Liver i-Biopsy and the Corresponding Intelligent Fibrosis Scoring Systems: i-Metavir F and i-Ishak F

摘要

An important goal of modern medicine is to replace invasive, painful procedures with non-invasive techniques for diagnosis. We investigated the possibility of a knowledge discovery in data approach, based on computational intelligence tools, to integrate information from various data sources - imaging data, clinical and laboratory data, to predict with acceptable accuracy the results of the biopsy. The resulted intelligent systems, tested on 700 patients with chronic hepatitis C, based on C5.0 decision trees and boosting, predict with 100% accuracy the fibrosis stage results of the liver biopsy, according to two largely accepted fibrosis scoring systems, Metavir and Ishak, with and without liver stiffness (FibroScan). We also introduced the concepts of intelligent virtual biopsy or i-Biopsy and that of i-scores. To our best knowledge i-Biopsy outperformed all similar systems published in the literature and offer a realistic opportunity to replace liver biopsy in many important medical contexts.