Enhancing Arrhythmia Prediction using the Naked Mole Rat Algorithm and Machine Learning

An irregular heartbeat is known as cardiac arrhythmia. Cardiac arrhythmia occurs when electrical impulses that instruct the heart to beat malfunction. To save lives, arrhythmia must be detected early. Machine Learning (ML) is one of the fastest, cheapest, and easiest disease detection approaches. This study introduces an improved Naked Mole Rat Algorithm (RLNMRA) to select highly influential features in diagnosis and then uses various ML classifiers to train the model. The experimental results showed accuracies of 95.0%, 99.0%, 97.0%, 98.0%, 98.0%, 92.0%, and 99.0% with KNN, RF, GB, SVM, LR, DT, and GNB, classifiers, respectively. These results were obtained after removing invalid features from the UCI Arrhythmia dataset. The proposed method was also evaluated using recall, precision, and F score. The performance of the proposed model indicates that it can be used in various domains.