Key result
A six-indicator XGBoost model predicts carotid plaque vulnerability in T2D with an AUC of ~0.88.
Why the study?
To develop and externally validate an interpretable machine-learning framework for estimating ultrasound-defined carotid plaque vulnerability in patients with type 2 diabetes mellitus and established carotid plaque.
Can an interpretable machine learning model using clinical, laboratory, and continuous glucose monitoring indicators accurately predict ultrasound-defined carotid plaque vulnerability in patients with type 2 diabetes?
Observational (n=884)
Yes
Can an interpretable machine learning model using clinical, laboratory, and continuous glucose monitoring indicators accurately predict ultrasound-defined carotid plaque vulnerability in patients with type 2 diabetes?
An interpretable machine learning model utilizing six clinical and continuous glucose monitoring indicators can accurately estimate carotid plaque vulnerability in patients with type 2 diabetes, potentially aiding in the prioritization of expert ultrasound characterization.
Answers are grounded in this paper and cite their sources.
Supports ML-based plaque risk estimation with CGM in T2DM; leaves open prospective validation and outcome impact.
Objective To develop and externally validate an interpretable machine-learning framework for estimating ultrasound-defined carotid plaque vulnerability among patients with type 2 diabetes mellitus (T2DM) and established carotid plaque. Methods In total, 884 T2DM patients with carotid atherosclerotic plaques from two medical centers were retrospectively recruited and allocated into training, internal validation, and external validation cohorts. Demographic, clinical, biochemical, continuous glucose monitoring (CGM), and inflammatory indicators were collected. CGM was performed for 72 consecutive hours using a retrospective CGM system (Medtronic iPro2; Medtronic, Northridge, CA, USA), and TIR was calculated from valid CGM recordings. Data preprocessing included clinically reviewed missing-data handling, standardization of continuous variables, and Synthetic Minority Over-sampling Technique (SMOTE), which was fitted only within the training data and, during cross-validation, within each training fold to avoid information leakage. Core predictors were identified by integrating feature-importance rankings derived from Random Forest, linear Support Vector Machine, and Logistic Regression. Five predictive models were developed and evaluated using discrimination, calibration, and clinical-utility metrics. Results Six core predictors were identified: systolic blood pressure (SBP), low-density lipoprotein cholesterol (LDL-C), age, time in range (TIR), systemic immune-inflammation index (SII), and smoking status. The XGBoost model showed the best overall validation performance, attaining an AUC of 0.882 (95% CI: 0.795-0.969) in the external validation set. SHAP analysis indicated that higher SBP, higher LDL-C, older age, higher SII, and smoking were associated with a higher predicted probability of vulnerable plaques, whereas higher TIR was associated with a lower predicted probability. Conclusion An interpretable XGBoost model based on six clinical, laboratory, and CGM-derived indicators showed acceptable discrimination, calibration, and clinical net benefit for estimating ultrasound-defined plaque vulnerability among patients with T2DM and established carotid plaque. The model is not a substitute for carotid ultrasound; pending prospective workflow and economic evaluation, it may support research-stage prioritization for expert plaque characterization when imaging capacity or expertise is constrained.
No takes yet. Share an insight, caveat, or question.
Cheng et al. (2026) conducted an observational in Type 2 diabetes mellitus with carotid atherosclerotic plaques (n=884). XGBoost machine learning model vs. Other machine learning models (Logistic Regression, LightGBM, Random Forest, SVM) was evaluated on Model discrimination (AUC) for ultrasound-defined carotid plaque vulnerability in the external validation set (AUC 0.882, 95% CI 0.795-0.969). An interpretable XGBoost model based on six clinical and continuous glucose monitoring indicators achieved an AUC of 0.882 for estimating ultrasound-defined carotid plaque vulnerability in patients with type 2 diabetes.
Synapse has enriched 10 related papers. Consider them for comparative context: