Multimorbidity Clusters: Clustering Binary Data From Multimorbidity Clusters: Clustering Binary Data From a Large Administrative Medical Database

Abstract

Our purpose in this article is to describe and illustrate the application of cluster analysis to identify clinically relevant multimorbidity groups. Multimorbidity is the co-occurrence of 2 or more illnesses within a single person, which raises the question whether consistent, clinically useful multimorbidity groups exist among sets of chronic illnesses. Our purpose in this article is to describe and illustrate the application of cluster analysis to identify clinically relevant multimorbidity groups. Application of cluster analysis involves a sequence of critical methodological and analytic decisions that influence the quality and meaning of the clusters produced. We illustrate the application of cluster analysis to identify multimorbidity clusters in a set of 45 chronic illnesses in primary care patients (N = 1,327,328), with 2 or more chronic conditions, served by the Veterans Health Administration. Six clinically useful multimorbidity clusters were identified: a Metabolic Cluster, an Obesity Cluster, a Liver Cluster, a Neurovascular Cluster, a Stress Cluster and a Dual Diagnosis Cluster. Cluster analysis appears to be a useful technique for identifying multiple disease clusters and patterns of multimorbidity.

Geographic and Racial/Ethnic Variations in Patterns of Multimorbidity Burden in Patients with Type 2 Diabetes

“…This study is limited by a lack of information on disease severity, chronological development of comorbid conditions, and clusters (combinations) of chronic conditions in specific demographic groups. 39 Another limitation is generalizability to the larger U.S. population with diabetes. However, our findings can be generalized to older adults in large healthcare systems such as the Geisinger Health System, Group Health, or Kaiser Permanente.…”

“…As an increasing number of studies examine shared etiologies and risk factors for disease clusters, clinical services and health policies must set targets toward management efforts that shape guidelines for best practices in multimorbidity, 39 but also cannot ignore patient-specific needs. This study will also aid in understanding patterns of multimorbidity in a way that facilitates planning and coordination of health services to align well with the needs of diverse groups of individuals with diabetes and heavy comorbidity burden.…”

Strategic Planning to Reduce the Burden of Stroke Among Veterans

“…13 Age-specific non-stroke death rates were derived from the U.S. Census Life Tables. In the absence of data, literature review with VA source preference 14-16 was conducted to inform assumptions. For example, while national sources were compared, the initial prevalence of TIA and stroke were estimated from a study on large administrative VA medical databases.…”

Health conditions in people with spinal cord injury: Contemporary evidence from a population-based community survey in Switzerland

“…The Lance-Williams method is appropriate for the descriptive analysis of multimorbidity in people with SCI, which presumably arises from multiple sequels of the primary condition, implying a hierarchical algorithm. The Lance-Williams algorithm provides a flexible method to conserve the original space between clusters of HCs as much as possible (20). To facilitate 2-dimensional graphical display the similarity matrix was mapped onto a 2-dimensional coordinate system using multidimensional scaling (21).…”