조재형 (차의과학대학교) | 한빛사논문 > 한빛사

한빛사논문

조회403

차의과학대학교

Diabetes Care, Jul 01 2025, dc250355 | https://doi.org/10.2337/dc25-0355 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

Jaehyeong Cho^1,2, Selin Woo ¹, Seung Ha Hwang ^1,3,4, Soeun Kim ^1,5, Hayeon Lee ^1,3,4, Jiyoung Hwang^1,6, Jaewon Kim ^1,6, Min Seo Kim ⁷, Lee Smith ^8,9, Sooji Lee ^1,6, Jinseok Lee ^3,4, Hong-Hee Won ¹⁰, Sang Youl Rhee ^1,5,6,11, Dong Keon Yon ^1,3,4,5,6,12

¹Center for Digital Health, Medical Science Research Institute, Kyung Hee University College of Medicine, Seoul, South Korea.
²Department of Medicine, CHA University School of Medicine, Seongnam, South Korea.
³Department of Biomedical Engineering, Kyung Hee University, Yongin, South Korea.
⁴Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin, South Korea.
⁵Department of Precision Medicine, Kyung Hee University College of Medicine, Seoul, South Korea.
⁶Department of Medicine, Kyung Hee University College of Medicine, Seoul, South Korea.
⁷Medical and Population Genetics and Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA.
⁸Centre for Health, Performance and Wellbeing, Anglia Ruskin University, Cambridge, U.K.
⁹Department of Public Health, Faculty of Medicine, Biruni University, Istanbul, Turkey.
¹⁰Department of Digital Health, Samsung Advanced Institute for Health Sciences and Technology, Sungkyunkwan University, Samsung Medical Center, Seoul, South Korea.
¹¹Department of Endocrinology and Metabolism, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea.
¹²Department of Pediatrics, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea.

J.C., S.W., S.H.H., and S.K. contributed equally as the first authors.
H.-H.W., S.Y.R., and D.K.Y. jointly supervised this work.
Corresponding author: Dong Keon Yon

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 explanations (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.

논문정보