Retinal vein occlusion risk prediction without fundus examination using a no-code machine learning tool for tabular data: a nationwide cross-sectional study from South Korea

• Published in: BMC medical informatics and decision making Vol. 25; no. 1; pp. 118 - 14
• Main Authors: Yu, Na Hyeon, Shin, Daeun, Ryu, Ik Hee, Yoo, Tae Keun, Koh, Kyungmin
• Format: Journal Article
• Language: English
• Published: London BioMed Central 07.03.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Adult; Aged; Alcohol use; Algorithms; Artificial neural networks; Biomarkers; Blood pressure; Blood tests; Body mass index; Cardiovascular disease; Code-free tool; Coding; Confidence intervals; Cross-Sectional Studies; Data collection; Data mining; Data Mining - methods; Datasets; Demographic aspects; Diabetes; Family income; Feasibility studies; Female; Fundus Oculi; Health Informatics; Health risks; Humans; Hypertension; Information Systems and Communication Service; Laboratories; Laboratory tests; Learning algorithms; Machine Learning; Male; Management of Computing and Information Systems; Medical history; Medicine; Medicine & Public Health; Metabolic disorders; Middle Aged; Neural coding; Neural networks; Neural Networks, Computer; No-code machine learning; Nutrition; Nutrition Surveys; Occlusion; Open source medical software; Osteoarthritis; Osteoporosis; Photography; Prediction models; Regression analysis; Republic of Korea - epidemiology; Retina; Retinal diseases; Retinal images; Retinal vein occlusion; Retinal Vein Occlusion - diagnosis; Retinal Vein Occlusion - epidemiology; Review boards; Risk assessment; Risk Assessment - methods; Risk factors; Source code; Statistical analysis; Tables (data); Technology application; Veins; Veins & arteries; Workflow; Republic of Korea; South Korea; Germany; Retinal vein occlusion; Code-free tool; No-code machine learning; Risk factors
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-025-02950-8

Background Retinal vein occlusion (RVO) is a leading cause of vision loss globally. Routine health check-up data—including demographic information, medical history, and laboratory test results—are commonly utilized in clinical settings for disease risk assessment. This study aimed to develop a machine learning model to predict RVO risk in the general population using such tabular health data, without requiring coding expertise or retinal imaging. Methods We utilized data from the Korea National Health and Nutrition Examination Surveys (KNHANES) collected between 2017 and 2020 to develop the RVO prediction model, with external validation performed using independent data from KNHANES 2021. Model construction was conducted using Orange Data Mining, an open-source, code-free, component-based tool with a user-friendly interface, and Google Vertex AI. An easy-to-use oversampling function was employed to address class imbalance, enhancing the usability of the workflow. Various machine learning algorithms were trained by incorporating all features from the health check-up data in the development set. The primary outcome was the area under the receiver operating characteristic curve (AUC) for identifying RVO. Results All machine learning training was completed without the need for coding experience. An artificial neural network (ANN) with a ReLU activation function, developed using Orange Data Mining, demonstrated superior performance, achieving an AUC of 0.856 (95% confidence interval [CI], 0.835–0.875) in internal validation and 0.784 (95% CI, 0.763–0.803) in external validation. The ANN outperformed logistic regression and Google Vertex AI models, though differences were not statistically significant in internal validation. In external validation, the ANN showed a marginally significant improvement over logistic regression ( P  = 0.044), with no significant difference compared to Google Vertex AI. Key predictive variables included age, household income, and blood pressure-related factors. Conclusion This study demonstrates the feasibility of developing an accessible, cost-effective RVO risk prediction tool using health check-up data and no-code machine learning platforms. Such a tool has the potential to enhance early detection and preventive strategies in general healthcare settings, thereby improving patient outcomes.