Scientists have developed an artificial intelligence app that promises to warn of dangerous variants of future pandemics. The study was published in the journal Cell Patterns, writes Science Alert.

The application is called the Early Warning Anomaly Detection (EWAD) system, and when tested against actual SARS-CoV-2 spread data, it accurately predicted which new variants of concern (VOCs) would emerge as the virus mutated.

To create the EWAD, scientists from Scripps Research and Northwestern University in the United States used machine learning. It involves using computers to analyze large amounts of data to identify patterns, develop algorithms, and then make predictions about how those patterns might manifest themselves in future, unknown scenarios.

In this case, the AI provided information on the genetic sequences of SARS-CoV-2 variants as the virus spread, the frequency of these variants, and the reported global mortality rate from COVID-19. The software was able to detect genetic shifts as the virus adapts, which typically manifests as an increase in infection rates and a decrease in mortality rates.

“We could see key gene variants appearing and becoming more prevalent, as the mortality rate also changed, and all this was happening weeks before the VOCs containing these variants were officially designated by the WHO,” says William Balch, a microbiologist at Scripps Research.

By testing the model against what has already happened and finding coincidences between real and predicted data, the scientists were able to prove the effectiveness of EWAD in predicting how measures such as vaccination and mask use might affect the virus’ evolution.

“One of the big lessons of this work is that it is important to take into account not just a few prominent variants, but also the tens of thousands of other undesignated variants, which we call the ‘variant dark matter,” added the scientist.

The researchers noted that their AI algorithms were able to identify the “rules” of the virus’s evolution that would otherwise go unnoticed, which could prove critical in fighting future pandemics as they emerge.

In addition, the system developed may allow scientists to better understand the basics of viral biology. This can be used to improve treatments and other public health measures.

As a reminder, COVID-19 was first detected in humans in December 2019 in the Chinese city of Wuhan. In 2020, the WHO declared the spread of the coronavirus a global pandemic. The disease has killed 6.8 million people around the world. In May this year, the WHO announced the end of the pandemic.