Deriving and validating a risk prediction model for long COVID: a population-based, retrospective cohort study in Scotland

Objectives
Using electronic health records, we derived and internally validated a prediction model to estimate risk factors for long COVID and predict individual risk of developing long COVID.

Design
Population-based, retrospective cohort study.

Setting
Scotland

Participants
Adults (≥18 years) with a positive COVID-19 test, registered with a general medical practice between March 1, 2020 and October 20, 2022.

Main outcome measures
Adjusted odds ratios (aORs) with 95% confidence intervals (CIs) for predictors of long COVID, and patients’ predicted probabilities of developing long COVID.

Results
68,486 (5.6%) patients were identified as having long COVID. Predictors of long COVID were increasing age (aOR 3.84; 95%CI 3.66-4.03 and aOR 3.66 95%CI 3.27-4.09 in first and second splines), increasing body mass index (BMI) (aOR 3.17; 95%CI 2.78-3.61 and aOR 3.09 95%CI 2.13-4.49 in first and second splines), severe COVID-19 (aOR 1.78; 95%CI 1.72-1.84); female sex (aOR 1.56; 95%CI 1.53-1.60), deprivation (most versus least deprived quintile, aOR 1.40; 95%CI 1.36-1.44), several existing health conditions. Predictors associated with reduced long COVID risk were testing positive while Delta or Omicron variants were dominant, relative to when the Wild-type variant was dominant (aOR 0.85; 95%CI 0.81-0.88 and aOR 0.64; 95%CI 0.61-0.67, respectively) having received one or two doses of COVID-19 vaccination, relative to unvaccinated (aOR 0.90; 95%CI 0.86-0.95 and aOR 0.96; 95%CI 0.93-1.00).

Conclusions
Older age, higher BMI, severe COVID-19 infection, female sex, deprivation, and comorbidities were predictors of long COVID. Vaccination against COVID-19 and testing positive while Delta or Omicron variants were dominant predicted reduced risk.