COVID-19 prediction algorithm

They created a classification algorithm that can determine whether a COVID-19 patient is likely to suffer from severe symptoms.

Trained and tested on roughly 100,000 RT-PCR records collected by the Israeli Ministry of Health, the algorithm looks at eight different features, including self-reported symptoms and age, to make its predictions.

Newly published data from Scripps' DETECT study included data from 30,529 device owners, although only 333 of those who were symptomatic also provided their COVID-19 testing results.