# Assisting the Diagnosis of Cirrhosis in Chronic Hepatitis C Patients Based on Machine Learning Algorithms: A Novel Non‐Invasive Approach

## TL;DR

This study uses machine learning to accurately detect cirrhosis in hepatitis C patients using routine lab tests, identifying key features and thresholds for non-invasive diagnosis.

## Contribution

A novel non-invasive machine learning approach for cirrhosis detection using routine lab data and determining cut-off values for key features.

## Key findings

- Random Forest achieved 89% accuracy in predicting cirrhosis using lab test data.
- Platelet, AFP, age, GGT, and PT were identified as the most important features for cirrhosis classification.
- Cut-off values for these features were determined, offering actionable thresholds for clinical use.

## Abstract

This study aimed to determine the important features and cut‐off values after demonstrating the detectability of cirrhosis using routine laboratory test results of chronic hepatitis C (CHC) patients in machine learning (ML) algorithms.

This retrospective multicenter (37 referral centers) study included the data obtained from the Hepatitis C Turkey registry of 1164 patients with biopsy‐proven CHC. Three different ML algorithms were used to classify the presence/absence of cirrhosis with the determined features.

The highest performance in the prediction of cirrhosis (Accuracy = 0.89, AUC = 0.87) was obtained from the Random Forest (RF) method. The five most important features that contributed to the classification were platelet, αlpha‐feto protein (AFP), age, gamma‐glutamyl transferase (GGT), and prothrombin time (PT). The cut‐off values of these features were obtained as platelet < 182.000/mm3, AFP > 5.49 ng/mL, age > 52 years, GGT > 39.9 U/L, and PT > 12.35 s. Using cut‐off values, the risk coefficients were AOR = 4.82 for platelet, AOR = 3.49 for AFP, AOR = 4.32 for age, AOR = 3.04 for GGT, and AOR = 2.20 for PT.

These findings indicated that the RF‐based ML algorithm could classify cirrhosis with high accuracy. Thus, crucial features and cut‐off values for physicians in the detection of cirrhosis were determined. In addition, although AFP is not included in non‐invasive indexes, it had a remarkable contribution in predicting cirrhosis.

Clinicaltrials.gov identifier: NCT03145844

Using the results of routine laboratory tests, it was proved by machine learning that cirrhosis can be diagnosed at a high rate. Threshold values were determined for the diagnosis of cirrhosis.