New York: In a groundbreaking study that combines the power of voice technology with artificial intelligence, researchers from Klick Labs in the United States have taken a major leap forward in diabetes detection. They’ve demonstrated that determining whether an individual has Type 2 diabetes can be as simple as having them speak a few sentences into their smartphone. This innovative approach has the potential to transform the way diabetes is screened and detected.
The AI Model for Diabetes Detection
The research team used six to ten seconds of a person’s voice, along with basic health data like age, sex, height, and weight, to create an AI model capable of distinguishing whether an individual has Type 2 diabetes. The results, detailed in the journal “Mayo Clinic Proceedings: Digital Health,” are quite promising. The model achieved an accuracy rate of 89 percent for women and 86 percent for men.
How the Study Was Conducted
To conduct this study, 267 participants—comprising individuals with and without Type 2 diabetes—were asked to record a specific phrase into their smartphones six times daily for a period of two weeks. More than 18,000 recordings were collected, and researchers analyzed 14 acoustic features to identify differences between non-diabetic and Type 2 diabetic individuals.
Voice as a Diagnostic Tool
The research findings have unveiled significant vocal variations between individuals with and without Type 2 diabetes. According to Jaycee Kaufman, first author of the study and a research scientist at Klick Labs, this discovery could revolutionize the way diabetes is screened. Current detection methods can be time-consuming, costly, and require extensive travel. Using voice technology, these barriers could potentially be eliminated.
Exploring Vocal Features
Researchers examined various vocal features, including subtle changes in pitch and intensity that the human ear can’t easily detect. With signal processing techniques, they were able to identify changes in the voice associated with Type 2 diabetes. Interestingly, these vocal variations manifested differently in males and females.
The Significance of Detecting Type 2 Diabetes
Type 2 diabetes is a significant global health concern. Approximately 240 million adults living with diabetes worldwide are unaware of their condition, and nearly 90 percent of diabetic cases are Type 2 diabetes. Common diagnostic tests for prediabetes and Type 2 diabetes include the glycated hemoglobin (A1C), fasting blood glucose (FBG) test, and the oral glucose tolerance test (OGTT).
A Non-Intrusive and Accessible Approach
Yan Fossat, Vice President of Klick Labs and the principal investigator of this study, highlighted the potential of this new non-intrusive and accessible approach. It has the capability to screen large numbers of individuals and help identify the substantial percentage of undiagnosed people with Type 2 diabetes. Fossat noted that this research underscores the remarkable potential of voice technology not only for identifying diabetes but also for addressing other health conditions. He emphasized the transformative potential of voice technology as an accessible and cost-effective digital screening tool for healthcare.
This groundbreaking research opens up new possibilities for efficient and accessible diabetes screening. As a result, individuals may benefit from earlier detection and treatment, ultimately improving their overall health and well-being.
