Development of laboratory-based risk scores to predict mortality in patients hospitalized with COVID-19
Bibliographic record
Abstract
Objectives Patient characteristics related to an increased risk of severe coronavirus disease 2019 (COVID-19) have been thoroughly studied since the beginning of the pandemic; however, clinical tools offering rapid and automated predictions of patients’ acute reactions to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection remain limited. This study explored the associations between laboratory markers and mortality in hospitalized patients with COVID-19 and developed a scoring model using laboratory data to estimate patients’ risk of mortality. Methods Participants were recruited from hospitals in the Greater Toronto Area between January 2020 and February 2022. Demographics, laboratory results, and treatment outcomes were collected from patient medical charts. Admission data for 33 biochemical and hematological markers assessing complete blood cell count, coagulation, general chemistry, inflammatory, liver, renal, and cardiac function were extracted for analyses. Results Logistic regression revealed that 6 laboratory markers, including creatinine, sodium, bicarbonate, base excess, pH, and lactate, were significantly associated with COVID-19 patient mortality. Five markers were incorporated into a multivariable model after excluding correlated analytes. Low bicarbonate levels were the only significant finding in the multivariable model associated with increased odds of mortality. Receiver operating characteristic (ROC) curves including area under the curves (AUCs) revealed that risk scores constructed from multivariable values performed similarly to their univariable counterparts in both the training (0.82 vs 0.83) and validation (0.80 vs 0.80) cohorts. Overall, the risk score exhibited 80% accuracy in predicting mortality, with greater sensitivity than specificity. Conclusions Developed risk scores provide moderate predictions of COVID-19 mortality, which could be improved by assessing larger populations. Additionally, significant markers from our cohort indicate that at-risk patients may present with acid‒base disruptions.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.030 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".