ArticleNature machine intelligence2020
From Local Explanations to Global Understanding with Explainable AI for Trees.
Article in Nature machine intelligence, 2020. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2,631 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
2,631 citing papers in PubMed, 1 synthesis or guideline pooled it, 8,062 citations in OpenAlex.
- Machine learning-assisted mRNA vaccine pharmacovigilance: a systematic review of multi-source real-world data.BMC medical informatics and decision making · 2026Pooled it
- Metabolic state-driven monitoring and control of abnormal pigment formation in sodium gluconate fermentation bySynthetic and systems biotechnology · 2027Article
- Article
- Article
- Machine learning-guided discovery of a bioactive hydrogel for spatiotemporally orchestrated tendon-to-bone healing.Bioactive materials · 2026Article
- Construction of performance score dynamic prediction system for clinical departments using explainable machine learning.Health information science and systems · 2026Article
- A simplified nomogram for predicting deep vein thrombosis: development in NHANES and retrospective single-center external validation.Annals of medicine · 2026Article
- Stereotactic Radiation Therapy for Lung Cancer Brain Metastases: Dose Optimization and Prognostic Prediction via Biologically Effective Dose-Based Empirical Dose-Response Modeling and Extreme Gradient Boosting-SHapley Additive Explanations Machine Learning.Advances in radiation oncology · 2026Article
- Clinician-accessible automated machine learning in oral healthcare: A systematic review.The Japanese dental science review · 2026Review
- Integrated machine learning risk model for predicting radiation pneumonitis in lung cancer patients with interstitial lung disease.Annals of medicine · 2026Article
- An explainable machine learning model for predicting in-hospital infection in patients with systemic lupus erythematosus.Renal failure · 2026Article
- The relative importance of neighborhood environment features in explaining preeclampsia risk using machine learning.Pregnancy (Hoboken, N.J.) · 2026Article
- Forest under stress: responses and recovery of water relations across scales during the compound drought in summer 2022.The New phytologist · 2026Article
- PTGS2/COX-2 is associated with neurovascular and blood-brain barrier changes in behaviourally classified MRL/lpr mice.Lupus science & medicine · 2026Article
- Advancing Near-Term Water Quality Forecasting with Explainable Machine Learning and Probabilistic Uncertainty Quantification.ACS ES&T water · 2026Article
- Pharmacological stratification of public bioactivity databases: a reusable, OECD-anchored curation and benchmarking framework demonstrated for opioid receptors.Digital discovery · 2026Article
- EDIT-B consortium: an external pan-European validation of an innovative machine learning-based test for bipolar disorder diagnosis.BMJ mental health · 2026Article
- Oesophageal tissue screening system for assessing the retention and mucosal absorption of biologics.Nature biomedical engineering · 2026Article
- Analysis of lipid-protein interactive oxidation and underlying pathways in aquatic products via multi-omics and machine learning: a case study of air-dried hairtail.Food chemistry: X · 2026Article
- Construction of risk prediction models for psoriasis based on 45 dietary nutrients using machine learning and SHAP analysis.Asia Pacific journal of clinical nutrition · 2026Article
2,571 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
10 authors at 2 institutions in 2 countries.
Funding
Abstract
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.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.