The Effect of Data Imbalance on the Interpretation Stability of LIME-Based Explainable AI on Nutritional Status Prediction Models
Indonesian Journal of Infomatics · 31.05.2026 · 1 (2) · 13-20
DOI: 10.66472/iji.v1i2.438 ↗Kurz gefasst
Fachartikel in der Zeitschrift Indonesian Journal of Infomatics, online erschienen am 31.05.2026. Verfasst von Sri Nurhayati und 4 weiteren Autor:innen.
Themen: Mangelernährung
Abstract (Originalsprache)
Data imbalance is a common challenge in nutritional status prediction because it can reduce classification performance and influence the reliability of Explainable Artificial Intelligence (XAI) interpretations. This study aims to examine the impact of data imbalance on the stability of Local Interpretable Model-Agnostic Explanations (LIME)-based interpretations. A Random Forest model was developed under two scenarios: using the original imbalanced dataset and using a balanced dataset generated through the Synthetic Minority Over-sampling Technique (SMOTE). Model performance was evaluated and compared, followed by LIME-based interpretation and stability analysis. The results indicate that SMOTE enhanced the model’s ability to identify minority classes, with recall increasing from 0.36 to 0.55, although overall accuracy slightly declined. LIME analysis revealed changes in feature contributions between the two scenarios, reflecting the influence of data distribution on model explanations. The interpretation stability score reached 0.80, suggesting relatively consistent explanations despite variations in class balance. These findings highlight the importance of jointly evaluating predictive performance and interpretation stability in health-related machine learning applications.
Zitieren
APA
Nurhayati, S., Hidayat, H., Ningrum, S. A., Hasibuan, Z. A., & Supatmi, S. (2026). The Effect of Data Imbalance on the Interpretation Stability of LIME-Based Explainable AI on Nutritional Status Prediction Models. Indonesian Journal of Infomatics, 1(2), 13-20. https://doi.org/10.66472/iji.v1i2.438
Vancouver
Nurhayati S, Hidayat H, Ningrum SA, Hasibuan ZA, Supatmi S. The Effect of Data Imbalance on the Interpretation Stability of LIME-Based Explainable AI on Nutritional Status Prediction Models. Indonesian Journal of Infomatics. 2026;1(2):13-20. doi:10.66472/iji.v1i2.438
BibTeX
@article{Nurhayati2026,
author = {Nurhayati, Sri and Hidayat, Hidayat and Ningrum, Siti Ar-Rachmi and Hasibuan, Zainal Arifin and Supatmi, Sri},
title = {The Effect of Data Imbalance on the Interpretation Stability of LIME-Based Explainable AI on Nutritional Status Prediction Models},
journal = {Indonesian Journal of Infomatics},
year = {2026},
volume = {1},
number = {2},
pages = {13--20},
doi = {10.66472/iji.v1i2.438}
}
EUVIMED