In "Linear Effects of Glucose Levels on Voice Fundamental Frequency in Type 2 diabetes and Individuals with Normoglycemia," researchers investigated how blood glucose levels influence the frequency of the voice in 505 participants across three glycemic statuses - non-diabetic, prediabetic, and Type-2 diabetic. Participants were fitted with continuous glucose monitors (CGMs) and recorded their voices multiple times daily for two weeks. The analysis revealed a linear relationship where an increase in CGM glucose levels corresponded to an increase in the fundamental frequency in the voice.
"By establishing a significant positive association between glucose levels and fundamental frequency, our study provides compelling justification for more research on using voice to predict and monitor glucose levels," said Jaycee Kaufman, lead author and scientist at Klick Labs. "Whereas current glucose monitoring methods are often invasive and inconvenient, voice-based glucose monitoring could be as easy as talking into a smartphone, which could change the game for the estimated 463 million people around the world living with Type 2 diabetes."
Klick Labs' latest research marks another step forward in its ongoing commitment to revolutionizing the detection and management of diabetes using voice tech and machine learning. Their October 2023 study in Mayo Clinic Proceedings: Digital Health demonstrated that voice and AI can screen for Type 2 diabetes with high accuracy. Previously, their "Screening for Impaired Glucose Homeostasis: A Novel Metric of Glycemic Control" research also appeared in Mayo Clinic Proceedings: Digital Health (May 2023), and their "Homeostasis as a proportional - integral control system" study was published in Nature Digital Medicine (May 2020).
Kaufman J, Jeon J, Oreskovic J, Fossat Y.
Linear effects of glucose levels on voice fundamental frequency in type 2 diabetes and individuals with normoglycemia.
Sci Rep. 2024 Aug 28;14(1):19012. doi: 10.1038/s41598-024-69620-z