Optimized Hybrid CNN_BILSTM Approach for Accurate and Efficient Heart Disease Prediction

S PRABAKARAN; E KAVITHA; Anusha R

doi:10.36948/ijfmr.2025.v07i06.63798

Optimized Hybrid CNN_BILSTM Approach for Accurate and Efficient Heart Disease Prediction

Author(s)	Mr. S PRABAKARAN, Dr. E KAVITHA, Ms. Anusha R
Country	India
Abstract	Heart disease remains the leading cause of death worldwide, responsible for millions of fatalities each year. Early diagnosis is crucial to reduce mortality and improve patient outcomes. Traditional machine learning models such as Gaussian Naive Bayes have shown limited effectiveness in capturing the complex and nonlinear patterns inherent in medical datasets. To address these limitations, this study proposes an optimized hybrid deep learning model that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks for heart disease prediction. CNN layers are utilized for extracting spatial features from structured clinical data, while BiLSTM layers effectively capture temporal dependencies, enhancing the model's ability to learn complex relationships. The model is trained and evaluated on the widely used heart_statlog_cleveland_hungary_final.csv dataset, which includes multiple cardiovascular health indicators. Advanced preprocessing techniques and model optimizations such as batch normalization and dropout are employed to improve training efficiency and prevent overfitting. The proposed hybrid CNN-BiLSTM model achieved a classification accuracy of 93%, outperforming the baseline Gaussian Naive Bayes model by a significant margin. This study demonstrates that integrating spatial and sequential learning through hybrid deep learning architectures can offer robust and scalable solutions for early heart disease prediction in clinical applications.
Keywords	Keywords— Heart disease prediction, Convolutional Neural Network (CNN), Gaussian Naive Bayes (GNB), Deep learning, Medical diagnostics, Feature extraction, Hyperparameter optimization, Cardiovascular health, Model performance, Data preprocessing.
Field	Engineering
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-18
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.63798

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Optimized Hybrid CNN_BILSTM Approach for Accurate and Efficient Heart Disease Prediction

Share this