Model MU4


Model MU4 predicts the risk of COVID positive patients to develop severe COVID-19 disease using blood test results.

It achieved an AUC of 0.86 (95% CI, 0.82-0.90) on the training dataset and an AUC of 0.90 (95% CI, 0.82-0.98) on the validation dataset. It was externally validated on five datasets, which showed AUCs ranging from 0.84 to 0.93 with accuracies ranging from 0.74 to 0.88.”

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