The Value of AI Based CT Severity Scoring System in Triage of Patients with COVID-19 Pneumonia as Regards Oxygen Requirement and Place of Admission

Abstract

Background: An important component of a pandemic like Covid 19 is to triage patients in order to prevent medical establishments from getting overwhelmed. The objective of our study is to find whether an initial HRCT chest can help triage patient by determining their oxygen requirement, the place of treatment, laboratory parameters and the risk of mortality and to compare 3 CT scoring systems (0-20 model, 0-25 model and percentage of involved lung) to find if one is a better predictor of prognosis than the other. Methods: This was a prospective observational study conducted at a Tertiary care hospital in Mumbai, India. Data collected included baseline demographics, days from swab positivity to CT scan, comorbidities, place of treatment, laboratory parameters, oxygen requirement and mortality. We divided the patients into mild, moderate and severe based on 3 criteria - 20 point CT score (OS1), 25 point CT score (OS2) and opacity percentage (OP). CT scans were analyzed using CT pneumonia analysis prototype software (Siemens Healthcare version 2.5.2, Erlangen, Germany). Findings: 740 patients were included in our study. All the 3 scoring systems showed a significant positive correlation with oxygen requirement, place of admission and death. No correlation with the laboratory parameters could be found. Based on ROC analysis a score of 4 for OS1, 9 for OS2 and 12.7% for OP was determined as the cut off for oxygen requirement. Interpretation: An early CT scan in patients affected with Covid 19 is predictive of the oxygen requirement of the patient. As severity scores increase the chances of requirement of higher oxygen and intubation increase. The severity scoring system can be based on lobar involvement and scored 0-20 or 0-25 or based on percentage of lung involved, as they are all predictive of oxygen requirement. CT severity scoring using an automated deep learning software programme is a great boon for determining oxygen requirement and triage.Funding Statement: No grant from any funding agency was received for this research.Declaration of Interests: We do not report and conflict of interest.Ethics Approval Statement: The Ethics Committee waived the need for ethical clearance and informed consent for this non-interventional study.