High Comorbidity Burden in Patients with SLE: Data from the Community-Based Lupus Registry of Crete

Abstract

Comorbidities and multimorbidity, often complicating the disease course of patients with chronic inflammatory rheumatic diseases, may be influenced by disease-intrinsic and extrinsic determinants including regional and social factors. We analyzed the frequency and co-segregation of self-reported comorbid diseases in a community-based Mediterranean registry of patients (n = 399) with systemic lupus erythematosus (SLE). Predictors for multimorbidity were identified by multivariable logistic regression, strongly-associated pairs of comorbidities by the Cramer's V-statistic, and comorbidities clusters by hierarchical agglomerative clustering. Among the most prevalent comorbidities were thyroid (45.6%) and metabolic disorders (hypertension: 24.6%, dyslipidemia: 33.3%, obesity: 35.3%), followed by osteoporosis (22.3%), cardiovascular (20.8%), and allergic (20.6%) disorders. Mental comorbidities were also common, particularly depression (26.7%) and generalized anxiety disorder (10.7%). Notably, 51.0% of patients had ≥3 physical and 33.1% had ≥2 mental comorbidities, with a large fraction (n = 86) displaying multimorbidity from both domains. Sociodemographic (education level, marital status) and clinical (disease severity, neurological involvement) were independently associated with physical or mental comorbidity. Patients were grouped into five distinct clusters of variably prevalent comorbid diseases from different organs and domains, which correlated with SLE severity patterns. Conclusively, our results suggest a high multimorbidity burden in patients with SLE at the community, advocating for integrated care to optimize outcomes.

Keywords: autoimmunity; cardiovascular; disease severity; mental disorders; metabolic risk factors; social factors.

Figure 1

Co-segregation of comorbidities in patients with SLE at the community-based registry of Crete. (A) Correlation matrix of various comorbidities from diverse organs and domains. Numbers inside each box represents the Cramer’s V statistic estimated for each pair of comorbidities with values > 0.10 signifying robust correlation. Color intensity corresponds to the chi-squared p-value for each pairwise association. (B) SLE patients were categorized according to the number of physical (none, 1 or 2, ≥3) and mental (none, 1, ≥2) comorbidities as described in the main text. Y axis shows the number of patients with various combinations of physical and mental comorbid disorders.

Figure 2

Distinct comorbidities phenotypes in patients with SLE revealed by cluster analysis. (A) Utilizing Gower’s distance and complete linkage method, hierarchical agglomerative clustering of the patients according to their comorbidity profile was performed. The chi-squared statistic was used to examine whether the distribution of the comorbidities differed between the identified patient clusters. The heatmap of the frequencies of comorbidities groups across the patient clusters is shown. Legend depicts the relative frequency (ranging from −1.5 to +1.5) of each comorbidity within each cluster. (B) Prevalence of SLE severity patterns (mild, moderate, severe) based on the BILAG system across the identified comorbidities clusters (cluster 1 to 5). Numbers are proportions (%).