If smartphones can be used to scan QR codes, who’s to say they can’t be used to trace diseases?
In the Philippines, Marvi Rebueno Trudeau is leading a joint public-private project that uses smartphones to detect malaria in blood samples.
Patients can take a snapshot with their phones, and – instead of scrutinising it under a microscope – feed the picture to a database. The algorithm then compares it with other blood samples and identifies if the disease is present.
“If this works, it could be trailblazing”, Trudeau told Apolitical, a digital publication.
The idea, however, was accidental. “It wasn’t a medical breakthrough at all”, said Mario Domingo, founder of Iloopp – the company that runs the algorithm. Her team were originally using AI to scan for Nike and Adidas brands on Instagram and social media.
“To do customer analytics on social media, we use machine learning to try to recognise patterns in images and see if people are getting ready to buy. We were trying to predict behaviour and I said, you know what, something a lot easier than this is blood cells.”
Domingo has broader plans beyond detection: “‘Once that’s done, we can trigger notifications through emails, SMS and apps to specific government agencies and NGOs. Sometimes the action is to mobilise doctors or it could be to trigger an order for mosquito nets, so mobilising medical teams and also the supply chains.”
She also highlights that the same idea can be used to detect Zika, MERS and dengue fever.
The digital trace of malaria cases will be able to help officials trace the source of outbreak, and the spread of infections in a household or village.
So far, the algorithm is 85 percent accurate, short of the 10 percent needed to match the quality of manual tests run by people.
In the Philippines, malaria cases are in steep decline, according to government statistics. Cases have gone down from 46,342 in 2005 to 394 in 2015, the Department of Health shows.