Predicting Asymptomatic Carriers

 Would appear to be very big thing if it works significantly, as it suggests below. 

AI Predicts Asymptomatic Carriers of Covid-19

IEEE Spectrum, Emily Waltz,  February 2, 2021

Researchers at technology company Synergies Intelligent Systems and Germany's Universität Hamburg have developed a machine learning algorithm that can identify which people in a moving crowd are most likely asymptomatic carriers of Covid-19. The continuous learning and inference of individual probability (CLIIP) algorithm bases its predictions on global positioning system (GPS)-tracked movement of people in a city, and known cases of infection. CLIIP's accuracy relies on people using a GPS-based smartphone application that tracks their location to within a meter (3.2 feet), and logging their positive viral test results. Synergies' Michael Chang said, "With this type of technology, we can quarantine a very small fraction of people—just 3% to 5%—and pretty effectively reduce the effect of the disease."

Identifying Asymptomatic Virus from Cough Prints

 Most interesting, depending upon how well it works in practice.

MIT Open Voice Model Used to Identify Asymptomatic COVID-19 Patients From Cough Recordings  By BRET KINSELLA  in Voicebot.ai

MIT researchers collected over 70,000 cough recordings from 5,320 people through a website in April and May of 2020 to see if an AI-based speech model could indicate whether someone had contracted COVID-19 even if they are asymptomatic. The hypothesis outlined in an IEEE Open Journal of Engineering in Medicine and Biology article in late September was, “COVID-19 subjects, especially including asymptomatics, could be accurately discriminated only from a forced-cough cell phone recording using Artificial Intelligence.”

The MIT Open Voice Model was trained using the recordings of 4,256 subjects to identify acoustic biomarkers that could indicate the presence of COVID-19 infection. The model was then tested on the remaining 1,064 subjects to determine efficacy. Models based on a Convolutional Neural Network (CNN) were enhanced with transfer learning from previous data sets designed to identify Alzheimer’s disease.

When the test cough recordings were run through the system, “it accurately identified 98.5% of coughs from people that were confirmed to have COVID-19, including 100 percent of asymptomatic — who reported they did not have symptoms but had tested positive for the virus,” according to reporting by MIT News.   ... "