Generalisable long COVID subtypes: findings from the NIH N3C and RECOVER programmes

• DOI: 10.1016/j.ebiom.2022.104413
• Publication Date: 2022-12-21T18:02:15Z
• Authors: Justin T. Reese; Hannah Blau; Elena Casiraghi; Timothy Bergquist; Johanna J. Loomba; Tiffany J. Callahan; Bryan Laraway; Corneliu Antonescu; Ben Coleman; Michael Gargano; Kenneth J. Wilkins; Luca Cappelletti; Tommaso Fontana; Nariman Ammar; Blessy Antony; T.M. Murali; J. Harry Caufield; Guy Karlebach; Julie A. McMurry; Andrew Williams; Richard Moffitt; Jineta Banerjee; Anthony E. Solomo...; Hannah Davis; Kristin Kostka; Giorgio Valentini; David Sahner; Christopher G. Chute; Charisse Madlock-...; Melissa A. Haendel; Peter N. Robinson; Heidi Spratt; Shyam Visweswaran; Joseph Eugene Flack; Yun Jae Yoo; Davera Gabriel; G. Caleb Alexander; Hemalkumar B. Mehta; Feifan Liu; Robert T. Miller; Rachel Wong; Elaine L. Hill; Lorna E. Thorpe; Jasmin Divers
• Keywords: Long COVID; Coronaviruses; Epidemiology; Clinical Sciences; 610; Clinical sciences; Human Phenotype Ontology; COVID-19; Human Phenotype Ontology; Long COVID; Machine learning; Precision medicine; Semantic similarity;; RECOVER Consortium; 03 medical and health sciences; Post-Acute COVID-19 Syndrome; Machine learning; Machine Learning and Artificial Intelligence; Humans; Precision Medicine; N3C Consortium; 0303 health sciences; JGM; Biomedical and Clinical Sciences; SARS-CoV-2; Precision medicine; COVID-19; Articles; 3. Good health; Good Health and Well Being; Infectious Diseases; Emerging Infectious Diseases; Networking and Information Technology R&D (NITRD); Semantic similarity; Public Health and Health Services; Disease Progression

Stratification of patients with post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) would allow precision clinical management strategies. However, long COVID is incompletely understood and characterised by a wide range of manifestations that are difficult to analyse computationally. Additionally, the generalisability of machine learning classification of COVID-19 clinical outcomes has rarely been tested.We present a method for computationally modelling PASC phenotype data based on electronic healthcare records (EHRs) and for assessing pairwise phenotypic similarity between patients using semantic similarity. Our approach defines a nonlinear similarity function that maps from a feature space of phenotypic abnormalities to a matrix of pairwise patient similarity that can be clustered using unsupervised machine learning.We found six clusters of PASC patients, each with distinct profiles of phenotypic abnormalities, including clusters with distinct pulmonary, neuropsychiatric, and cardiovascular abnormalities, and a cluster associated with broad, severe manifestations and increased mortality. There was significant association of cluster membership with a range of pre-existing conditions and measures of severity during acute COVID-19. We assigned new patients from other healthcare centres to clusters by maximum semantic similarity to the original patients, and showed that the clusters were generalisable across different hospital systems. The increased mortality rate originally identified in one cluster was consistently observed in patients assigned to that cluster in other hospital systems.Semantic phenotypic clustering provides a foundation for assigning patients to stratified subgroups for natural history or therapy studies on PASC.NIH (TR002306/OT2HL161847-01/OD011883/HG010860), U.S.D.O.E. (DE-AC02-05CH11231), Donald A. Roux Family Fund at Jackson Laboratory, Marsico Family at CU Anschutz.