COVID-19: Adaptation of a model to predict healthcare resource needs in Valle del Cauca, Colombia
Bibliographic record
Abstract
Background: Valle del Cauca is the region with the fourth-highest number of COVID-19 cases in Colombia (>50,000 on September 7, 2020). Due to the lack of anti-COVID-19 therapies, decision-makers require timely and accurate data to estimate the incidence of disease and the availability of hospital resources to contain the pandemic. Methods: We adapted an existing model to the local context to forecast COVID-19 incidence and hospital resource use assuming different scenarios: (1) the implementation of quarantine from September 1st to October 15th (average daily growth rate of 2%); (2-3) partial restrictions (at 4% and 8% growth rates); and (4) no restrictions, assuming a 10% growth rate. Previous scenarios with predictions from June to August were also presented. We estimated the number of new cases, diagnostic tests required, and the number of available hospital and intensive care unit (ICU) beds (with and without ventilators) for each scenario. Results: We estimated 67,700 cases by October 15th when assuming the implementation of a quarantine, 80,400 and 101,500 cases when assuming partial restrictions at 4% and 8% infection rates, respectively, and 208,500 with no restrictions. According to different scenarios, the estimated demand for reverse transcription-polymerase chain reaction tests ranged from 202,000 to 1,610,600 between September 1st and October 15th. The model predicted depletion of hospital and ICU beds by September 20th if all restrictions were to be lifted and the infection growth rate increased to 10%. Conclusion: Slowly lifting social distancing restrictions and reopening the economy is not expected to result in full resource depletion by October if the daily growth rate is maintained below 8%. Increasing the number of available beds provides a safeguard against slightly higher infection rates. Predictive models can be iteratively used to obtain nuanced predictions to aid decision-making
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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".