Clustering and Healthcare Costs With Multiple Chronic Conditions in a US Study

Abstract

Objective: To investigate healthcare costs and contributors to costs for multiple chronic conditions (MCCs), common clusters of conditions and their impact on cost and utilization. Methods: This was a cross-sectional analysis of US financial claims data representative of the US population, including Medicare, Medicaid, and Commercial insurance claims in 2015. Outcome measures included healthcare costs and contributors; ranking of clusters of conditions according to frequency, strength of association and unsupervised (k-means) analysis; the impact of clustering on costs and contributors to costs. Results: Of 1,878,951 patients, 931,045(49.6%) had MCCs, 56.5% weighted to the US population. Mean age was 53.0 years (SD16.7); 393,121(42.20%) were male. Mean annual healthcare spending was $12,601, ranging from $4,385 (2 conditions) to $33,874 (11 conditions), with spending increasing by 22-fold for inpatient services, 6-fold for outpatient services, 4.5-fold for generic drugs, and 4.2-fold for branded drugs. Cluster ranking using the 3 methodologies yielded similar results: highest ranked clusters included metabolic syndrome (12.2% of US insured patients), age related diseases (7.7%), renal failure (5.6%), respiratory disorders (4.5%), cardiovascular disease(CVD) (4.3%), cancers (4.1-4.3%), mental health-related clusters (1.0-1.5%), and HIV/AIDS (0.2%). Highest spending was in HIV/AIDS clusters ($48,293), mental health-related clusters ($38,952-$40,637), renal disease ($38,551), and CVD ($37,155); with 89.9% of spending on outpatient and inpatient care combined, and 10.1% on medication. Conclusion and Relevance: Over 57% of insured patients in the US may have MCCs. MCC Clustering is frequent and is associated with healthcare utilization. The findings favor health system redesign toward a multiple condition approach for clusters of chronic conditions, alongside other cost-containment measures for MCCs.

Keywords: cancer; cardiovascular disease; chronic disease; disease clustering; healthcare costs; mental health; multimorbidity.

Figure 1

Total average health spend and contributors to cost by number of chronic conditions. Costs are weighted to the US population and are reported in US$. Comparison between costs by number of conditions was statistically significant overall (p < 0.001), for inpatient (p < 0.001), outpatient (p < 0.001), branded drugs (p < 0.001), and generic drugs (p < 0.001).

Figure 2

Total average health spend and contributors to cost by cluster of conditions. Costs are weighted to the US population and reported in US$. Comparisons for cost between clusters of conditions were statistically significant overall (p < 0.001), for inpatient (p < 0.001), outpatient (p < 0.001), branded drugs (p < 0.001), and generic drugs (p < 0.001).

Figure 3

Health Service Utilization in terms of cost, reported by Cluster. Costs are weighted to the US population and are reported in US$. Comparisons for cost between clusters of conditions were statistically significant for inpatient (p < 0.001), specialty procedure (p < 0.001), primary care (p < 0.001), emergency care (p = 0.003), and psychiatric care (p < 0.001).