Health Informatics Journal最新文献

{"title":"Evaluation of large language models in a national orthopaedic proficiency examination: Implications for health informatics and medical education.","authors":"Bünyamin Arı","doi":"10.1177/14604582261470637","DOIUrl":"10.1177/14604582261470637","url":null,"abstract":"<p><p>ObjectiveThis study evaluates the performance of large language models (LLMs)-ChatGPT-4.0, Gemini 2.0 Pro, o3-mini, Doctor GPT and DeepSeek-V3-in a national orthopaedic proficiency examination and explores their implications for health informatics and medical education. The responses of these models were analysed to assess accuracy rates and differences between models.MethodA total of 100 multiple-choice questions from the 2024 TOTEK examination were administered to each AI model under identical conditions. Correct and incorrect responses were recorded, and differences in performance were evaluated using chi-square testing and frequency analysis. Question categories were also compared to identify domain-specific variations.Resultso3-mini achieved the highest accuracy rate (79%), while Gemini 2.0 showed the lowest (68%); all models exceeded the 60% pass threshold. A statistically significant difference between models was identified in the Surgical Procedures category, in which Gemini 2.0 answered fewer questions correctly (23/36) than the other models (30-32/36) (χ² = 9.87, df = 4, p = 0.043). No significant differences were observed in the remaining categories (all p > 0.05), and the overall difference in accuracy between models did not reach statistical significance (χ² = 4.01, df = 4, p = 0.405). Clinical decision-making and visual content-based questions were the most challenging for all models.ConclusionAI models demonstrate generally high accuracy in medical examinations; however, they struggle with interpreting clinical context, recognising atypical medical scenarios and answering questions involving visual content.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261470637"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148609999","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":"Implementation of electronic health record systems in private health facilities: A qualitative study in Ghana.","authors":"Eva Saeh Afriyie, Richard Abeiku Bonney, Loretta Adu-Boahemaa Antwi, Mary Yeboah, Kofi Akohene Mensah","doi":"10.1177/14604582261460299","DOIUrl":"10.1177/14604582261460299","url":null,"abstract":"<p><p>IntroductionElectronic Health Record Systems (EHRS) are transforming healthcare delivery globally, yet their implementation in resource-constrained settings like Ghana remains underexplored. This study evaluated EHRS adoption in private hospitals in Ghana's Suame Municipality, assessing structural readiness, process integration, and outcomes to identify barriers and enablers of successful digital transition.MethodsA qualitative study design was employed, involving semi-structured interviews with 28 purposively selected healthcare workers (clinicians, administrators, IT staff) across four private hospitals. Data were analyzed using Braun and Clarke's thematic analysis to identify patterns in infrastructure, workflow adaptations, and perceived impacts. Theoretical saturation guided sample adequacy.ResultsThree key themes emerged: (1) Structural challenges, including uneven IT infrastructure distribution, staffing gaps (e.g., reliance on single IT personnel), and inadequate training; (2) Process improvements, such as streamlined documentation and claims processing, despite intermittent system failures reverting to paper-based backups; and (3) Mixed outcomes, with reported efficiency gains (e.g., error reduction) offset by policy voids and financial constraints limiting scalability.ConclusionWhile EHRS implementation in Ghana's private sector shows promise in improving workflows, its sustainability is threatened by infrastructural deficits, workforce capacity gaps, and unclear governance. The study recommends public-private partnerships for financing and hybrid paper-digital systems to mitigate disruptions.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261460299"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148220495","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 clinical reasoning of large language models on complex rheumatology cases: A multidimensional evaluation of four artificial intelligence.","authors":"Yannick Laurent Tchenadoyo Bayala, Fulgence Kaboré, Charles Sougué, Aboubakar Ouedraogo, Yamyellé Enselme Zongo, Wendlassida Joelle Stéphanie Zabsonré/Tiendrebeogo, Dieu-Donné Ouedraogo","doi":"10.1177/14604582261448687","DOIUrl":"10.1177/14604582261448687","url":null,"abstract":"<p><p>BackgroundLarge language models (LLMs) have demonstrated promising capabilities in medical diagnostic reasoning, yet their performance in specialized clinical domains such as rheumatology remains incompletely characterized. While diagnostic accuracy has been evaluated, critical dimensions including calibration, reasoning quality, and temporal stability have not been systematically assessed across contemporary models.ObjectivesThis study aimed to comprehensively evaluate and compare the diagnostic accuracy, certainty expression, reasoning quality, and hallucination rates of four state-of-the-art LLMs ChatGPT-4, Claude 3.5, DeepSeek-V3, and Gemini 1.5 Pro in complex rheumatologic case scenarios.DesignA cross-sectional, analytical, and comparative study was conducted following STARD and TRIPOD guidelines, adapted for LLM evaluation. Nine complex rheumatologic cases from published case reports were evaluated at three time points (Days 1, 5, and 10) between July 1 and September 18,2025.MethodsStandardized clinical vignettes were submitted to each LLM under controlled experimental conditions. Two blinded senior rheumatologists independently assessed diagnostic accuracy, reasoning quality across five analytical dimensions using Likert scales, and hallucination frequency. Certainty expression and temporal stability were quantified using intraclass correlation coefficients. Correlation analyses examined relationships between reasoning quality and confidence expression.ResultsAll models achieved near-perfect diagnostic accuracy, with ChatGPT, Claude and Gemini correctly identifying the primary diagnosis in 100% of cases and DeepSeek in 88.9%. However, Spearman correlation analysis revealed uniformly weak and non-significant associations between reasoning quality and expressed certainty across all models (ρ range: -0.156 to 0.215, all p>0.05), indicating fundamental miscalibration. ChatGPT demonstrated the highest reasoning score (3.89±0.23) and lowest hallucination rate (7.4%), while Gemini showed the highest hallucination frequency (18.5%). Temporal stability was excellent for ChatGPT (ICC=0.84) and good for DeepSeek (ICC=0.79).ConclusionDespite exceptional diagnostic accuracy, current LLMs exhibit critical limitations in confidence calibration and variable hallucination rates, representing significant barriers to safe clinical deployment in rheumatology.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261448687"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789759","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":"Development of a population based patient cancer data warehouse from multiple electronic health record systems.","authors":"Karla Siegler, Jason Smith, Emily Walker, Jingyu Bu, Paula Robson, Lorraine Shack","doi":"10.1177/14604582261440410","DOIUrl":"10.1177/14604582261440410","url":null,"abstract":"<p><p>ObjectiveCancer is a significant cause of death globally. Effective management requires use of real-world data to inform treatment and planning. This demands improvements in data management to support healthcare delivery, research, and patient outcomes. Electronic health records (EHR) offer a potential solution yet integrating and interpreting the data poses challenges. To address this we developed Data Environment for Cancer Inquiries and Decisions or DECIDe. DECIDe is a cancer data warehouse consolidating patient data from multiple systems in use at Alberta Health Services (AHS).MethodsDECIDe's development began with stakeholder engagement and requirements gathering followed by design. The warehouse includes landing, staging, analysis, and reporting schemas that facilitate integration and transformation. Primary EHR, cancer registry, and legacy EHR data were extracted, transformed, and loaded into DECIDe.ResultsDECIDe integrated 2,100+ tables into 36 analysis tables with data from 1,055,186 unique patients. Integration exceeded 93% across all data sources demonstrating robust consolidation. DECIDe's structured format enables efficient storage, retrieval, and analysis, laying the foundation for comprehensive reporting and analytics.ConclusionDECIDe addresses challenges in managing healthcare data, supporting analytics into cancer trends and treatment outcomes. Unique to Canadian healthcare DECIDe provides a comprehensive view of cancer care, enhancing decision-making and research opportunities.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261440410"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147846427","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":"Evaluating the quality and reliability of endometrial cancer related videos on Chinese short-video platforms: A cross-sectional study.","authors":"Jinghong Liang, Mengyao Huang, Shiyuan Qi, Qingjian Ye, Xiaomao Li","doi":"10.1177/14604582261445744","DOIUrl":"10.1177/14604582261445744","url":null,"abstract":"<p><p>ObjectiveTo conduct a multidimensional evaluation of endometrial cancer (EC)-related videos on major Chinese short-video platforms.MethodsA cross-sectional study conducted on May 8, 2025 analyzed 226 eligible EC-related videos from TikTok, Rednote, and Bilibili. Video quality was assessed using Global Quality Scale (GQS) and Video Information and Quality Index (VIQI), reliability using modified DISCERN (mDISCERN), and understandability and actionability using Patient Education Materials Assessment Tool (PEMAT).ResultsAmong 226 videos, TikTok emphasized symptoms/risk factors and scored highest in engagement, reliability (mDISCERN=2.0, <i>P=</i>0.002), and understandability (88%). Bilibili led in VIQI (median=17.0) but had the lowest understandability (67%). Professional videos outperformed patient-generated content (all <i>P<</i>0.05). Video length correlated positively with quality but negatively with engagement and understandability (all <i>P<</i>0.01).ConclusionsEC-related videos vary widely in quality and lack consistent actionability. Strategic content design and platform-level verification are needed to improve reliability and public health impact.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261445744"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789927","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":"An informatics-based data-led prioritization strategy to facilitate objective and equitable care for an ethnically diverse urban cohort of people with type 1 diabetes: A proof-of-concept study.","authors":"Panagiotis Pavlou, Khuram Chaudhry, Ollie French, Sarah Keane, Thomas Johnston, Anna Brackenridge, Stephen Thomas, Yuk-Fun Liu, Daghni Rajasingam, Dulmini Kariyawasam, Janaka Karalliedde","doi":"10.1177/14604582261436276","DOIUrl":"10.1177/14604582261436276","url":null,"abstract":"<p><p>BackgroundEthnicity and socioeconomic factors contribute to higher morbidity and mortality in people with type 1 diabetes (pwT1D), partly due to reduced access to specialised care and technology. Objectively prioritising high-risk individuals in resource-limited settings is challenging. Data-led prioritisation (DLP) uses health informatics to stratify pwT1D based on new-onset risk factors since their last review. This may help overcome implicit bias, structural racism, and care barriers. However, data on its use in pwT1D are limited.MethodsIn this proof-of-concept study, DLP was implemented from July to September 2023 in a university hospital serving an ethnically diverse population. Clinical and demographic data were collected from 697 adults with T1D (50.5% female, 23.5% non-White, 37% from poor socioeconomic backgrounds). DLP identified 76 individuals (10.9%) as highest risk.ResultsNon-White patients were more likely to be in the highest-risk group (30/164, 18.3%) than White patients (35/372, 9.4%), <i>p</i>=0.004. Those from the most deprived socioeconomic backgrounds were also more likely to be high-risk (40/256, 15.7%) vs others (36/433, 8.3%), <i>p</i>=0.008.ConclusionDLP may enable objective risk stratification in pwT1D and could help reduce bias linked to ethnicity and deprivation. Further large-scale research is warranted to demonstrate the use of such systems in diabetes care.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261436276"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789817","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":"Evaluation of medical device calibration knowledge, perceived importance, and implementation support among healthcare professionals in Ghana.","authors":"Isaac Acquah, Benjamin Appiah Yeboah, Mawusi Gbemavor-Assonhe, Kojo Sam Micah","doi":"10.1177/14604582261448684","DOIUrl":"10.1177/14604582261448684","url":null,"abstract":"<p><p>ObjectivesMedical device calibration underpins accuracy, precision, and reliability, which are critical to optimal device performance and quality healthcare delivery. Despite its importance, little empirical evidence exists on calibration knowledge among healthcare professionals in sub-Saharan Africa. This study assessed such knowledge in Ghana by examining familiarity with calibration principles, procedures, device-specific practices, institutional support, and factors influencing competence.MethodsA cross-sectional survey of 425 healthcare workers (technicians/clinical engineers, nurses, midwives, and doctors) employed a structured questionnaire. Statistical analyses (<i>t</i>-tests, ANOVA, and correlation analysis) were conducted to identify differences and associations in calibration knowledge and practices.ResultsAnalyses revealed significant knowledge gaps. Technicians/clinical engineers outperformed other groups, while early-career professionals (1-3 years' experience) scored higher than mid-career counterparts (7-10 years), highlighting shortcomings in continuous professional development. Formal training was also associated with higher scores.ConclusionThese findings highlight the urgent need for structured, role-specific training and ongoing professional education to close calibration knowledge gaps, safeguard patient safety, and optimise device performance. The results provide evidence for policy reforms and workforce development strategies to strengthen medical device management and healthcare quality.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261448684"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147823736","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":"Tebyan: An AI-powered system for estimating developmental levels from children's human figure drawings.","authors":"Wedad M Alawad, Areen Alquayid, Sara Alghofaily, Shada Alharbi, Deem Alorainy","doi":"10.1177/14604582261460248","DOIUrl":"10.1177/14604582261460248","url":null,"abstract":"<p><p>ObjectiveTo develop and evaluate an AI-powered mobile application, Tebyan, to estimate children's developmental levels from Draw-A-Person (DAP) test drawings and support the early identification of developmental concerns.MethodsThe system predicts drawing-based developmental age and compares it with the child's chronological age, where an age gap may indicate the need for further evaluation. Nine deep learning models were created using MobileNet, ResNet, and EfficientNet architectures across binary, four-class, and eight-class configurations.ResultsAcross all nine model configurations, performance decreased as class granularity increased. The two-class models achieved strong and balanced results (≈80% accuracy), four-class models showed moderate performance (≈55-65%), and eight-class models performed lowest (≈30-40%). Macro-averaged sensitivity, specificity, precision, and F1-scores were reported with 95% confidence intervals. Based on balance and stability, the four-class MobileNet model was selected for integration into the Tebyan application, supporting a more precise evaluation of developmental progression from the drawings.ConclusionTebyan provides an AI-based approach for estimating developmental levels from children's drawings by comparing the model's predicted age group with the child's actual age. While not a diagnostic tool, the system offers a supportive resource that may help caregivers and educators identify developmental patterns that warrant further attention.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261460248"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148220671","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":"Deep learning framework for automated classification of thoracolumbar fractures using spinal CT images.","authors":"Xiao Qu, Yucheng Shu, Huazhang Zhu, Chao Zhang, Dagang Tang, Ningdao Li, Xiaoji Luo","doi":"10.1177/14604582261462739","DOIUrl":"10.1177/14604582261462739","url":null,"abstract":"<p><p>ObjectiveThoracolumbar fractures (T11-L2) are common spinal injuries, and accurate classification is essential for treatment planning. However, diagnosis remains challenging because of complex fracture morphology and variability in clinical experience. This study evaluated the feasibility of a deep learning framework for automated classification of thoracolumbar fractures using CT images.MethodsA retrospective study was conducted using CT images from 596 patients with thoracolumbar fractures. A convolutional neural network based on a Multiple Instance Learning (MIL) framework was developed, using AlexNet with a gated attention mechanism for feature aggregation. Separate models were trained for coronal (Z-type) and axial (S-type) views, and an ensemble strategy combined the two predictions. Model performance was compared with that of interns and senior physicians.ResultsThe S-type model achieved a classification accuracy of 75.2%, while the Z-type model achieved an accuracy of 88.0%. The ensemble model reached an overall accuracy of 83.8%. With assistance from the deep learning model, the diagnostic accuracy of interns improved from 74% to 95%, approaching the performance of senior physicians (98%).ConclusionThe proposed deep learning framework showed promising performance for automated classification of thoracolumbar fractures and may serve as a decision-support tool to improve diagnostic efficiency.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261462739"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148273730","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":"Influencing factors and acceptance levels of robotic and smart home health technologies among older adults: A systematic review.","authors":"Reyhaneh Jaberi, Sharareh Rostam Niakan Kalhori, Fateme Bahador, Saeedeh Heydarian, Zohreh Javanmard","doi":"10.1177/14604582261436632","DOIUrl":"10.1177/14604582261436632","url":null,"abstract":"<p><p>BackgroundSmart home technologies and assistive robots play a role in enhancing the well-being of older adults. This study aims to evaluate the factors and acceptance level of these technologies among seniors and to explore the factors affecting their acceptance.MethodsThree databases were systematically searched using keywords to identify relevant articles. The retrieved studies were screened based on eligibility criteria. Key features of the studies and the acceptance status of the aforementioned technologies among seniors were documented in a data extraction form.ResultsTwenty-seven studies met the eligibility criteria. Robots (74.1%), sensors (18.5%), wireless technologies (3.7%), and smart home voice assistants (3.7%) were utilized by seniors. Remote patient monitoring (33.3%) was the most prevalent application of these technologies. Approximately 89% of the studies reported positive attitudes toward these technologies. \"Technology convenience\" (22.2%) emerged as the most significant reason for smart technology acceptance. Conversely, \"concerns about privacy and security\" (14.8%) and \"lack of need for technology\" (14.8%) were the most frequently cited reasons for non-acceptance.ConclusionsTo enhance the adoption of reviewed technologies, it is crucial to implement strategies that raise awareness, ensure data security, and address the actual needs of this demographic in both the design and implementation phases.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 2","pages":"14604582261436632"},"PeriodicalIF":2.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147789924","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}