86Segmenting persistently high-cost individuals into actionable groups

Abstract

\n \n \n Despite growing evidence describing high cost patients, decision-makers struggle to implement effective strategies to improve care and curb spending in this population. Using a multi-phased approach, we aimed to classify high cost patients into homogeneous subgroups amenable to targeted interventions.\n \n \n \n We linked population-level administrative health data in Alberta, Canada from 2012-2017. We defined “persistently high-cost” as those in the top 1% of cumulative inpatient, outpatient and medication cost in at least two consecutive years. We used latent class analysis to separate this persistent high-cost population into potentially actionable subgroups.\n \n \n \n Of the 3,795,067 adults residing in Alberta, 21,361 were ‘persistently high-cost’. Latent class models identified 10 high-cost subgroups: individuals with CKD (19.3% of persistent high-cost individuals), those undergoing joint surgery/replacement and rehabilitation (18.6%), individuals with IBD (11.6%), patients receiving biologics for autoimmune conditions (11.3%), patients receiving high cost drugs for other conditions (11.1%), community-dwelling individuals with multimorbid chronic conditions (9.0%), individuals with schizophrenia (6.8%), individuals with other mental health issues (6.2%), rural individuals with COPD (3.4%), and frail elderly in institutional settings (2.7%).\n \n \n \n Latent class analysis was able to identify 10 persistently high-cost groups based on meaningful differences in health care spending, demographics, and clinical diagnoses.\n \n \n \n This taxonomy will inform the identification of interventions shown to improve care and reduce cost for each subgroup in addition to consultation with key stakeholders to identify and reflect on key barriers and facilitators to implementing identified interventions within the local context.\n