LIVER DISEASE PREDICTION USING MACHINE LEARNING

Liver disease is a major global health concern, with millions of people affected worldwide. Early diagnosis is crucial for effective treatment, yet it often remains challenging due to the lack of easily identifiable symptoms in the initial stages. This project aims to develop a machine learning (ML) model for predicting liver disease, using clinical and laboratory data such as age, gender, liver function test results, and other relevant health indicators. The dataset is preprocessed to handle missing values and normalize features. Various machine learning algorithms, including logistic regression, decision trees, random forest, and support vector machines, are employed to build predictive models. The performance of these models is evaluated using metrics like accuracy, precision, recall, F1-score, and ROC-AUC. The goal is to identify the most effective model for liver disease prediction, which could assist healthcare professionals in early diagnosis and decision-making. The study also explores feature importance to determine key indicators of liver disease.