Mathematical Model Analysis for Liver Tumor Prediction

Human liver disease is a genetic problem caused by drinking too much alcohol or being infected by a virus. If not diagnosed in the early stages, it can lead to liver disease or cancer. This paper proposes a method for predicting the likelihood of a patient developing a certain illness in the future. The decision is based on comparative evidence available and the assumption that all other physical parameters remain unchanged. Despite the fact that technical advancements have resulted in the collection of data pertaining to patients with various disease states, assessing the prediction efficiency of machine learning algorithms is a crucial step. Many real-world databases, including liver disease diagnosis data, have a problem with class imbalance. The fundamental essence of the parameters is perceived by the diversity in the core propensity of the attributes. To catch the random trends of the attributes, the prediction model is formulated using the Brownian motion framework. The contribution of the key blood attributes in liver disease is demonstrated using Spearman's correlation coefficient, which examines the correlation between different blood parameters and the result, is improved. This paper discusses about the statistical methods used to forecast liver tumor.