (2.4 ± 0.6 vs. 1.4 ± 0.7). and empathy (4.8 ± 0.4 vs. 4.0 ± 0.8). The average word count of ChatGPT’s responses (298.8 ± 82.3 words) was significantly longer than that of physicians (106.1 ± 95.0 words). In topic-specific analysis, ChatGPT-4o outperformed physicians, except in General Consultation and Child Infections (p = 0.07, 0.08 respectively).</div></div><div><h3>Conclusion</h3><div>The findings suggest that ChatGPT-4o has the potential to enhance patient education, medical training, and clinical decision support. Future research should explore AI’s real-world clinical impact, its role in improving medical education, and strategies to refine AI-generated responses for conciseness and cultural relevance.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"203 ","pages":"Article 106047"},"PeriodicalIF":3.7,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632556","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}