Identification of post-COVID condition in a large population: a machine learning approach
Bibliographic record
Abstract
Post-COVID condition (PCC) is a continuation or new development of symptoms long after recovery from acute illness of COVID-19. Administrative health data is a powerful source of information for large epidemiologic studies. However, PCC is undercoded in the health data; studies relying on PCC diagnosis can substantially underestimate disease prevalence. A machine learning (ML) model was developed to identify people with PCC from those with and without known COVID-19. The cross-sectional study included people with general practitioner visits between April 1, 2021, and March 31, 2022, in the province of Alberta, Canada. Predictors were derived from hospital admission, ambulatory care, and physician visit datasets; strategies were employed to minimize information loss and bias. Using diagnosed PCC as the reference standard, a penalized elastic-net logistic regression model was developed. Model development dataset included 3000 PCC cases and 27,437 non-cases. The model performed well in predicting the cases, with a receiver operating characteristic curve area of 0.96, 73% sensitivity, and 99% specificity. Applying the model to a population-based sample of 3.3 million identified 309,390 persons living with PCC, or a period prevalence estimate of 9.3%. Findings suggest an ML model approach can identify PCC from the health data with excellent accuracy. Our model was unique in incorporating individuals’ healthcare utilization information and trained with cases even without known COVID-19. Considering the underdetection of SARS-CoV-2 infections and undercoding of long-COVID in health data in many jurisdictions, the demonstrated approach would provide a practical alternative to identify persons living with PCC.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".