Liver Disease Prediction And Classification Using Machine Learning Techniques
DOI:
https://doi.org/10.62647/Keywords:
Liver Diseases, Machine Learning, Decision trees, Support Vector Machines (SVMs), Random Forests, Gradient enhancements, Neural Networks, PCA, ROC, Confusion Matrix, Deep Learning and Hybrid models.Abstract
Liver diseases remains global health
challenge that requires early detection and
precise classification for effective
management and treatment. Machine
learning (ML) technology is a powerful tool in
healthcare, offering innovative solutions for
predictive analysis and diagnostic accuracy.
This paper focuses on the use of machine
learning algorithms for predicting and
classifying liver diseases. Using a variety of
data sets involving clinical and biochemical
parameters, different ML models – such as
decision trees, support vector machines
(SVMs), random forests, gradient
enhancements, and neural networks – are
applied and evaluated. The key steps include
data preprocessing, model selection and
optimization to improve predictive accuracy
and robustness. Techniques such as Principal
Component Analysis (PCA) are used to
reduce dimensions, while high-parameter
adjustments optimize model performance.
Evaluation metrics, including accuracy,
precision, recall, F1 score, and region under
the Receiver Operating Characteristic Curve
(AUC-ROC), provide a comprehensive
assessment of models. The study highlights
the importance of the analysis of the
importance of features to identify the key
factors that influence the onset and
progression of liver disease. Comparative
analysis reveals the strengths and limitations
of each algorithm in handling unbalanced
data sets and different clinical scenarios. The
results highlight the potential of machine
learning as a decision support tool in the
management of liver diseases, opening the
way for personalized medicine and improved
patient outcomes. Future work will integrate
advanced techniques such as deep learning
and hybrid models to further improve
diagnostic capabilities and enable real-time
application in clinical settings.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Author

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.