Vocal changes appear to occur in individuals with T2D versus those without diabetes, according to a study published Mayo Clinic Proceedings: Digital Health. Jaycee M. Kaufman, MSc, and colleagues investigated the potential of voice analysis as a prescreening or monitoring tool for T2D. Voices were compared for 267 participants without diabetes (79 women, 113 men) and those with diabetes (18 women,57 men). Significant differences were observed between voice recordings of adults with and without diabetes, both for the entire dataset and in an age-matched and BMI-matched sample. Overall, pitch and pitch standard deviation achieved the highest predictive accuracy. For women, relative average perturbation jitter was also significant, as were intensity and 11-point amplitude perturbation quotient shimmer for men. When combining these features with age and BMI, the optimal prediction models achieved accuracies of 0.75 for women and 0.70 for men in the age-matched and BMI-matched sample.
