Abstract: It is critical to diagnose liver illness early on in order to receive the best therapy possible. Machine learning algorithms is growing rapidly such as SVM, K-mean clustering, KNN, Random Forest, Logistic regression, and others. The input is usually numerical data of various factors, and the output findings are obtained in real-time, predicting whether or not the patient has a liver problem. In this project, used a variety of supervised machine-learning methods before deciding which one is best for the model. Existing systems rely on classical deep learning models, which are inefficient and imprecise. They aren't precise enough. This proposing model is to use classification algorithms to identify liver patients from healthy individuals. Here, we choose the algorithm in this module that serves as the best fit. The dataset is taken from the Kaggle dataset. The advantages of the proposed model are that it shows high accuracy, is fast processing and is highly scalable. With the effective use of the presented model, practitioners can make intelligent clinical decisions.
Keywords: Bivariate analysis, correlating columns, MSE Loss Function, Removing Null values, Replacing Non-acceptable zero values, Univariate analysis
|
DOI:
10.17148/IJARCCE.2023.125125
