A Multimodal Predictive Model for Chronic Kidney Disease and Its Association With Vascular Complications in Patients With Type 2 Diabetes: Model Development and Validation Study in South Korea and the U.K.
Authors:
- 1 July 2025
- journal article
- Published by American Diabetes Association in Diabetes Care
- Vol. 48 (9) , 1562-1570
Abstract
OBJECTIVE: To develop a multimodal model to predict chronic kidney disease (CKD) in patients with type 2 diabetes mellitus (T2DM), given the limited research on this integrative approach. RESEARCH DESIGN AND METHODS: We obtained multimodal data sets from Kyung Hee University Medical Center (n = 7,028; discovery cohort) for training and internal validation and UK Biobank (n = 1,544; validation cohort) for external validation. CKD was defined based on ICD-9 and ICD-10 codes and/or estimated glomerular filtration rate (eGFR) ≤60 mL/min/1.73 m2. We ensembled various deep learning models and interpreted their predictions using explainable artificial intelligence (AI) methods, including Shapley additive explanation values (SHAP) and gradient-weighted class activation mapping (Grad-CAM). Subsequently, we investigated the potential association between the model probability and vascular complications. RESULTS: The multimodal model, which ensembles visual geometry group 16 and deep neural network, presented high performance in predicting CKD, with area under the receiver operating characteristic curve of 0.880 (95% CI 0.806–0.954) in the discovery cohort and 0.722 in the validation cohort. SHAP and Grad-CAM highlighted key predictors, including eGFR and optic disc, respectively. The model probability was associated with an increased risk of macrovascular complications (tertile 1 [T1]: adjusted hazard ratio, 1.42 [95% CI 1.06–1.90]; T2: 1.59 [1.17–2.16]; T3: 1.64 [1.20–2.26]) and microvascular complications (T3: 1.30 [1.02–1.67]). CONCLUSIONS: Our multimodal AI model integrates fundus images and clinical data from binational cohorts to predict the risk of new-onset CKD within 5 years and associated vascular complications in patients with T2DM.Keywords
All Related Versions
Funding Information
- Ministry of Health & Welfare, South Korea (HE23C002800)
- Institute for Information and Communications Technology Promotion (IITP-2024-RS-2024-00438239)
- Institute for Information and Communications Technology Promotion (RS-2024-00509257)
- National Research Foundation of Korea (RS-2023-00262002)
- National Research Foundation of Korea (RS-2024-00460379)
This publication has 39 references indexed in Scilit:
- Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyeClinicalMedicine, 2025
- CKD Progression Prediction in a Diverse US Population: A Machine-Learning ModelKidney Medicine, 2023
- Diabetic vascular diseases: molecular mechanisms and therapeutic strategiesSignal Transduction and Targeted Therapy, 2023
- Medical image data augmentation: techniques, comparisons and interpretationsArtificial Intelligence Review, 2023
- Chronic kidney disease prediction based on machine learning algorithmsJournal of Pathology Informatics, 2023
- Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney diseaseDiabetologia, 2021
- Convolutional neural network for the detection of pancreatic cancer on CT scansThe Lancet Digital Health, 2020
- A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populationsThe Lancet Digital Health, 2020
- Chronic Kidney Disease Diagnosis and ManagementJAMA, 2019
- A calibration hierarchy for risk models was defined: from utopia to empirical dataJournal of Clinical Epidemiology, 2016