Hypersphere clustering to characterize healthcare providers using prescriptions and procedures from Medicare claims data.

Summary

A new autoencoder framework organizes healthcare providers into clusters based on their prescription and procedure patterns using Medicare claims data. This method improves the accuracy of provider characterization, offering a more effective tool for analyzing clinical behaviors in high-dimensional datasets.

Key result

A novel autoencoder framework for hypersphere clustering outperformed traditional two-step projected K-means and K-medoids approaches in characterizing healthcare providers based on high-dimensional sparse count vectors of clinical actions.

Abstract

We consider the task of producing a useful clustering of healthcare providers from their clinical action signature- their drug, procedure, and billing codes. Because high-dimensional sparse count vectors are challenging to cluster, we develop a novel autoencoder framework to address this task. Our solution creates a low-dimensional embedded representation of the high-dimensional space that preserves angular relationships and assigns examples to clusters while optimizing the quality of this clustering. Our method is able to find a better clustering than under a two-step alternative, e.g., projected K means/medoids, where a representation is learned and then clustering is applied to the representation. We demonstrate our method's characteristics through quantitative and qualitative analysis of real and simulated data, including in several real-world healthcare case studies. Finally, we develop a tool to enhance exploratory analysis of providers based on their clinical behaviors.