Application of a Computer Vision Tool for Automated Glottic Tracking to Vocal Fold Paralysis Patients

Objectives: (1) Demonstrate true vocal fold (TVF) tracking software (AGATI [Automated Glottic Action Tracking by artificial Intelligence]) as a quantitative assessment of unilateral vocal fold paralysis (UVFP) in a large patient cohort. (2) Correlate patient-reported metrics with AGATI measurements of TVF anterior glottic angles, before and after procedural intervention. Study Design: Retrospective cohort study. Setting: Academic medical center. Methods: AGATI was used to analyze videolaryngoscopy from healthy adults (n = 72) and patients with UVFP (n = 70). Minimum, 3rd percentile, 97th percentile, and maximum anterior glottic angles (AGAs) were computed for each patient. In patients with UVFP, patient-reported outcomes (Voice Handicap Index 10, Dyspnea Index, and Eating Assessment Tool 10) were assessed, before and after procedural intervention (injection or medialization laryngoplasty). A receiver operating characteristic curve for the logistic fit of paralysis vs control group was used to determine AGA cutoff values for defining UVFP. Results: Mean (SD) 3rd percentile AGA (in degrees) was 2.67 (3.21) in control and 5.64 (5.42) in patients with UVFP (P <.001); mean (SD) 97th percentile AGA was 57.08 (11.14) in control and 42.59 (12.37) in patients with UVFP (P <.001). For patients with UVFP who underwent procedural intervention, the mean 97th percentile AGA decreased by 5 degrees from pre- to postprocedure (P =.026). The difference between the 97th and 3rd percentile AGA predicted UVFP with 77% sensitivity and 92% specificity (P <.0001). There was no correlation between AGA measurements and patient-reported outcome scores. Conclusions: AGATI demonstrated a difference in AGA measurements between paralysis and control patients. AGATI can predict UVFP with 77% sensitivity and 92% specificity.