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

Liver cirrhosis is a major health concern globally, often diagnosed at advanced stages due to the limitations of traditional diagnostic methods. This project proposes an automated approach using machine learning and Explainable AI (XAI) to enhance the diagnosis of liver cirrhosis stages. The system leverages multiple machine learning algorithms, including Logistic Regression, Random Forest, SVM, and Gradient Boosting, to classify cirrhosis stages based on clinical and laboratory data. Hyperparameter tuning and cross-validation techniques are applied to ensure optimal model performance. Additionally, the integration of Explainable AI methods ensures transparency and interpretability of the model's predictions, making it easier for healthcare professionals to understand the reasoning behind each diagnosis. The system provides a user-friendly interface where users can input clinical data, and the model predicts the cirrhosis stage along with an explanation for the prediction. The project aims to automate the process, reduce diagnostic errors, and assist healthcare professionals in making more informed decisions.

Keywords: liver cirrhosis, machine learning, Explainable AI, cross-validation, classification, prediction, clinical data, transparency, hyperparameter tuning, healthcare.