Predicting Long-Term Mortality in Patients with Angina across the Spectrum of Dysglycemia: A Machine Learning
Yu-Hsuan Li1,2, Wayne Huey-Herng Sheu1,3, Wen-Chao Yeh4
1Division of Endocrinology and Metabolism, Department of Internal Medicine, Taichung Veterans General Hospital, Taichung 40705, Taiwan.
Insights
A new machine learning model accurately predicts long-term mortality in angina patients with dysglycemia. Integrating oral glucose tolerance test (OGTT) data improves risk identification for better patient outcomes.
Area of Science:
- Cardiology
- Endocrinology
- Machine Learning in Medicine
Background:
- Angina patients exhibit varying mortality risks, influenced by glycemic status.
- Accurate mortality prediction is crucial for managing patients with coronary artery disease and dysglycemia.
Purpose of the Study:
- To develop and validate a machine learning model for predicting long-term mortality in angina patients.
- To assess the model's performance across the spectrum of dysglycemia, including integration of oral glucose tolerance test (OGTT) data.
Main Methods:
- A cohort of 1479 angina patients undergoing coronary angiography was analyzed.
- A random survival forest model was developed using LASSO-selected features: age, heart rate, OGTT glucose levels, ARB use, diuretic use, and smoking history.
- Model performance was validated using five-fold cross-validation, assessing discriminative ability (Harrell's C-index) and calibration (Brier score).
Main Results:
- The developed model demonstrated strong predictive performance with a Harrell's C-index of 0.829 and a Brier score of 0.08.
- The model significantly outperformed the Global Registry of Acute Coronary Events (GRACE) discharge score in predicting mortality among patients with obstructive coronary artery disease (0.829 vs. 0.739, p < 0.001).
Conclusions:
- A novel machine learning model effectively predicts long-term mortality in angina patients.
- Incorporating OGTT results enhances the model's ability to identify high-risk individuals across the dysglycemia spectrum.
- This tool can aid clinicians in risk stratification and personalized management of angina patients.
Abstract:
We aimed to develop and validate a model for predicting mortality in patients with angina across the spectrum of dysglycemia. A total of 1479 patients admitted for coronary angiography due to angina were enrolled. All-cause mortality served as the primary endpoint. The models were validated with five-fold cross validation to predict long-term mortality. The features selected by least absolute shrinkage and selection operator (LASSO) were age, heart rate, plasma glucose levels at 30 min and 120 min during an oral glucose tolerance test (OGTT), the use of angiotensin II receptor blockers, the use of diuretics, and smoking history. This best performing model was built using a random survival forest with selected features. It had a good discriminative ability (Harrell's C-index: 0.829) and acceptable calibration (Brier score: 0.08) for predicting long-term mortality. Among patients with obstructive coronary artery disease confirmed by angiography, our model outperformed the Global Registry of Acute Coronary Events discharge score for mortality prediction (Harrell's C-index: 0.829 vs. 0.739, p < 0.001). In conclusion, we developed a machine learning model to predict long-term mortality among patients with angina. With the integration of OGTT, the model could help to identify a high risk of mortality across the spectrum of dysglycemia.
More Related Videos
05:16Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
Published on: June 10, 2025
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Related Concept Videos
01:26Angina IV: Management
01:30Coronary Artery Disease I: Introduction
01:22Diabetes Mellitus: Type 2 and Gestational
01:20Angina V: Nursing Management
01:15Diabetes: Symptoms, Diagnosis, and Complications