Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
arXiv:1511.01644 · doi:10.1214/15-AOAS848
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.
arXiv commentPublished at http://dx.doi.org/10.1214/15-AOAS848 in the Annals of Applied Statistics (http://www.imstat.org/aoas/) by the Institute of Mathematical Statistics (http://www.imstat.org)
References in corpus (6)
Cited by in corpus (144)
- Methods for Interpreting and Understanding Deep Neural Networks
- A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
- Interpretable machine learning: definitions, methods, and applications
- A Survey on the Explainability of Supervised Machine Learning
- Model-Agnostic Interpretability of Machine Learning
- Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
- Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
- Society-in-the-Loop: Programming the Algorithmic Social Contract
- "Why Should I Trust You?": Explaining the Predictions of Any Classifier
- A Review of Challenges and Opportunities in Machine Learning for Health
- Towards Out-Of-Distribution Generalization: A Survey
- Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs
- Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences
- A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
- Designing Interpretable ML System to Enhance Trust in Healthcare: A Systematic Review to Proposed Responsible Clinician-AI-Collaboration Framework
- A review of possible effects of cognitive biases on the interpretation of rule-based machine learning models
- Interpreting Blackbox Models via Model Extraction
- Post-hoc explanation of black-box classifiers using confident itemsets
- An Evaluation of the Human-Interpretability of Explanation
- Learning Certifiably Optimal Rule Lists for Categorical Data
- How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
- Explainable Artificial Intelligence: a Systematic Review
- Logic Explained Networks
- XAIR: A Framework of Explainable AI in Augmented Reality
- Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
- "Why Should You Trust My Explanation?" Understanding Uncertainty in LIME Explanations
- Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions
- Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making
- Explainable Activity Recognition for Smart Home Systems
- Entropy-based Logic Explanations of Neural Networks
- Towards Relatable Explainable AI with the Perceptual Process
- A study on the Interpretability of Neural Retrieval Models using DeepSHAP
- Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations
- A Hierarchy of Limitations in Machine Learning
- Dissonance Between Human and Machine Understanding
- Interpretable multiclass classification by MDL-based rule lists
- Interpretable Random Forests via Rule Extraction
- Leveraging Rationales to Improve Human Task Performance
- Causality Learning: A New Perspective for Interpretable Machine Learning
- Bias In, Bias Out? Evaluating the Folk Wisdom
- MLIC: A MaxSAT-Based framework for learning interpretable classification rules
- MAGIX: Model Agnostic Globally Interpretable Explanations
- Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
- Programs as Black-Box Explanations
- A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
- Considerations When Learning Additive Explanations for Black-Box Models
- Neural Network Attributions: A Causal Perspective
- Model Distillation for Revenue Optimization: Interpretable Personalized Pricing
- The Price of Interpretability
- Knowledge-based Transfer Learning Explanation
- Or's of And's for Interpretable Classification, with Application to Context-Aware Recommender Systems
- "How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations
- What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play
- Learning Interpretable Rules for Scalable Data Representation and Classification
- Scalable Rule-Based Representation Learning for Interpretable Classification
- Embedding Deep Networks into Visual Explanations
- IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules
- Decision Tree Classification with Differential Privacy: A Survey
- Global Model Interpretation via Recursive Partitioning
- Explainable AI using expressive Boolean formulas
- Fairwashing: the risk of rationalization
- A Decision-Theoretic Approach for Model Interpretability in Bayesian Framework
- Efficient learning of large sets of locally optimal classification rules
- Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
- Robust subgroup discovery
- Machine Learning Meets Microeconomics: The Case of Decision Trees and Discrete Choice
- Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond
- Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning
- Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning
- Explaining Explanations to Society
- Accurate Explanation Model for Image Classifiers using Class Association Embedding
- Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making
- Efficient Learning of Interpretable Classification Rules
- Safe RuleFit: Learning Optimal Sparse Rule Model by Meta Safe Screening
- Improving the Interpretability of Deep Neural Networks with Knowledge Distillation
- VINE: Visualizing Statistical Interactions in Black Box Models
- Interpretable and Fair Boolean Rule Sets via Column Generation
- Optimal Sparse Decision Trees
- Learning Cost-Effective Treatment Regimes using Markov Decision Processes
- Rationalizing Predictions by Adversarial Information Calibration
- Scalable Bayesian Rule Lists
- SUBPLEX: Towards a Better Understanding of Black Box Model Explanations at the Subpopulation Level
- Interpretability with Accurate Small Models
- QCBA: Improving Rule Classifiers Learned from Quantitative Data by Recovering Information Lost by Discretisation
- Evaluation of Human-Understandability of Global Model Explanations using Decision Tree
- A hybrid machine learning framework for analyzing human decision making through learning preferences
- An interpretable neural network model through piecewise linear approximation
- When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making
- Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs
- Causal Rule Sets for Identifying Subgroups with Enhanced Treatment Effect
- An exact counterfactual-example-based approach to tree-ensemble models interpretability
- Automation of Quantum Dot Measurement Analysis via Explainable Machine Learning
- MonoNet: Towards Interpretable Models by Learning Monotonic Features
- Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
- A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas
- When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis
- RuleMatrix: Visualizing and Understanding Classifiers with Rules
- Robust and Stable Black Box Explanations
- Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations
- Dissecting users' needs for search result explanations
- MCA-based Rule Mining Enables Interpretable Inference in Clinical Psychiatry
- Interpreting search result rankings through intent modeling
- Latent Factor Interpretations for Collaborative Filtering
- Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspective
- Feature Attributions and Counterfactual Explanations Can Be Manipulated
- Modeling Conceptual Understanding in Image Reference Games
- Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain
- Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
- Concave Quadratic Cuts for Mixed-Integer Quadratic Problems
- A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution
- Explaining Transition Systems through Program Induction
- Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations
- Using Program Induction to Interpret Transition System Dynamics
- Fair Decision Rules for Binary Classification
- Valid Explanations for Learning to Rank Models
- A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds
- Model-Agnostic Linear Competitors -- When Interpretable Models Compete and Collaborate with Black-Box Models
- Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence
- Transparent Classification with Multilayer Logical Perceptrons and Random Binarization
- Optimal Explanations of Linear Models
- Multi-Value Rule Sets
- A Formal Language Approach to Explaining RNNs
- Learning Interpretable Concept-Based Models with Human Feedback
- GLAD: GLocalized Anomaly Detection via Human-in-the-Loop Learning
- Computing Human-Understandable Strategies
- Learning Cost-Effective and Interpretable Regimes for Treatment Recommendation
- Simplifying the explanation of deep neural networks with sufficient and necessary feature-sets: case of text classification
- A general approach to compute the relevance of middle-level input features
- Grounding Visual Explanations
- Visualizing Rule Sets: Exploration and Validation of a Design Space
- A Categorisation of Post-hoc Explanations for Predictive Models
- Explainability via Responsibility
- Information-theoretic Evolution of Model Agnostic Global Explanations
- How to improve the interpretability of kernel learning
- Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities
- Axiomatic Interpretability for Multiclass Additive Models
- CACTUS: Detecting and Resolving Conflicts in Objective Functions
- Analysis and classification of main risk factors causing stroke in Shanxi Province
- Interpretable Quantile Regression by Optimal Decision Trees
- Interpretable Machine Learning Classifiers for Brain Tumour Survival Prediction
- Directional Decision Lists
- An Exploration And Validation of Visual Factors in Understanding Classification Rule Sets
- Coverage-based Outlier Explanation
- Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification