A Machine-Learning Algorithm for the Automated Perceptual Evaluation of Dysphonia Severity.

OBJECTIVES: Auditory-perceptual assessments are the gold standard for assessing voice quality. This project aims to develop a machine-learning model for measuring perceptual dysphonia severity of audio samples consistent with assessments by expert raters. METHODS: The Perceptual Voice Qualities Database samples were used, including sustained vowel and Consensus Auditory-Perceptual Evaluation of Voice sentences, which were previously expertly rated on a 0-100 scale. The OpenSMILE (audEERING GmbH, Gilching, Germany) toolkit was used to extract acoustic (Mel-Frequency Cepstral Coefficient-based, n = 1428) and prosodic (n = 152) features, pitch onsets, and recording duration. We utilized a support vector machine and these features (n = 1582) for automated assessment of dysphonia severity. Recordings were separated into vowels (V) and sentences (S) and features were extracted separately from each. Final voice quality predictions were made by combining the features extracted from the individual components with the whole audio (WA) sample (three file sets: S, V, WA). RESULTS: This algorithm has a high correlation (r = 0.847) with estimates of expert raters. The root mean square error was 13.36. Increasing signal complexity resulted in better estimation of dysphonia, whereby combining the features outperformed WA, S, and V sets individually. CONCLUSION: A novel machine-learning algorithm was able to perform perceptual estimates of dysphonia severity using standardized audio samples on a 100-point scale. This was highly correlated to expert raters. This suggests that ML algorithms could offer an objective method for evaluating voice samples for dysphonia severity.

Cannabinoid Use in the Treatment of Laryngeal Dystonia and Vocal Tremor: A Pilot Investigation.

OBJECTIVES/HYPOTHESIS: Laryngeal dystonia and vocal tremor can be debilitating conditions with suboptimal treatment options. Botulinum toxin chemodenervation is typically the first-line treatment and is considered the gold standard. However, patient response to botulinum toxin varies widely. There is anecdotal evidence for the use of cannabinoids in treating laryngeal dystonia with a scarcity of research investigating this potential treatment option. The primary objective of this study is to survey patients with laryngeal dystonia and vocal tremor to gauge how some people are using cannabinoids to treat their condition and to ascertain patient perceptions of cannabinoid effectiveness. STUDY DESIGN: This is a cross-sectional survey study. METHODS: An eight-question anonymous survey was distributed to people with abductor spasmodic dysphonia adductor spasmodic dysphonia, vocal tremor, muscle tension dysphonia, and mixed laryngeal dystonia via the Dysphonia International (formerly National Spasmodic Dysphonia Association) email listserv. RESULTS: 158 responses: 25 males and 133 females, (mean [range] age, 64.9 [22-95] years). 53.8% of participants had tried cannabinoids for the purposes of treating their condition at some point, with 52.9% of this subset actively using cannabis as part of their treatment. Most participants who have used cannabinoids as a treatment rank their effectiveness as somewhat effective (42.4%) or ineffective (45.9%). Participants cited a reduction in voice strain and anxiety as reasons for cannabinoid effectiveness. CONCLUSIONS: People with laryngeal dystonia and/or vocal tremor currently use or have tried using cannabinoids as a treatment for their condition. Cannabinoids were better received as a supplementary treatment than as a stand-alone treatment.

Provider and Patient Satisfaction with Telemedicine Voice Therapy During the COVID-19 Pandemic.

OBJECTIVES: The COVID-19 pandemic expanded the use of telemedicine, but there is no literature exploring both patient and provider satisfaction specifically in the provision of voice therapy. This study aims to investigate patient and provider satisfaction with virtual voice therapy, its associated factors, and any correlation between the two. METHODS: Cross-sectional study. Participants included 226 adults who underwent voice therapy delivered via telepractice at the USC Voice Center between April and October 2020. Patients and providers self-reported their level of satisfaction on a visual analog scale (VAS; range 0-100). Patient satisfaction was additionally measured using a previously validated Telemedicine Satisfaction Questionnaire (TSQ; range 1-5), and a binary question about their desire to choose telemedicine over in-person therapy in the future. Three speech-language pathologists rated provider satisfaction for all 226 patients. Patient satisfaction survey was completed by 55 patients. Multivariable linear regression analyses and linear mixed-effects models were used to assess the results. RESULTS: Patient and provider mean (SD) VAS satisfaction scores were 86.8 (18.6) and 80.6 (19.7), respectively. The mean (SD) TSQ score was 4.4 (0.6). In a multivariable model, patient satisfaction levels were significantly higher for hypofunctional than for hyperfunctional dysphonia diagnoses. Forty-four (73%) patients reported they would prefer telemedicine voice therapy over in-person appointments, which was significantly correlated with internet reliability (P = 0.04). For providers, satisfaction was significantly lower for patients whose diagnosis had changed after initiation of voice therapy (Δ = -16.0 [95% CI: -28.7 to -3.2]) and for encounters with Asian patients compared to White patients (Δ = -11.6 [95% CI: -18.9 to -4.2]). Patient and provider satisfaction scores were weakly correlated (r = 0.19). CONCLUSIONS: Our findings suggest that virtual voice therapy is not simply an alternative to in-person service, but rather an effective method useful beyond the current pandemic with proper diagnosis and technical support.

Cricothyroid Muscle Botulinum Toxin Chemodenervation to Treat Recalcitrant High-Pitched Functional Dysphonia in an Adult Male.

INTRODUCTION: Functional dysphonia occurs in the absence of structural or neurologic laryngeal abnormalities with various manifestations including aphonia and inappropriate vocal pitch. Voice therapy is the first-line treatment, and literature on treatment options for functional dysphonia unresponsive to voice therapy is limited. METHODS: Retrospective medical records review and report of a case. RESULTS: We report a unique case of an adult male with recalcitrant high-pitched functional dysphonia of adult-onset that was successfully treated with a single cricothyroid muscle botulinum toxin (Botox) chemodenervation injection. CONCLUSION: Cricothyroid muscle botulinum toxin chemodenervation can be an effective treatment for recalcitrant functional dysphonia.

The Voice Problem Impact Scales (VPIS).

INTRODUCTION: Patient-reported outcome measures (PROMs) are important for systematically assessing a person's perspectives and experiences with disease to inform clinical decision-making. However, PROMs can occasionally fail to capture subtle differences amongst subgroups. In response to this problem, the aim of the current study was to examine the convergent validity of four patient-reported voice activity and participation scales to better reflect and describe the impact of a voice problem in a patient's work, home, social and overall life. It was hypothesized that augmenting the validated PROM with a directed situational short instrument may enhance patient and clinician communication. This would allow for further description of individual areas of activity limitations or participation restrictions that are relevant to the patient, potentially informing therapeutic goals. METHODS: The Voice Problem Impact Scales (VPIS) were developed following the criteria outlined by Francis et al (2016). A retrospective chart review was completed for voice therapy treatment seeking patients at the USC Voice Center. Results from the Voice Handicap Index-10 (VHI-10) and VPIS scores were recorded at the time of the evaluation. Consensus Auditory Perceptual Evaluation of Voice (CAPE-V) assessment was performed by an SLP with fellowship training in voice. RESULTS: Three hundred four charts were reviewed, and 198 met inclusion criteria. When considering all patients, VHI-10 scores were significantly correlated with each domain of the VPIS, including overall (R = 0.635, P < 0.001), work (R = 0.436, P < 0.001), social (R = 0.714, P < 0.001), and home (R = 0.637, P < 0.001). For females aged 18-39 and aged ≥60, the VHI-10 was correlated with all domains except work. CAPE-V score was significantly correlated with the social domain (R = 0.236, P = 0.001). Using the corrected significance level, it was not correlated with the overall (R = 0.165, P = 0.022), home (R = 0.197, P = 0.006), or work domains (R = 0.042, P = 0.567). The VHI-10 was not correlated with any of the VPIS domains for males aged 18-39, was correlated with all domains for males aged 40-59, and was correlated with all domains except work for males aged ≥60. Age was the only significant predictor of the work domain (ß = -4.631 P < 0.001), with a model fit of R2 = 0.101. CONCLUSIONS: Scores from each domain of the VPIS are significantly correlated with VHI-10 scores thus confirming the instrument's convergent validity. There are certain groups for which currently used questionnaires may underrepresent the impact of dysphonia on the patient's life. The VPIS represents a broad tool that might allow the patient to interpret each scale within their individual context and cultural background. The VPIS emphasizes the significance of the dysphonia on quality of life in four common environments. Using this instrument can augment questionnaires and initiate conversations between the provider and patient to determine the area(s) where voice impairment is most important enhancing shared decision-making on therapeutic goals for plan of care.

Laryngologists' Reported Decision-Making in Presbyphonia Treatment.

OBJECTIVE: Decision-making regarding behavioral versus procedural intervention in the treatment of presbyphonia has not been well defined. The study objective was to survey laryngologists' reported practice patterns and decision-making in presbyphonia. METHODS: All laryngology faculty in U.S. academic medical centers with residency programs were recruited to complete an anonymous 29-item survey regarding decision-making in presbyphonia treatment. The survey included 5 sections: demographics, first-line treatment distribution, factors that drive decision-making toward procedural intervention, treatment progression if first-line treatment is insufficient, durable treatment. RESULTS: Of 153 laryngologists surveyed, 89 responded (58%). Voice therapy (VT) was the most often reported first-line treatment, with 57% of respondents indicating the majority of their patients receive VT initially. Most respondents (83%) indicated they occasionally use procedural intervention as first-line treatment. Factors driving first-line procedural intervention were severe glottal insufficiency (87%), high occupational/social voice demands (76%), voice not stimulable for change (73%), difficulty attending VT (70%), severe dysphonia (65%), and dysphagia (61%). The majority of respondents indicated the following do not affect their decision to pursue procedural intervention: patient age (88%); medical comorbidities (63%); patient's desire for a "quick fix" (55%); patient-reported outcome measures (51%). Most respondents (81%) use trial injection augmentation before durable treatment. Of durable treatments, bilateral thyroplasty was preferred (71%), followed by CaHA (15%) and lipoinjection (11%). CONCLUSIONS: This study is the first to our knowledge to examine factors that influence decision-making in presbyphonia treatment. While VT remains the most frequent first-line treatment, study results better inform decision-making regarding first-line procedural intervention.

Pilot Evaluation of Community-Based Vocal Health Screenings.

INTRODUCTION: Community-based health fairs can help identify at-risk populations, improve health literacy, and facilitate access to medical services. No community-based screenings specifically targeting vocal health were identified in the literature. The purpose of this study is to compare the results of community-based vocal health screenings across two populations: a group of community members with unknown risk of voice problems, and a group of actors belonging to a profession with a known increased risk of voice problems. METHODS: Vocal health screenings were conducted at two free, community-based health fair events in the Los Angeles area. One was open to the public, and one was organized specifically for actors who are members of the Screen Actors Guild-American Federation of Television and Radio Artists. A total of 142 community members (94 nonactors and 48 actors) were administered a questionnaire on current vocal health and voice-related quality of life indices (Vocal Handicap Index-10, Vocal Fatigue Index), followed by review and discussion with a laryngologist or a speech pathologist trained in assessment and treatment of voice disorders. RESULTS: A significantly higher percentage of actors (55.1%) reported current voice problems than nonactors (33.0%; χ2 = 7.122, df = 1, P = 0.008). Additionally, as measured by the Vocal Fatigue Index 2 subscale, actors reported a greater amount of perceived pain with phonation than the nonactors. Despite over half of the actors reporting current voice concerns, only 7% reported having sought medical advice regarding these concerns. CONCLUSIONS: The results of this study suggest that vocal health screenings can help identify persons with voice complaints. However, in order to determine if vocal health screenings help close prevalence-presentation gap and are useful to both medical professionals and participants, more research is needed.