Using machine learning involving diagnoses and medications as a risk prediction tool for post-acute sequelae of COVID-19 (PASC) in primary care.

Journal: BMC medicine
PMID:

Abstract

BACKGROUND: The aim of our study was to determine whether the application of machine learning could predict PASC by using diagnoses from primary care and prescribed medication 1 year prior to PASC diagnosis.

Authors

  • Seika Lee
    Occupational and Environmental Medicine, Department of Medical Sciences, Uppsala University, Uppsala, Sweden.
  • Marta A Kisiel
    Occupational and Environmental Medicine, Department of Medical Sciences, Uppsala University, Uppsala, Sweden. marta.kisiel@medsci.uu.se.
  • Pia Lindberg
    Division of Immunology and Respiratory Medicine, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden.
  • Åsa M Wheelock
    Respiratory Medicine Unit, Department of Medicine & Centre for Molecular Medicine, Karolinska Institutet, Karolinska Institutet, Slona, 171 65, Stockholm, Sweden.
  • Anna Olofsson
    Division of Biostatistics, Institute of Environmental Medicine, Karolinska Institutet, 17177, Stockholm, Sweden. Electronic address: anna.olofsson.2@ki.se.
  • Julia Eriksson
    Division of Biostatistics, Institute of Environmental Medicine, Karolinska Institutet, Stockholm, Sweden.
  • Judith Bruchfeld
    Division of Infectious Diseases, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden.
  • Michael Runold
    Division of Immunology and Respiratory Medicine, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden.
  • Lars Wahlström
    Centre for Psychiatry Research, Karolinska Institutet, Stockholm, Sweden.
  • Andrei Malinovschi
    Clinical Physiology, Department of Medical Sciences, Uppsala University, Uppsala, Sweden.
  • Christer Janson
    Department of Medical Sciences: Respiratory, Allergy and Sleep Research, Uppsala University, Uppsala, Sweden.
  • Caroline Wachtler
    Department of Neurobiology, Care Sciences and Society, Division of Family Medicine and Primary Care, Karolinska Institutet, Huddinge, Sweden.
  • Axel C Carlsson
    Department of Neurobiology, Care Sciences and Society, Division of Family Medicine and Primary Care, Karolinska Institutet, Huddinge, Sweden; Academic Primary Health Care Centre, Region Stockholm, Stockholm, Sweden. Electronic address: axel.carlsson@ki.se.