Author(s)
Wen-Hsuan Tseng, MD
Ming-Sui Lee, PhD
Ze-Siang Wang, MS
Tsung-Lin Yang, MD, PhD
Affiliation(s)
National Taiwan University Hospital; National Taiwan University College of Medicine, Taipei, Taiwan; National Taiwan University College of Medicine, Taipei, Taiwan,
Abstract:
Hyaluronic acid (HA) can be degraded over time. However, persistence of the effects after injection laryngoplasty (IL) for unilateral vocal fold paralysis (UVFP) has been observed. The purpose of the study was to develop a non-invasive method with clinical applicability for objective evaluation of the biomaterial effects of the injected HA using artificial intelligence-based ultrasonic assessment. Imaging phantoms were built for designing the algorithm for machine learning. Subsequently, adult patients without formal voice training, who underwent HA IL for UVFP were recruited. The Voice Handicap Index-10 questionnaire, GRBAS scale and normalized glottal closure were evaluated before IL. Patients received ultrasonography for estimation of HA volume as well as voice outcome assessments at 2 weeks, and 2 and 6 months after IL. Contours of HA were described well and volumes were estimated accordingly for imaging phantoms and all participants. Clinical voice outcomes were significantly improved post-operatively and remained stationary. Contrarily, estimated HA volume decreased significantly across time points (1.21±0.53 at 2 weeks, 0.63±0.35 at 2 months, P< 0.001; 0.32±0.25 at 6 months, P< 0.001). Three patients received secondary procedures at 2 months. There were no significant differences in clinical voice outcomes at baseline and 2-week. For ultrasonic outcomes, HA volumes were similar at 2-week and 2-month. However, the remaining HA percentage at 2 months was numerically lower in 2nd-IL group (50.84% v.s. 55.15%). In conclusion, the volume change of the injected HA over time for an individual was estimated non-invasively. The prolonged effect after treatment, longer than HA longevity, was demonstrated objectively for the first time.