Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease Detection
Early and accurate detection of liver disease is critical to improving patient outcomes yet remains challenging due to class imbalance and noisy clinical data. In this study, we present a robust ensemble learning framework applied to the Indian Liver Patient Dataset, incorporating systematic data c...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Al-Iraqia University - College of Engineering
2025-06-01
|
| Series: | Al-Iraqia Journal for Scientific Engineering Research |
| Subjects: | |
| Online Access: | https://ijser.aliraqia.edu.iq/index.php/ijser/article/view/314 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850157062503268352 |
|---|---|
| author | Abdulrahman Ahmed Jasim Hajer Alwindawi Layth Rafea Hazim |
| author_facet | Abdulrahman Ahmed Jasim Hajer Alwindawi Layth Rafea Hazim |
| author_sort | Abdulrahman Ahmed Jasim |
| collection | DOAJ |
| description |
Early and accurate detection of liver disease is critical to improving patient outcomes yet remains challenging due to class imbalance and noisy clinical data. In this study, we present a robust ensemble learning framework applied to the Indian Liver Patient Dataset, incorporating systematic data cleaning, normalization, and Synthetic Minority Over‑Sampling (SMOTE) to address missing values, outliers, and class skew. We then perform correlation-based feature reduction before training a stacking classifier that combines Random Forest, XGBoost, and ExtraTrees base learners with an ExtraTrees meta‑learner. Using stratified 10‑fold cross‑validation on the balanced cohort (n = 792), our ensemble achieves 91.6 % accuracy, 92 % F1‑score, and a high area under the ROC curve, outperforming individual models and prior published approaches. These results demonstrate the potential of heterogeneous ensembles for clinical decision support in hepatology and lay the groundwork for prospective validation in diverse patient populations.
|
| format | Article |
| id | doaj-art-c70402e5f0da4d4f8932c19e914222a8 |
| institution | OA Journals |
| issn | 2710-2165 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Al-Iraqia University - College of Engineering |
| record_format | Article |
| series | Al-Iraqia Journal for Scientific Engineering Research |
| spelling | doaj-art-c70402e5f0da4d4f8932c19e914222a82025-08-20T02:24:17ZengAl-Iraqia University - College of EngineeringAl-Iraqia Journal for Scientific Engineering Research2710-21652025-06-014210.58564/IJSER.4.2.2025.314Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease DetectionAbdulrahman Ahmed Jasim0Hajer Alwindawi1Layth Rafea Hazim2Dept. of Electrical and Computer Engineering, Altinbas University, Istanbul, TurkeyDept. of Artificial Intelligence Engineering, Bahçeşehir University, Istanbul, TurkeyDept. of Electrical and Computer Engineering, Altinbas University, Istanbul, Turkey Early and accurate detection of liver disease is critical to improving patient outcomes yet remains challenging due to class imbalance and noisy clinical data. In this study, we present a robust ensemble learning framework applied to the Indian Liver Patient Dataset, incorporating systematic data cleaning, normalization, and Synthetic Minority Over‑Sampling (SMOTE) to address missing values, outliers, and class skew. We then perform correlation-based feature reduction before training a stacking classifier that combines Random Forest, XGBoost, and ExtraTrees base learners with an ExtraTrees meta‑learner. Using stratified 10‑fold cross‑validation on the balanced cohort (n = 792), our ensemble achieves 91.6 % accuracy, 92 % F1‑score, and a high area under the ROC curve, outperforming individual models and prior published approaches. These results demonstrate the potential of heterogeneous ensembles for clinical decision support in hepatology and lay the groundwork for prospective validation in diverse patient populations. https://ijser.aliraqia.edu.iq/index.php/ijser/article/view/314Telemedicine, Artificial Intelligence (AI), Machine Learning, Stacking Classifier, Liver Diseases |
| spellingShingle | Abdulrahman Ahmed Jasim Hajer Alwindawi Layth Rafea Hazim Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease Detection Al-Iraqia Journal for Scientific Engineering Research Telemedicine, Artificial Intelligence (AI), Machine Learning, Stacking Classifier, Liver Diseases |
| title | Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease Detection |
| title_full | Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease Detection |
| title_fullStr | Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease Detection |
| title_full_unstemmed | Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease Detection |
| title_short | Empowering Diagnostics: An Ensemble Machine Learning Model for Early Liver Disease Detection |
| title_sort | empowering diagnostics an ensemble machine learning model for early liver disease detection |
| topic | Telemedicine, Artificial Intelligence (AI), Machine Learning, Stacking Classifier, Liver Diseases |
| url | https://ijser.aliraqia.edu.iq/index.php/ijser/article/view/314 |
| work_keys_str_mv | AT abdulrahmanahmedjasim empoweringdiagnosticsanensemblemachinelearningmodelforearlyliverdiseasedetection AT hajeralwindawi empoweringdiagnosticsanensemblemachinelearningmodelforearlyliverdiseasedetection AT laythrafeahazim empoweringdiagnosticsanensemblemachinelearningmodelforearlyliverdiseasedetection |