Truace
Subscribe

Enhancing Liver Cirrhosis Diagnosis Using Machine Learning With Explainable AI and Cross-Validated Hyperparameter Tuning Techniques

Cirrhosis is a form of Chronic Liver Disease (CLD) resulting from sustained liver damage from several causes, including viral infection, autoimmune disorders, cholestatic and metabolic disease Non-Alcoholic Fatty Liver Disease (NAFLD) or heavy alcohol use. Testing for the presence of Liver Cirrhosis (LC) is one of the most critical diagnostics and prognostic assessments for patients. Detecting liver illness in its early stages is challenging as initial symptoms are often mild and difficult to diagnose. Cirrhosis…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-1896· cite & verify
Enhancing Liver Cirrhosis Diagnosis Using Machine Learning With Explainable AI and Cross-Validated Hyperparameter Tuning Techniques
Doctor Wenlock outside St Thomas's Hospital - geograph.org.uk - 3101668 by PAUL FARMER. CC BY-SA 2.0 · https://creativecommons.org/licenses/by-sa/2.0

In brief

Researchers designed and tested a non-invasive diagnostic model for liver cirrhosis that combines an XGBoost classifier with explainable AI. They compared it against several other machine learning models and report that it performed best, reaching 91.19% on a cirrhosis dataset using ten-fold cross-validation.

Cirrhosis often stays silent until it is advanced, so earlier and more trustworthy detection could matter for patients. The explainability component targets clinician distrust of opaque models, but the abstract gives no detail on data source, external validation, or use in real clinical practice.

Main points

  1. The model combines an XGBoost classifier with an explainable AI framework for cirrhosis diagnosis.
  2. It was evaluated with 10-fold cross-validation and reached 91.19% on a cirrhosis dataset.
  3. The authors report it outperformed various other machine learning models.
  4. Explainability is meant to expose decision reasoning and thereby guide treatment strategies.

The gain

An XGBoost classifier paired with explainable AI diagnosed liver cirrhosis at 91.19% accuracy on a cirrhosis dataset under 10-fold cross-validation, and the explanations aim to make model decisions transparent to clinicians.

The rundown

Cirrhosis is a form of chronic liver disease caused by sustained liver damage from viral infection, autoimmune disorders, cholestatic and metabolic disease, non-alcoholic fatty liver disease, or heavy alcohol use. Early symptoms are often mild, so detection in the early stages is difficult.

The source argues that complex models lack explanations for their decisions, which creates clinician distrust. The study responds by adding explainable AI to make the reasoning behind predictions visible.

The proposed approach is described as non-invasive and was assessed against various machine learning models, with the authors reporting superior results.

Sources

  1. Peer-reviewedInternational Journal of Advanced Research in Science Communication and Technology2026-10-18

The debate