Speaking with mask in the COVID-19 era: Multiclass machine learning classification of acoustic and perceptual parameters.

The intensive use of personal protective equipment often requires increasing voice intensity, with possible development of voice disorders. This paper exploits machine learning approaches to investigate the impact of different types of masks on sustained vowels /a/, /i/, and /u/ and the sequence /a'jw/ inside a standardized sentence. Both objective acoustical parameters and subjective ratings were used for statistical analysis, multiple comparisons, and in multivariate machine learning classification experiments. Significant differences were found between mask+shield configuration and no-mask and between mask and mask+shield conditions. Power spectral density decreases with statistical significance above 1.5 kHz when wearing masks. Subjective ratings confirmed increasing discomfort from no-mask condition to protective masks and shield. Machine learning techniques proved that masks alter voice production: in a multiclass experiment, random forest (RF) models were able to distinguish amongst seven masks conditions with up to 94% validation accuracy, separating masked from unmasked conditions with up to 100% validation accuracy and detecting the shield presence with up to 86% validation accuracy. Moreover, an RF classifier allowed distinguishing male from female subject in masked conditions with 100% validation accuracy. Combining acoustic and perceptual analysis represents a robust approach to characterize masks configurations and quantify the corresponding level of discomfort.

Treatment outcomes in patients with laryngotracheal lesions and compromised airway during and prior to the coronovirus disease 2019 pandemic: a tertiary institution's experience.

OBJECTIVE: This study aimed to compare treatment outcomes in patients with laryngeal and tracheal stenosis treated during and prior to the coronavirus disease 2019 pandemic period. METHOD: Patients treated for laryngotracheal lesions with impending airway compromise during the active pandemic period were matched with those treated for similar lesions in the preceding years in a monocentric tertiary hospital setting. RESULTS: During the pandemic period of 55 days, 31 patients underwent 47 procedures. Seven patients (2 children, 5 adults) had open airway surgery, and one had an operation-specific complication. Twenty-four patients (10 children, 14 adults) underwent 40 endoscopic interventions without any complications. Operation specific results during and prior to the pandemic were comparable. CONCLUSION: The management strategy in patients with laryngotracheal lesions and impending airway compromise should not be altered during periods of risk from coronavirus disease 2019. Avoiding a tracheostomy by performing primary corrective surgery or proceeding with a definitive decannulation would be beneficial in these patients to reduce the risk of contagion.