19 October 2023 , 09:43
614
0
A six-second voice clip on your phone could be enough to diagnose type 2 diabetes, thanks to a new AI technology.
The test, hailed as a 'potential game-changer', could screen for the disease by just saying a few sentences into your smartphone. The research, published in Mayo Clinic Proceedings: Digital Health, combines voice tech with artificial intelligence. It could help identify millions of people with undiagnosed Type 2 diabetes. The team from Klick Labs in Toronto, Canada, say their test is 89% accurate for women and 86% for men.
The test uses a short voice clip and basic health data like age, sex, height, and weight to create an AI model. This model can tell if a person has Type 2 diabetes. Researchers asked 267 people, diagnosed as either non-diabetic or Type 2 diabetic, to record a phrase on their smartphone six times a day for two weeks. From over 18,000 recordings, scientists analysed 14 acoustic features to spot differences between non-diabetic and Type 2 diabetic individuals. The team studied various vocal features, like changes in pitch and intensity that we can't hear.
Scientists have used signal processing to detect changes in the voice caused by Type 2 diabetes, with these vocal changes differing between men and women. Researcher Jaycee Kaufman, who led the study, said: "Our research highlights significant vocal variations between individuals with and without Type 2 diabetes and could transform how the medical community screens for diabetes. Current methods of detection can require a lot of time, travel, and cost. Voice technology has the potential to remove these barriers entirely." she added.
Nearly half of the 480 million adults worldwide living with diabetes don't know they have it, and almost 90% of these cases are Type 2 diabetes. Diabetes UK reports that 4.3 million people in Britain have either type 1 or type 2 diabetes, with another 2.4 million at high risk of developing the condition. Type 2 diabetes is largely driven by lifestyle factors like poor diet and obesity. Professor Yan Fossat, vice president of Klick Labs and principal investigator of this study, believes their non-intrusive and accessible approach could help identify the large percentage of undiagnosed people with Type 2 diabetes.
Martin Lewis issues 8-week warning to phone users ahead of huge price hikes
He said: "Our research underscores the tremendous potential of voice technology in identifying Type 2 diabetes and other health conditions. Voice technology could revolutionise healthcare practices as an accessible and affordable digital screening tool." He added that this could be used to check for high blood pressure, prediabetes and issues related to women's health.
* An AI tool was used to add an extra layer to the editing process for this story. You can report any errors to [email protected]