A Digital Twin Approach for deepened Classification of Patients with Hepatitis, Fibrosis and Cirrhosis

Abstract

With the advent of digital Healthcare system, the world has started to implement various technologies to promote better and quality healthcare solutions to the individuals, increase the life expectancy and reduce the healthcare cost. One among them, is the Digital Twin (DT) which takes the Digital healthcare to its next stage of providing patient tailored treatment to the people. Digital Twin (DT) is the concept of creating the replica of an existing process, workflow or an asset, which enables the data flow between the real component and its counterpart. Accordingly, a hepatitis infection level classifier was built with machine learning and deep learning algorithms to diagnose liver infection and classify the type of hepatitis infection. The implemented models successfully predicted the type of liver infection - hepatitis, fibrosis and cirrhosis with high accuracy. The Artificial Neural network (ANN) outperforms traditional machine learning algorithms in handling sample data related to liver infection. The predicted results have shown that integrating DT to the smart healthcare field would improve the healthcare procedures to provide specific patient tailored treatment and will bring together the patients and healthcare professionals to a smart and intelligent Health- Ecosystem.