JMIR Publications

ABSTRACT

Background:

Acoustic biomarkers derived from speech signals is a promising non-invasive technique for diagnosing Type 2 Diabetes Mellitus (T2DM). Despite its potential, there remains a critical gap in knowledge regarding the optimal number of voice recordings and recording schedule necessary to achieve effective diagnostic accuracy.

Objective:

Our objective was to determine the optimal number of voice samples, and ideal recording schedule (frequency & timing), which is required to maintain T2DM diagnostic efficacy while reducing patient burden.

Methods:

We analyzed voice recordings from 78 adults (22 women), including 39 individuals diagnosed with T2DM. Participants had an average age of 45.26±10.63 years and BMI of 28.07±4.59 kg/m². In total, 5,035 voice recordings were collected, with an average of 4.91±1.45 recordings per day, and higher adherence observed among women (5.13±1.38 vs. 4.82±1.46 in men). We evaluated the diagnostic accuracy of a previously developed voice-based model under different recording conditions. Segmented linear regression was used to assess model accuracy across varying numbers of voice recordings, and Kendall’s Tau correlation measured the relationship between recording settings and accuracy. A significance threshold of P<0.05 was applied.

Results:

Our results showed that including up to 6 voice recordings notably improved model accuracy for T2DM compared to using only one recording, with accuracy increasing from 59.61 to 65.02 for men and from 65.55 to 69.43 for women). Additionally, the day on which voice recordings were collected did not significantly affect model accuracy (P>0.05). However, adhering to recording within a single day demonstrated higher accuracy, with accuracy of 73.95% for women and 85.48% for men when all recordings were from the second and first days, respectively.

Conclusions:

This study underscores the optimal voice recording settings to reduce patients burden while maintaining diagnostic efficacy.