Assessment of utilization efficiency using machine learning techniques: A study of heterogeneity in preoperative healthcare utilization among super-utilizers

Introduction: In the United States, 5% of patients represent up to 55% of all health care costs. This study sought to define healthcare utilization patterns among super-utilizers, as well as assess possible variation in patient outcomes. Methods: Medicare super-utilizers undergoing either a total hip or knee arthroplasty were identified and entered into a cluster analysis using annual preoperative charges to identify distinct patterns of utilization. Results: Among 19,522 super-utilizers who underwent THA or TKA, there was a marked heterogeneity in overall utilization with 5 distinct clusters of utilization patterns. Of note, comorbidity burden was similar among the 5 clusters. Patient outcomes also varied by Cluster type, ranging from 6.9% to 16.5% experi-encing complications and 1.0%-3.2% experiencing 90-day mortality. Conclusion: While previous studies have suggested that super-utilizers are a homogenous group of pa-tients, the current study demonstrated a large degree of heterogeneity within super-utilizers. Variations in utilization patterns were associated with postoperative outcomes and subsequent health care costs. (c) 2020 Elsevier Inc. All rights reserved.