What does this research mean for the field?

A stacked ensemble artificial intelligence framework integrating multiple base classifiers via a Multilayer Perceptron meta-learner achieves highly accurate cardiovascular disease risk prediction, yielding 96.06% accuracy and 99.31% ROC-AUC. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The research aims to develop a hybrid AI model for predicting cardiovascular disease risk using ensemble methods and neural networks.

March 24, 2026Open Access

A hybrid artificial intelligence approach for cardiovascular disease prediction using ensemble learning, neural networks, and interpretable models

Key Result

A stacked ensemble artificial intelligence framework achieved 96.06% accuracy, 96.12% F1-score, and 99.31% ROC-AUC for predicting cardiovascular disease risk.

Key Points

The research aims to develop a hybrid AI model for predicting cardiovascular disease risk using ensemble methods and neural networks.
Utilized the Framingham Heart Disease dataset for analysis.
Employed stacked ensemble learning with five base classifiers and a Multilayer Perceptron meta-learner.
Implemented data preprocessing techniques including Hampel filtering, mean imputation, Min-Max normalization, PCA, and SMOTE.
Evaluated model performance using metrics like accuracy, F1-score, and ROC-AUC.
Achieved 96.06% accuracy and 96.12% F1-score with the stacked ensemble model.
ROC-AUC reached 99.31%, indicating excellent predictive performance.
Identified key features for risk estimation, including blood pressure, smoking, cholesterol, and age.

Structured PICO

Does a stacked ensemble learning framework improve the prediction of cardiovascular disease risk compared to stand-alone classifiers?

Population

Patients from the Framingham Heart Disease dataset evaluated for cardiovascular disease risk

Intervention

Stacked ensemble learning framework (XGBoost, LightGBM, CatBoost, Gradient Boosting, and AdaBoost integrated through an MLP meta-learner)

Comparator

Stand-alone classifiers

Outcome

Prediction of cardiovascular disease (CVD) risk (measured by accuracy, F1-score, and ROC-AUC)

A stacked ensemble learning framework integrating multiple classifiers achieved highly accurate and interpretable cardiovascular disease risk prediction.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

This study presents a stacked ensemble learning framework for accurate prediction of cardiovascular disease (CVD) risk using the Framingham Heart Disease dataset. Five highly differentiable base classifiers—XGBoost, LightGBM, CatBoost, Gradient Boosting, and AdaBoost—have been integrated through a Multilayer Perceptron (MLP) meta-learner. Preprocessing entailed Hampel filtering for outlier elimination, mean imputation for handling missing data, Min-Max normalization, PCA dimension reduction on the basis of nine components, and SMOTE for class balance restoration. Stacked ensemble model produced 96.06% accuracy, 96.12% F1-score, and 99.31% ROC-AUC, significantly superior to stand-alone classifiers. In a bid to ensure interpretability, feature importance was explored and revealed that components relating to blood pressure, smoking, cholesterol, and age played most critical roles in risk estimation. Correspondingly, these features possessed complex, non-linear effects demonstrating threshold-like behavior reflecting model’s decision-making. Correlation analyses corroborated good model alignment, where CatBoost and XGBoost revealed highest agreement of feature importance with the ensemble. This work illustrates the merit of uniting comprehensive learners with explainable AI for reliable, interpretable, and highly scalable CVD risk classification, making the architecture deployable in the clinic for early detection and personalized preventive strategies.