The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
From local explanations to global understanding with explainable AI for trees
Open accessAbstract
Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are popular non-linear predictive models, yet comparatively little attention has been paid to explaining their predictions. Here, we improve the interpretability of tree-based models through three main contributions: 1) The first polynomial time algorithm to compute optimal explanations based on game theory. 2) A new type of explanation that directly measures local feature interaction effects. 3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction. We apply these tools to three medical machine learning problems and show how combining many high-quality local explanations allows us to represent global structure while retaining local faithfulness to the original model. These tools enable us to i) identify high magnitude but low frequency non-linear mortality risk factors in the US population, ii) highlight distinct population sub-groups with shared risk characteristics, iii) identify non-linear interaction effects among risk factors for chronic kidney disease, and iv) monitor a machine learning model deployed in a hospital by identifying which features are degrading the model's performance over time. Given the popularity of tree-based machine learning models, these improvements to their interpretability have implications across a broad set of domains.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“SHAP [6] popularized this for machine learning feature importance, with extensions to tree models [5].”
From AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation (2025) · cites this paper as [5]
In the citing paper
“The algorithm provides interpretable explanations suitable for regression and classification of models with tree structure applied to tabular data [22,39].”
From Explainable AI (XAI): Core Ideas, Techniques, and Solutions (2023) · cites this paper as [39]
In the citing paper
“ML and AI techniques, such as social network analysis and agent-based modeling, can model the complex interactions between individuals and their social environments to identify key leverage points for interventions that promote health and well-being across communities [40, 47].”
From Integrating machine learning and artificial intelligence in life-course epidemiology: pathways to innovative public health solutions (2024) · cites this paper as [40]
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Self-citation"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623
Shapley, L. (1988) · Cambridge University Press eBooks · doi:10.1017/cbo9780511528446.003 · Cited by 10,698
Heart Disease and Stroke Statistics—2016 Update: A Report From the American Heart Association
Mozaffarian, D., Benjamin, E. J., Go, A. S., Arnett, D. K., Blaha, M. J., Cushman, M., Das, S. R., de Ferranti, S., Després, J.-P., Fullerton, H. J., et al. (2016) · Circulation · doi:10.1161/cir.0000000000000350 · Cited by 6,596
A Randomized Trial of Intensive versus Standard Blood-Pressure Control
The SPRINT Research Group (2015) · New England Journal of Medicine · doi:10.1056/nejmoa1511939 · Cited by 6,325
Heart Disease and Stroke Statistics—2015 Update: A Report From the American Heart Association
Mozaffarian, D., Benjamin, E. J., Go, A. S., Arnett, D. K., Blaha, M. J., Cushman, M., de Ferranti, S., Després, J.-P., Fullerton, H. J., Howard, V. J., et al. (2015) · Circulation · doi:10.1161/cir.0000000000000152 · Cited by 5,797
Repeated observation of breast tumor subtypes in independent gene expression data sets
Sørlie, T., Tibshirani, R. J., Parker, J. S., Hastie, T. J., Marron, J. S., Nobel, A. B., Deng, S., Johnsen, H., Pesich, R., Geisler, S. B., et al. (2003) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0932692100 · Cited by 5,508
Cited by
Sorted by citations
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Samek, W., Montavon, G., Lapuschkin, S., Anders, C. J., & Muller, K.-R. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3060483 · Cited by 1,477
“sex of the participant (figure is adapted from [115]).”
BackgroundMethodInfluentialExplainable AI (XAI): Core Ideas, Techniques, and Solutions
Dwivedi, R., Dave, D., Naik, H., Singhal, S., Omer, R., Patel, P., Qian, B., Wen, Z., Shah, T., Morgan, G., et al. (2023) · ACM Computing Surveys · doi:10.1145/3561048 · Cited by 1,386
An interpretable mortality prediction model for COVID-19 patients
Li, Y., Zhang, H., Gonçalves, J. M., Xiao, Y., Wang, M., Guo, Y., Sun, C., Tang, X., Jing, L., Zhang, M., et al. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0180-7 · Cited by 1,328
Deep Neural Networks and Tabular Data: A Survey
Borisov, V., Leemann, T., Seßler, K., Haug, J., Pawelczyk, M., & Kasneci, G. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3229161 · Cited by 1,400
Metadata
- Authors
- Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I.
- Affiliations
- Microsoft (United States) (US)
- University of Washington (US)
- Corresponding author
- Lee, Su-In
- ORCID
- Venue
- Nature Machine Intelligence
- Published
- 2020-01-17
- Volume
- 2
- Issue
- 1
- Pages
- 56-67
- ISSN
- 2522-5839 (ISSN-L)
- PMC
- PMC7326367
- OpenAlex
- W2999615587
- Cited by
- 10,551
- References
- 38
- Citations by year
- 2026: 3607 · 2025: 2330 · 2024: 1650 · 2023: 1197 · 2022: 959 · 2021: 614 · 2020: 187
- FWCI
- 291.51
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- Nature Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Science Foundation (DGE-1256082, DBI-1759487, DBI-1552309, DBI-1355899)
- American Cancer Society (127332-RSG-15-097-01-TBG)
- U.S. Department of Health & Human Services | National Institutes of Health (R35 GM 128638, R01 NIA AG 061132)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
- Keywords
- explainable AI, tree-based models, local explanations, mortality risk, chronic kidney disease, model monitoring, machine learning in medicine
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
