Prediction of Cardiovascular Complication in Patients with Newly Diagnosed Type 2 Diabetes Using an XGBoost/ GRU-ODE-Bayes-Based Machine-Learning Algorithm

Aug 5, 2026

Upload by Aurora

Cardiovascular disease poses major threats to patients with type 2 diabetes mellitus (T2DM), yet risk stratification can guide prevention and individualized care. This study builds machine-learning–based cardiovascular risk engines for newly diagnosed T2DM patients in Korea using retrospective data from 26,166 cases. A buffer, observation, and 5-year outcome framework targets diabetes-related events. Results show GRU-ODE-Bayes and XGBoost risk engines outperform conventional regression, enabling accurate, practical prediction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Background

Methods

Data and outcome design

Model evaluation

Results

Conclusion

Original Article Endocrinol Metab 2024;39:176-185 [https://doi.org/10.3803/EnM.2023.1739](https://doi.org/10.3803/EnM.2023.1739)[ ](https://doi.org/10.3803/EnM.2023.1739)[pISSN 2093-596X](pISSN 2093-596X) · eISSN 2093-5978 Prediction of Cardiovascular Complication in Patients with Newly Diagnosed Type 2 Diabetes Using an XGBoost/ GRU-ODE-Bayes-Based Machine-Learning Algorithm Joonyub Lee1, Yera Choi2, Taehoon Ko3, Kanghyuck Lee3,4, Juyoung Shin 1,3,5, Hun-Sung Kim 1,3 1Division of Endocrinology and Metabolism, Department of Internal Medicine, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul; 2NAVER CLOVA AI Lab, Seongnam; Departments of 3Medical Informatics, 4Biomedicine and Health Sciences, College of Medicine, The Catholic University of Korea; 5Health Promotion Center, Seoul St. Mary’s Hospital, Seoul, Korea Background: Cardiovascular disease is life-threatening yet preventable for patients with type 2 diabetes mellitus (T2DM) . Because each patient with T2DM has a different risk of developing cardiovascular complications, the accurate stratification of cardiovascular risk is critical. In this study, we proposed cardiovascular risk engines based on machine-learning algorithms for newly diagnosed T2DM patients in Korea. Methods: To develop the machine-learning-based cardiovascular disease engines, we retrospectively analyzed 26,166 newly diagnosed T2DM patients who visited Seoul St. Mary’s Hospital between July 2009 and April 2019. To accurately measure diabetes-related cardiovascular events, we designed a buffer (1 year), an observation (1 year), and an outcome period (5 years) . The entire dataset was split into training and testing sets in an 8:2 ratio, and this procedure was repeated 100 times. The area under the receiver operating characteristic curve (AUROC) was calculated by 10-fold cross-validation on the training dataset. Results: The machine-learning-based risk engines (AUROC XGBoost = 0.781±0.014 and AUROC gated recurrent unit [GRU]-ordinary differential equation [ODE]-Bayes = 0.812±0.016) outperformed the conventional regression-based model (AUROC = 0.723± 0.036) . Conclusion: GRU-ODE-Bayes-based cardiovascular risk engine is highly accurate, easily applicable, and can provide valuable information for the individualized treatment of Korean patients with newly diagnosed T2DM. | Keywords: Cardiovascular diseases; Diabetes mellitus, type 2; Korea; Machine learning | | | --- | --- | | INTRODUCTION
Patients with type 2 diabetes mellitus (T2DM) are at an increased risk of developing vascular complications [1,2] . Sustained hyperglycemia, along with common concomitant T2DM | medical conditions (obesity, hypertension, dyslipidemia, and smoking), exert deleterious effects on endothelial cells throughout the body. Accordingly, patients with diabetes are prone to develop microvascular (retinopathy, nephropathy, and neuropathy) and macrovascular (stroke, myocardial infarction, periph- | | Received: 16 May 2023, Revised: 22 July 2023, Accepted: 9 August 2023
Corresponding author: Hun-Sung Kim
Department of Medical Informatics, College of Medicine, The Catholic University of Korea, 222 Banpo-daero, Seocho-gu, Seoul 06591, Korea
Tel: +82-2-3147-8425, Fax: +82-504-292-9080, E-mail: [01cadiz@hanmail.net](01cadiz@hanmail.net) | Copyright © 2024 Korean Endocrine Society
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by-nc/4.0/](licenses/by-nc/4.0/)) [which permits unrestricted non-commercial use](which permits unrestricted non-commercial use), distribution, and reproduction in any medium, provided the original work is properly cited. | 176 [www.e-enm.org](www.e-enm.org) Cardiovascular Complication Risk Engine eral artery disease, and aortic diseases) complications, significantly incr

FAQs

Why is accurate cardiovascular risk stratification important for newly diagnosed T2DM patients?

Cardiovascular disease is life-threatening but preventable, and different patients have different risks of developing complications. Early individualized risk assessment helps guide therapy and efficiently use limited medical resources.

How were the cardiovascular events and study periods defined in the methods?

The study used a buffer period of 1 year, an observation period of 1 year, and an outcome period of 5 years to accurately measure diabetes-related cardiovascular events.

Which machine-learning models performed best compared with conventional regression?

The GRU-ODE-Bayes-based risk engine achieved AUROC 0.812±0.016 and XGBoost achieved AUROC 0.781±0.014, both outperforming the conventional regression-based model with AUROC 0.723±0.036.

Aug 5, 2026

Upload by Aurora