A Clinical Decision Support System for COVID-19 Severity Ris
Now open: Certificate Course in Management of Covid-19 by Govt. Of Gujarat and PlexusMDKnow more...Now open: Certificate Course in Management of Covid-19 by Govt. Of Gujarat and PlexusMDKnow more...
Get authentic, real-time news that helps you fight COVID-19 better.
Install PlexusMD App for doctors. It's free.
Several pneumonia severity assessment scores are well established, e.g. the CRB-65 (confusion, respiratory rate, blood pressure, age ?65) or the pneumonia severity index (PSI) scores.

However, do they perform well for COVID-19 or could a specific score be more predictive?

To find out, researchers applied machine learning to derive a prognostic score from the clinical, laboratory, and radiographic parameters of a retrospective cohort of 299 patients with COVID-19 hospitalized in Wuhan, China, from December 23, 2019, to February 13, 2020.

The main outcome was the onset of severe or critical illness (respiratory failure requiring mechanical ventilation, shock, intensive care unit admission, organ failure, or death).

The model with best prediction in the training dataset (area under the curve [AUC]: 0.86) used the parameters age, proportion of lymphocytes in the differential, C-reactive protein, lactate dehydrogenase, creatine kinase, urea, and calcium, all determined at hospital admission.

This score was then validated with 5 international scores. The score predicted severe COVID-19 better than the PSI score.

This model might be useful to access the onset of severe and critical illness among COVID-19 patients and triage at hospital admission.

Source: https://www.jwatch.org/na52036/2020/07/21/clinical-decision-support-system-covid-19-severity-risk
S●●●●m T●●●●r and 4 others like this