A team has discovered a method to test for Type 2 diabetes by having individuals speak into their smartphones.
Using an Al model developed by a U.S. team from Klick Labs, a person speaking into their smartphone for as little as 10 seconds can be tested for Type 2 diabetes. The test reveals an accuracy rate of 89% for women and 86% for men.
This research demonstrates a transformative shift in how the medical community screens for diabetes.
The study involved 18,000 recordings which were analysed to identify acoustic features distinguishing non-diabetics from diabetics.
Through signal processing, the team was able to identify subtle changes in pitch and intensity. According to figures from the International Diabetes Federation, this tool could be valuable for the estimated 240 million adults worldwide living with the condition unknowingly.
The latest research demonstrates the role AI continues to play in healthcare. With the convergence of machine learning models and data science, there is a notable improvement in patient treatment and support for medical discoveries.
This research emphasises the potential of voice technology in identifying Type 2 diabetes and other health conditions.
Moreover, traditional detection methods necessitate time, travel, and expenses, whereas voice technology holds the potential to eliminate these barriers.
Source: Mayo Clinic Proceedings: Digital Health
Image Credit: iStock
