What does this research mean for the field?

Machine learning models, particularly an ensemble voting classifier and XGBoost, can accurately predict heart attack risk from clinical data, with chest pain type and exercise-induced angina being the most critical predictive features. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To train, evaluate, and optimize machine learning models and an ensemble hard voting classifier for predicting heart attack risk using clinical health indicators.

October 5, 2026Dijlah Journal of Engineering Sciences ISSN 3078-9664 e-ISSN 3078-9656

Predicting Heart Attacks using Machine Learning with Multiple Models and Hard Voting to Improve Accuracy

Q: What is the clinical evidence from this study?

Population: Heart attack (n=303). Intervention: XGBoost and ensemble voting classifier vs. Other machine learning models (kNN, SVM, etc.). Primary outcome: Prediction accuracy.

View Full Paper

Ask AI

Bookmark

Key result

XGBoost predicts heart attack likelihood with ~90% accuracy, outperforming kNN and SVM classifiers.

n=303

Why the study?

Heart attacks remain a leading cause of mortality globally, motivating the development of more effective methods for prevention and early detection using clinical data and machine learning.

Can machine learning models accurately predict the likelihood of a heart attack using clinical data?

Key Points

To train, evaluate, and optimize machine learning models and an ensemble hard voting classifier for predicting heart attack risk using clinical health indicators.
Analyzed clinical data from N=303 patients across 14 distinct physiological characteristics, applying feature scaling and categorical encoding.
Trained and evaluated seven classification algorithms—logistic regression, decision trees, random forest, support vector machines, k-nearest neighbors, Naïve Bayes, and Extreme Gradient Boosting (XGBoost)—alongside an ensemble voting classifier on partitioned train/test sets.
Evaluated diagnostic performance across accuracy, precision, recall, F1-score, and ROC-AUC metrics.
XGBoost achieved the highest individual model performance with a prediction accuracy of 90.2%, substantially outperforming k-nearest neighbors and support vector machines.
The ensemble hard voting classifier exceeded the performance of the best-performing individual model.
Feature importance evaluation identified chest pain type and exercise-induced angina as the two most critical clinical predictors of heart attack occurrence.

Structured PICO

Can machine learning models accurately predict the likelihood of a heart attack using clinical data?

Population

303 patients with 14 distinct clinical characteristics evaluated to predict the likelihood of a heart attack using machine learning models.

Exposure

Machine learning models (including XGBoost and an ensemble voting classifier) for predicting the likelihood of a heart attack

Comparator

Other machine learning models (logistic regression, decision trees, random forest, SVM, kNN, Naïve Bayes)

Outcome

Prediction accuracy

Machine learning models, particularly XGBoost and ensemble voting classifiers, can predict heart attacks with high accuracy based on clinical characteristics like chest pain type and exercise-induced angina.

Limitations

Need for bigger datasets
Need for more complete ensemble techniques and other characteristics
Small dataset (future efforts could use bigger datasets)

Authors

AHahmed hashim

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Should not guide clinical decisions; leaves open external validation in larger, prospective cohorts.

Cite This Study

ahmed hashim (2025) studied Heart attack (n=303). XGBoost and ensemble voting classifier vs. Other machine learning models (kNN, SVM, etc.) was evaluated on Prediction accuracy. An XGBoost machine learning model predicted the likelihood of a heart attack with 90.2% accuracy, outperforming kNN and SVM classifiers.

synapsesocial.com/papers/6ac2fd087180a622ddd4df5b https://doi.org/10.65204/djes.v2i2.88

Topics

Artificial intelligence in cardiology

View Full Paper

Ask AI

Bookmark

Predicting Heart Attacks using Machine Learning with Multiple Models and Hard Voting to Improve Accuracy

Key Points

Structured PICO

Limitations

Discussion

Implication

Cite This Study

Topics

Predicting Heart Attacks using Machine Learning with Multiple Models and Hard Voting to Improve Accuracy

Key Points

Structured PICO

Limitations

Discussion

Implication

Cite This Study

Also Consider

Topics

Also Consider