The coexistence of liver diseases poses significant clinical challenges, requiring effective predictive models for early detection and intervention. In this study, we employed decision tree and logistic regression algorithms to predict the likelihood of liver disease in individuals diagnosed . Distinct datasets were utilized, for liver disease prediction, containing relevant clinical attributes. Through rigorous experimentation and evaluation, our models demonstrated promising performance in identifying the presence of liver disease in individuals.

scikit-learn, GridSearchCV, preprocessing, model_selection, metrics, imblearn, pandas, numpy

Logistic Regression, Decision Tree classifier, Random forest classifier