Analysis of factors on voice quality in thyroidectomy patients.

OBJECTIVE: Vocal cord paralysis (VCP) is a serious complication in thyroidectomy operations; however, its management remains unclear. The present study evaluated the voice parameters of patients who underwent surgery using Intraoperative Neurophysiologic Monitoring (IONM). PATIENTS AND METHODS: A total of 52 patients (41 females and 11 males) who underwent a total thyroidectomy operation were evaluated using objective and subjective voice analysis examinations before and after surgery. Acoustic parameters, such as Fundamental Frequency (F0), Shimmer, Jitter, Noise-to-Harmonic ratio (NHR), and aerodynamic parameters, including S/Z ratio and maximum phonation time (MPT), were analyzed. Objective findings, including the VHI-10 (Voice Handicap Index) and V-RQOL (Voice-Related Quality of Life), were also analyzed. The relationship between voice parameters and IONM values was investigated. RESULTS: The objective analysis (acoustic and aerodynamic parameters) showed no difference (p>0.05). However, the subjective analysis, which involved the VHI-10 and V-RQOL measures, revealed a significant difference before and after the operation (p<0.05). The Spearman correlation analysis showed that the NHR postoperative 1st-month parameter negatively correlated (rho=-0.317, p<0.059), while the F0 postoperative 6th-month parameter positively correlated (rho=0.347) with the amplitude difference before and after dissection (Right R2-R1 difference) for the right RLN measured in IONM. CONCLUSIONS: Patients who are planning to undergo a thyroidectomy procedure should undergo voice assessment during both the preoperative and postoperative periods. IONM could improve voice quality outcomes.

Vocal fold electromyography in patients with endoscopic features of unilateral laryngeal paralysis.

<b><br>Introduction:</b> Electromyography (EMG) of the larynx provides information on the electrophysiological condition of laryngeal muscles and innervation. Integration of information obtained from the EMG exams with the clinical parameters as obtained by other methods for laryngeal assessment (endoscopy, perceptual and acoustic analysis, voice self-assessment) provides a multidimensional picture of dysphonia, which is of particular importance in patients with vocal fold (VF) mobility disorders accompanied by glottic insufficiency.</br> <b><br>Aim:</b> The aim of this study was to evaluate laryngeal EMG records acquired in subjects with unilateral vocal fold immobilization with signs of atrophy and glottic insufficiency.</br> <b><br>Material and methods:</b> From the available material of 74 EMG records of patients referred for the exam due to unilateral laryngeal paralysis, records of 17 patients with endoscopic features suggestive of complete laryngeal muscle denervation were selected. The EMG study of thyroarytenoid muscles of mobile and immobile VFs was evaluated qualitatively and quantitatively at rest and during volitional activity involving free phonation of vowel /e/ [ε].</br> <b><br>Results:</b> In all patients, the EMG records from mobile VFs were significantly different from those from immobile VFs. Despite endoscopic features of paralysis, no VF activity whatsoever was observed in as few as 2 patients so as to meet the neurophysiological definition of paralysis. In 88% of cases, electromyographic activity of the thyroarytenoid muscle was observed despite immobilization and atrophy of the vocal fold. In these patients, neurogenic type of record was observed with numerous high- -amplitude mobility units. On the basis of the results, quantitative features of EMG records indicative of paralysis and residual activity of the thyroarytenoid muscle were determined.</br> <b><br>Conclusions:</b> Qualitative and quantitative analysis of laryngeal EMG records provides detailed information on the condition of vocal fold muscles and innervation. EMG records of mobile vs immobile VFs differ significantly from each other. Endoscopic evaluation does not provide sufficient basis for the diagnosis of complete laryngeal muscle denervation.</br>.

Predominantly unilateral laryngomalacia in infants with unilateral vocal fold paralysis.

BACKGROUND: Neonatal unilateral vocal fold paralysis may arise iatrogenically, idiopathically, or in the context of an underlying neurologic disorder. Management is often supportive, focusing on diet modification to allow for safe oral feeding. We describe the clinical course of six infants with unilateral vocal fold paralysis who developed predominantly unilateral laryngomalacia ipsilateral to the affected vocal fold with associated severe respiratory symptoms and feeding difficulty. METHODS: Retrospective review of six infants with unilateral vocal fold paralysis and predominantly unilateral laryngomalacia. Charts were reviewed for etiology of vocal fold paralysis, presenting symptoms, operative details, postoperative course, and outcomes for breathing and swallowing. RESULTS: Etiology of vocal fold paralysis included cardiac surgery in four patients, intubation-related in one, and idiopathic in one. Presenting symptoms included increased work of breathing, stridor, feeding difficulty, respiratory failure requiring noninvasive respiratory support, and weak cry. All infants were on nasogastric tube feedings. Direct microlaryngoscopy with unilateral or predominantly unilateral (conservative contralateral aryepiglottic fold division) supraglottoplasty was performed. Stridor and work of breathing improved in all six patients within 1 week postoperatively. Oral feeding improved in three patients within 2 weeks. Three patients had persistent feeding impairment with improvement within one year. CONCLUSIONS: Predominantly unilateral laryngomalacia may arise in the context of unilateral vocal fold paralysis. Addressing the ipsilateral cuneiform collapse can improve breathing and feeding. This may be an under-described phenomenon and represents an additional reason to include the otolaryngologist early in the care of infants with suspected possible new unilateral vocal fold paralysis. Breathing and swallow can improve post-operatively, but feeding may remain limited by the vocal fold paralysis and any medical comorbidities. Ongoing follow-up and collaboration with speech-language pathology to optimize feeding are important.

Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis.

Voice change is often the first sign of laryngeal cancer, leading to diagnosis through hospital laryngoscopy. Screening for laryngeal cancer solely based on voice could enhance early detection. However, identifying voice indicators specific to laryngeal cancer is challenging, especially when differentiating it from other laryngeal ailments. This study presents an artificial intelligence model designed to distinguish between healthy voices, laryngeal cancer voices, and those of the other laryngeal conditions. We gathered voice samples of individuals with laryngeal cancer, vocal cord paralysis, benign mucosal diseases, and healthy participants. Comprehensive testing was conducted to determine the best mel-frequency cepstral coefficient conversion and machine learning techniques, with results analyzed in-depth. In our tests, laryngeal diseases distinguishing from healthy voices achieved an accuracy of 0.85-0.97. However, when multiclass classification, accuracy ranged from 0.75 to 0.83. These findings highlight the challenges of artificial intelligence-driven voice-based diagnosis due to overlaps with benign conditions but also underscore its potential.

Comparison of the diagnostic and prognostic abilities of flexible laryngoscopy and dynamic digital radiography for vocal cord paralysis: A prospective observational study.

BACKGROUND: Although flexible laryngoscopy (FL) is the reference modality for diagnosing vocal cord paralysis (VCP), FL involves patient discomfort and insertion intolerance. Dynamic digital radiography (DDR) with high spatial and temporal resolution is easier to use and less invasive when evaluating VCP. METHODS: Seventy-eight patients underwent FL and DDR before and after neck surgery. Qualitative and quantitative vocal cord movement (VCM) evaluations were conducted. Patients with postoperative VCP were followed-up regularly. RESULTS: DDR exhibited diagnostic performance with 67% sensitivity and 100% specificity. The cutoff for VCM was 2.4 mm, with DDR exhibiting 100% sensitivity and 78% specificity. All cords with transient VCP had positive VCM at both 3 weeks and 2 months. Additionally, 50% and 75% of cords with permanent VCP had negative VCM at 3 weeks and 2 months, respectively. CONCLUSIONS: DDR is promising for the diagnosis of postoperative VCP and early prediction of permanent postoperative VCP.

The Impact of Medical Comorbidities on Cough Improvement Following Superior Laryngeal Block.

INTRODUCTION: Chronic refractory cough is defined as cough lasting greater than 8 weeks and with an unclear etiology. Blockade of the internal branch superior laryngeal nerve (iSLN) has been shown to be safe and effective in the treatment of chronic cough. It remains unknown, however, if underlying comorbidities impact patient response to iSLN blockade. METHODS: A total of 44 patients aged 18 years and older were seen at our institution's Laryngology clinics between 2019 and 2022 and treated with iSLN blockade. Patient demographics, comorbidities, and pre- and post-treatment cough severity index (CSI) scores were collected from electronic medical records. Two-tailed independent T tests were used to compare CSI scores between groups with and without 4 underlying comorbidities: GERD, pulmonary history, smoking history, and evidence of vocal fold paresis or asymmetry on stroboscopy. RESULTS: Patients with a history of GERD or smoking and those with evidence of glottic insufficiency had similar improvements in CSI compared to those who did not (22.5 ± 26.4 vs 45.0 ± 47.1, P = .36; 32.7 ± 27.8 vs 29.0 ± 38, P = .85; 41.3 ± 18.8 vs 27.2 ± 37.7, P = .195). Patients with underlying pulmonary conditions had a significantly reduced response to iSLN blockade than did patients without underlying disease (9.85 ± 15.0 vs 47.4 ± 38.1, P = .028). CONCLUSION: Underlying lung pathology may contribute to decreased iSLN blockade efficacy in the treatment of chronic refractory cough from laryngeal hypersensitivity and its treatment is likely necessary for optimal symptom reduction. Characterizing patient comorbidity profiles can help guide patient counseling on expected treatment efficacy.

Noticeable effect of lower baseline amplitude on the predictive accuracy of intraoperative amplitude changes for postoperative vocal cord palsy: a prospective cohort study.

BACKGROUND: To explore the effect of lower baseline amplitude on its predictive accuracy of postoperative vocal cord paralysis (VCP) in monitored thyroid surgery. MATERIALS AND METHODS: Clinical and electrophysiological data were collected during thyroid surgeries performed between November and December 2021 at China-Japan Union Hospital. Univariate/multivariate regression analysis were applied to these data to examine a possible correlation. A receiver operating characteristic curve was used to evaluate predictive efficacy. RESULTS: A total of 631 nerves-at-risk (NAR) were identified in 460 patients who were divided into two groups according to postoperative development of VCP. The VCP group included a higher percentage of NAR with V1<1000 (68.2 vs. 40.7%, respectively; P =0.014) and NAR with R1<1400 (77.3 vs. 47.0%, respectively; P =0.005) compared with the non-VCP group. Multivariate regression analysis further identified V1<1000 [odds ratio (OR)=2.688, P =0.038], R1<1400 (OR=3.484, P =0.018) as independent risk factors for postoperative temporary VCP. The receiver operating characteristic curve showed the AUC value of V signal decline for predicting VCP was 0.87. The diagnostic efficiency of R signal decline reached as high as 0.973. A multivariate logistic regression analysis identified independent risk factors for V1<1000 and these included: higher BMI (OR=1.072, P =0.013), hypertension (OR=1.816, P =0.015), smoking (OR=1.814, P =0.031), and male sex (OR=2.016, P =0.027). CONCLUSION: In our cohort, lower baseline amplitude was an independent risk factor for developing transient postoperative VCP. It also affected the predictive efficacy of intraoperative amplitude changes on VCP. Higher BMI, hypertension, smoking, and male sex may also be closely associated with lower initial amplitude. Thus, maintaining a higher initial amplitude is critical for patient safety during thyroid surgery.

Trust in Machine Learning Driven Clinical Decision Support Tools Among Otolaryngologists.

BACKGROUND: Machine learning driven clinical decision support tools (ML-CDST) are on the verge of being integrated into clinical settings, including in Otolaryngology-Head & Neck Surgery. In this study, we investigated whether such CDST may influence otolaryngologists' diagnostic judgement. METHODS: Otolaryngologists were recruited virtually across the United States for this experiment on human-AI interaction. Participants were shown 12 different video-stroboscopic exams from patients with previously diagnosed laryngopharyngeal reflux or vocal fold paresis and asked to determine the presence of disease. They were then exposed to a random diagnosis purportedly resulting from an ML-CDST and given the opportunity to revise their diagnosis. The ML-CDST output was presented with no explanation, a general explanation, or a specific explanation of its logic. The ML-CDST impact on diagnostic judgement was assessed with McNemar's test. RESULTS: Forty-five participants were recruited. When participants reported less confidence (268 observations), they were significantly (p = 0.001) more likely to change their diagnostic judgement after exposure to ML-CDST output compared to when they reported more confidence (238 observations). Participants were more likely to change their diagnostic judgement when presented with a specific explanation of the CDST logic (p = 0.048). CONCLUSIONS: Our study suggests that otolaryngologists are susceptible to accepting ML-CDST diagnostic recommendations, especially when less confident. Otolaryngologists' trust in ML-CDST output is increased when accompanied with a specific explanation of its logic. LEVEL OF EVIDENCE: 2 Laryngoscope, 134:2799-2804, 2024.

Deep learning in voice analysis for diagnosing vocal cord pathologies: a systematic review.

OBJECTIVES: With smartphones and wearable devices becoming ubiquitous, they offer an opportunity for large-scale voice sampling. This systematic review explores the application of deep learning models for the automated analysis of voice samples to detect vocal cord pathologies. METHODS: We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines. We searched MEDLINE and Embase databases for original publications on deep learning applications for diagnosing vocal cord pathologies between 2002 and 2022. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS: Out of the 14 studies that met the inclusion criteria, data from a total of 3037 patients were analyzed. All studies were retrospective. Deep learning applications targeted Reinke's edema, nodules, polyps, cysts, unilateral cord paralysis, and vocal fold cancer detection. Most pathologies had detection accuracy above 90%. Thirteen studies (93%) exhibited a high risk of bias and concerns about applicability. CONCLUSIONS: Technology holds promise for enhancing the screening and diagnosis of vocal cord pathologies. While current research is limited, the presented studies offer proof of concept for developing larger-scale solutions.

An Atypical Cause of Hoarseness in a Patient With Thyroid Nodules.

Hoarseness due to vocal fold paresis (VFP) has a multitude of etiologies including systemic lupus erythematosus (SLE). During a clinical evaluation of a 58-year-old woman with long-standing hoarseness, an incidental finding of thyroid nodules was found to have VFP. Direct laryngoscopy and vocal fold biopsy confirmed the source was an inflammatory process involving the cricoarytenoid joint of the right hemilarynx. A presumptive diagnosis of SLE was made 3 years before meeting the clinical criteria of overt SLE. The VFP debut of SLE is extremely rare, and a literature review includes a handful of case reports (4 of a total of 37) since 1959. Only partial recovery of laryngeal function using glucocorticoids and Plaquenil was accomplished in the current case.

Association of Sociodemographic Factors on the Presentation and Management of Unilateral Vocal Fold Immobility.

OBJECTIVE: To determine the association of social determinants of health (SDOH) on the presentation and management of unilateral vocal fold immobility (UVFI). METHODS: Retrospective chart review of 207 adult UVFI patients evaluated at a tertiary-care hospital between 2018 and 2019 was performed. Sociodemographic factors including gender, median household income, preferred language, and insurance type were recorded. Confounding clinical factors including etiology of UVFI, Voice Handicap Index-10 (VHI-10) score, laryngoscopic findings, and intervention history were extracted from medical records. Multivariable logistic regression was performed using sociodemographic and clinical factors. RESULTS: Patient demographics and socioeconomic status were not associated with time to presentation. Patients presenting with glottic insufficiency and UVFI due to malignancy or recurrent laryngeal nerve (RLN) sacrifice had a shorter time to presentation. Higher household income was associated with greater number of interventions (p = 0.02), but neither income nor insurance type affected intervention type or timing. Female patients were less likely to undergo injection medialization laryngoplasty (odds ratio [OR] 0.25, p = 0.005). Older patients were more likely to undergo injection (OR 1.04, p = 0.027). Patients with large glottic gaps (OR 21.2, p = 0.014) and higher VHI-10 scores (OR 1.06, p = 0.047) were more likely to undergo surgery. CONCLUSION: Higher household income was associated with greater number of interventions and longer duration of care at a private tertiary-care hospital. RLN sacrifice, known malignancy, and glottic insufficiency significantly reduced the time to presentation. Type of intervention received was a complex interplay of both demographic and clinical factors. Large prospective studies should examine the role of SDOH in the presentation and management of UVFI. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:297-304, 2024.

Vocal Cord Paralysis after Repair of Esophageal Atresia.

OBJECTIVE: Etiology of vocal cord paralysis (VCP) and laryngeal dysfunction may be congenital or surgical trauma of recurrent and superior laryngeal nerves. We assessed the incidence, risk factors, and morbidity of VCP after repair of esophageal atresia (EA). METHODS: Medical records of 201 EA patients from 2000 to 2022 were reviewed for this retrospective study. Postrepair vocal cord examination (VCE) included awake nasolaryngeal fiberoscopy by otolaryngologist or laryngoscopy under spontaneous breathing anesthesia. Before 2017, postoperative VCE was performed in symptomatic patients only and routinely after 2017. MAIN RESULTS: Overall, VCE was performed on 79 (38%) patients (52 asymptomatic), whereas 122 asymptomatic patients underwent no VCE. VCP was diagnosed in 32 of 79 patients (right 12, left 10, and bilateral 10; symptomatic 25 and asymptomatic unilateral 7) corresponding with extrapolated overall VCP incidence of 16 to 24% among 201 patients including asymptomatic ones. Ten patients (bilateral VCP 8 and left VCP 2) required tracheostomy. Of 10 patients with bilateral VCP, three underwent laryngotracheal expansion surgery (left VC lateralization in one and laryngoplasty in two with acquired subglottic stenosis), three remained tracheostomy dependent, three were off tracheostomy, and one died of complications after redo esophageal reconstruction. All patients with unilateral VCP managed without tracheostomy. Cervical dissection or ostomy formation was a major risk factor of VCP. CONCLUSION: Repair of EA is associated with a considerable risk of VCP and associated morbidity. Cervical EA surgery significantly increased the risk of VCP. Bilateral VCP may eventually require laryngotracheal expansion surgery.

Technical Challenges for Laryngeal Electromyography.

BACKGROUND/OBJECTIVE: Laryngeal electromyography (LEMG) is a useful diagnostic test in the evaluation of vocal fold paralysis (VFP). This study investigates factors that can make LEMG challenging to perform. METHODS: Patients with subacute unilateral VFP presented for LEMG were prospectively enrolled. Demographic data including BMI, previous neck surgery, and anatomic factors were collected. Patient-reported pain related to the procedure was recorded on a visual analogue scale (VAS). Electromyographer and otolaryngologist recorded a consensus rating of the perceived difficulty in performing the test and confidence in using the results for clinical decision-making. RESULTS: A total of 111 patients (56.8% female) were enrolled between August 2015 and August 2018. The mean age was 55 ± 14 years, and the average body mass index (BMI) was 28.5 ± 6.4. The mean patient-reported VAS score for pain was 35 ± 24. Notably, 31.2% of the tests were considered "very easy," 32.1% were considered "mildly challenging" and 23.9% and 12.8% were considered "moderately challenging" and "extremely challenging," respectively, by the clinicians. Common factors affecting LEMG difficulty included poorly palpable surface anatomy (50.5%) and patient intolerance (15.6%). Clinicians felt confident in 76.1% of the test findings. Bivariate analyses showed that prior neck surgery is associated with elevated VAS (p = 0.02), but clinician-perceived difficulty of performing the test is not associated with elevated VAS scores (p = 0.55). CONCLUSIONS: Majority of LEMG tests are well tolerated by patients. Physicians reported more confidence using LEMG for clinical decision-making when the test was easier to perform. Difficult surface anatomy and patient intolerance affects clinician confidence in integrating the test results with clinical care. LEVEL OF EVIDENCE: 3 Laryngoscope, 134:831-834, 2024.

Parálisis bilateral de las cuerdas vocales con obstrucción aguda de la vía aérea y traqueotomía urgente en una paciente con ictus vertebrobasilar agudo / Bilateral vocal cord paralysis with acute airway obstruction and urgent tracheotomy in a patient with an acute vertebrobasilar stroke

Introducción El ictus vertebrobasilar puede suponer un reto diagnóstico. La parálisis bilateral de las cuerdas vocales como manifestación de ictus agudo es muy rara, pero potencialmente mortal, por la posibilidad de obstrucción aguda de la vía aérea. No hay casos descritos de parálisis bilateral de las cuerdas vocales como presentación de ictus agudo de etiología neurológica mixta central y periférica. Caso clínico Mujer de 88 años con disfonía secuelar a parálisis de la cuerda vocal derecha postiroidectomía que presentó un cuadro brusco de vértigo, dismetría y disartria leve (National Institutes of Health Stroke Scale: 2) asociado a hipertensión arterial. La tomografía computarizada cerebral urgente demostró trombosis distal oclusiva de la arteria vertebral izquierda sin isquemia establecida. Por mejoría sintomática con control tensional, no se realizó terapia de revascularización. Cuatro horas después, la paciente desarrolló de forma brusca estridor inspiratorio e insuficiencia respiratoria grave por parálisis bilateral de las cuerdas vocales con obstrucción completa de la vía aérea. Se realizó una traqueotomía urgente con mejoría respiratoria. Una tomografía computarizada cerebral de control a las 24 horas mostró un infarto establecido en el hemicerebelo izquierdo y la región bulbar lateral, congruente con territorio de la arteria cerebelosa posterior inferior izquierda. Conclusión Nuestro caso ilustra la posibilidad de la rara aparición de una parálisis bilateral aguda de las cuerdas vocales en el contexto de un ictus agudo junto con una afectación periférica crónica del nervio recurrente laríngeo. Aunque es excepcional, ejemplifica el potencial riesgo asociado a los ictus vertebrobasilares. Un tratamiento más agresivo de reperfusión podría ser adecuado en estos casos, pese a un déficit inicialmente leve, por la posibilidad de progresar a complicaciones vitales. (AU)

INTRODUCTION Vertebrobasilar stroke can be a diagnostic challenge. Bilateral vocal cord paralysis is very rare as a manifestation of acute stroke, yet it is potentially life-threatening because of the possibility of acute airway obstruction. No cases of bilateral vocal cord paralysis have been reported as a presenting symptom of acute stroke of mixed central and peripheral neurological aetiology. CASE REPORT An 88-year-old woman with dysphonia resulting from paralysis of the right vocal cord following a thyroidectomy presented with sudden onset of vertigo, dysmetria and mild dysarthria (National Institutes of Health Stroke Scale: 2) associated with arterial hypertension. An urgent brain computed tomography (CT) scan evidenced distal occlusive thrombosis of the left vertebral artery without established ischaemia. Due to the improvement of symptoms achieved with control of her blood pressure, revascularisation therapy was not performed. Four hours later, the patient suddenly developed inspiratory stridor and severe respiratory failure due to bilateral vocal cord paralysis with complete airway obstruction. An urgent tracheotomy was performed, which resulted in an improvement in her breathing. A control brain CT scan performed at 24 hours showed established infarction in the left hemicerebellum and lateral medullary region, consistent with the territory of the left posterior inferior cerebellar artery. CONCLUSION. Our case illustrates the possibility of the rare occurrence of acute bilateral vocal cord paralysis in the context of acute stroke in conjunction with chronic peripheral involvement of the recurrent laryngeal nerve. Although exceptional, it exemplifies the potential risk associated with vertebrobasilar strokes. A more aggressive reperfusion therapy may be appropriate in these cases, despite an initially mild deficit, because of the possibility of progression to life-threatening complications. (AU)

[The consensus among experts on the diagnosis and treatment of pediatric vocal cord paralysis].

Pediatric vocal ford paralysis is a vocal cord movement disorder caused by damage to the pediatric laryngeal motor nerves.It is mainly characterized by voice, breathing,and swallowing difficulties,and in severe cases,it can lead to choking in affected children. Currently, the diagnosis and treatment of this condition pose a significant challenge for pediatric otolaryngologists, as the goal is to minimize damage to the vocal folds and laryngeal framework.In order to standardize the diagnosis and treatment of pediatric vocal cord paralysis, the Pediatric Otolaryngology Committee of the Chinese Medical Association,in collaboration with multiple children's medical centers nationwide, have formulated this consensus document.

Screening for Vocal Fold Movement Impairment in Children Undergoing Esophageal and Airway Surgery.

INTRODUCTION: Children undergoing cervical and/or thoracic operations are at risk for recurrent laryngeal nerve injury, resulting in vocal fold movement impairment (VFMI). Screening for VFMI is often reserved for symptomatic patients. OBJECTIVE: Identify the prevalence of VFMI in screened preoperative patients prior to an at-risk operation to evaluate the value of screening all patients at-risk for VFMI, regardless of symptoms. METHODS: A single center, retrospective review of all patients undergoing a preoperative flexible nasolaryngoscopy between 2017 and 2021, examining the presence of VFMI and associated symptoms. RESULTS: We evaluated 297 patients with a median (IQR) age of 18 (7.8, 56.3) months and a weight of 11.3 (7.8, 17.7) kilograms. Most had a history of esophageal atresia (EA, 60%), and a prior at-risk cervical or thoracic operation (73%). Overall, 72 (24%) patients presented with VFMI (51% left, 26% right, and 22% bilateral). Of patients with VFMI, 47% did not exhibit the classic symptoms (stridor, dysphonia, and aspiration) of VFMI. Dysphonia was the most prevalent classic VFMI symptom, yet only present in 18 (25%) patients. Patients presenting with a history of at-risk surgery (OR 2.3, 95%CI 1.1, 4.8, p = 0.03), presence of a tracheostomy (OR 3.1, 95%CI 1.0, 10.0, p = 0.04), or presence of a surgical feeding tube (OR 3.1, 95%CI 1.6, 6.2, p = 0.001) were more likely to present with VFMI. CONCLUSION: Routine screening for VFMI should be considered in all at-risk patients, regardless of symptoms or prior operations, particularly in those with a history of an at-risk surgery, presence of tracheostomy, or a surgical feeding tube. LEVEL OF EVIDENCE: 3 Laryngoscope, 133:3564-3570, 2023.

Predictive Outcomes of Deep Learning Measurement of the Anterior Glottic Angle in Bilateral Vocal Fold Immobility.

OBJECTIVE: (1) To compare maximum glottic opening angle (anterior glottic angle, AGA) in patients with bilateral vocal fold immobility (BVFI), unilateral vocal fold immobility (UVFI) and normal larynges (NL), and (2) to correlate maximum AGA with patient-reported outcome measures. METHODS: Patients wisth BVFI, UVFI, and NL were retrospectively studied. An open-source deep learning-based computer vision tool for vocal fold tracking was used to analyze videolaryngoscopy. Minimum and maximum AGA were calculated and correlated with three patient-reported outcomes measures. RESULTS: Two hundred and fourteen patients were included. Mean maximum AGA was 29.91° (14.40° SD), 42.59° (12.37° SD), and 57.08° (11.14° SD) in BVFI (N = 70), UVFI (N = 70), and NL (N = 72) groups, respectively (p < 0.001). Patients requiring operative airway intervention for BVFI had an average maximum AGA of 24.94° (10.66° SD), statistically different from those not requiring intervention (p = 0.0001). There was moderate negative correlation between Dyspnea Index scores and AGA (Spearman r = -0.345, p = 0.0003). Maximum AGA demonstrated high discriminatory ability for BVFI diagnosis (AUC 0.92, 95% CI 0.81-0.97, p < 0.001) and moderate ability to predict need for operative airway intervention (AUC 0.77, 95% CI 0.64-0.89, p < 0.001). CONCLUSIONS: A computer vision tool for quantitative assessment of the AGA from videolaryngoscopy demonstrated ability to discriminate between patients with BVFI, UVFI, and normal controls and predict need for operative airway intervention. This tool may be useful for assessment of other neurological laryngeal conditions and may help guide decision-making in laryngeal surgery. LEVEL OF EVIDENCE: III Laryngoscope, 133:2285-2291, 2023.