A Statistical Method for Prediction of Liver Disease based on the Brownian Motion Model

A prediction method is proposed in this paper to anticipate the probability of a patient to have a particular disease in the future. The decision is based on the available statistical data assuming that all the other physical conditions remain unaltered. As the case study, variation in the different parameters of the Liver Function Test (LFT) is studied respect to the patient's age. The diversity in the central tendency of the attributes is considered to perceive the underlying nature of the parameters. The prediction model is formulated based on the Brownian motion concept to capture the random patterns of the attributes. Correlation between different blood parameters is examined using Spearman's correlation coefficient to exhibit the contribution of the key blood attributes in liver disease. Our method produces better accuracy, sensitivity, and specificity over other state-of-the-art prediction techniques. The satisfactory inquisitive results of our approach would definitely inspire the researchers of interdisciplinary areas.