Volume 15, Issue 7 · IJARST · ISSN 2319-1783 / 2320-1126

A Prognostic and Scalable Liver Disease Prediction System Using Ensemble Machine Learning and Cloud–Edge Computing

A Prognostic and Scalable Liver Disease Prediction System Using Ensemble Machine Learning and Cloud–Edge Computing is an open-access, peer-reviewed research paper by Anuj Garg, Vishwa Gupta, published in Volume 15, Issue 7 of the International Journal of Advanced Research in Science and Technology (IJARST), a UGC-approved journal (Print ISSN 2319-1783, Online ISSN 2320-1126).

Author

Anuj Garg, Vishwa Gupta

Abstract

Chronic liver disease often progresses without noticeable symptoms, making early diagnosis difficult and increasing the risk of severe hepatic damage. Therefore, the development of an accurate and scalable prediction system is essential for timely clinical intervention. This paper proposes a prognostic liver disease prediction framework based on structured clinical biomarkers integrated with a cloud–edge computing architecture for efficient and real-time healthcare support. Experiments were conducted using the publicly available Liver Disease Patient Dataset (LPD) containing 30,691 patient records with ten demographic and biochemical attributes. The data preprocessing pipeline included missing-value removal, label encoding, stratified 80/20 train–test splitting, feature scaling using StandardScaler, and class imbalance handling through SMOTEENN to improve model robustness. Four supervised machine learning algorithms — XGBoost, Gradient Boosting, Random Forest, and Multi-Layer Perceptron (MLP) — were comparatively evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. Among the evaluated models, Random Forest achieved the best performance with an accuracy of 99.94%, an F1-score of 99.90%, and an ROC-AUC of 1.000, while maintaining a recall above 99%, which is particularly important for minimizing missed liver disease cases. In addition, a cloud–edge deployment framework is proposed to support low-latency inference at healthcare facilities while enabling centralized model training and analytics in the cloud. The study also acknowledges dataset limitations, including duplicate records, to ensure transparent interpretation of the reported results. The proposed framework demonstrates the potential of ensemble machine learning for accurate, scalable, and clinically applicable liver disease prediction.

Keywords: Liver disease prediction, Ensemble Machine Learning, Random Forest, XGBoost, SMOTEENN, Cloud–Edge Computing, Clinical Decision Support, Healthcare Analytics.

DOI: https://doi.org/10.62226/ijarst20262741

DOI

https://doi.org/10.62226/ijarst20262741

PAGES : 2322-2328 | 6 VIEWS | 2 DOWNLOADS

How do you cite this paper?

Anuj Garg, Vishwa Gupta — “A Prognostic and Scalable Liver Disease Prediction System Using Ensemble Machine Learning and Cloud–Edge Computing.” International Journal of Advanced Research in Science and Technology (IJARST), Volume 15, Issue 7. DOI: https://doi.org/10.62226/ijarst20262741.

Download Full Article