Voice Technology and AI: A New Frontier in Diabetes Detection
A recent study by Klick Labs has demonstrated the potential of voice technology, combined with artificial intelligence, to detect type 2 diabetes. This innovative approach, which uses just a few seconds of a person’s voice, could revolutionize diabetes screening, making it more accessible and cost-effective.
- The AI model used 6 to 10 seconds of a person’s voice and basic health data to distinguish whether an individual has type 2 diabetes.
- The model achieved an accuracy of 89% for women and 86% for men.
- The study involved 267 participants who recorded a phrase on their smartphone six times daily for two weeks.
- Vocal changes caused by type 2 diabetes manifested differently in males and females.
- The research suggests that voice technology could remove the time, travel, and cost barriers associated with current diabetes detection methods.
Our research highlights significant vocal variations between individuals with and without type 2 diabetes and could transform how the medical community screens for diabetes,. Current methods of detection can require a lot of time, travel, and cost. Voice technology has the potential to remove these barriers entirely.
— Jaycee Kaufman, first author of the paper and research scientist at Klick Labs
More on Type 2 Diabetes