Sunday, September 01, 2024

Voice linked to blood sugar: the potential for voice-based diabetes monitoring

Amazing stuff!

Caveat: The voice is influenced by a host of other factors. The researchers did not present convincing charts of their findings (the Nature article has only two figures.).

From the abstract:
"Glucose levels in the body have been hypothesized to affect voice characteristics. One of the primary justifications for voice changes are due to Hooke’s law, in which a variation in the tension, mass, or length of the vocal folds, mediated by the body’s glucose levels, results in an alteration in their vibrational frequency. To explore this hypothesis, 505 participants were fitted with a continuous glucose monitor (CGM) and instructed to record their voice using a custom mobile application up to six times daily for 2 weeks. Glucose values from CGM were paired to voice recordings to create a sampled dataset that closely resembled the glucose profile of the comprehensive CGM dataset. Glucose levels and fundamental frequency (F0) had a significant positive association within an individual, and a 1 mg/dL increase in CGM recorded glucose corresponded to a 0.02 Hz increase in F0 (CI 0.01–0.03 Hz, P < 0.001). This effect was also observed when the participants were split into non-diabetic, prediabetic, and Type 2 Diabetic classifications (P = 0.03, P = 0.01, & P = 0.01 respectively). Vocal F0 increased with blood glucose levels, but future predictive models of glucose levels based on voice may need to be personalized due to high intraclass correlation."

Voice linked to blood sugar: the potential for voice-based diabetes monitoring "When blood sugar levels go high, so does voice pitch, according to a new study. It paves the way for detecting type 2 diabetes or monitoring diabetics’ blood sugars simply by talking into a smartphone and having AI analyze their speech."

New Diabetes Research in Scientific Reports Links Blood Glucose Levels and Voice (original news release) "Klick Labs’ latest findings highlight potential for voice-based blood sugar monitoring; discovery follows scientists’ pioneering work using vocal biomarkers and AI to detect Type 2 diabetes"

No comments: