Related Experiment Video
Updated: Aug 16, 2025
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
Published on: February 21, 2025
Feature Selection and Dwarf Mongoose Optimization Enabled Deep Learning for Heart Disease Detection
S Balasubramaniam1, K Satheesh Kumar1, V Kavitha2
1Department of Futures Studies, University of Kerala, Thiruvananthapuram, Kerala, India.
Insights
This study introduces a hybrid method for accurate heart disease prediction, improving detection rates using optimized deep learning models and novel feature selection techniques for better patient outcomes.
Area of Science:
- Medical Data Analysis
- Machine Learning Applications
- Cardiovascular Health
Background:
- Heart disease remains a leading global cause of mortality.
- Effective heart disease prediction is crucial for timely medical intervention.
- Current data mining and machine learning methods show limitations due to insufficient test data.
Purpose of the Study:
- To enhance the efficacy of heart disease detection performance.
- To introduce a novel hybrid feature selection method for improved accuracy.
- To develop an optimized deep learning model for precise prediction.
Main Methods:
- Data preprocessing involved quantile normalization and missing data imputation.
- A hybrid feature selection approach using Congruence coefficient Kumar-Hassebrook similarity was employed.
- Heart disease prediction was performed using SqueezeNet optimized by the dwarf mongoose optimization algorithm (DMOA).
Main Results:
- The DMOA-SqueezeNet model achieved high performance metrics.
- Maximum accuracy reached 0.925.
- Sensitivity and specificity were recorded at 0.926 and 0.918, respectively.
Conclusions:
- The proposed hybrid feature selection and DMOA-SqueezeNet model significantly improve heart disease prediction accuracy.
- This approach addresses limitations of existing methods by enhancing data quality and model optimization.
- The findings suggest a promising direction for developing more effective tools in cardiovascular health management.
Abstract:
Heart disease causes major death across the entire globe. Hence, heart disease prediction is a vital part of medical data analysis. Recently, various data mining and machine learning practices have been utilized to detect heart disease. However, these techniques are inadequate for effectual heart disease prediction due to the deficient test data. In order to progress the efficacy of detection performance, this research introduces the hybrid feature selection method for selecting the best features. Moreover, the missed value from the input data is filled with the quantile normalization and missing data imputation method. In addition, the best features relevant to disease detection are selected through the proposed hybrid Congruence coefficient Kumar-Hassebrook similarity. In addition, heart disease is predicted using SqueezeNet, which is tuned by the dwarf mongoose optimization algorithm (DMOA) that adapts the feeding aspects of dwarf mongoose. Moreover, the experimental result reveals that the DMOA-SqueezeNet method attained a maximum accuracy of 0.925, sensitivity of 0.926, and specificity of 0.918.
