Liver cirrhosis prediction using logistic regression, naïve bayes and KNN

Liver cirrhosis, often a symptomless blood-borne disease in its early stages, presents significant diagnostic and treatment challenges. As the disease advances, these difficulties only increase. This study introduces an artificial intelligence system based on machine learning to aid healthcare providers in the early detection of liver cirrhosis. With this aim, three distinct predictive models have been developed using a variety of physiological metrics and machine learning techniques including Logistic Regression (LR), Naïve Bayes and KNN Classification. Among these, LR emerges as the most effective, achieving an accuracy of approximately 85%. The models are developed using the openly accessible Liver Cirrhosis data dataset.