Title: AI Voice Analysis Shows Promising Results in Detecting Type 2 Diabetes, Study Finds
Subtitle: Klick Labs’ Pioneering Research Combines Voice Recognition and AI for Revolutionary Diabetes Screening
Date: October 17, 2023
A groundbreaking study conducted by scientists at Klick Labs has identified voice technology as a potential breakthrough in detecting Type 2 diabetes. The research, published in Mayo Clinic Proceedings: Digital Health, highlights the remarkable accuracy achieved by analyzing just a few seconds of a person’s voice using artificial intelligence (AI). The non-intrusive method has the potential to revolutionize diabetes screening by eliminating current detection barriers, such as time, cost, and travel.
In the study, researchers leveraged voice recognition technology and AI to develop an innovative model capable of accurately distinguishing whether an individual has Type 2 diabetes. By analyzing six to 10 seconds of people’s voices along with basic health data (age, sex, height, and weight), the AI model achieved an impressive accuracy rate of 89 percent for women and 86 percent for men.
During the two-week study, the Klick Labs team asked 267 participants, consisting of both non-diabetic individuals and individuals diagnosed with Type 2 diabetes, to record a designated phrase into their smartphones six times daily. With more than 18,000 recordings at their disposal, scientists analyzed 14 acoustic features to identify differences between non-diabetic and Type 2 diabetic individuals.
Jaycee Kaufman, the first author of the paper and a research scientist at Klick Labs, emphasized the potential of this breakthrough in transforming diabetes screening. Kaufman stated, “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.”
The vocal variations detected by the AI model were found to manifest differently in males and females, a surprising finding that further underscores the complexity of the disease.
According to the International Diabetes Federation, almost one in two adults living with diabetes worldwide are unaware of their condition, with nearly 90 percent of cases being Type 2 diabetes. The diagnostic tests currently used for prediabetes and Type 2 diabetes, such as the glycated hemoglobin (A1C) and fasting blood glucose (FBG) tests, often involve visiting healthcare providers. Klick Labs’ non-intrusive and accessible approach offers the potential to screen large numbers of people and identify undiagnosed cases of Type 2 diabetes.
Yan Fossat, vice president of Klick Labs and principal investigator of the study, emphasized the significant potential of voice technology in healthcare. Fossat stated, “Our research underscores the tremendous potential of voice technology in identifying Type 2 diabetes and other health conditions. Voice technology could revolutionize healthcare practices as an accessible and affordable digital screening tool.”
Moving forward, the researchers plan to replicate the study and expand their investigations into using voice as a diagnostic tool in other areas, including prediabetes, women’s health, and hypertension.
The study conducted by Klick Labs opens up new possibilities in diabetes screening, offering a convenient, cost-effective, and non-intrusive alternative to current methods. As further research and advancements continue to unfold, the potential for voice technology to shape healthcare practices becomes increasingly promising.
Reference:
“Acoustic Analysis and Prediction of Type 2 Diabetes Mellitus Using Smartphone-Recorded Voice Segments” by Jaycee M. Kaufman, Anirudh Thommandram, and Yan Fossat, 17 October 2023, Mayo Clinic Proceedings: Digital Health.
DOI: 10.1016/j.mcpdig.2023.08.005