A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME
Advanced Intelligent Systems · 2025-01 · 7 (1)
DOI: 10.1002/aisy.202400304 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 27.06.2024. Verfasst von Ahmed M. Salih und 6 weiteren Autor:innen. Die Arbeit wurde bisher 935-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: British Heart Foundation, National Institute for Health Research Collaboration for Leadership in Applied Health Research and Care North West Coast.
Abstract (Originalsprache)
eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end‐users in their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, the way the explainability metrics of these two methods are generated is discussed and a framework for the interpretation of their outputs, highlighting their weaknesses and strengths is proposed. Specifically, their outcomes in terms of model‐dependency and in the presence of collinearity among the features, relying on a case study from the biomedical domain (classification of individuals with or without myocardial infarction) are discussed. The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation.
Förderung
- British Heart Foundation
- National Institute for Health Research Collaboration for Leadership in Applied Health Research and Care North West Coast
Zitieren
APA
Salih, A. M., Raisi‐Estabragh, Z., Galazzo, I. B., Radeva, P., Petersen, S. E., Lekadir, K., & Menegaz, G. (2025). A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME. Advanced Intelligent Systems, 7(1). https://doi.org/10.1002/aisy.202400304
Vancouver
Salih AM, Raisi‐Estabragh Z, Galazzo IB, Radeva P, Petersen SE, Lekadir K, et al. A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME. Advanced Intelligent Systems. 2025;7(1). doi:10.1002/aisy.202400304
BibTeX
@article{Salih2025,
author = {Salih, Ahmed M. and Raisi‐Estabragh, Zahra and Galazzo, Ilaria Boscolo and Radeva, Petia and Petersen, Steffen E. and Lekadir, Karim and Menegaz, Gloria},
title = {A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME},
journal = {Advanced Intelligent Systems},
year = {2025},
volume = {7},
number = {1},
doi = {10.1002/aisy.202400304}
}
EUVIMED