Advanced Heart Attack Risk Prediction Using a Stacked Hybrid Machine Learning Approach

Q: What is the clinical evidence from this study?

Population: Heart disease (n=303). Intervention: Stacked Hybrid Machine Learning Model. Primary outcome: Prediction accuracy.

Q: What does this research mean for the field?

A stacked hybrid machine learning model combining Random Forest, Support Vector Machine, and Gradient Boosting with Logistic Regression achieves 81.67% accuracy in predicting heart disease risk from clinical attributes. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Siva Sankara PhaniTammireddy; KanchustambhamSupriya Ambika; Yadlapalli Hema; Pilla Naga Adinarayana; Akula Venkata Mani Subrahamanyam

doi:10.69996/fmep.2026009

March 31, 2026Journals Fringe Multi-Engineering ProceedingsOpen Access

Advanced Heart Attack Risk Prediction Using a Stacked Hybrid Machine Learning Approach

View Full Paper

Ask AI

Bookmark

Share

Key result

Stacked hybrid machine learning model predicts heart disease with ~82% accuracy.

n=303

Why the study?

Heart disease remains a leading cause of mortality worldwide, and timely prediction can significantly reduce fatal outcomes through early detection and risk assessment.

Can a stacked hybrid machine learning approach accurately predict heart attack risk using standard clinical parameters?

Key Points

To design and implement a stacked hybrid machine learning model for accurate early detection of heart attack risk and cardiovascular disease assessment.
Evaluated on the UCI Cleveland Heart Disease dataset comprising N=303 patient records across 14 attributes (13 clinical input features including age, blood pressure, cholesterol, and heart rate).
Applied preprocessing with data normalization (scaled between 0–1) and split the data into 80% training and 20% testing sets.
Implemented a stacked hybrid architecture combining Random Forest, Support Vector Machine, and Gradient Boosting as base models, feeding into a Logistic Regression meta-model with LASSO regularization.
The stacked hybrid model yielded confusion matrix values of True Positive = 120, True Negative = 128, False Positive = 25, and False Negative = 30 across the 303 samples.
Achieved an overall prediction accuracy of 81.67% for determining the presence or absence of heart disease.
Demonstrated a precision of 82.7%, correctly identifying heart disease cases over four-fifths of the time while delivering automated feature-based health suggestions.

Structured PICO

Can a stacked hybrid machine learning approach accurately predict heart attack risk using standard clinical parameters?

P

Population

303 patient records from the Cleveland Heart Disease dataset were analyzed to train and evaluate a hybrid machine learning model for heart attack prediction.

I

Intervention

Stacked hybrid machine learning approach combining Logistic Regression, Random Forest, Support Vector Machine (SVM), and Gradient Boosting.

C

Comparator

Base machine learning models evaluated individually (Logistic Regression, Random Forest, SVM, Gradient Boosting).

O

Outcome

Accuracy in predicting the presence or absence of heart disease.

Implication

A stacked hybrid machine learning architecture combining multiple algorithms can predict the presence of heart disease with 81.67% accuracy based on basic clinical parameters.

Abstract

This paper presents the design and implementation of a Heart Attack Prediction System using Machine learning techniques, aimed at improving early detection and risk assessment of cardiovascular diseases. Heart disease remains one of the leading causes of mortality worldwide, and timely prediction can significantly reduce fatal outcomes. The proposed system utilizes patient medical parameters such as age, blood pressure, cholesterol levels, heart rate, and other clinical attributes to predict the likelihood of a heart attack. A hybrid machine learning approach is employed, combining algorithms such as Logistic Regression, Random Forest, Support Vector Machine (SVM), and Gradient Boosting to achieve high prediction accuracy. In addition to prediction, the system provides personalized health suggestions based on input features, making it a decision-support and preventive healthcare tool. Experimental results demonstrate improved prediction performance and actionable insights for users.

Discussion

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

Cite This Study

PhaniTammireddy et al. (2026) studied Heart disease (n=303). Stacked Hybrid Machine Learning Model was evaluated on Prediction accuracy. A stacked hybrid machine learning model combining multiple algorithms achieved an overall accuracy of 81.67% and an area under the curve of 0.87 for predicting heart disease.

synapsesocial.com/papers/6ad0fc963afa093ea9acfe92 https://doi.org/10.69996/fmep.2026009

Topics

Artificial intelligence in cardiology

View Full Paper

Ask AI

Bookmark

Share

Advanced Heart Attack Risk Prediction Using a Stacked Hybrid Machine Learning Approach

Key Points

Structured PICO

Implication

Abstract

Discussion

Cite This Study

Topics

Advanced Heart Attack Risk Prediction Using a Stacked Hybrid Machine Learning Approach

Key Points

Structured PICO

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

More on Artificial intelligence in cardiology

Topics

Keep reading

More related papers

More on Artificial intelligence in cardiology