Falling Rule Lists
This work addresses the need for interpretable risk stratification models in healthcare, where high-risk patients must be prioritized, though it appears incremental as it builds on existing rule-based methods with a specific monotonicity constraint.
The authors tackled the problem of learning classification models for risk stratification in healthcare by introducing falling rule lists, which are ordered if-then rules with monotonically decreasing success probabilities, and they developed a Bayesian framework for learning these models without relying on greedy decision tree methods.
Falling rule lists are classification models consisting of an ordered list of if-then rules, where (i) the order of rules determines which example should be classified by each rule, and (ii) the estimated probability of success decreases monotonically down the list. These kinds of rule lists are inspired by healthcare applications where patients would be stratified into risk sets and the highest at-risk patients should be considered first. We provide a Bayesian framework for learning falling rule lists that does not rely on traditional greedy decision tree learning methods.