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

TL;DR

This paper presents a novel pooling method called 'Grid' combined with neural network predictions, significantly reducing COVID-19 testing requirements by 73%, surpassing existing pooling techniques.

Contribution

Introduction of the 'Grid' pooling method combined with neural network predictions to substantially decrease COVID-19 testing volume.

Findings

Test reduction of 73% using 'Grid' pooling and neural networks

'Grid' outperforms Dorfman and double-pooling methods

Efficient testing strategy for large-scale COVID-19 screening

Abstract

We show that combining a prediction model (based on neural networks), with a new method of test pooling (better than the original Dorfman method, and better than double-pooling) called 'Grid', we can reduce the number of Covid-19 tests by 73%.