Related Experiment Video
Updated: Jan 11, 2026
06:22
Modeling and Evaluation of Murine Diabetic Cardiomyopathy Model
Published on: November 29, 2024
1.3K
Development and External Validation of a Machine Learning-Based Model for Predicting Heart Failure Risk in Type 2
Yuqing Liu1, Ping Wang2, Min Wang3
1Department of Endocrinology, The First Affiliated Hospital with Nanjing Medical University, Nanjing, People's Republic of China.
Diabetes, Metabolic Syndrome and Obesity : Targets and Therapy
|November 19, 2025
Summary
A new machine learning nomogram accurately predicts heart failure risk in type 2 diabetes mellitus (T2DM) patients using routine clinical data. This accessible tool aids risk stratification in primary care settings lacking advanced diagnostics.
Area of Science:
- Cardiology
- Endocrinology
- Data Science
Background:
- Type 2 diabetes mellitus (T2DM) significantly increases the risk of heart failure (HF), a major cause of morbidity and mortality.
- The biomarker NT-proBNP is a reliable HF predictor in T2DM, but its measurement is often unavailable in Chinese primary care.
- Accessible HF risk stratification tools are crucial for T2DM patients, especially in resource-limited settings.
Purpose of the Study:
- To develop and externally validate a machine learning-based nomogram for predicting elevated NT-proBNP (≥125 pg/mL) in T2DM patients.
- To provide a practical and interpretable tool for HF risk assessment in primary healthcare settings.
- To identify key clinical predictors of elevated NT-proBNP in T2DM.
Main Methods:
- Retrospective enrollment of 564 T2DM patients for model development and 302 for external validation.
- Feature selection using least absolute shrinkage and selection operator (LASSO) regression.
- Construction and evaluation of five machine learning models with 10-fold cross-validation; optimal model presented as a nomogram.
Main Results:
- Six predictors identified: estimated glomerular filtration rate, age, serum albumin, hemoglobin, urine albumin-to-creatinine ratio, and age ≥ 65 years.
- The machine learning nomogram achieved AUCs of 0.806 (training) and 0.861 (external validation), demonstrating good calibration and clinical utility.
- Estimated glomerular filtration rate was identified as the most influential predictor via SHapley Additive exPlanations (SHAP).
Conclusions:
- An interpretable, machine learning-based nomogram effectively predicts elevated NT-proBNP in T2DM patients using routine clinical variables.
- The developed nomogram demonstrates robust performance and generalizability, offering a practical solution for HF risk stratification.
- This tool is particularly valuable for resource-limited primary care settings in China.
Related Concept Videos
01:30Heart Failure IV: Classification and Diagnostic Evaluation
300
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
300
01:22Diabetes Mellitus: Type 2 and Gestational
4.3K
Type 2 diabetes, characterized by insulin resistance, arises when the insulin receptors on cells lose responsiveness to insulin, diminishing the cell's capacity to take up glucose, resulting in elevated blood glucose levels. To receive a diagnosis of Type 2 diabetes, a series of blood glucose tests are necessary to assess whether the blood glucose falls within normal parameters. If the result is out of the normal range, a patient may be diagnosed as prediabetic or diabetic, depending on the...
4.3K