A Machine Learning Framework for Hepatic Health Analysis
Digital Transformation and Technology Dynamics · 17.11.2025 · 1
DOI: 10.69013/ys3539cj ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Transformation and Technology Dynamics, online erschienen am 17.11.2025. Verfasst von Md. Ashraful Islam Albi und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
Liver disease is among the leading contributors to global morbidity and mortality, and its early stages are frequently asymptomatic, so diagnosis often occurs only once damage is advanced. Confirmatory investigation still relies on imaging and biopsy, which are costly, invasive and scarce in low-resource settings, while routine biochemical panels require expert interpretation that is not uniformly available. This paper presents a machine learning framework for hepatic health analysis that classifies liver conditions from routine clinical and biochemical markers and, where hepatitis is indicated, resolves the case to a specific subtype. The study uses clinical and demographic data reportedly collected from multiple government and non-government hospitals and diagnostic centres. The dataset includes age, gender, total and direct bilirubin, alkaline phosphatase, AST (SGOT), ALT (SGPT), total proteins, albumin and the albumin-to-globulin ratio. A preprocessing pipeline covering missing-value imputation, outlier removal, categorical encoding and feature scaling reduced the dataset from approximately 30,000 records to approximately 20,000 analysable records. A clinically grounded rule set assigned each record to one of six classes—Hepatitis, Cirrhosis, Fatty Liver (NAFLD), Cholestasis, Healthy and Uncertain— and a second rule layer resolved hepatitis cases into Acute Viral (A/E), Chronic Hepatitis B, Hepatitis C, Alcoholic Hepatitis, Autoimmune Hepatitis and NASH. Random Forest, K-Nearest Neighbours, a Support Vector Classifier and a Voting ensemble were trained and compared using a stratified split. The Voting Classifier produced the highest and most balanced performance, with 99% accuracy, followed by K-Nearest Neighbours at 98% and Random Forest at 97%, while the Support Vector Classifier reached 65%. The resulting model was deployed as a Streamlit web application that returns a predicted disease class and, where applicable, a hepatitis subtype in real time, with input guidance for each condition. The paper also discusses the limitations affecting the interpretation of the reported results, particularly the dependence of the class labels on the same biochemical thresholds that the classifiers learn to reproduce.
Zitieren
APA
Albi, M. A. I., & Shishir, M. S. H. (2025). A Machine Learning Framework for Hepatic Health Analysis. Digital Transformation and Technology Dynamics, 1. https://doi.org/10.69013/ys3539cj
Vancouver
Albi MAI, Shishir MSH. A Machine Learning Framework for Hepatic Health Analysis. Digital Transformation and Technology Dynamics. 2025:1. doi:10.69013/ys3539cj
BibTeX
@article{Albi2025,
author = {Albi, Md. Ashraful Islam and Shishir, Md Shahadat Hossain},
title = {A Machine Learning Framework for Hepatic Health Analysis},
journal = {Digital Transformation and Technology Dynamics},
year = {2025},
pages = {1},
doi = {10.69013/ys3539cj}
}
EUVIMED