One of COVID-19’s nastiest tricks is the way it can infect someone and not cause any symptoms. This allows the virus to proliferate under the radar of contact tracers. But new artificial intelligence could help track down these silent carriers.
In a paper published Friday in the journal Scientific Reports, researchers at Synergies Intelligent Systems and Universität Hamburg describe a machine learning algorithm that can identify people in a moving crowd who are most likely asymptomatic carriers of the virus that causes COVID-19. The algorithm makes these predictions based on the GPS-tracked movement of people in a city environment, and known cases of infection.
Such precision contact tracing could reduce the number of people needlessly quarantined by lockdowns and conventional contact tracing, according to the authors of the paper. “With this type of technology, we can quarantine a very small fraction of people—just three to five percent—and pretty effectively reduce the effect of the disease,” says Michael Chang, co-founder of Synergies.
The tool could also be used to identify superspreaders: people infected with the virus who transmit it to a disproportionately high number of people. This could aid public health leaders in prioritizing where to concentrate vaccine supplies to head off an outbreak, Chang says.
One limitation of the tool is that its accuracy depends on people willingly using a GPS-based app on their phones. Such an app would track their location to an accuracy of one meter, and log any positive COVID-19 test results.
“The mobile data is also collectible from cellular data,” says Jianwei Zhang, a professor at Universität Hamburg and an author of the paper. “If we could use data other than GPS to build interactive relations between people—for example by using cameras or indoor localization methods—this would boost the [algorithm’s] prediction accuracy.”
A number of researchers developed digital contact tracing apps early on in the pandemic. Such software was used extensively in East Asia, drawing criticism over privacy rights of citizens. The technology was not widely adopted in many other regions of the world.
The new machine learning technology boosts the accuracy of digital contact tracing by factoring in asymptomatic transmission. The authors call their system “continuous learning and inference of individual probability” or CLIIP. It’s based on a gradient boost ensemble learning tree model. The model is updated with real world data using individual directed graph, or IDG, which is the direction for recording the interactions between individuals at a certain time.
The algorithm also integrates real world data such as credit card transactions, public transport data, and building cameras to determine how long and how often people came into contact, and how much physical distance was between them. The real world data came from a city in China that the authors would not disclose.
The algorithm can also factor in mask wearing, hand washing and health. “Such information can be given by a user via an interactive interface or automatically extracted using further sensors,” says Zhang. “This would make the CLIIP predictions more precise.”
The system labels people based on their disease status, such as susceptible, quarantined, exposed, infected, hospitalized and recovered. “By using these labels, we are using our interactive model to learn what would happen between one guy and his surroundings,” says Shangching Liu, an AI engineer at Synergies who co-authored the paper. Synergies Intelligent Systems is an AI company that builds augmented analytics technologies that decrease the barriers to AI.
Emily Waltz is a freelance science journalist specializing in the intersection of technology and the human body. Her favorite topics include electrical stimulation of the nervous system, wearable sensors, genetic engineering, and tiny robots designed to dive deep into the body. In addition to IEEE Spectrum, Emily is a frequent contributor to the journal Nature Biotechnology. She has also written for Nature, Scientific American, Discover, Outside, and The New York Times. For every story she writes, Emily’s goal is to say something true and useful. She likes to hear from readers and can be contacted through her website or on Twitter.