A Study Comparing Explainability Methods: A Medical User Perspective

Matejová, Miroslava; Gojdičová, Lucia; Paralič, Ján

doi:10.2478/aei-2025-0005

Abstract

In recent years, we have witnessed the rapid development of artificial intelligence systems and their presence in various fields. These systems are very efficient and powerful, but often unclear and insufficiently transparent. Explainable artificial intelligence (XAI) methods try to solve this problem. XAI is still a developing area of research, but it already has considerable potential for improving the transparency and trustworthiness of AI models. Thanks to XAI, we can build more responsible and ethical AI systems that better serve people’s needs. The aim of this study is to focus on the role of the user. Part of the work is a comparison of several explainability methods such as LIME, SHAP, ANCHORS and PDP on a selected data set from the field of medicine. The comparison of individual explainability methods from various aspects was carried out using a user study.

References

ARRIETA, A.B. – DÍAZ-RODRÍGUEZ, N. – DEL SER, J. – BENNETOT, A. – TABIK, S. – BARBADO, A. – GARCIA, S. – GIL-LOPEZ, S. – MOLINA, D. – BENJAMINS, R. – CHATILA, R. – HERRERA, F.: Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, vol. 58, pp. 82–115, 2020.
Search in Google Scholar Back to article
BRENNEN, A.: What do people really want when they say they want ‘explainable AI?’ we asked 60 stakeholders, Conference on Human Factors in Computing Systems - Proceedings, Apr. 2020.
Search in Google Scholar Back to article
LANGER, M. – OSTER, D. – SPEITH, T. – HERMANNS, H. – KÄSTNER, L. – SCHMIDT, E. – SESING, A. – BAUM, K.: What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research. Artificial Intelligence, vol. 296, 2021.
Search in Google Scholar Back to article
RIBEIRO, M. T. – SINGH, S. – GUESTRIN, C.: “Why Should I Trust You?”: Explaining the Predictions of Any Classifier, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144, 2016.
Search in Google Scholar Back to article
LUNDBERG, S. M. – LEE, S. I.: A Unified Approach to Interpreting Model Predictions, Advances in Neural Information Processing Systems, pp. 4766–4775, Dec. 2017.
Search in Google Scholar Back to article
RIBEIRO, M. T. – SINGH, S. – GUESTRIN, C.: Anchors: High-Precision Model-Agnostic Explanations, Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1, 2018.
Search in Google Scholar Back to article
FRIEDMAN, J. H.: Greedy function approximation: A gradient boosting machine. Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
Search in Google Scholar Back to article
ROSENFELD, A.: Better Metrics for Evaluating Explainable Artificial Intelligence, Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, pp. 45–50, 2021.
Search in Google Scholar Back to article
HOFFMAN, R. R. – MUELLER, S. T. – KLEIN, G. – LITMAN, J.: Metrics for Explainable AI: Challenges and Prospects. CoRR, 2018.
Search in Google Scholar Back to article
CHROMIK, M. – SCHUESSLER, M.: A Taxonomy for Human Subject Evaluation of Black-Box Explanations in XAI. ExSS-ATEC@IUI, 2020.
Search in Google Scholar Back to article
DIEBER, J. – KIRRANE, S.: Why model why? Assessing the strengths and limitations of LIME. ArXiv, 2020.
Search in Google Scholar Back to article
AECHTNER, J. – CABRERA, L. – KATWAL, D. – ONGHENA, P. – VALENZUELA, D. P. – WILBIK, A.: Comparing User Perception of Explanations Developed with XAI Methods, IEEE International Conference on Fuzzy Systems, July 2022.
Search in Google Scholar Back to article
DAUDT, F. – CINALLI, D. – GARCIA, A. C. B.: Research on Explainable Artificial Intelligence Techniques: An User Perspective, IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp. 144–149, 2021.
Search in Google Scholar Back to article
WANG, X. – YIN, M.: Effects of Explanations in AI-Assisted Decision Making: Principles and Comparisons, ACM Transactions on Interactive Intelligent Systems, vol. 12, no. 4, 2022.
Search in Google Scholar Back to article
SHIN, D.: The effects of explainability and causability on perception, trust, and acceptance: Implications for explainable AI. International Journal of Human-Computer Studies, vol. 146, 2021.
Search in Google Scholar Back to article

A Study Comparing Explainability Methods: A Medical User Perspective

Abstract

Paradigm

My account