Now, AI can tell in just 10 seconds whether you have diabetes by simply listening to your voice

A team from US-based Klick Labs created an AI model capable of distinguishing whether a person has Type 2 diabetes from six to 10 seconds of voice audio, with tests revealing an 89 per cent accuracy rate for women and 86 per cent for men.

“Our research highlights significant vocal variations between individuals with and without Type 2 diabetes and could transform how the medical community screens for diabetes,” said Jaycee Kaufman, a research scientist at Klick Labs.

“Current methods of detection can require a lot of time, travel and cost. Voice technology has the potential to remove these barriers entirely.”

The study involved analysing 18,000 recordings in order to identify acoustic features that differentiated non-diabetics from diabetics. Using signal processing, they were able to detect subtle changes in pitch and intensity that are imperceptible to the human ear.

The tool could prove useful for the estimated 240 million adults around the world who are currently living with the condition without realising, according to figures from the International Diabetes Federation.

The latest research demonstrates the ever-growing role AI plays in healthcare, with the convergence of machine learning models, data science helping to improve patient treatment and assisting medical discoveries.

The researchers claim the artificial intelligence model, which requires basic health data from the subject in order to determine whether they are diabetic, could be expanded to diagnose other health conditions.

“Our research underscores the tremendous potential of voice technology in identifying Type 2 diabetes and other health conditions,” said Yan Fossat, vice president of Klick Labs and leader of the research.

“Voice technology could revolutionise healthcare practices as an accessible and affordable digital screening tool.”

The technology was detailed in a study, titled ‘Acoustic analysis and prediction of Type 2 Diabetes Mellitus using smartphone-recorded voice segments’, published in the journal Mayo Clinic Proceedings: Digital Health.

The Independent