A combination of 'pooling' with a prediction model can reduce by 73% the number of COVID-19 (Corona-virus) tests

These tests are the most common way to empirically identify carriers of the virus, and urgently need to be conducted on a large scale. Today, patients are granted a test if deemed necessary by the government and are carried out individually, i.e., every sample is tested separately. The problem is that the number of samples gathered today supersedes the amount of tests that can be conducted daily; Moreover, the worldwide shortage in equipment and resources prevents a much-needed increase in the number of daily tests. As a result, the testing system today is at full capacity, and falls short of the need. Two recent developments are relevant to the solution that we describe here: 1. Data regarding tests and the patients behind them has been gathered (over 120,000 tests in Israel as of Mid.