ACDC: $α$-Carving Decision Chain for Risk Stratification
It addresses risk stratification for healthcare resource allocation, but appears incremental as a variant of decision trees.
The paper tackled the problem of risk stratification in healthcare by introducing ACDC, a decision chain algorithm that carves out pure subsets of majority class examples to identify minority class examples, showing effectiveness on large, class-imbalanced datasets.
In many healthcare settings, intuitive decision rules for risk stratification can help effective hospital resource allocation. This paper introduces a novel variant of decision tree algorithms that produces a chain of decisions, not a general tree. Our algorithm, $α$-Carving Decision Chain (ACDC), sequentially carves out "pure" subsets of the majority class examples. The resulting chain of decision rules yields a pure subset of the minority class examples. Our approach is particularly effective in exploring large and class-imbalanced health datasets. Moreover, ACDC provides an interactive interpretation in conjunction with visual performance metrics such as Receiver Operating Characteristics curve and Lift chart.