Related Experiment Video
Updated: Jun 22, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.8K
Enhanced cardiovascular disease prediction through self-improved Aquila optimized feature selection in quantum neural
Aman Darolia1, Rajender Singh Chhillar1, Musaed Alhussein2
1Department of Computer Science and Applications, M.D. University, Rohtak, Haryana, India.
Frontiers in Medicine
|July 5, 2024
Summary
This study introduces a novel hybrid model for predicting cardiovascular disease (CVD) with high accuracy. The model utilizes an optimized feature set and combines long short-term memory (LSTM) with a quantum neural network (QNN) for improved cardiovascular risk prediction.
Area of Science:
- Cardiovascular disease (CVD) research
- Healthcare data analysis
- Machine learning in medicine
Background:
- Cardiovascular disease (CVD) is a leading cause of global mortality.
- Effective data mining and prediction are crucial for healthcare decision-making.
- High dimensionality in medical datasets challenges traditional machine learning algorithms for CVD prediction.
Purpose of the Study:
- To develop a novel hybrid model for accurate cardiovascular disease (CVD) prediction.
- To address the challenge of high dimensionality in medical datasets through an optimal feature set.
- To enhance the precision and reliability of CVD risk assessment.
Main Methods:
- A four-stage process: preprocessing, feature extraction, feature selection (FS), and classification.
- Feature extraction using measures of central tendency, qualitative variation, dispersion, and symmetrical uncertainty.
- Optimized FS via the self-improved Aquila optimization approach.
- Hybrid classification model combining Long Short-Term Memory (LSTM) and Quantum Neural Network (QNN), with optimized LSTM weights.
Main Results:
- Dataset 1: Accuracy 96.69%, Sensitivity 96.62%, Specificity 96.77%.
- Dataset 2: Accuracy 95.54%, Sensitivity 95.86%, Specificity 94.51%.
- The hybrid model demonstrated superior performance in CVD prediction compared to existing methods.
Conclusions:
- The proposed hybrid model with an optimized feature set significantly improves cardiovascular disease prediction accuracy.
- The integration of LSTM and QNN frameworks, coupled with Aquila feature tuning, enhances predictive capabilities.
- This research highlights the potential of advanced computational tools in revolutionizing disease prediction and healthcare management.
