Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
From MaRDI portal
Publication:902909
DOI10.1214/15-AOAS848zbMATH Open1454.62348arXiv1511.01644OpenAlexW2118022153WikidataQ56340208 ScholiaQ56340208MaRDI QIDQ902909FDOQ902909
Authors: Benjamin Letham, Cynthia Rudin, Tyler H. Mccormick, David Madigan 
Publication date: 4 January 2016
Published in: The Annals of Applied Statistics (Search for Journal in Brave)
Abstract: We aim to produce predictive models that are not only accurate, but are also interpretable to human experts. Our models are decision lists, which consist of a series of if...then... statements (e.g., if high blood pressure, then stroke) that discretize a high-dimensional, multivariate feature space into a series of simple, readily interpretable decision statements. We introduce a generative model called Bayesian Rule Lists that yields a posterior distribution over possible decision lists. It employs a novel prior structure to encourage sparsity. Our experiments show that Bayesian Rule Lists has predictive accuracy on par with the current top algorithms for prediction in machine learning. Our method is motivated by recent developments in personalized medicine, and can be used to produce highly accurate and interpretable medical scoring systems. We demonstrate this by producing an alternative to the CHADS score, actively used in clinical practice for estimating the risk of stroke in patients that have atrial fibrillation. Our model is as interpretable as CHADS, but more accurate.
Full work available at URL: https://arxiv.org/abs/1511.01644
Recommendations
- A Bayesian framework for learning rule sets for interpretable classification
- Bayesian Model Averaging in Proportional Hazard Models: Assessing the Risk of a Stroke
- Fractal and multifractional-based predictive optimization model for stroke subtypes' classification
- Bayesian hierarchical rule modeling for predicting medical conditions
Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to biology and medical sciences; meta analysis (62P10) Bayesian problems; characterization of Bayes procedures (62C10)
Cites Work
- LIBLINEAR: a library for large linear classification
- BART: Bayesian additive regression trees
- Predictive learning via rule ensembles
- Heuristics of instability and stabilization in model selection
- Inference from iterative simulation using multiple sequences
- Title not available (Why is that?)
- Random forests
- Bagging predictors
- A Bayesian CART algorithm
- Bayesian Inference on Network Traffic Using Link Count Data
- Title not available (Why is that?)
- Statistical modeling: The two cultures. (With comments and a rejoinder).
- Very simple classification rules perform well on most commonly used datasets
- Using decision lists to construct interpretable and parsimonious treatment regimes
- Learning theory analysis for association rules and sequential event prediction
- Learning with decision lists of data-dependent features
- Title not available (Why is that?)
- Node harvest
- Bayesian treed models
- Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
- To explain or to predict?
- Title not available (Why is that?)
- Dynamic trees for learning and design
- Inductive Logic Programming: Theory and methods
- Bayesian hierarchical rule modeling for predicting medical conditions
- Title not available (Why is that?)
- Efficient sequential decision-making algorithms for container inspection operations
Cited In (27)
- Robust subgroup discovery. Discovering subgroup lists using MDL
- SIRUS: stable and interpretable RUle set for classification
- Efficient Learning of Interpretable Classification Rules
- False discovery rate control for effect modification in observational studies
- A Bayesian framework for learning rule sets for interpretable classification
- Learning certifiably optimal rule lists for categorical data
- Efficient learning of large sets of locally optimal classification rules
- Building more accurate decision trees with the additive tree
- Maximizing interpretability and cost-effectiveness of surgical site infection (SSI) predictive models using feature-specific regularized logistic regression on preoperative temporal data
- Bayesian hierarchical rule modeling for predicting medical conditions
- bsnsing: A Decision Tree Induction Method Based on Recursive Optimal Boolean Rule Composition
- Computing human-understandable strategies: deducing fundamental rules of poker strategy
- A survey on the explainability of supervised machine learning
- Interpretable machine learning: fundamental principles and 10 grand challenges
- Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals
- Logic explained networks
- Rationalizing predictions by adversarial information calibration
- Learning optimized risk scores
- Classification rules in relaxed logical form
- Lexicographic preferences for predictive modeling of human decision making: a new machine learning method with an application in accounting
- A decision-theoretic approach for model interpretability in Bayesian framework
- Causal Rule Sets for Identifying Subgroups with Enhanced Treatment Effects
- Ultra-strong machine learning: comprehensibility of programs learned with ILP
- Learning customized and optimized lists of rules with mathematical programming
- Considerations when learning additive explanations for black-box models
- Bayesian quickest detection of credit card fraud
- Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
Uses Software
This page was built for publication: Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q902909)
