Otolaryngologic Symptom Severity Post SARS-CoV-2 Infection.

OBJECTIVE(S): To assess laryngologic symptomatology following severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and determine whether symptom severity correlates with disease severity. METHODS: Single-institution survey study in participants with documented SARS-CoV-2 infection between March 2020 and February 2021. Data acquired included demographic, infection severity characteristics, comorbidities, and current upper aerodigestive symptoms via validated patient reported outcome measures. Primary outcomes of interest were scores of symptom severity questionnaires. Coronavirus disease of 2019 (COVID-19) severity was defined by hospitalization status. Descriptive subgroup analyses were performed to investigate differences in demographics, comorbidities, and symptom severity in hospitalized participants stratified by ICU status. Multivariate logistical regression was used to evaluate significant differences in symptom severity scores by hospitalization status. RESULTS: Surveys were distributed to 5300 individuals with upper respiratory infections. Ultimately, 470 participants with COVID-19 were included where 352 were hospitalized and 118 were not hospitalized. Those not hospitalized were younger (45.87 vs. 56.28 years), more likely female (74.17 vs. 58.92%), and less likely white (44.17 vs. 52.41%). Severity of dysphonia, dyspnea, cough, and dysphagia was significantly worse in hospitalized patients overall and remained worse at all time points. Cough severity paradoxically worsened in hospitalized respondents over time. Dyspnea scores remained abnormally elevated in respondents even 12 months after resolution of infection. CONCLUSIONS: Results indicate that laryngologic symptoms are expected to be worse in patients hospitalized with COVID-19. Dyspnea and cough symptoms can be expected to persist or even worsen by 1-year post infection in those who were hospitalized. Dysphagia and dysphonia symptoms were mild. Nonhospitalized participants tended to have minimal residual symptoms by 1 year after infection.

Quantifying and Improving the Performance of Speech Recognition Systems on Dysphonic Speech.

OBJECTIVE: This study seeks to quantify how current speech recognition systems perform on dysphonic input and if they can be improved. STUDY DESIGN: Experimental machine learning methods based on a retrospective database. SETTING: Single academic voice center. METHODS: A database of dysphonic speech recordings was created and tested against 3 speech recognition platforms. Platform performance on dysphonic voice input was compared to platform performance on normal voice input. A custom speech recognition model was trained on voice from patients with spasmodic dysphonia or vocal cord paralysis. Custom model performance was compared to base model performance. RESULTS: All platforms performed well on normal voice, and 2 platforms performed significantly worse on dysphonic speech. Accuracy metrics on dysphonic speech returned values of 84.55%, 88.57%, and 93.56% for International Business Machines (IBM) Watson, Amazon Transcribe, and Microsoft Azure, respectively. The secondary analysis demonstrated that the lower performance of IBM Watson and Amazon Transcribe was driven by performance on spasmodic dysphonia and vocal fold paralysis. Thus, a custom model was built to increase the accuracy of these pathologies on the Microsoft platform. Overall, the performance of the custom model on dysphonic voices was 96.43% and on normal voices was 97.62%. CONCLUSION: Current speech recognition systems generally perform worse on dysphonic speech than on normal speech. We theorize that poor performance is a consequence of a lack of dysphonic voices in each platform's original training dataset. We address this limitation with transfer learning used to increase the performance of these systems on all dysphonic speech.

The oral health impact of electronic cigarette use: a systematic review.

Introduction: Electronic cigarette (e-cigarette) use is becoming more prevalent and is particularly popular among adolescents and conventional smokers. While the oral health sequelae of conventional smoking are well-established, the impact of e-cigarettes on oral health is still unknown. This study aims to systematically review the available research evidence on the oral health impact of e-cigarette use.Methods: This systematic review was conducted according to PRISMA guidelines and used the Effective Public Health Practice Project Quality Assessment Tool to evaluate the evidence. Three electronic databases (PubMed, Web of Science, and Embase) were systematically searched for studies including case reports. Two independent reviewers extracted data and synthesized the findings.Results: Ninety-nine articles were included in this systematic review. Analyses of the articles yielded seven categories based on symptom similarity and/or focus: mouth effects, throat effects, periodontal effects, dental effects, cytotoxic/genotoxic/oncologic effects, oral microbiome effects, and traumatic/accidental injury. The majority of mouth and throat symptoms experienced by e-cigarette users were relatively minor and temporary, with some evidence that conventional smokers who switched to e-cigarettes experienced mitigation of these symptoms. E-cigarette exposure increased the risk for deteriorating periodontal, dental and gingival health as well as changes to the oral microbiome. Extensive dental damage as a result of e-cigarette explosions were described in case reports. Components of e-cigarette vapor have known cytotoxic, genotoxic, and carcinogenic properties.Conclusions: Although switching to e-cigarettes may mitigate oral symptomatology for conventional smokers, findings from this review suggest that a wide range of oral health sequelae may be associated with e-cigarette use. Well-designed studies to investigate oral health outcomes of e-cigarette use are needed.