Stage Prediction of Liver Cirrhosis Disease using Machine Learning

Liver cirrhosis is a critical blood-borne disease that often remains asymptomatic in its early stages, complicating early diagnosis and treatment. As the disease progresses, diagnosing and managing it becomes increasingly challenging. This project aims to develop an artificial intelligence system utilizing machine learning algorithms to aid healthcare professionals in the early detection of liver cirrhosis. Specifically, the goal is to create a predictive system that can determine the stages of liver cirrhosis using machine learning techniques. The project will involve a comparative analysis of several established supervised learning models and ensemble learning techniques, including Support Vector Machine (SVM), Decision Tree Classifier, Random Forest Classifier, and Gradient Boosting Classifier. These models will be evaluated for their accuracy and precision. The dataset for this project consists of 418 records and 20 attributes. Key steps in the project include conducting exploratory data analysis, establishing baseline models, and evaluating them using hold-out validation and k-fold cross-validation. Feature engineering techniques will also be employed to enhance model accuracy. The most effective model will be selected and deployed as the final predictive system, which will be accessible through a web application developed with the Streamlit library.