Voice’s New Frontier: Diabetes Detection
New research has found significant vocal variations in people with and without type 2 diabetes and suggests that voice technologies could, therefore, be used to detect the condition.
The research, conducted by Klick Labs, identified 14 acoustic features that differentiated people with and without type 2 diabetes. These include variations in voice pitch and intensity.
Identifying people with type 2 diabetes could be as simple as having them speak a few sentences on their smartphones. It found that with just 6 to 10 seconds of an individual’s voice, coupled with basic health information, such as age, gender, height, and weight, it would be possible to develop an AI model capable of detecting type 2 diabetes.
Globally, the International Diabetes Foundation estimates that 240 million adults have diabetes, and more than half are unaware of their condition.
Jaycee Kaufman, a research scientist at Klick Labs, which includes a team of data scientists, engineers, and biologists who conduct scientific research and develop artificial intelligence and software solutions, said current diabetes detection methods often demand considerable time, travel, and expense, while voice technology could eliminate these barriers entirely.
Current screening methods typically involve a visit to the doctor’s office and special blood and urine tests. Kaufman said the new model could “transform” how people are screened for diabetes.
The model developed by Klick Labs was reportedly accurate for 89 percent of women and 86 percent of men. To conduct the study, 267 people, both diagnosed as non-diabetic and with type 2 diabetes, were asked to record a specific phrase into their smartphones six times a day for two weeks, resulting in more than 18,000 recordings.
“Our research underscores the tremendous potential of voice technology in identifying type 2 diabetes and other health conditions. Voice technology could revolutionize healthcare practices as an accessible and affordable digital screening tool,” concluded Yan Fossat, vice president of Klick Labs and principal investigator for this study.