AI can detect diabetes — just by listening to you talk: study

health

by alex mitchell

Please consult a robot doctor.

A new medical study has found that artificial intelligence can detect type 2 diabetes by listening to a patient for just 6 to 10 seconds.

Research by Klick Labs was published in .Mayo Clinic Proceedings: Digital Health” showed an 89% correct diagnosis rate for women and 86% for men. According to the release I will explain the breakthrough points in detail.

“Our study highlights significant differences in speech between individuals with and without type 2 diabetes, and has the potential to change the way the medical community screens for diabetes,” said lead author Jaycee Kaufman. “There is,” he said.

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

Researchers had 267 people with and without type 2 diabetes record phrases on their smartphones six times a day for two weeks. More than 18,000 recordings were analyzed for more than 14 different acoustic features that differed between diabetic and non-diabetic patients. Participants also provided basic health data such as age, height, and weight.

Signal processing technology was able to perceive certain sounds in vocal pitches that are unresponsive to the human ear. These hidden sounds provided the necessary clues, Kaufman said.

“Our study highlights the tremendous potential of voice technology in identifying type 2 diabetes and other health conditions,” said Jan Fossat, vice president and principal investigator at Klick.

“Voice technology has the potential to revolutionize healthcare settings as an accessible and affordable digital testing tool.”

Click’s next step is to replicate the study and expand voice search to look for things like prediabetes and high blood pressure.

This news follows recent breakthroughs in biological implants from MIT. This bioimplant fits more seamlessly into the body and aids in the delivery of medications such as insulin.