Scientists have created an AI tool that predict spreading of a flu virus

Wouldn't you like a tool that intimidated you when you're surrounded by a highly contagious infection of influenza? If so, your wishes have been answered. Scientists have been working on a tool that uses artificial intelligence to do just the same.

As the influenza infections spread at a fast pace, as it moves about as the people move around, it is difficult to track it in real time. But the study published in the journal Nature Communications says that a new approach, called ARGONet, makes accurate predictions than the earlier high-performing forecasting approach, ARGO.

"Timely and reliable methodologies for tracking influenza activity across locations can help public health officials mitigate epidemic outbreaks and may improve communication with the public to raise awareness of potential risks," said Mauricio Santillana, from Computational Health Informatics Program at Boston Children's Hospital in the US.

The new approach uses machine two flu detection models and machine learning. The first model ARGO used information from electronic health records, flu-related Google searches and historical flu activity in any region. The study showed ARGO on its own outperformed Google Flu Trends, the previous forecasting system that operated from the years 2008 to 2015. But to improve the accuracy further, ARGONet added a second model which drew on spatial-temporal patterns of flu spread in neighbouring areas. The machine learning system was fed with flu predictions from both models to reduce errors in predictions.

The researchers truly believe that their dual model approach will set a foundation for "precision public health" in infectious diseases.