Your browser doesn't support javascript.
loading
Generalizable Long COVID Subtypes: Findings from the NIH N3C and RECOVER Programs
Justin Reese; Hannah Blau; Timothy Bergquist; Johanna J. Loomba; Tiffany Callahan; Bryan Laraway; Corneliu Antonescu; Elena Casiraghi; Ben Coleman; Michael Gargano; Kenneth Wilkins; Luca Cappelletti; Tommaso Fontana; Nariman Ammar; Blessy Antony; T. M. Murali; Guy Karlebach; Julie A. McMurry; Andrew Williams; Richard Moffitt; Jineta Banerjee; Anthony E. Solomonides; Hannah Davis; Kristin Kostka; Giorgio Valentini; David Sahner; Christopher G. Chute; Charisse Madlock-Brown; Melissa A. Haendel; Peter N. Robinson.
Afiliación
  • Justin Reese; Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
  • Hannah Blau; The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
  • Timothy Bergquist; Sage Bionetworks. Seattle, WA, USA
  • Johanna J. Loomba; The Integrated Translational Health Research Institute of Virginia (iTHRIV), University of Virginia, Charlottesville, Virginia, USA.
  • Tiffany Callahan; Department of Biomedical Informatics, Columbia University, New York, NY, USA
  • Bryan Laraway; University of Colorado Anschutz Medical Campus, Aurora, CO, USA
  • Corneliu Antonescu; University of Arizona - Banner Health, Phoenix, AZ
  • Elena Casiraghi; AnacletoLab, Dipartimento di Informatica, Universita degli Studi di Milano, Italy
  • Ben Coleman; The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
  • Michael Gargano; The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
  • Kenneth Wilkins; Biostatistics Program, National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, USA.
  • Luca Cappelletti; AnacletoLab, Dipartimento di Informatica, Universita degli Studi di Milano, Italy
  • Tommaso Fontana; AnacletoLab, Dipartimento di Informatica, Universita degli Studi di Milano, Italy
  • Nariman Ammar; University of Tennessee Health Science Center, Memphis, TN, USA
  • Blessy Antony; Department of Computer Science, Virginia Tech, Blacksburg, VA, USA.
  • T. M. Murali; Department of Computer Science, Virginia Tech, Blacksburg, VA, USA.
  • Guy Karlebach; The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
  • Julie A. McMurry; University of Colorado Anschutz Medical Campus, Aurora, CO, USA
  • Andrew Williams; Tufts Medical Center Clinical and Translational Science Institute, Tufts Medical Center, Boston, MA, USA
  • Richard Moffitt; Stony Brook University Department of Biomedical Informatics and Stony Brook Cancer Center, Stony Brook, NY, USA
  • Jineta Banerjee; Sage Bionetworks. Seattle, WA, USA
  • Anthony E. Solomonides; NorthShore University HealthSystem Research Institute, Evanston, IL
  • Hannah Davis; Patient-Led Research Collaborative, NY, USA
  • Kristin Kostka; Northeastern University, OHDSI Center at the Roux Institute, Boston, MA, USA
  • Giorgio Valentini; AnacletoLab, Dipartimento di Informatica, Universita degli Studi di Milano, Italy
  • David Sahner; Axle Informatics, Rockville, MD, USA
  • Christopher G. Chute; Schools of Medicine, Public Health, and Nursing, Johns Hopkins University, Baltimore, MD
  • Charisse Madlock-Brown; University of Tennessee Health Science Center, Memphis, TN, USA
  • Melissa A. Haendel; University of Colorado Anschutz Medical Campus, Aurora, CO, USA
  • Peter N. Robinson; The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
Preprint en En | PREPRINT-MEDRXIV | ID: ppmedrxiv-22275398
ABSTRACT
Accurate stratification of patients with post-acute sequelae of SARS-CoV-2 infection (PASC, or long COVID) would allow precision clinical management strategies. However, the natural history of long COVID is incompletely understood and characterized by an extremely wide range of manifestations that are difficult to analyze computationally. In addition, the generalizability of machine learning classification of COVID-19 clinical outcomes has rarely been tested. We present a method for computationally modeling 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 procedures. Using k-means clustering of this similarity matrix, we found six distinct clusters of PASC patients, each with distinct profiles of phenotypic abnormalities. There was a significant association of cluster membership with a range of pre-existing conditions and with measures of severity during acute COVID-19. Two of the clusters were associated with severe manifestations and displayed increased mortality. We assigned new patients from other healthcare centers to one of the six clusters on the basis of maximum semantic similarity to the original patients. We show that the identified clusters were generalizable across different hospital systems and that the increased mortality rate was consistently observed in two of the clusters. Semantic phenotypic clustering can provide a foundation for assigning patients to stratified subgroups for natural history or therapy studies on PASC.
Licencia
cc_by_nc
Texto completo
Añadir a Mi BVS
Imprimir
XML
Buscar en Google
Texto completo: 1 Colección: 09-preprints Base de datos: PREPRINT-MEDRXIV Tipo de estudio: Prognostic_studies Idioma: En Año: 2022 Tipo del documento: Preprint
Texto completo
Añadir a Mi BVS
Imprimir
XML
Buscar en Google
Texto completo: 1 Colección: 09-preprints Base de datos: PREPRINT-MEDRXIV Tipo de estudio: Prognostic_studies Idioma: En Año: 2022 Tipo del documento: Preprint