Model MU3

Model MU3 contained semantic CT features and age

Model awaiting external validation

Model MU3 predicts the risk of COVID positive patients to develop severe COVID-19 disease using semantic CT features.

Lesion range was identified as areas of ground-glass opacity or consolidation and was graded with a 6-point scale according to the lesion volume proportion in each single lobe:
0 = no lung parenchyma involved, 1 = up to 5% of lung parenchyma involved, 2 = 5-25%, 3 = 26-50%, 4 = 51-75%, and 5 = 76-100% of lung parenchyma involved.
Using age and and this lesion range score, the model had an AUC of 0.75 (95% CI, 0.70-0.80) on the training dataset and an AUC of 0.83 (95% CI, 0.72-0.94) on the validation dataset.
The final CT score is a total score from five lobes.


Reference: Wu G, et al.

Definition of severe disease: Severe illness is defined as meeting at least one of the following criteria during hospitalization:
• respiratory distress with respiratory frequency ≥ 30/min
• pulse oximeter oxygen saturation ≤ 93% at rest
• oxygenation index (artery partial pressure of oxygen/inspired oxygen fraction) ≤ 300 mmHg
• respiratory failure requiring mechanical ventilation
• shock
• ICU admission due to combined organ failure
• death