Cluster analysis and its application to healthcare claims data: a study of end-stage renal disease patients who initiated hemodialysis

Abstract

BackgroundCluster analysis (CA) is a frequently used applied statistical technique that helps to reveal hidden structures and “clusters” found in large data sets. However, this method has not been widely used in large healthcare claims databases where the distribution of expenditure data is commonly severely skewed. The purpose of this study was to identify cost change patterns of patients with end-stage renal disease (ESRD) who initiated hemodialysis (HD) by applying different clustering methods.MethodsA retrospective, cross-sectional, observational study was conducted using the Truven Health MarketScan® Research Databases. Patients aged ≥18 years with ≥2 ESRD diagnoses who initiated HD between 2008 and 2010 were included. The K-means CA method and hierarchical CA with various linkage methods were applied to all-cause costs within baseline (12-months pre-HD) and follow-up periods (12-months post-HD) to identify clusters. Demographic, clinical, and cost information was extracted from both periods, and then examined by cluster.ResultsA total of 18,380 patients were identified. Meaningful all-cause cost clusters were generated using K-means CA and hierarchical CA with either flexible beta or Ward’s methods. Based on cluster sample sizes and change of cost patterns, the K-means CA method and 4 clusters were selected: Cluster 1: Average to High (n = 113); Cluster 2: Very High to High (n = 89); Cluster 3: Average to Average (n = 16,624); or Cluster 4: Increasing Costs, High at Both Points (n = 1554). Median cost changes in the 12-month pre-HD and post-HD periods increased from $185,070 to $884,605 for Cluster 1 (Average to High), decreased from $910,930 to $157,997 for Cluster 2 (Very High to High), were relatively stable and remained low from $15,168 to $13,026 for Cluster 3 (Average to Average), and increased from $57,909 to $193,140 for Cluster 4 (Increasing Costs, High at Both Points). Relatively stable costs after starting HD were associated with more stable scores on comorbidity index scores from the pre-and post-HD periods, while increasing costs were associated with more sharply increasing comorbidity scores.ConclusionsThe K-means CA method appeared to be the most appropriate in healthcare claims data with highly skewed cost information when taking into account both change of cost patterns and sample size in the smallest cluster.

Comparison of Healthcare Utilization and Out-of-pocket Expenditure for Severe Disease by Health Security System: based on End-stage Renal Disease in South Korea

“…The meaning of this study is to identify the actual burden on ESRD because the cost studies in the past have been based on insurance claims data [17,[29][30][31][32][33][34]. The detailed meaning is as follows.…”

Lifetime Costs of Surviving Cancer—A Queensland Study (COS-Q): Protocol of a Large Healthcare Data Linkage Study

“…Aim (2) Identify factors associated with high/low health service usage/cost: We will develop a detailed data analytical plan to undertake statistical analyses of cost data and identify factors associated with high/low health service usage/cost, such as socio-demographic (e.g., geographic location, ethnicity, age, sex) and clinical characteristics (e.g., type of cancer, time since diagnosis). We will consider appropriate statistical approaches, such as non-parametric bootstrapping [40], cluster analysis [41], quantile regression analyses [42], two-part models (if zero values are an issue), quintile regression (splitting cost outcomes into 5 levels) and Generalized Linear Models (GLM) [43]. The latter are particularly suitable for highly right-skewed data, such as health care costs.…”

Symbiotic Simulation System: Hybrid Systems Model Meets Big Data Analytics

“…Within healthcare, clustering techniques have been largely used to identify patient groups. K-means clustering appears to be very widely used in identifying patient groups which have high degrees of similarity (Tomar and Agarwal 2013;Liao et al 2016). To take one example, clustering aids in the identification of entity groups (e.g.…”