Shulou(Shulou.com)11/24 Report--

CTOnews.com, Oct. 22 (Xinhua)-- Type 2 diabetes can be diagnosed by voice just by saying a few words to a smartphone, a new study has found. The new technology, which combines sound technology and artificial intelligence, can help identify millions of undiagnosed people with type 2 diabetes. The study is in the journal Mayo Clinic Progress: digital Health (Mayo Clinic Proceedings:Digital Health).

The study, conducted by Klick Labs in Toronto, Canada, said their tests were 89 per cent accurate for women and 86 per cent for men. The principle is to use a recording of a person of 6 to 10 seconds, as well as some basic health data, such as age, sex, height and weight, to create an artificial intelligence model that can tell whether the person has type 2 diabetes.

The researchers asked 267 people diagnosed with non-diabetes or type 2 diabetes to record a sentence on their smartphones six times a day for two weeks. From more than 18000 recordings, the scientists analyzed differences in 14 acoustic features between non-diabetic and type 2 diabetic individuals, including changes in pitch and intensity that are imperceptible to the human ear. Through signal processing, scientists were able to detect sound changes caused by type 2 diabetes, which are different for men and women.

Researcher Jaycee Kaufman, lead author of this article, said: "our study highlights the great potential of sound technology in identifying type 2 diabetes, which can change the way medical screening is conducted. Current testing methods may require a lot of time, travel and cost, and sound technology has the potential to completely remove these barriers."

According to CTOnews.com, there are 480 million adults worldwide with diabetes, nearly half of whom do not know they have the disease, and nearly 90% of diabetes cases are type 2 diabetes. Type 2 diabetes is mainly caused by a bad lifestyle, and poor diet and obesity are the two main factors.

Professor Yan Fossat, vice president of Klick Lab and lead author of this article, said this non-invasive and easily accessible method could provide screening services for a large population and help identify a large number of undiagnosed patients with type 2 diabetes. "our research highlights the great potential of sound technology in identifying type 2 diabetes and other health problems," he said. Sound technology can be used as a reliable and economical digital screening tool to lead health care change. " He also said the technique could also be used to test high blood pressure, pre-diabetes and women's health.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.