Interpretability in HealthCare A Comparative Study of Local Machine Learning Interpretability Techniques
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Although complex machine learning models (e.g., Random Forest, Neural Networks) are commonly outperforming the traditional simple interpretable models (e.g., Linear Regression, Decision Tree), in the healthcare domain, clinicians find it hard to understand and trust these complex models due to the lack of intuition and explanation of their predictions. With the new General Data Protection Regulation (GDPR), the importance for plausibility and verifiability of the predictions made by machine learning models has become essential. To tackle this challenge, recently, several machine learning interpretability techniques have been developed and introduced. In general, the main aim of these interpretability techniques is to shed light and provide insights into the predictions process of the machine learning models and explain how the model predictions have resulted. However, in practice, assessing the quality of the explanations provided by the various interpretability techniques is still questionable. In this paper, we present a comprehensive experimental evaluation of three recent and popular local model agnostic interpretability techniques, namely, LIME, SHAP and Anchors on different types of real-world healthcare data. Our experimental evaluation covers different aspects for its comparison including identity, stability, separability, similarity, execution time and bias detection. The results of our experiments show that LIME achieves the lowest performance for the identity metric and the highest performance for the separability metric across all datasets included in this study. On average, SHAP has the smallest average time to output explanation across all datasets included in this study. For detecting the bias, SHAP enables the participants to better detect the bias.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
17. A Value for n-Person Games
Shapley, L. S. (1953) · Contributions to the Theory of Games (AM-28), Volume II · doi:10.1515/9781400881970-018 · Cited by 6,950
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 3×
“In this work, we present a detailed experimental evaluation of three recent and popular local model agnostic interpretability techniques, namely, LIME [17], Anchors [18] and SHAP [21] on different types (tabular and text data) of real-world healthcare data using five different metrics, namely, identity, stability, sep…”
MethodInfluentialEuropean Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · cited 1×
“…attention especially after the new GDPR imposed by the European Parliament in May 2018 that forces industries to ’explain’ any decision taken when automated decision making takes place: ” a right of explanation for all individuals to obtain meaningful explanations of the logic involved ” [8].”
BackgroundWhy and why not explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552
Accountability of AI Under the Law: The Role of Explanation
Doshi-Velez, F., Kortz, M., Budish, R., Bavitz, C., Gershman, S. J., O'Brien, D., Scott, K., Shieber, S., Waldo, J., Weinberger, D., et al. (2017) · doi:10.2139/ssrn.3064761 · Cited by 457
Honegger, M. (2018) · arXiv · doi:10.48550/arxiv.1808.05054 · Cited by 32 · cited 3×
“We used the following five metrics to compare between different the interpretability techniques: 1) Identity : this metric states that if there are two identical instances, then they must have identical explanations [10].”
BackgroundMethodInfluential
Cited by
Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model
Zhang, J., Ma, X., Zhang, J., Sun, D., Zhou, X., Mi, C., & Wen, H. (2023) · Journal of Environmental Management · doi:10.1016/j.jenvman.2023.117357 · Cited by 661
Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
Das, A., & Rad, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11371 · Cited by 504
Interpretability of machine learning-based prediction models in healthcare
Stiglic, G., Kocbek, P., Fijacko, N., Zitnik, M., Verbert, K., & Cilar, L. (2020) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1379 · Cited by 541
Chou, Y.-L., Moreira, C., Bruza, P., Ouyang, C., & Jorge, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.003 · Cited by 302
Ennab, M., & Mcheick, H. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1444763 · Cited by 238
Ennab, M., & Mcheick, H. (2022) · Diagnostics · doi:10.3390/diagnostics12071557 · Cited by 76
“Interfaces for explanations in human-AI interaction: proposing a design evaluation approach,”
Mucha, H., Robert, S., Breitschwerdt, R., & Fellmann, M. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451759 · Cited by 30
Michalowski, M., Wilk, S., Bauer, J. M., Carrier, M., Viktor, H., & Michalowski, W. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-95838-0_29 · Cited by 1
Metadata
- Authors
- El Shawi, R., Sherif, Y., Al-Mallah, M., & Sakr, S.
- Venue
- 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 275-280
- OpenAlex
- W2966829450
- Cited by
- 72
- References
- 7
- FWCI
- 3.41
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.