Liver Disease Classification Using Decision Tree and Random Forest Algorithms

Abstract

Diagnosing diseases using technology is no longer uncommon. With advancements in healthcare technology, decision-making, particularly in detecting liver diseases, has become more efficient. Liver, an essential human organ, sees its functionality decline in patients with liver diseases. According to WHO data (2013), 28 million individuals in Indonesia suffer from liver diseases, marking it as one of the ten deadliest diseases. Early detection is crucial for effective treatment. This study aims to predict liver diseases using the Random Forest algorithm. Feature selection and classifier choice are pivotal for improving accuracy and computational efficiency. Using the Liver Disease Patient Dataset, the study involved data analysis, preprocessing, algorithm modeling, and visualization. Results show the Random Forest algorithm achieved an accuracy of 0.713326 with an F1 score of 81%