New Program can Help COVID Alert App Improve Vaccination Campaigns

Researchers are developing a program that could be added to the COVID alert app used on smartphones to better target vaccination campaigns.

The COVID alert app is based on the Google-Apple exposure notification API (GAEN API), a functionality that the tech companies rolled out in April 2020. The Canadian government built an app around the GAEN API, which became the COVID alert app, and managed the system for uploading positive cases. The COVID alert app tracks the contacts an individual has by virtually pinging the smartphones of those around them.

The innovation in the add-on the researchers developed is to use the app to target vaccinations. Instead of targeting specific geographies or demographic groups, the researchers propose a strategy based on individual contacts.

"Digital contact tracing apps can be a simple way to optimize vaccination strategies without people having to give up private information," said Mark Penney, a researcher in the Department of Applied Mathematics at the University of Waterloo.

Penney and co-authors recently released a research study showing that such a strategy would almost half the number of vaccines required to bring the pandemic under control.

The new program was specifically designed with privacy in mind and only keeps a record of the number of contacts, not any location or other personal data. The add-on was purposefully made to be "a blunt tool," said Yigit Yargic, a PhD researcher at the Perimeter Institute for Theoretical Physics and one of the co-investigators on the study.

"We don't want to be able to identify who someone contacts or where they go," he said. "All that we need to know is how many total contacts someone may have. The app keeps a cryptographic token, like a digital handshake, for any contact. It would then prioritize people who have the most contacts for vaccinations."

The research project started at the onset of the pandemic and was in progress when there was a scarcity of vaccines in Canada. As the vaccine rollout began, the strategy used in Ontario was to prioritize vaccines to regions or demographics that were deemed most at risk. The new app takes that same strategy to another level by targeting not just hotspots or vulnerable populations but the people, for whatever reasons, most likely to be vectors for spreading the virus.

"The app might tell you, if you were an essential worker and coming into contact with lots of people, that you should get a vaccine," said Penney. "If you're a person working from home and not meeting many people, you probably wouldn’t get a notification to get vaccinated. The point is to target the people who are most likely to spread the disease."

The results of the modelling and simulations for the new app were a resounding success, resulting in a massive increase in the effectiveness of a limited number of vaccines. However, Yargic points out, "the version of the app used in the model is idealized in the sense that only those selected would get the vaccine, and everyone the app selected ends up being vaccinated."

The researchers highlighted that the program can also be used for other infectious diseases. For example, it could be a tool to inform people if they should get a regular flu shot based on their contact patterns.

Penney MD, Yargic Y, Smolin L, Thommes EW, Anand M, et al.
"Hot-spotting" to improve vaccine allocation by harnessing digital contact tracing technology: An application of percolation theory.
PLOS ONE 16(9): e0256889, 2021. doi: 10.1371/journal.pone.0256889

Most Popular Now

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

AI Body Composition Measurements can Pre…

Adiposity - or the accumulation of excess fat in the body - is a known driver of cardiometabolic diseases such as heart disease, stroke, type 2 diabetes, and kidney disease...

AI can Strengthen Pandemic Preparedness

How to identify the next dangerous virus before it spreads among people is the central question in a new Comment in The Lancet Infectious Diseases. In it, researchers discuss how...

'Future-Guided' AI Improves Se…

In the world around us, many things exist in the context of time: a bird’s path through the sky is understood as different positions over a period of time, and...

New AI Tool Scans Social Media for Hidde…

A new artificial intelligence tool can scan social media data to discover adverse events associated with consumer health products, according to a study published September 30th in the open-access journal...

Highland to Help Companies Seize 'N…

Health tech growth partner Highland has today revealed its new identity - reflecting a sharper focus as it helps health tech companies to find market opportunities, convince target audiences, and...

New Antibiotic Targets IBD - and AI Pred…

Researchers at McMaster University and the Massachusetts Institute of Technology (MIT) have made two scientific breakthroughs at once: they not only discovered a brand-new antibiotic that targets inflammatory bowel diseases...

Study Finds One-Year Change on CT Scans …

Researchers at National Jewish Health have shown that subtle increases in lung scarring, detected by an artificial intelligence-based tool on CT scans taken one year apart, are associated with disease...

New AI Tools Help Scientists Track How D…

Artificial intelligence (AI) can solve problems at remarkable speed, but it’s the people developing the algorithms who are truly driving discovery. At The University of Texas at Arlington, data scientists...

Yousif's Story with Sectra and The …

Embarking on healthcare technology career after leaving his home as a refugee during his teenage years, Yousif is passionate about making a difference. He reflects on an apprenticeship in which...

AI Tool Offers Deep Insight into the Imm…

Researchers explore the human immune system by looking at the active components, namely the various genes and cells involved. But there is a broad range of these, and observations necessarily...