AI could help to avoid a future pandemic, according to a new study which highlights its ability to control outbreaks of new infectious diseases.
A team of researchers from the University of Gothenburg looked at how machine learning can be used to find effective testing methods during epidemic outbreaks.
Using a simulation, they developed a method which was able to use information on the first case of a disease to estimate the risk to the rest of the population.
Despite having limited data available, the AI could then go on to outline the best possible testing strategies, something which could have helped contain COVID-19 earlier.
It showed which individuals offered the best potential for testing allowing scientists learn to more about future diseases and how to control them sooner.
The machine learning could also adapt to specific characteristics of the disease and be tweaked to match this.
This AI technique utilises computer algorithms, with the software being able to automatically process data and spot patterns in these, meaning it can learn from these.
Researchers noted that this could be the beginning of being able to implement more targeted initiatives to reduce the spread of future infections.
However they also said because the study was a simulation of an epidemic, testing with real data is needed to improve the outcomes further. This also meant it was too early for it to be used for the ongoing COVID-19 pandemic.
Lead author Laura Natali said: “In the study, the outbreak can quickly be brought under control when the method is used, while random testing leads to uncontrolled spread of the outbreak with many more infected individuals.
“Under real world conditions, information can be added, such as demographic data, age and health-related conditions, which can improve the method’s effectiveness even more.
“The same method can also be used to prevent reinfections in the population if immunity after the disease is only temporary.”
She also spoke about how this controlled method of testing was more effective than those previously used.
“When a large outbreak has begun, it is important to quickly and effectively identify infectious individuals.
“In random testing, there is a significant risk failing to achieve this, but with a more goal-oriented testing strategy we can find more infected individuals and thereby also gain the necessary information to decrease the spread of infection.
“We show that it is possible to use relatively simple and limited information to make predictions of who would be most beneficial to test. This allows better use of available testing resources.”