Cirrhosis Patient Survival Prediction Analysis Using ML Algorithms

This research aims to produce accurate and clinically applicable pre dictions of life expectancy for cirrhosis patients, leveraging sophisticated computer algorithms such as logistic regression, random tree regression analysis, decision tree classifier, and support vector machine (SVM). Seventeen different aspects of patient data, including age, test results, and various health indicators, are considered in our approach. The central objective is to train these algorithms to discern patterns from the provided data, aiming to enhance the understanding of the complexity of liver cirrhosis. The ultimate goal is to improve the accuracy of predicting whether a patient will survive. By concentrating on straightforward and easily interpretable attributes, we aim to develop predictions that are practical for healthcare professionals. The analysis entails a thorough comparison of four algorithms, focusing on their performance metrics, specifically accuracy and reliability, in predicting the survival of cirrhosis patients. The aim is to identify the most effective algorithms as crucial tools for healthcare providers. These tools empower professionals to make well-informed decisions regarding patient care, addressing the complexity of cirrhosis. The research offers healthcare professionals a potent and accessible method for predicting patient survival, ultimately influencing patient outcomes and optimizing care strategies. This investigation contributes valuable insights into the field, providing a robust framework for improving patient care and outcomes in the context of liver cirrhosis.