Paper Contents
Abstract
Globally liver disease is a major health concern. Improving patient outcomes depends heavily on early identification. Create a predictive model that can help identify those who are risk of liver disease by using these algorithms. The dataset includes a range of clinical and laboratory indicators, including alkaline phosphates levels, age, gender, total and direct bilirubin levels, and more. The machine learning models are trained and tested using these features as inputs. Analysing the provided input parameters, the Nave Bayes algorithm determines a probability that a patient has liver disease. It does this by assuming that features are independent of one another. In contrast, Random Forest builds a collection of decision trees and aggregates their forecasts to provide a single prediction. Through the process of fitting data to a Naive Bayes and Random forest calculates the possibility that liver disease patients prediction .Several criteria are used to assess each algorithms performance, including accuracy, precision, recall. The outcomes of these assessments will be used to identify the best algorithm for hepatic disease prediction.
Copyright
Copyright © 2024 k.jenifer. This is an open access article distributed under the Creative Commons Attribution License.
