JMIR Medical Informatics最新文献

{"title":"Analysis of Retinal Thickness in Patients With Chronic Diseases Using Standardized Optical Coherence Tomography Data: Database Study Based on the Radiology Common Data Model.","authors":"ChulHyoung Park, So Hee Lee, Da Yun Lee, Seoyoon Choi, Seng Chan You, Ja Young Jeon, Sang Jun Park, Rae Woong Park","doi":"10.2196/64422","DOIUrl":"10.2196/64422","url":null,"abstract":"<p><strong>Background: </strong>The Observational Medical Outcome Partners-Common Data Model (OMOP-CDM) is an international standard for harmonizing electronic medical record (EMR) data. However, since it does not standardize unstructured data, such as medical imaging, using this data in multi-institutional collaborative research becomes challenging. To overcome this limitation, extensions such as the Radiology Common Data Model (R-CDM) have emerged to include and standardize these data types.</p><p><strong>Objective: </strong>This work aims to demonstrate that by standardizing optical coherence tomography (OCT) data into an R-CDM format, multi-institutional collaborative studies analyzing changes in retinal thickness in patients with long-standing chronic diseases can be performed efficiently.</p><p><strong>Methods: </strong>We standardized OCT images collected from two tertiary hospitals for research purposes using the R-CDM. As a proof of concept, we conducted a comparative analysis of retinal thickness between patients who have chronic diseases and those who have not. Patients diagnosed or treated for retinal and choroidal diseases, which could affect retinal thickness, were excluded from the analysis. Using the existing OMOP-CDM at each institution, we extracted cohorts of patients with chronic diseases and control groups, performing large-scale 1:2 propensity score matching (PSM). Subsequently, we linked the OMOP-CDM and R-CDM to extract the OCT image data of these cohorts and analyzed central macular thickness (CMT) and retinal nerve fiber layer (RNFL) thickness using a linear mixed model.</p><p><strong>Results: </strong>OCT data of 261,874 images from Ajou University Medical Center (AUMC) and 475,626 images from Seoul National University Bundang Hospital (SNUBH) were standardized in the R-CDM format. The R-CDM databases established at each institution were linked with the OMOP-CDM database. Following 1:2 PSM, the type 2 diabetes mellitus (T2DM) cohort included 957 patients, and the control cohort had 1603 patients. During the follow-up period, significant reductions in CMT were observed in the T2DM cohorts at AUMC (P=.04) and SNUBH (P=.007), without significant changes in RNFL thickness (AUMC: P=.56; SNUBH: P=.39). Notably, a significant reduction in CMT during the follow-up was observed only at AUMC in the hypertension cohort, compared to the control group (P=.04); no other significant differences in retinal thickness were found in the remaining analyses.</p><p><strong>Conclusions: </strong>The significance of our study lies in demonstrating the efficiency of multi-institutional collaborative research that simultaneously uses clinical data and medical imaging data by leveraging the OMOP-CDM for standardizing EMR data and the R-CDM for standardizing medical imaging data.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64422"},"PeriodicalIF":3.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11870599/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143473332","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":"A Risk Warning Model for Anemia Based on Facial Visible Light Reflectance Spectroscopy: Cross-Sectional Study.","authors":"Yahan Zhang, Yi Chun, Hongyuan Fu, Wen Jiao, Jizhang Bao, Tao Jiang, Longtao Cui, Xiaojuan Hu, Ji Cui, Xipeng Qiu, Liping Tu, Jiatuo Xu","doi":"10.2196/64204","DOIUrl":"10.2196/64204","url":null,"abstract":"<p><strong>Background: </strong>Anemia is a global public health issue causing symptoms such as fatigue, weakness, and cognitive decline. Furthermore, anemia is associated with various diseases and increases the risk of postoperative complications and mortality. Frequent invasive blood tests for diagnosis also pose additional discomfort and risks to patients.</p><p><strong>Objective: </strong>This study aims to assess the facial spectral characteristics of patients with anemia and to develop a predictive model for anemia risk using machine learning approaches.</p><p><strong>Methods: </strong>Between August 2022 and September 2023, we collected facial image data from 78 anemic patients who met the inclusion criteria from the Hematology Department of Shanghai Hospital of Traditional Chinese Medicine. Between March 2023 and September 2023, we collected data from 78 healthy adult participants from Shanghai Jiading Community Health Center and Shanghai Gaohang Community Health Center. A comprehensive statistical analysis was performed to evaluate differences in spectral characteristics between the anemic patients and healthy controls. Then, we used 10 different machine learning algorithms to create a predictive model for anemia. The least absolute shrinkage and selection operator was used to analyze the predictors. We integrated multiple machine learning classification models to identify the optimal model and developed Shapley additive explanations (SHAP) for personalized risk assessment.</p><p><strong>Results: </strong>The study identified significant differences in facial spectral features between anemic patients and healthy controls. The support vector machine classifier outperformed other classification models, achieving an accuracy of 0.875 (95% CI 0.825-0.925) for distinguishing between the anemia and healthy control groups. In the SHAP interpretation of the model, forehead-570 nm, right cheek-520 nm, right zygomatic-570 nm, jaw-570 nm, and left cheek-610 nm were the features with the highest contributions.</p><p><strong>Conclusions: </strong>Facial spectral data demonstrated clinical significance in anemia diagnosis, and the early warning model for anemia risk constructed based on spectral information demonstrated a high accuracy rate.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64204"},"PeriodicalIF":3.1,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11845237/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426005","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":"Transforming Informed Consent Generation Using Large Language Models: Mixed Methods Study.","authors":"Qiming Shi, Katherine Luzuriaga, Jeroan J Allison, Asil Oztekin, Jamie M Faro, Joy L Lee, Nathaniel Hafer, Margaret McManus, Adrian H Zai","doi":"10.2196/68139","DOIUrl":"10.2196/68139","url":null,"abstract":"<p><strong>Background: </strong>Informed consent forms (ICFs) for clinical trials have become increasingly complex, often hindering participant comprehension and engagement due to legal jargon and lengthy content. The recent advances in large language models (LLMs) present an opportunity to streamline the ICF creation process while improving readability, understandability, and actionability.</p><p><strong>Objectives: </strong>This study aims to evaluate the performance of the Mistral 8x22B LLM in generating ICFs with improved readability, understandability, and actionability. Specifically, we evaluate the model's effectiveness in generating ICFs that are readable, understandable, and actionable while maintaining the accuracy and completeness.</p><p><strong>Methods: </strong>We processed 4 clinical trial protocols from the institutional review board of UMass Chan Medical School using the Mistral 8x22B model to generate key information sections of ICFs. A multidisciplinary team of 8 evaluators, including clinical researchers and health informaticians, assessed the generated ICFs against human-generated counterparts for completeness, accuracy, readability, understandability, and actionability. Readability, Understandability, and Actionability of Key Information indicators, which include 18 binary-scored items, were used to evaluate these aspects, with higher scores indicating greater accessibility, comprehensibility, and actionability of the information. Statistical analysis, including Wilcoxon rank sum tests and intraclass correlation coefficient calculations, was used to compare outputs.</p><p><strong>Results: </strong>LLM-generated ICFs demonstrated comparable performance to human-generated versions across key sections, with no significant differences in accuracy and completeness (P>.10). The LLM outperformed human-generated ICFs in readability (Readability, Understandability, and Actionability of Key Information score of 76.39% vs 66.67%; Flesch-Kincaid grade level of 7.95 vs 8.38) and understandability (90.63% vs 67.19%; P=.02). The LLM-generated content achieved a perfect score in actionability compared with the human-generated version (100% vs 0%; P<.001). Intraclass correlation coefficient for evaluator consistency was high at 0.83 (95% CI 0.64-1.03), indicating good reliability across assessments.</p><p><strong>Conclusions: </strong>The Mistral 8x22B LLM showed promising capabilities in enhancing the readability, understandability, and actionability of ICFs without sacrificing accuracy or completeness. LLMs present a scalable, efficient solution for ICF generation, potentially enhancing participant comprehension and consent in clinical trials.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e68139"},"PeriodicalIF":3.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11841745/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143416106","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":"Performance Assessment of Large Language Models in Medical Consultation: Comparative Study.","authors":"Sujeong Seo, Kyuli Kim, Heyoung Yang","doi":"10.2196/64318","DOIUrl":"https://doi.org/10.2196/64318","url":null,"abstract":"<p><strong>Background: </strong>The recent introduction of generative artificial intelligence (AI) as an interactive consultant has sparked interest in evaluating its applicability in medical discussions and consultations, particularly within the domain of depression.</p><p><strong>Objective: </strong>This study evaluates the capability of large language models (LLMs) in AI to generate responses to depression-related queries.</p><p><strong>Methods: </strong>Using the PubMedQA and QuoraQA data sets, we compared various LLMs, including BioGPT, PMC-LLaMA, GPT-3.5, and Llama2, and measured the similarity between the generated and original answers.</p><p><strong>Results: </strong>The latest general LLMs, GPT-3.5 and Llama2, exhibited superior performance, particularly in generating responses to medical inquiries from the PubMedQA data set.</p><p><strong>Conclusions: </strong>Considering the rapid advancements in LLM development in recent years, it is hypothesized that version upgrades of general LLMs offer greater potential for enhancing their ability to generate \"knowledge text\" in the biomedical domain compared with fine-tuning for the biomedical field. These findings are expected to contribute significantly to the evolution of AI-based medical counseling systems.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64318"},"PeriodicalIF":3.1,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143411778","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":"Enhancing Surgery Scheduling in Health Care Settings With Metaheuristic Optimization Models: Algorithm Validation Study.","authors":"João Lopes, Tiago Guimarães, Júlio Duarte, Manuel Santos","doi":"10.2196/57231","DOIUrl":"10.2196/57231","url":null,"abstract":"<p><strong>Background: </strong>Health care is facing many challenges. The recent pandemic has caused a global reflection on how clinical and organizational processes should be organized, which requires the optimization of decision-making among managers and health care professionals to deliver care that is increasingly patient-centered. The efficiency of surgical scheduling is particularly critical, as it affects waiting list management and is susceptible to suboptimal decisions due to its complexity and constraints.</p><p><strong>Objective: </strong>In this study, in collaboration with one of the leading hospitals in Portugal, Centro Hospitalar e Universitário de Santo António (CHUdSA), a heuristic approach is proposed to optimize the management of the surgical center.</p><p><strong>Methods: </strong>CHUdSA's surgical scheduling process was analyzed over a specific period. By testing an optimization approach, the research team was able to prove the potential of artificial intelligence (AI)-based heuristic models in minimizing scheduling penalties-the financial costs incurred by procedures that were not scheduled on time.</p><p><strong>Results: </strong>The application of this approach demonstrated potential for significant improvements in scheduling efficiency. Notably, the implementation of the hill climbing (HC) and simulated annealing (SA) algorithms stood out in this implementation and minimized the scheduling penalty, scheduling 96.7% (415/429) and 84.4% (362/429) of surgeries, respectively. For the HC algorithm, the penalty score was 0 in the urology, obesity, and pediatric plastic surgery medical specialties. For the SA algorithm, the penalty score was 5100 in urology, 1240 in obesity, and 30 in pediatric plastic surgery. Together, this highlighted the ability of AI-heuristics to optimize the efficiency of this process and allowed for the scheduling of surgeries at closer dates compared to the manual method used by hospital professionals.</p><p><strong>Conclusions: </strong>Integrating these solutions into the surgical scheduling process increases efficiency and reduces costs. The practical implications are significant. By implementing these AI-driven strategies, hospitals can minimize patient wait times, maximize resource use, and enhance surgical outcomes through improved planning. This development highlights how AI algorithms can effectively adapt to changing health care environments, having a transformative impact.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e57231"},"PeriodicalIF":3.1,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11840878/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400472","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: Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Health Analytics.","authors":"Félix Camirand Lemyre, Simon Lévesque, Marie-Pier Domingue, Klaus Herrmann, Jean-François Ethier","doi":"10.2196/71249","DOIUrl":"10.2196/71249","url":null,"abstract":"","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e71249"},"PeriodicalIF":3.1,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11835779/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400462","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":"InfectA-Chat, an Arabic Large Language Model for Infectious Diseases: Comparative Analysis.","authors":"Yesim Selcuk, Eunhui Kim, Insung Ahn","doi":"10.2196/63881","DOIUrl":"10.2196/63881","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Infectious diseases have consistently been a significant concern in public health, requiring proactive measures to safeguard societal well-being. In this regard, regular monitoring activities play a crucial role in mitigating the adverse effects of diseases on society. To monitor disease trends, various organizations, such as the World Health Organization (WHO) and the European Centre for Disease Prevention and Control (ECDC), collect diverse surveillance data and make them publicly accessible. However, these platforms primarily present surveillance data in English, which creates language barriers for non-English-speaking individuals and global public health efforts to accurately observe disease trends. This challenge is particularly noticeable in regions such as the Middle East, where specific infectious diseases, such as Middle East respiratory syndrome coronavirus (MERS-CoV), have seen a dramatic increase. For such regions, it is essential to develop tools that can overcome language barriers and reach more individuals to alleviate the negative impacts of these diseases.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to address these issues; therefore, we propose InfectA-Chat, a cutting-edge large language model (LLM) specifically designed for the Arabic language but also incorporating English for question and answer (Q&A) tasks. InfectA-Chat leverages its deep understanding of the language to provide users with information on the latest trends in infectious diseases based on their queries.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This comprehensive study was achieved by instruction tuning the AceGPT-7B and AceGPT-7B-Chat models on a Q&A task, using a dataset of 55,400 Arabic and English domain-specific instruction-following data. The performance of these fine-tuned models was evaluated using 2770 domain-specific Arabic and English instruction-following data, using the GPT-4 evaluation method. A comparative analysis was then performed against Arabic LLMs and state-of-the-art models, including AceGPT-13B-Chat, Jais-13B-Chat, Gemini, GPT-3.5, and GPT-4. Furthermore, to ensure the model had access to the latest information on infectious diseases by regularly updating the data without additional fine-tuning, we used the retrieval-augmented generation (RAG) method.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;InfectA-Chat demonstrated good performance in answering questions about infectious diseases by the GPT-4 evaluation method. Our comparative analysis revealed that it outperforms the AceGPT-7B-Chat and InfectA-Chat (based on AceGPT-7B) models by a margin of 43.52%. It also surpassed other Arabic LLMs such as AceGPT-13B-Chat and Jais-13B-Chat by 48.61%. Among the state-of-the-art models, InfectA-Chat achieved a leading performance of 23.78%, competing closely with the GPT-4 model. Furthermore, the RAG method in InfectA-Chat significantly improved document retrieval accuracy. Notably, RAG retrieved more accurate documents based on que","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e63881"},"PeriodicalIF":3.1,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11851044/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143392495","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":"Implementation of WHO SMART Guidelines-Digital Adaptation Kits in Pathfinder Countries in Africa: Processes and Early Lessons Learned.","authors":"Rosemary K Muliokela, Kuwani Banda, Abdulaziz Mohammed Hussen, Sarai Bvulani Malumo, Andrew Kashoka, Angel Mwiche, Innocent Chiboma, Maria Barreix, Muyereka Nyirenda, Zvanaka Sithole, Natschja Ratanaprayul, Berhanu Fikadie Endehabtu, Hanna Abayneh Telake, Adane Weldeab, William J M Probert, Ӧzge Tunçalp, Ernest Maya, Mulatu Woldetsadik, Binyam Tilahun, Chris Guure, Kafui Senya, Lale Say, Tigest Tamrat","doi":"10.2196/58858","DOIUrl":"10.2196/58858","url":null,"abstract":"<p><strong>Background: </strong>The adoption of digital systems requires processes for quality assurance and uptake of standards to achieve universal health coverage. The World Health Organization developed the Digital Adaptation Kits (DAKs) within the SMART (Standards-based, Machine-readable, Adaptive, Requirements-based, and Testable) guidelines framework to support the uptake of standards and recommendations through digital systems. DAKs are a software-neutral mechanism for translating narrative guidelines to support the design of digital systems. However, a systematic process is needed to implement and ensure the impact of DAKs in country contexts.</p><p><strong>Objective: </strong>This paper details the structured process and stepwise approach to customize the DAKs to the national program and digital context in 5 countries in Africa with diverse program guideline uptake and significant digital health investments: Ethiopia, Ghana, Malawi, Zambia, and Zimbabwe. All these countries have existing digital systems, which have the potential to be updated with the DAKs.</p><p><strong>Methods: </strong>A DAK assessment tool was developed and used to assess guideline digitization readiness and opportunities for system uptake in each country. Multistakeholder teams were established to conduct the content review and alignment of the generic DAK to national guidelines and protocols through a series of stakeholder consultations, including stakeholder orientation, content review and alignment, content validation, and software update meetings.</p><p><strong>Unlabelled: </strong>Country adaptation processes identified requirements for national-level contextualization and highlighted opportunities for refinement of DAKs. Quality assurance of the content during the content review and validation processes ensured alignment with national protocols. Adaptation processes also facilitated the adoption of the DAKs approach into national guidelines and strategic documents for sexual and reproductive health.</p><p><strong>Conclusions: </strong>Country experiences offered early insights into the opportunities and benefits of a structured approach to digitalizing primary health care services. They also highlighted how this process can be continuously refined and sustained to enhance country-level impact.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e58858"},"PeriodicalIF":3.1,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11830483/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143384238","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":"Diagnosis of Chronic Kidney Disease Using Retinal Imaging and Urine Dipstick Data: Multimodal Deep Learning Approach.","authors":"Youngmin Bhak, Yu Ho Lee, Joonhyung Kim, Kiwon Lee, Daehwan Lee, Eun Chan Jang, Eunjeong Jang, Christopher Seungkyu Lee, Eun Seok Kang, Sehee Park, Hyun Wook Han, Sang Min Nam","doi":"10.2196/55825","DOIUrl":"10.2196/55825","url":null,"abstract":"<p><strong>Background: </strong>Chronic kidney disease (CKD) is a prevalent condition with significant global health implications. Early detection and management are critical to prevent disease progression and complications. Deep learning (DL) models using retinal images have emerged as potential noninvasive screening tools for CKD, though their performance may be limited, especially in identifying individuals with proteinuria and in specific subgroups.</p><p><strong>Objective: </strong>We aim to evaluate the efficacy of integrating retinal images and urine dipstick data into DL models for enhanced CKD diagnosis.</p><p><strong>Methods: </strong>The 3 models were developed and validated: eGFR-RIDL (estimated glomerular filtration rate-retinal image deep learning), eGFR-UDLR (logistic regression using urine dipstick data), and eGFR-MMDL (multimodal deep learning combining retinal images and urine dipstick data). All models were trained to predict an eGFR<60 mL/min/1.73 m², a key indicator of CKD, calculated using the 2009 CKD-EPI (Chronic Kidney Disease Epidemiology Collaboration) equation. This study used a multicenter dataset of participants aged 20-79 years, including a development set (65,082 people) and an external validation set (58,284 people). Wide Residual Networks were used for DL, and saliency maps were used to visualize model attention. Sensitivity analyses assessed the impact of numerical variables.</p><p><strong>Results: </strong>eGFR-MMDL outperformed eGFR-RIDL in both the test and external validation sets, with area under the curves of 0.94 versus 0.90 and 0.88 versus 0.77 (P<.001 for both, DeLong test). eGFR-UDLR outperformed eGFR-RIDL and was comparable to eGFR-MMDL, particularly in the external validation. However, in the subgroup analysis, eGFR-MMDL showed improvement across all subgroups, while eGFR-UDLR demonstrated no such gains. This suggested that the enhanced performance of eGFR-MMDL was not due to urine data alone, but rather from the synergistic integration of both retinal images and urine data. The eGFR-MMDL model demonstrated the best performance in individuals younger than 65 years or those with proteinuria. Age and proteinuria were identified as critical factors influencing model performance. Saliency maps indicated that urine data and retinal images provide complementary information, with urine offering insights into retinal abnormalities and retinal images, particularly the arcade vessels, being key for predicting kidney function.</p><p><strong>Conclusions: </strong>The MMDL model integrating retinal images and urine dipstick data show significant promise for noninvasive CKD screening, outperforming the retinal image-only model. However, routine blood tests are still recommended for individuals aged 65 years and older due to the model's limited performance in this age group.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e55825"},"PeriodicalIF":3.1,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11830489/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143384235","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":"Development and Validation of a Machine Learning Algorithm for Predicting Diabetes Retinopathy in Patients With Type 2 Diabetes: Algorithm Development Study.","authors":"Sunyoung Kim, Jaeyu Park, Yejun Son, Hojae Lee, Selin Woo, Myeongcheol Lee, Hayeon Lee, Hyunji Sang, Dong Keon Yon, Sang Youl Rhee","doi":"10.2196/58107","DOIUrl":"10.2196/58107","url":null,"abstract":"<p><strong>Background: </strong>Diabetic retinopathy (DR) is the leading cause of preventable blindness worldwide. Machine learning (ML) systems can enhance DR in community-based screening. However, predictive power models for usability and performance are still being determined.</p><p><strong>Objective: </strong>This study used data from 3 university hospitals in South Korea to conduct a simple and accurate assessment of ML-based risk prediction for the development of DR that can be universally applied to adults with type 2 diabetes mellitus (T2DM).</p><p><strong>Methods: </strong>DR was predicted using data from 2 independent electronic medical records: a discovery cohort (one hospital, n=14,694) and a validation cohort (2 hospitals, n=1856). The primary outcome was the presence of DR at 3 years. Different ML-based models were selected through hyperparameter tuning in the discovery cohort, and the area under the receiver operating characteristic (ROC) curve was analyzed in both cohorts.</p><p><strong>Results: </strong>Among 14,694 patients screened for inclusion, 348 (2.37%) were diagnosed with DR. For DR, the extreme gradient boosting (XGBoost) system had an accuracy of 75.13% (95% CI 74.10-76.17), a sensitivity of 71.00% (95% CI 66.83-75.17), and a specificity of 75.23% (95% CI 74.16-76.31) in the original dataset. Among the validation datasets, XGBoost had an accuracy of 65.14%, a sensitivity of 64.96%, and a specificity of 65.15%. The most common feature in the XGBoost model is dyslipidemia, followed by cancer, hypertension, chronic kidney disease, neuropathy, and cardiovascular disease.</p><p><strong>Conclusions: </strong>This approach shows the potential to enhance patient outcomes by enabling timely interventions in patients with T2DM, improving our understanding of contributing factors, and reducing DR-related complications. The proposed prediction model is expected to be both competitive and cost-effective, particularly for primary care settings in South Korea.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e58107"},"PeriodicalIF":3.1,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11830482/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143384233","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}