Multiclass Classification of Nonalcoholic Steatohepatitis Mouse Models Using Dielectric Properties as Disease Biomarker

Non-Alcoholic Steatohepatitis (NASH) is known as the key cause of cirrhosis in adults. As the name suggests, NASH is described as the excessive fat accumulation in the nonalcoholics. The genomic components play a vital role in the development and progression of the NASH. The existing imaging modalities have limited use in the diagnosis of NASH leading to delayed presentation of the disease. Owing to this, risk of hepatocellular carcinoma and the need for liver transplant is on a rising trend in patients with NASH. Even with the advent of new diagnostic techniques, biopsy is still considered the fundamental tool for confirming NASH. However, due to the highly invasive nature of the biopsy, its broad application becomes very difficult. Therefore, it is important to validate a tool which will identify the detection and progression of steatohepatitis and help in the timely diagnosis of the disease. Dielectric spectroscopy can be used to measure the dielectric properties of the tissue as a function of the frequency. This work introduces a feasibility study to classify between murine healthy liver and liver affected by two types of diets including nonalcoholic steatohepatitis using dielectric property of liver tissue as a biomarker. Multiclass classification using different machine learning models is performed. Among them, K-Nearest Neighbors Classifier and Random Forest Classifier showed good accuracy i.e., 89% and 90% respectively.