Machine Learning Models to Classify Normal and Fibrotic Mouse Liver Model using Dielectric Properties

In this work dielectric permittivity was used to classify between normal and fibrotic mouse liver model. Data set was binary classified using six machine learning models i.e., Logistic Regression, Support vector classification, K-Nearest Neighbors Classifier, Decision Tree Classifier, Random Forest Classifier and Naive Bayes. Based on the accuracy and AUC score, K-Nearest Neighbors Classifier shows the best performance. This is a preliminary study to understand the feasibility of using electrical property such as complex permittivity as a biomarker to classify normal and fibrotic liver of diseased mouse model using machine learning models. The result of this work shows that the machine learning models can be used to distinguish between healthy and diseased liver with more than 80% accuracy. This technology shows immense possibility to expand in future to quantify disease severity and develop non-invasive diagnostic tools.