Predictive Hierarchical Clustering: Learning clusters of CPT codes for improving surgical outcomes

TL;DR

This paper introduces Predictive Hierarchical Clustering (PHC), a novel algorithm for clustering CPT codes to improve the prediction of surgical outcomes by optimizing cluster formation based on predictive performance.

Contribution

The paper presents a new clustering algorithm that groups CPT codes based on predictive modeling, enhancing outcome prediction accuracy over traditional clinical judgment-based clusters.

Findings

PHC outperforms existing clustering methods in predicting surgical outcomes.

Clusters formed by PHC improve the accuracy of outcome prediction models.

The Bayesian approach allows flexible control over cluster size and sparsity.

Abstract

We develop a novel algorithm, Predictive Hierarchical Clustering (PHC), for agglomerative hierarchical clustering of current procedural terminology (CPT) codes. Our predictive hierarchical clustering aims to cluster subgroups, not individual observations, found within our data, such that the clusters discovered result in optimal performance of a classification model. Therefore, merges are chosen based on a Bayesian hypothesis test, which chooses pairings of the subgroups that result in the best model fit, as measured by held out predictive likelihoods. We place a Dirichlet prior on the probability of merging clusters, allowing us to adjust the size and sparsity of clusters. The motivation is to predict patient-specific surgical outcomes using data from ACS NSQIP (American College of Surgeon's National Surgical Quality Improvement Program). An important predictor of surgical outcomes is the actual surgical procedure performed as described by a CPT code. We use PHC to cluster CPT codes, represented as subgroups, together in a way that enables us to better predict patient-specific outcomes compared to currently used clusters based on clinical judgment.