Stacking Ensemble Learning Approach for Non-Alcoholic Fatty Liver Disease Identification: Leveraging Explainable Machine Learning for Enhanced Prediction Models
,
Abstract
Purpose: The prevalence of Non-Alcoholic Fatty Liver Disease (NAFLD) has significantly increased over the past two decades, becoming a leading cause of liver disease in industrialized nations, particularly among individuals who do not consume alcohol. This study aims to develop an efficient detection method for NAFLD using a stacked ensemble learning approach, which integrates multiple machine learning models to enhance predictive accuracy.
Materials and Methods: The dataset utilized in this research was sourced from an open platform and includes critical attributes such as age, gender, Body Mass Index (BMI), height, time to death or last follow-up, and survival status. We implemented a variety of machine learning algorithms, including XGBoost, CatBoost, Decision Trees, and AdaBoost, within a stacking framework to optimize performance. The proposed methodology involved several steps: data preparation, feature engineering, model training, and evaluation. Additionally, we employed explainable AI techniques to identify the most influential features contributing to NAFLD prediction, thereby enhancing the model's interpretability.
Results: The stacked ensemble model achieved an impressive classification accuracy of 95.9%, outperforming individual models and demonstrating the robustness of the ensemble approach. Confusion Metrics, ROC curves, and Calibration Curves are used to evaluate the proposed approach with state-of-the-art approaches. The suggested stacking methodology demonstrates superior performance in all contexts. When Explainable Machine Learning is applied to the proposed approach, it reveals that NAFLD is more common in middle-aged and elderly individuals, but is also present in younger age groups to some extent. Also, the prevalence of NAFLD is higher in males.
Conclusion: The results underscore the potential of a stacked ensemble approach for clinical applications in NAFLD screening and diagnosis, highlighting its importance in healthcare decision-making. By combining various machine learning techniques, we have developed a reliable and resilient model that improves detection accuracy and offers transparency in its predictions. Combining XGBoost, CatBoost, Decision Tree, and AdaBoost in a stacked ensemble model yielded the best results. The findings also indicate that age and gender are significant predictors of NAFLD, with the model providing valuable insights into the underlying patterns associated with the disease. This research contributes to the growing body of knowledge on machine learning applications in gastroenterology and emphasizes the need for explainable models in clinical settings.
2-J. M. Paik, L. Henry, Y. Younossi, J. Ong, S. Alqahtani, and Z. M. Younossi, “The burden of nonalcoholic fatty liver disease (NAFLD) is rapidly growing in every region of the world from1990 to 2019,” Hepatol Commun, vol. 7, no. 10, Oct. 2023, doi: 10.1097/HC9.0000000000000251.
3-K. Riazi et al., “The prevalence and incidence of NAFLD worldwide: a systematic review and meta-analysis,” Lancet Gastroenterol Hepatol, vol. 7, no. 9, pp. 851–861, Sep. 2022, doi: 10.1016/S2468-1253(22)00165-0.
4-X. Zhu et al., “Presence of sarcopenia identifies a special group of lean NAFLD in middle-aged and older people,” Hepatol Int, vol. 17, no. 2, pp. 313–325, Apr. 2023, doi: 10.1007/S12072-022-10439-Z/METRICS.
5-V. W. S. Wong, M. Ekstedt, G. L. H. Wong, and H. Hagström, “Changing epidemiology, global trends and implications for outcomes of NAFLD,” J Hepatol, vol. 79, no. 3, pp. 842–852, Sep. 2023, doi: 10.1016/J.JHEP.2023.04.036.
6-F. Radu, C. G. Potcovaru, T. Salmen, P. V. Filip, C. Pop, and C. Fierbințeanu-Braticievici, “The Link between NAFLD and Metabolic Syndrome,” Diagnostics 2023, Vol. 13, Page 614, vol. 13, no. 4, p. 614, Feb. 2023, doi: 10.3390/DIAGNOSTICS13040614.
7-A. Bianco et al., “Diet and Exercise Exert a Differential Effect on Glucose Metabolism Markers According to the Degree of NAFLD Severity,” Nutrients 2023, Vol. 15, Page 2252, vol. 15, no. 10, p. 2252, May 2023, doi: 10.3390/NU15102252.
8-N. Ujjwal, A. Singh, A. K. Jain, and R. G. Tiwari, “Exploiting Machine Learning for Lumpy Skin Disease Occurrence Detection,” 2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2022, 2022, doi: 10.1109/ICRITO56286.2022.9964656.
9-R. G. Tiwari, S. K. Yadav, A. Misra, and A. Sharma, “Classification of Swarm Collective Motion Using Machine Learning,” Smart Innovation, Systems and Technologies, vol. 316, pp. 173–181, 2023, doi: 10.1007/978-981-19-5403-0_14/COVER.
10-N. K. Trivedi, R. G. Tiwari, A. K. Agarwal, and V. Gautam, “A Detailed Investigation and Analysis of Using Machine Learning Techniques for Thyroid Diagnosis,” 2023 International Conference on Emerging Smart Computing and Informatics, ESCI 2023, 2023, doi: 10.1109/ESCI56872.2023.10099542.
11-V. Khullar, R. G. Tiwari, A. K. Agarwal, and S. Dutta, “Physiological Signals Based Anxiety Detection Using Ensemble Machine Learning,” Lecture Notes in Networks and Systems, vol. 291, pp. 597–608, 2022, doi: 10.1007/978-981-16-4284-5_53.
12-S. Qin et al., “Machine learning classifiers for screening nonalcoholic fatty liver disease in general adults,” Scientific Reports 2023 13:1, vol. 13, no. 1, pp. 1–7, Mar. 2023, doi: 10.1038/s41598-023-30750-5.
13-H. Ma, C. F. Xu, Z. Shen, C. H. Yu, and Y. M. Li, “Application of Machine Learning Techniques for Clinical Predictive Modeling: A Cross-Sectional Study on Nonalcoholic Fatty Liver Disease in China,” Biomed Res Int, vol. 2018, 2018, doi: 10.1155/2018/4304376.
14-T. C. F. Yip et al., “Laboratory parameter-based machine learning model for excluding non-alcoholic fatty liver disease (NAFLD) in the general population,” Aliment Pharmacol Ther, vol. 46, no. 4, pp. 447–456, Aug. 2017, doi: 10.1111/APT.14172.
15-P. Sorino et al., “Selecting the best machine learning algorithm to support the diagnosis of Non-Alcoholic Fatty Liver Disease: A meta learner study,” PLoS One, vol. 15, no. 10, p. e0240867, Oct. 2020, doi: 10.1371/JOURNAL.PONE.0240867.
16-Y.-H. Cheng, C.-Y. Chou, and Y. Hsiung, “Application of Machine Learning Methods to Predict Non-Alcohol Fatty Liver Disease in Taiwanese High-Tech Industry Workers”.
17-“Non-alcohol fatty liver disease (NAFLD).” Accessed: Mar. 04, 2024. [Online]. Available: https://www.kaggle.com/datasets/utkarshx27/non-alcohol-fatty-liver-disease/data
18-Z. Xu, D. Shen, T. Nie, Y. Kou, N. Yin, and X. Han, “A cluster-based oversampling algorithm combining SMOTE and k-means for imbalanced medical data,” Inf Sci (N Y), vol. 572, pp. 574–589, Sep. 2021, doi: 10.1016/J.INS.2021.02.056.
19-Ş. K. Çorbacıoğlu and G. Aksel, “Receiver operating characteristic curve analysis in diagnostic accuracy studies: A guide to interpreting the area under the curve value,” Turk J Emerg Med, vol. 23, no. 4, p. 195, Oct. 2023, doi: 10.4103/TJEM.TJEM_182_23.
20-J. Van Loco, M. Elskens, C. Croux, and H. Beernaert, “Linearity of calibration curves: Use and misuse of the correlation coefficient,” Accreditation and Quality Assurance, vol. 7, no. 7, pp. 281–285, Jul. 2002, doi: 10.1007/S00769-002-0487-6/METRICS.
| Files | ||
| Issue | Vol 13 No 2 (2026) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/fbt.v13i2.21937 | |
| Keywords | ||
| Machine learning; Ensemble learning; Stacking models; Explainable AI; Interpretable machine learning; Feature importance. | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
