Enhancing Early Detection of Liver Disease Through a Meta-Learning Approach Using Super Learner and Model Interpretability

DOI

10.2991/978-94-6239-693-7_15How to use a DOI?

Keywords

Liver disease; Super Learner; Logistic Regression; Decision Trees; Random Forests; Support Vector Machines (SVM); Gradient Boosting Machines (GBM); Meta-Learner; Explainable AI (XAI); SHAP; LIME; Machine Learning; Predictive Modeling

Abstract

Liver disease is currently a significant societal health issue in many countries around the world, and the causative factors include alcohol abuse, food poisoning, drugs, and environmental pollution. This needs to be identified early and handled effectively to slow down the progression of the disease and burden the health care system. In this paper, a predictive model is proposed to classify liver disease with the use of the Super Learner ensemble method which is a combination of Logistic Regression, Decision Trees, Random Forest, Support Vector Machines (SVM), and Gradient Boosting Machines (GBM) with a Logistic Regression Meta-Learner. This is the best combination strategy that incorporates the forecasts of these models in order to increase accuracy and generalization. In order to enhance transparency, the model uses the Explainable AI (XAI) methods, such as SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-agnostic Explanations), to help healthcare professionals better understand the predictions. The approaches assist in determining the most powerful features and thus offer an insight that can be used to make informed clinical decisions as far as liver disease diagnosis is concerned. The proposed model has a high potential in the healthcare sector in terms of early detection and helping to make clinical decisions.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Madherla Shiva Prasad
AU  - Shiva Alaparathi
AU  - D. Aishwarya
PY  - 2026
DA  - 2026/06/16
TI  - Enhancing Early Detection of Liver Disease Through a Meta-Learning Approach Using Super Learner and Model Interpretability
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 126
EP  - 137
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_15
DO  - 10.2991/978-94-6239-693-7_15
ID  - Prasad2026
ER  -