Science and Research

Long-term trends in Post-COVID severity: a machine learning analysis from the POP/COVIDOM cohort of the German NAPKON Cohort Network

BACKGROUND: Post-COVID syndrome (PCS) affects many survivors with varying symptom profiles driven by acute disease severity (PCS-S) or individual resilience (PCS-R). While cross-sectional studies have identified risk factors and gender differences, long-term trajectories remain unclear. This study investigates the stability and progression of PCS-S and PCS-R scores after 9, 24 and 36 months from initial diagnosis, identifying key predictive factors stratified by gender. METHODS: We analyzed data from 1526 participants of the German National Pandemic Cohort Network (NAPKON), modeling symptom-based PCS-score trajectories over time with linear mixed-effects models. Data were split into training (n = 944), test (n = 233), and two-site external validation (n = 349) sets. Gender-stratified elastic-net regression used nine-month clinical and psychosocial measures to predict PCS scores at 24 and 36 months. All data were collected between November 2020 and February 2024. The study is registered on ClinicalTrials.gov (NCT04679584) and in the German Registry for Clinical Studies (DRKS00023742). FINDINGS: PCS-S and PCS-R scores showed small but significant declines between 9 and 36 months (

  • Gutzeit, J.
  • Weiß, M.
  • Bahmer, T.
  • Lieb, W.
  • Schreiber, S.
  • Vehreschild, J. J.
  • Nürnberger, C.
  • Pütz, S. M.
  • Heim, E.
  • Ruß, A. K.
  • Dempfle, A.
  • Krawczak, M.
  • Poick, S.
  • Schäfer, A.
  • Morbach, C.
  • Lehmann, C.
  • Polidori, M. C.
  • Reese, J. P.
  • Zoller, T.
  • Krist, L.
  • Heyckendorf, J.
  • Reinke, L. M.
  • Deckert, J.
  • Hein, G.

Keywords

  • Elastic net regression
  • Fatigue
  • Long COVID
  • Machine-learning
  • Post-COVID syndrome
  • Symptom trajectories
Publication details
DOI: 10.1016/j.eclinm.2026.103822
Journal: EClinicalMedicine
Pages: 103822 
Work Type: Original
Location: ARCN
Disease Area: PALI
Partner / Member: Ghd
Access-Number: 41852926


chevron-down