Longitudinal Cluster Analysis of Hemodialysis Patients with COVID-19 in the Pre-Vaccination Era

SIMPLE SUMMARY: Clinical presentation and outcomes of Coronavirus disease 2019 (COVID-19) are very heterogeneous. Among the different populations affected by COVID-19, special attention should be given to patients undergoing maintenance hemodialysis. Indeed, these patients present some peculiar characteristics that may influence disease course, leading to elevated morbidity and mortality. Furthermore, in hemodialysis patients, clinical presentations and disease severity may vary widely. Therefore, the identification of clinical and laboratory factors useful to stratify the risk of these patients could be of help in guiding clinical decision making. Starting from this observation, in this study, we tested and validated, in two cohorts of hemodialysis patients with COVID-19, an innovative analytical procedure that combines linear mixed effect modeling and cluster analysis on longitudinal data. The application of this strategy allowed patient stratification from simple and widely available data. Our results could contribute to improving COVID-19 management and supporting the implementation of longitudinal cluster analysis strategy in other clinical settings. ABSTRACT: Coronavirus disease 2019 (COVID-19) in hemodialysis patients (HD) is characterized by heterogeneity of clinical presentation and outcomes. To stratify patients, we collected clinical and laboratory data in two cohorts of HD patients at COVID-19 diagnosis and during the following 4 weeks. Baseline and longitudinal values were used to build a linear mixed effect model (LME) and define different clusters. The development of the LME model in the derivation cohort of 17 HD patients (66.7 ± 12.3 years, eight males) allowed the characterization of two clusters (cl1 and cl2). Patients in cl1 presented a prevalence of females, higher lymphocyte count, and lower levels of lactate dehydrogenase, C-reactive protein, and CD8 + T memory stem cells as a possible result of a milder inflammation. Then, this model was tested in an independent validation cohort of 30 HD patients (73.3 ± 16.3 years, 16 males) assigned to cl1 or cl2 (16 and 14 patients, respectively). The cluster comparison confirmed that cl1 presented a milder form of COVID-19 associated with reduced disease activity, hospitalization, mortality rate, and oxygen requirement. Clustering analysis on longitudinal data allowed patient stratification and identification of the patients at high risk of complications. This strategy could be suitable in different clinical settings.