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.

Prediction of a Difficult Airway Using the ARNE Score and Flexible Laryngoscopy in Patients with Laryngeal Pathology.

Background and Objectives: The ARNE score was developed for the prediction of a difficult airway for both general and ear, nose and throat (ENT) surgery with a universal cut-off value. We tested the accuracy of this score in the case of laryngeal surgery and provided an insight into its effects in combination with flexible laryngoscopy. Materials and Methods: This prospective pilot clinical study included 100 patients who were being scheduled for microscopic laryngeal surgery. We calculated the ARNE score for every patient, and flexible laryngoscopy was provided preoperative. Difficult intubation was assessed according to the intubation difficulty score (IDS). Results: A total of 33% patients had difficult intubation according to the IDS. The ARNE score showed limited accuracy for the prediction of difficult intubation in laryngology with p < 0.0001 and an AUC of 0.784. Flexible laryngoscopy also showed limitations when used as an independent parameter with p < 0.0001 and an AUC of 0.766. We defined a new cut-off value of 15.50 for laryngology, according to the AUC. After the patients were divided into two groups, according to the new cut-off value and provided cut-off value, the AUC improved to 0.707 from 0.619, respectively. Flexible laryngoscopy improved the prediction model of the ARNE score to an AUC of 0.882 and of the new cut-off value to an AUC of 0.833. Conclusions: It is recommended to use flexible laryngoscopy together with the ARNE score in difficult airway prediction in patients with laryngeal pathology. Also, the universally recommended cut-off value of 11 cannot be effectively used in laryngology, and a new cut-off value of 15.50 is recommended.

Clinical Voice Outcomes for Two Voice Rest Protocols after Phonomicrosurgery.

OBJECTIVES: Voice rest is commonly recommended for patients with benign vocal fold lesions (BVFLs) after phonomicrosurgery. The study compares the clinical voice outcomes of two protocols, 7-day complete voice rest (CVR) and 3-day CVR followed by 4-day relative voice rest (CVR + RVR), for patients with BVFLs after phonomicrosurgery. STUDY DESIGN: Prospective, randomized controlled trial. METHOD: Patients with BVFLs undergoing phonomicrosurgery were recruited prospectively and randomly assigned to either protocol. Outcomes were assessed on objective measures of acoustics (fundamental frequency, frequency range, mean intensity, cepstral peak analysis) and aerodynamics (vital capacity, airflow rate, subglottal pressure, phonation threshold pressure), as well as subjective measures, both provider-reported through the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V), and patient-reported through the Voice Handicap Index (VHI). Clinical measures were collected at three-time points: preoperatively, 1-week postoperatively (on voice rest), and 1-month postoperatively. In addition, adherence was estimated using a vocal dosimeter. RESULTS: Twenty-five patients were recruited and randomized to 7-day CVR (n = 13) and CVR + RVR regimen (n = 12). Statistically significant changes were found within both groups for subglottal pressure (p = 0.03) and VHI score (p < 0.001) comparing pre-operative baseline to 1-month postoperative follow-up. There were no statistically significant differences between the groups. Regardless of group assignment, a significant decrease in overall severity ratings for the CAPE-V was found by comparing the preoperative scores to postoperative scores at 1-week (p < 0.001) and 1-month (p < 0.001). CONCLUSION: Both groups improved their overall voice quality comparably 1 month after undergoing phonomicrosurgery as measured by objective and subjective parameters. LEVELS OF EVIDENCE: 2. Laryngoscope, 134:2812-2818, 2024.

Breathing patterns in people with exercise-induced laryngeal obstruction.

Exercise-induced laryngeal obstruction (EILO) is common, but we lack readily available diagnostic tools. The larynx represents an important point of resistance in the airways, and we therefore hypothesized that EILO is associated with characteristic breathing patterns possible to record from a standard incremental ergospirometry test. We studied 24 individuals with moderate/severe EILO and 20 individuals with no-EILO, mean (SD) age 17 (6.1) and 24 (6.4) years, respectively. EILO versus no-EILO was verified from maximal continuous laryngoscopy treadmill exercise (CLE) tests, which also included ergospirometry. We described the relationships between minute ventilation ( V˙E ) versus tidal volume (VT ) and V˙E versus carbon dioxide output ( V˙CO2 ), using respectively quadratic and linear equations, and applied adjusted regression models to compare ergospirometry data and curve parameters. Compared to the no-EILO group, the group with EILO had prolonged inspiratory time (Tin ), lower breathing frequency (Bf ), lower V˙E , and lower inspiratory flow rate ( V˙in ) at peak exercise. Mathematical modeling of the breathing pattern relationships was feasible in both groups, with similar coefficients of variation. For V˙E versus VT , the mathematical curve parameters were similar. For V˙E versus V˙CO2 , the slope was similar but the intercept was lower in the EILO group. EILO was associated with prolonged Tin , lower Bf , V˙E , and V˙E . The relationship between V˙E versus VT was similar, whereas for V˙E versus V˙CO2 , the slope was almost parallel but shifted downward for the EILO group. Most ergospirometry data overlapped, except V˙in which discriminated between EILO and no-EILO in a promising way.

The Effect of the Mother's Participation in Therapy on Children with Vocal Fold Nodules.

OBJECTIVES: Vocal fold nodules (VFN) are a bilateral epithelial thickening of the membranous vocal folds. In this study, children with VFN and their mothers took part in voice therapy. We then compared acoustic analyzes and subjective evaluations to those in previous literature to determine whether voice therapy is more effective for children with VFN when their mothers also take part in therapy. METHODS: Children aged eight to 12 years who were diagnosed with bilateral VFN between January 2018 and January 2020 were included in this study. Participating children diagnosed with bilateral VFN were divided into two groups based on the wishes and cooperation of their families. Group 1 consisted of 16 patients; Group 2 included 17 patients. The children in Group 1 received voice therapy alone; children in Group 2 took part in therapy with their mothers. For all participants, the average fundemental frequency (F0), jitter percentages, shimmer percentages, maximum phonation time (MPT) and s/z ratios were measured. Pediatric voice handicap index (p-VHI) values were calculated as well. RESULTS: The two groups' measures pre-treatment and post-treatment were compared. Except for p-VHI, no significant difference was observed between the two groups. However, p-VHI post-treatment was significantly lower in Group 2 than in Group 1. CONCLUSIONS: Involving the families and even teachers of children with VFN in voice therapy can increase the effectiveness of therapy. The family's involvement increases the child's motivation in therapy. The mother's presence during therapy, supporting the child or even doing the work with the child, can be a very important source of motivation for the child, who may already be tired from school and other activities. Thus, the mother's involvement increases the child's compliance with and interest in therapy.

Localised laryngotracheal amyloidosis: a differential diagnosis not to forget.

We present a case of multifocal laryngotracheal amyloidosis (LTA) in a 43-year-old man with persistent and progressive dysphonia and dyspnoea, and a first inconclusive histology. Although laryngeal amyloidosis accounts for fewer than 1% of all benign laryngeal tumours, it is in fact the most common site of amyloid deposition in the head, neck and respiratory tract. The clinical scenario is non-specific and diagnosis depends on a high degree of suspicion and on histology. Imaging is useful in mapping lesions, which are often more extensive than they appear during laryngoscopy. Despite being a benign entity, the prognosis is variable with a high-rate and long-latency recurrences, requiring long-term follow-up.

A 532-nm KTP Laser for Vocal Fold Polyps: Efficacy and Relative Factors.

OBJECTIVE: We retrospectively analyzed the laryngoscopy results and voice outcomes of patients with vocal polyps who received potassium titanyl phosphate (KTP) laser treatments in a clinician's office, in order to establish the effectiveness and relative factors affecting the efficacy of this treatment. MATERIAL AND METHODS: We enrolled 25 patients with vocal polyps who had undergone KTP laser treatment in the Department of Otorhinolaryngology at our hospital between July 2017 and November 2019. Pre- and postoperative evaluations were measured using laryngovideostroboscopy (LVS), the Voice Handicap Index questionnaire (VHI-30), the GRBAS scale (G hoarseness, R roughness, B breathiness, A asthenia, S strain), and objective acoustic parameters. The reduction rate of lesions was calculated and relative factors affecting efficacy (size, side, location, the position of lesions, type, gender, and occupation) were tested. RESULTS: Areas of lesions decreased from 101.95 ± 70.16 before surgery to 30.49 ± 35.80 after surgery (Z = 5.234, P < .001). The LVS data showed that the postoperative proportions of normal to mild conditions were the same or higher than the preoperative data in 3 instances: glottal closure (100% vs 100%), amplitude (90.91% vs 63.64%), and mucosal wave (81.82% vs 54.55%). A significant improvement was observed in VHI-30 scores, GRBAS scores, and acoustic parameters (P < .05). The size of lesions had an effect on the GRBAS scores (P < .001) but not on VHI-30 scores and objective acoustic parameters (P > .05). Other factors we tested did not affect voice outcomes. CONCLUSION: Potassium titanyl phosphate laser treatment can effectively reduce the lesion area of vocal polyps and improve the voice quality. The presence of small lesions seems to predict good subjective assessments of voice quality, but it remains to be seen whether this correlates with true voice quality.

Predictors of Increased Surgical Drain Output following Type I Thyroplasty for Glottic Insufficiency.

OBJECTIVE: To determine predictors of increased drain output following type I thyroplasty for glottic insufficiency. STUDY DESIGN: Retrospective chart review. METHODS: A retrospective review was conducted for patients who underwent type I thyroplasty for glottic insufficiency from 2014-2019. The primary outcome was 24-hour drain output. Increased drain output was defined as >50th percentile for the sample. Univariate logistic regression models and linear regression models were used. RESULTS: There were 84 patients with a mean age of 58.9 (SD 16.9) years. Twenty-four-hour drain output ranged from 0 to 29 mL with a mean of 9.47 (SD 6.49) mL. Patients with a history of tobacco use (OR 3.33; 95% CI, 1.24-8.95; P = .017) and prior neck surgery (OR 3.52; 95% CI, 1.26 to 9.83; P = .016) were significantly more likely to have increased drain output following surgery; these patients had a mean increase in 24-hour drain output of 3.51 mL (95% CI, 0.52 to 6.51; P = .022) and 1.74 mL (95% CI, -1.41 to 4.89; P = .274), respectively. Type of implant (Gore-Tex vs. Silastic; P = .425) and operative technique (unilateral vs. bilateral; P = .506) were not significantly associated with drain output. CONCLUSION: History of tobacco use and prior surgery of the neck predict increased drain output following type I thyroplasty surgery. These patients may derive the most benefit from surgical drain placement. More research is needed to confirm these findings and elucidate potential mechanisms. LEVEL OF EVIDENCE: 4 Laryngoscope, 131:1557-1560, 2021.

Objective Measures of Stroboscopy and High-Speed Video.

Videostroboscopy and high-speed imaging is now an accepted way to evaluate laryngeal function in patients with voice disorders. In patients with neurolaryngological diseases such as tremor, laryngeal spasm, and paralysis, having an objective way to evaluate vocal function is desirable. Using digital imaging and analysis, both the videostroboscopy and the high-speed video can be analyzed to obtain relevant measures of vocal function. From the videostroboscopy, the montage of the glottal cycle derived from steady of vocal vibration can be analyzed by using edge tracking software to obtain the glottal area waveform. The waveform is an indication of the efficiency of the vocal folds in acting as an oscillator and gives direct information as to the open and closed phase, the symmetry of vocal fold vibration and the degree of amplitude contribution from each fold. High-speed video overcomes the deficiencies of stroboscopy by allowing for all voice gestures to be studies. Using digital kymography and analysis of the vibrogram, analysis of the onset of vocal fold oscillation, evaluation of diplophonia, tremor, and voice breaks becomes possible. Furthermore, analysis of the high-speed video kymograph tracing using signal analysis allow the investigator to evaluate the frequency and power relationships of vocal fold vibratory function in the normal and disordered state.

Unusual cause of laryngeal dyspnea and swallowing troubles in a 2-year old child.

Plexiform neurofibromas are rare benign tumors developed from peripheral nervous system often associated with neurofibromatosis type 1. We report the case of multifocal plexiform neurofibromas in a 2-year-old child with cervical mass obstructing the trachea causing respiratory distress. A cervical ultrasound examination was performed followed by enhanced CT and MRI. Imaging revealed an expansive cervical mass extended from the base of the skull to the mediastinum associated with similar pelvic and sacral foraminal masses. The target like MRI aspect on T2-weighted images was suggestive of the neural origin. Biopsy under ultrasound control confirmed the diagnosis of plexiform neurofibroma.

Triggers of breathlessness in inducible laryngeal obstruction and asthma.

BACKGROUND: Inducible laryngeal obstruction (ILO) is often misdiagnosed as, or may coexist with, asthma. Identifying differences in triggering factors may assist clinicians to differentiate between the two conditions and could give mechanistic insights. OBJECTIVE: To identify and compare patient-reported triggers in ILO and asthma. METHODS: This was a two-part study. Initially, we conducted a retrospective case note review of the triggers of ILO from endoscopically confirmed ILO patients to generate a Breathlessness Triggers Survey (BrTS). Triggers were categorized as scents, environmental factors, temperature, emotions, mechanical factors and daily activities. Secondly, ILO and/or asthma patients completed the BrTS prospectively, rating the likelihood of each item triggering their symptoms using a five-point Likert scale (strongly disagree to strongly agree). Chi-square testing was performed to compare responses by cohort. RESULTS: Data from 202 patients with ILO [73% female, mean (SD) age 53(16) years] were included in the case note review. For the prospective study, 38 patients with ILO only [63% females, age 57(16) years], 39 patients with asthma only [(56% female, age 53(13) years] and 12 patients with both ILO and asthma [83% female, mean age, 57 (14) years)] completed the BrTS. The triggers identified in the case note review were confirmed in the independent sample of patients with ILO and/or asthma and identified several difference in prevalence of the triggers between disease types. Mechanical factors (talking [P < .001], shouting [P = .007] and swallowing [P = .002]) were more common in the ILO cohort compared to patients with asthma. Environmental factors (pollen/flowers [P = .005] and damp air [P = .012]) were more common in asthma. There were no differences between groups in frequency of reporting scents as triggers (except for vinegar, more common in ILO, P = .019), temperature, emotions or daily activities. CONCLUSION: There were notable differences between patient-reported triggers of ILO and asthma, which may support clinician differential diagnosis.

Predicting Airway Invasion Using Screening Tools and Laryngeal Kinematics in People with Parkinson's Disease: A Pilot Study.

BACKGROUND: Dysphagia in Parkinson's disease (PD) is a common manifestation, particularly in advanced disease stages. However, the pathophysiology and time course of dysphagia progression remains unclear in non-advanced disease stages (e.g., Hoehn & Yahr stages I-III). Conflicting reports from investigations of the perception of dysphagia in people with PD further complicates our understanding of dysphagia in this population. OBJECTIVE: The objectives of this research were to evaluate the ability of screening tools to detect swallowing impairments and how laryngeal kinematics predict the occurrence of abnormal swallowing events. METHODS: 14 individuals with non-advanced PD, no previous history of dysphagia diagnosis, and self-reported difficulty swallowing participated. The Swallow Disturbance Questionnaire (SDQ) and 3-oz water swallow test (WSST) were administered, along with a videoflouroscopic swallow study (VFSS). Laryngeal kinematics were represented by laryngeal vestibule closure reaction time (LVrt) and laryngeal vestibule closure duration (LVCd). The Penetration-Aspiration Scale (PAS) was used to quantify airway invasion. RESULTS: A logistic regression indicated a significant model of predicting airway invasion from our predictors (p = 0.003). LVrt and SDQ (p < 0.05) provided the largest impact (OR = 1.11; 1.17). The WSST showed no significance in predicting swallow impairment (p > 0.05). CONCLUSION: Decreased airway safety related to laryngeal kinematic function in PD may be manifesting at non-advanced disease stages to varied degrees. Our results support expectations of dysphagia manifestation in PD although screening practices may not adequately identify impairment. Future research should target specific laryngeal characteristics within this population to better understand the physiological cause of swallowing impairment and developof targeted interventions.

Differences in Weeklong Ambulatory Vocal Behavior Between Female Patients With Phonotraumatic Lesions and Matched Controls.

Purpose Previous work using ambulatory voice recordings has shown no differences in average vocal behavior between patients with phonotraumatic vocal hyperfunction and matched controls. This study used larger groups to replicate these results and expanded the analysis to include distributional characteristics of ambulatory voice use and measures indicative of glottal closure. Method Subjects included 180 adult women: 90 diagnosed with vocal fold nodules or polyps and 90 age-, sex-, and occupation-matched controls with no history of voice disorders. Weeklong summary statistics (average, variability, skewness, kurtosis) of voice use were computed from neck-surface acceleration recorded using an ambulatory voice monitor. Voice measures included estimates of sound pressure level (SPL), fundamental frequency (f o), cepstral peak prominence, and the difference between the first and second harmonic magnitudes (H1-H2). Results Statistical comparisons resulted in medium-large differences (Cohen's d ≥ 0.5) between groups for SPL skewness, f o variability, and H1-H2 variability. Two logistic regressions (theory-based and stepwise) found SPL skewness and H1-H2 variability to classify patients and controls based on their weekly voice data, with an area under the receiver operating characteristic curve of 0.85 and 0.82 on training and test sets, respectively. Conclusion Compared to controls, the weekly voice use of patients with phonotraumatic vocal hyperfunction reflected higher SPL tendencies (negatively skewed SPL) with more abrupt glottal closure (reduced H1-H2 variability, especially toward higher values). Further work could examine posttreatment data (e.g., after surgery and/or therapy) to determine the extent to which these differences are associated with the etiology and pathophysiology of phonotraumatic vocal fold lesions.

Trends in the Incidence and Treatment of Benign Vocal Fold Lesions in Korea, 2006-2015: A Nationwide Population-based Study.

OBJECTIVE: The aim of this study was to determine the prevalence and demographics of benign vocal fold lesions (BVFL) and trends in its treatment in Korea based on data collected from the National Health Insurance Service database. MATERIAL AND METHODS: Data for patients diagnosed with BVFL (ICM-10 codes J381, J382, J384) from 2006 to 2015 were selected for analysis. Patient characteristics, including sex, age, income, area of residence, and comorbidity, were analyzed. Treatment was divided into surgical management and conservative management using operation codes. RESULTS: The prevalence and incidence of BVFL increased from 7.07% and 5.29%, respectively, in 2006 to 12.47% and 7.98% in 2015. Compared with the non-BVFL population, patients with BVFL were more likely to be female, reside in an urban area, and have gastroesophageal reflux disease. There was no significant change in the incidence of surgical treatment during the study period (around 6000 per year); however, the surgical treatment rate decreased from 19.29% to 8.38%. The probability of undergoing surgical treatment for BVFL was higher in men, those aged 50-59 years, and those in the lowest quartile for income, except for the medical aid group. CONCLUSION: In Korea, there was an increase in the number of patients diagnosed with BVFL and a decrease in the operation rate for this condition between 2006 and 2015. Diagnosis of BVFL varied significantly based on income and sex; however, the only variable affecting the operation rate was patient age.

Original Research: Aerosolized Lidocaine: Effective for Safer Arousal After Suspension Laryngoscopy.

AIM: To examine the systemic and local effects of the lidocaine on the larynx and trachea which is applied after the end of the surgery and through various application methods. STUDY DESIGN: Randomized controlled prospective study. METHOD: The study is composed of patients who underwent suspension laryngoscopy (SL) for benign laryngeal diseases (cysts, polyp, granuloma, etc) and American Society of Anesthesiologists (ASA) I, between January 2017 and January 2018. The patients were randomly divided into 3 groups. In the first group nothing is applied at the end of the surgery and called as control group, second group received 7 pufs of aerosolized 10% lidocaine solution (70 mg) over larynx and trachea and third group received cotton swaps that impregnated in 1 ml of 20 mg lidocaine solution over surgical area for 1 minutes. Operation and arousal times, heart rate and mean arterial blood pressure levels were noted and compared. Also laryngospasm, cough, and agitation scores were obtained during arousal. RESULTS: 64 patients were included in the study. Laryngospasm was not observed in any of the patients. In group 2 (aerosolized lidocaine group), patients' blood pressure remained similar while increased in other groups (P < 0.05). Agitation scores were significantly lower in group 2 compared to the other groups (P = 0.012). Cough reflex is observed less in group 2 but result was not statistically significant (P = 0.13) CONCLUSION: The usage of aerosolized lidocaine after suspension laryngoscopy is very effective in blocking the stimulation of superior laryngeal nerve and sympathetic nerves which were responsible for the pressor reflexes. The inhibition of these reflexes before or during arousal could secure a safer arousal.

Readibility, Understandability, and Quality of Online Education Materials for Vocal Fold Nodules.

OBJECTIVE: Vocal fold nodules are benign vocal fold lesions that can adversely affect quality of life. Differential diagnosis and treatment modalities of this disease are variable and patients often tend to use online materials to learn the insights. Access to knowledge via Internet is very easy; however, it is important to choose wisely because false and biased information might lead the patient to an inappropriate decision. In this study, we have evaluated the quality, readability, and understandability of online materials for vocal fold nodules. METHODS: An Internet search was performed for "Vocal fold nodule," "vocal fold nodule treatment," and "voice therapy for vocal fold nodule" by using Google search engine. Readability of each website was evaluated by using www.readable.io. Understandability and actionability of pages were measured by using the Patient Education Materials Assessment Tool (PEMAT). In the end, DISCERN instrument was used to measure the quality of information presented. RESULTS: After exclusion, total of 26 web pages were evaluated during the study. Four web pages graded as A level, 5 as B level, 11 as C level, and 5 as D level for language use. Average grade level for all of the web pages is 11.14 ± 1.75. Overall understandability score was found 59.0+ 12.1 (26.7-77.1), and overall quality score was measured 34.95 + 6.58 (53.75-26.5). CONCLUSION: The quality, readability, and understandability of the written materials are very low and in order for patients to read and learn from the online sources, contents of the written materials should be revised.

Relationship Between Laryngeal Signs and Symptoms, Acoustic Measures, and Quality of Life in Finnish Primary and Kindergarten School Teachers.

OBJECTIVE: This study investigated the relationship between the acoustic measure smoothed cepstral peak prominence (CPPS), teacher's quality of life as measured by the voice activity and participation profile (VAPP), laryngeal signs and symptoms, voice related health problems and laryngoscopic findings in Finnish teachers. The relationship between CPPS and sound pressure level (SPL) was also assessed. METHODS: Vowel and text samples from 183 healthy Finnish teachers (99 kindergarten teachers [KT] and 84 primary school teachers [PST]) were analyzed for CPPS. Text reading was recorded in conversational loudness by PST, and KT were recorded wearing headphones, while listening to a masking noise of children talking to simulate their classroom voice and environment. CPPS values were correlated with the VAPP, self-reported laryngeal signs and symptoms, voice related health variables, and laryngoscopic findings. RESULTS: There was a significant difference between the two groups for CPPS text, PST showed significantly lower CPPS values (10.44) than KT (11.52). There was no difference between the two groups for CPPS vowel phonation. There was a significant correlation between SPL text and CPPS text for KT (P < 0.001, r = 0.43) but not for PST (P < 0.10, r = 0.16). There was a significant correlation between SPL vowel and CPPS vowel for both PST (P < 0.001, r = 0.47) and KT (P < 0.001, r = 0.45). CPPS did not correlate with the VAPP, laryngeal signs and symptoms, health variables or laryngeal findings. Factorial analysis of variance resulted in a significant relationship between the VAPP, laryngeal signs and symptoms, and teacher type. Teacher type and symptoms had a significant effect on VAPP scores. CONCLUSIONS: In the present work CPPS does not correlate with vocal health indicators of functionally healthy teachers. CPPS was significantly influenced by differences in speaking voice SPL, emphasizing the impact of recording conditions and technique. There was a significant relationship between laryngeal signs and symptoms, teacher type and the VAPP. Laryngeal signs and symptoms and teacher type are important variables and should be included in the clinical evaluation of occupational voice users, and voice problems.

Application of Thulium Laser as Office-based Procedure in Patients With Vocal Fold Polyps.

PURPOSE: To report the voice outcome measures of thulium laser therapy as an office procedure in patients with vocal fold polyps. METHOD: This is a retrospective chart review of all patients with vocal fold polyps who underwent office-based thulium laser treatment between November 2016 and December 2017. Demographic data were collected. Objective voice outcome measures included extent of resolution, type of closure, and mucosal wave characteristics. Also, subjective outcome measures were reported, namely, Voice Handicap Index-10. RESULTS: A total of 20 patients were enrolled with a mean age of 50.95 ± 14.70 years. All patients had unilateral vocal fold polyps except for one who had bilateral polyps. Out of the 20 patients, 16 had complete regression of disease and 4 had partial regression. The number of patients with incomplete glottal closure decreased from 12 pretreatment to only 1 patient posttreatment, and the number of patients with impaired mucosal waves decreased from 13 to 5. There was also a significant decrease in the mean VHI-10 score before and after treatment (15.61 vs. 4.61 P value < 0.001). CONCLUSION: Thulium laser can be used as an office procedure for the treatment of vocal fold polyps.

An Acoustic-Signal-Based Preventive Program for University Lecturers' Vocal Health.

INTRODUCTION: Professional activities of university lecturers involve continued and sustained use of the voice, leading in many cases to increased risk of developing voice disorders. Risk identification followed by the fast application of preventive or corrective measures is a key issue in this context. OBJECTIVE: Define and implement a preventive program for the vocal health of university lecturers by using acoustic features automatically extracted from voice recordings to identify risk groups and manage preventive or corrective actions MATERIAL AND METHODS: A total of 170 subjects, aged between 18 and 65, were recruited at the San Pedro de Alcántara Hospital and at the University of Extremadura in Cáceres (Spain). They formed three groups-one of 25 people suffering from vocal fold nodules, another of 25 healthy people, and the third of 120 university lecturers. Medical history and voice status assessment was performed, and voice recordings were made following a research protocol. A feature extraction, selection, and classification procedure was applied to the voice recordings to provide the best predictors for discriminating between pathological and healthy voices. The model parameters were then used to determine the lecturers' probability of suffering vocal fold nodules or other pathologies with similar dysphonic speech. These probabilities were used to classify the lecturers into three risk groups-low, medium, and high. These groups were taken as the basis to assign the lecturers to a primary, secondary, or tertiary prevention level. Different preventive or corrective actions were applied for each prevention level. RESULTS: The best set of predictors comprised sample entropy, correlation dimension, pitch period entropy, glottal noise excitation, and sex, achieving an overall accuracy of 92% with a random forest classifier. They all showed statistically significant differences between vocal fold nodules and healthy groups (P < 0.05). Three out of the four best acoustic features were nonlinear, showing the importance of nonlinear dynamics for clinical practice. The model parameters were applied to the predictors of the lecturers so as to assign them to the different risk groups, leading to 60.8% (73 out of 120) of the lecturers in the low-risk group, 29.2% (35 out of 120) in the medium-risk group, and 10% (12 out of 120) in the high-risk group. The prevention levels were assigned on the basis of this classification and the medical history and laryngological evaluation of some specific subjects. A statistically significant association was found between the voice status and the assigned prevention level (P < 0.001), with there being a clear dependence relationship (Cramér's V = 0.630). CONCLUSION: It is feasible to develop and apply a preventive voice program for university lecturers that is aided by features automatically extracted from voice recordings. As the program progresses, it is expected that the information automatically provided for the assignment to prevention levels will become ever more precise. The method proposed can be extended to other voice professionals and other voice disorders.