Heart disease diagnosis using optimized features of hybridized ALCSOGA algorithm and LSTM classifier

Area of Science:

• Cardiology
• Artificial Intelligence
• Computational Biology

Background:

• Cardiac disease is a leading global cause of mortality, often diagnosed late due to subtle symptoms.
• Existing heart disease prediction methods lack sufficient accuracy, necessitating improved diagnostic tools.

Purpose of the Study:

• To develop an advanced hybrid optimization algorithm for effective feature selection in heart disease prediction.
• To enhance the accuracy and reliability of early heart disease detection using machine learning.

Main Methods:

• A hybridized Ant Lion Crow Search Optimization Genetic Algorithm (ALCSOGA) was developed for feature selection.
• Stochastic Learning rate optimized Long Short Term Memory (LSTM) was employed for classification of optimized features.
• Comparative analysis included accuracy, recall, F1-score, precision, and statistical metrics (SS, df, F crit, F, p, MS).

Main Results:

• The proposed ALCSOGA method demonstrated superior performance in feature selection for heart disease prediction.
• The LSTM classifier achieved high accuracy in identifying cardiac disease based on optimized features.
• Statistical analysis confirmed the significant efficiency of the proposed system over conventional approaches.

Conclusions:

• The hybridized ALCSOGA and LSTM model offers a highly efficient and accurate system for early heart disease prediction.
• This approach holds significant potential for improving patient outcomes by enabling timely diagnosis and intervention.
• Further research can explore the integration of this model into clinical decision-support systems.