In this paper we present a methodology of classifying hepatic (liver) lesions
using multidimensional persistent homology, the matching metric (also called
the bottleneck distance), and a support vector machine. W
ML algorithms and machine learning optimization are used to evaluate different liver illness datasets and identify the most excellent categorization models by modifying hyperparameters such as Phosphotase, Direct Billirubin, Protiens, Albumin, and Albumin Globulin, essential for minimizing the cost function and visualizing the pattern.