Clinical Report: Deep Learning Model for Forecasting Coronary Heart Disease

Overview

This study developed a deep learning model to forecast coronary heart disease (CHD) in hypertensive patients using 24-hour ambulatory blood pressure monitoring (ABPM).

Background

Coronary heart disease (CHD) is a leading cause of morbidity and mortality globally. Early identification of high-risk patients is essential. Traditional risk assessment methods often rely on static clinical measurements. The use of 24-hour ambulatory blood pressure monitoring (ABPM) and machine learning techniques can enhance the prediction of cardiovascular events in hypertensive patients.

Data Highlights

Key Findings

• The deep neural network model achieved an AUC of 0.822 in the training cohort and 0.796 in the validation cohort.
• Feature selection retained nine predictors, including diabetes mellitus and mean systolic blood pressure.
• Time in target range (TTR) was identified as a primary driver of model predictions.
• The model demonstrated superior calibration with the lowest Brier score of 0.172.
• SHAP analysis was utilized to evaluate model interpretability.

Clinical Implications

The developed model allows for the identification of high-risk CHD patients based on routinely available clinical variables.

Conclusion

The deep learning model requires further validation in diverse clinical settings.

Related Resources & Content

1. Frontiers in Cardiovascular Medicine, 2026 -- Evaluation of coronary heart disease risk prediction based on simple physical examination parameters by machine learning model: a retrospective cohort model development and validation study
2. Frontiers in Cardiovascular Medicine, 2026 -- Development and validation of an interpretable machine learning model for predicting atrial fibrillation risk in middle-aged and older patients with coronary heart disease
3. Frontiers in Digital Health, 2026 -- Explainable and interpretable models for predicting early-onset hypertension in the Tlalpan 2020 cohort
4. npj Digital Medicine, 2025 -- Development and evaluation of a machine learning model predicting out-of-hospital cardiac arrest using environmental factors
5. 2024 ESC Guidelines for the management of elevated blood pressure and hypertension
6. New England Journal of Medicine, 2015 -- A Randomized Trial of Intensive versus Standard Blood-Pressure Control
7. PubMed -- Time in Target Range for Blood Pressure and Adverse Health Outcomes: A Systematic Review
8. 2024 ESC Guidelines for the management of elevated blood pressure and hypertension
9. A Randomized Trial of Intensive versus Standard Blood-Pressure Control | New England Journal of Medicine
10. Time in Target Range for Blood Pressure and Adverse Health Outcomes: A Systematic Review - PubMed