TalentBattle_Internship

Healthcare Analytics for liver disease prediction Chronic liver diseases, including cirrhosis, represent a significant healthcare challenge globally. Cirrhosis progression can lead to life-threatening complications, necessitating accurate predictive tools for early intervention. In this project, we employed machine learning techniques, specifically Logistic Regression, to develop a predictive model for cirrhosis progression. The dataset used comprises clinical and demographic attributes of patients collected from the Mayo Clinic trial in primary biliary cirrhosis (PBC) of the liver. Extensive data preprocessing, exploratory data analysis (EDA), model training, and evaluation were conducted. The Logistic Regression model exhibited promising accuracy in predicting cirrhosis progression, with detailed analysis revealing key contributing factors. This project underscores the potential of machine learning in healthcare for disease prognosis and personalized patient care strategies. Future work may involve incorporating additional data sources and advanced modelling techniques for enhanced predictive capabilities.