Investigating the role of artificial intelligence in predicting perceived dysphonia level

This study aims to investigate the role of one of these models in the field of voice pathology and compare its performance in distinguishing the perceived dysphonia level.

Demographic information, voice self-assessments, and acoustic measurements related to a sample of 50 adult dysphonic outpatients were presented to ChatGPT and Perplexity AI chatbots, which were interrogated for the perceived dysphonia level.

The agreement between the auditory-perceptual assessment by experts and ChatGPT and Perplexity AI chatbots, as determined by Cohen’s Kappa, was not statistically significant (p = 0.429). There was also a low positive correlation (r_s = 0.30, p = 0.03) between the diagnosis made by ChatGPT and Perplexity AI chatbots (r_s = 0.30, p = 0.03).

It seems that AI could not play a vital role in helping the voice care teams determine the perceptual level of dysphonia.