Predictive model and risk analysis for peripheral vascular disease in type 2 diabetes mellitus patients using machine learning and shapley additive explanation

Aug 5, 2026

Peripheral vascular disease (PVD) poses a major macrovascular threat to patients with type 2 diabetes mellitus (T2DM), making early risk prediction essential for clinical decision-making. A retrospective cohort of 4,372 inpatients was analyzed using electronic health records, with preprocessing, recursive feature elimination, and training/testing split. Six machine learning models were optimized via grid search and 10-fold cross-validation, while SHAP provided interpretability for the best-performing approach.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Background

Purpose

Methods

Dataset and preprocessing

Modeling and evaluation

Interpretability with SHAP

Results

Conclusion

TYPE Original Research PUBLISHED 28 February 2024 DOI 10.3389/fendo.2024.1320335 OPEN ACCESS EDITED BY Bert B. Little, University of Louisville, United States REVIEWED BY Jorge Francisco Gomez Cerezo, Universidad Europeas de Madrid, Spain Rasoul Goli, Urmia University of Medical Sciences, Iran *CORRESPONDENCE Feng Ju [hy0208014@hainmc.edu.cn](hy0208014@hainmc.edu.cn) †These authors have contributed equally to this work and share ﬁrst authorship RECEIVED 12 October 2023 ACCEPTED 06 February 2024 PUBLISHED 28 February 2024 CITATION Liu L, Bi B, Cao L, Gui M and Ju F (2024) Predictive model and risk analysis for peripheral vascular disease in type 2 diabetes mellitus patients using machine learning and shapley additive explanation. Front. Endocrinol. 15:1320335 . doi: 10.3389/fendo.2024.1320335 COPYRIGHT © 2024 Liu, Bi, Cao, Gui and Ju. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Predictive model and risk analysis for peripheral vascular disease in type 2 diabetes mellitus patients using machine learning and shapley additive explanation Lianhua Liu 1†, Bo Bi 1†, Li Cao 1, Mei Gui 1 and Feng Ju 2* 1 International School of Public Health and One Health, Hainan Medical University, Haikou, Hainan, China, 2 Department of Endocrinology, Second Afﬁliated Hospital of Hainan Medical University, Haikou, Hainan, China Background: Peripheral vascular disease (PVD) is a common complication inpatients with type 2 diabetes mellitus (T2DM) . Early detection or prediction the risk of developing PVD is important for clinical decision-making. Purpose: This study aims to establish and validate PVD risk prediction models and perform risk factor analysis for PVD in patients with T2DM using machine learning and Shapley Additive Explanation(SHAP) based on electronic health records. Methods: We retrospectively analyzed the data from 4,372 inpatients with diabetes in a hospital between January 1, 2021, and March 28, 2023 . The data comprised demographic characteristics, discharge diagnoses and biochemical index test results. After data preprocessing and feature selection using Recursive Feature Elimination(RFE), the dataset was split into training and testing sets at a ratio of 8:2, with the Synthetic Minority Over-sampling Technique(SMOTE) employed to balance the training set. Six machine learning(ML) algorithms, including decision tree (DT), logistic regression (LR), random forest (RF), support vector machine(SVM), extreme gradient boosting (XGBoost) and Adaptive Boosting(AdaBoost) were applied to construct PVD prediction models. A grid search with 10-fold cross-validation was conducted to optimize the hyperparameters. Metrics such as accuracy, precision, recall, F1-score, Gmean, and the area under the receiver operating characteristic curve (AUC) assessed the models’ effectiveness. The SHAP method interpreted the bestperforming model. Results: RFE identiﬁed the optimal 12 predictors. The XGBoost model outperformed other ﬁve ML models, with an AUC of 0 . 945, G-mean of 0 . 843, accuracy of 0 . 890, precision of 0 . 930, recall of 0 . 927, and F1-score of 0 .928. The feature importance of ML models and SHAP results indicated that Hemoglobin (Hb), age, total bile acids (TBA) and lipoprotein(a)(LP-a) are the top four important risk factors for PVD in T2DM. Frontiers in Endocrinology 01 [frontiersin.org](frontiersin.org) Conclusion: The machine learning approach successfully developed a PVD risk prediction model with good performance. The model identiﬁed the factors associated with PVD and offered phy

FAQs

What problem does the study address for patients with type 2 diabetes?

The study targets early prediction of peripheral vascular disease (PVD) risk in patients with type 2 diabetes mellitus (T2DM) to support clinical decisions.

How were the predictive models built and evaluated?

The researchers used electronic health records from 4,372 inpatients, applied preprocessing and recursive feature elimination, balanced the training set with SMOTE, and trained six machine learning algorithms. Hyperparameters were optimized using grid search with 10-fold cross-validation, and performance was assessed using metrics such as accuracy, precision, recall, F1-score, G-mean, and AUC.

Which model performed best and what key risk factors were identified?

The XGBoost model performed best with the highest reported AUC. SHAP and feature-importance results highlighted hemoglobin (Hb), age, total bile acids (TBA), and lipoprotein(a) (LP-a) as top risk factors for PVD in T2DM.

Aug 5, 2026

Upload by Emma Wilson