Back

Hematological Parameters as Predictors of COVID-19 Infection: A Cohort Study Using Brazilian Hospital Data

Utley, J.

2024-05-09 infectious diseases
10.1101/2024.05.08.24307015 medRxiv
Show abstract

ObjectivesTo determine if hematology test results can indicate COVID-19 infection. MethodsA cohort study used 2020 Brazilian hospital data for 6,573 patients to run inferential analyses of fourteen red and white blood cell hematology test results, adjusted for age and sex, by patient COVID-19 status. ResultsTen hematological biomarkers were statistically significant predictors of COVID-19 PCR test results; the strongest were Total White Blood Cells: OR=0.90 (0.88-0.93), Basophils: OR=0.97 (0.97-0.98), Total Red Blood Cells: OR=0.88 (0.78-0.99), Hemoglobin: OR=0.93 (0.89-0.97), Hematocrit: OR=0.97 (0.96-0.99). Patient sex was also a strong predictor of COVID-19 PCR test results: OR=1.43 (1.26-1.62). ConclusionsCOVID-19 produces measurable impacts on red and white blood cells that are significant predictors of PCR results. A routine blood draw may offer probabilistic insight as a diagnostic predictor of infection. The virus is associated with impacts in red blood cells vital oxygen transport attributes. Public Health ImplicationsA faster diagnostic tool for COVID-19 will assist providers to triage and isolate those with the virus, reducing hospital transmission. Results are being used to develop a predictive model with high sensitivity and specificity.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.