Back

Cluster Analysis Identifies Long COVID Subtypes In Belgian Patients

Mfouth Kemajou, P.; Besse-Hammer, T.; Lebouc, C.; Coppieters, Y.

2023-12-13 public and global health
10.1101/2023.11.22.23298807 medRxiv
Show abstract

SARS CoV-2 infection presents complications known as long Covid, a multisystemic organ disease which allow multidimensional analysis. ObjectivesThis study aims to identify Long Covid clusters and to relate them to the clinical classification devised at the Clinical Research Unit of Brugmann University Hospital, Brussels. MethodA two-stage multidimensional exploratory analysis was performed on a cohort of 205 long Covid patients, involving a Factorial Analysis of Mixed Data (FAMD), and then Hierarchical Clustering Post Component Analysis (HCPC). ResultsThe studys sample comprised 76% women, with an average age of 44.5 years. Three clinical forms were identified: long, persistent, and post-viral syndrome. Multidimensional analysis identified three clusters: cluster 1 (myalgia-like pain) associated with the persistent clinical form; cluster 2 (neurocognitive disorders) linked to the long clinical form; cluster 3 (neurocognitive disorders, anxio-depressive syndrome, joint pain and myalgia, peripheral nervous system disorders with dysautonomia, including Postural Orthostatic Tachycardia Syndrome, along with digestive system disorders). However, biological data did not provide sufficient differentiation between the clusters. ConclusionLong Covid phenotypes, as well as clinical forms, appear to be associated with distinct pathophysiological mechanisms or genetic predisposition, warranting further investigation.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.