Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In iScience

The SARS-CoV-2 virus has caused tremendous healthcare burden worldwide. Our focus was to develop a practical and easy to deploy system to predict the severe manifestation of disease in COVID-19 patients with an aim to assist clinicians in triage and treatment decisions. Our proposed predictive algorithm is a trained artificial intelligence-based network using 8,427 COVID-19 patient records from four healthcare systems. The model provides a severity risk score along with likelihoods of various clinical outcomes, namely ventilator use and mortality. The trained model using patient age and nine laboratory markers has the prediction accuracy with an area under the curve (AUC) of 0·78 95% CI: 0·77-0·82, and the negative predictive value NPV of 0·86 95% CI: 0·84-0·88 for the need to use a ventilator and has an accuracy with AUC of 0·85 95% CI: 0·84-0·86, and the NPV of 0·94 95% CI: 0·92-0·96 for predicting in-hospital 30-day mortality.

Singh Vivek, Kamaleswaran Rishi, Chalfin Donald, Buño-Soto Antonio, San Roman Janika, Rojas-Kenney Edith, Molinaro Ross, von Sengbusch Sabine, Hodjat Parsa, Comaniciu Dorin, Kamen Ali