Hybrid Approach for Heart and Liver Disease Prediction

In the present day, machine learning is frequently used across several industries. Machine learning is utilized as an effective assisting mechanism in clinical diagnostics. Due to excessive alcohol intake, inhalation of poisonous gases, narcotics, contamination of meals, and a bad lifestyle, the incidence of liver and heart disease is increasing among individuals. Over the world, the highest death rate is noted by both liver and cardiac diseases. To save lives, it is essential to identify disorders as soon as possible. Healthcare organizations that implement machine learning classification algorithms see amazing results that improve the efficiency and accuracy of disease diagnosis. Tools and techniques for machine learning help to extract usable data from datasets, producing more precise results. In this study, a Random Walk grey wolf optimization model with the adaptive boosting (AB) approach is used to develop a hybrid model for the categorization of heart and liver data. The machine learning repository at UCI is where the datasets are sourced from. The outcomes are computed using metrics such as classification error rate, accuracy, recall, correctness, and F1 score. The results are compared to the Random Walk grey wolf optimization adaptive boosting algorithm (RWGWOAB).