-
Journal of the American College of... Mar 2022In this study, we aimed to report our experience with the use of intraoperative transcutaneous laryngeal ultrasonography (TLUSG) to evaluate the vocal cord twitch...
BACKGROUND
In this study, we aimed to report our experience with the use of intraoperative transcutaneous laryngeal ultrasonography (TLUSG) to evaluate the vocal cord twitch response during predissection vagus nerve stimulation in thyroid surgeries and examine the reliability of this technique when compared with that of laryngeal twitch palpation (LTP).
STUDY DESIGN
The prospective data collection of consecutive patients who underwent open thyroidectomy with intraoperative neuromonitoring (IONM) was reviewed retrospectively. We recorded the electromyographic activity and assessed the vocal cord twitch response on LTP, TLUSG. We compared the accessibility, sensitivity, and specificity of the techniques.
RESULTS
A total of 110 patients (38 men and 72 women) with 134 nerves at risk were enrolled. The vocal cord was assessable by TLUSG in 103 (93.6%) patients and by LTP in 64 (59.1%) patients. Two patients showed negative predissection IONM signal but positive on TLUSG and the presence of laryngeal twitch response confirmed by laryngoscopy. Fourteen patients showed positive IONM signals and presence of the vocal cord twitch response on TLUSG but not on LTP. The sensitivity and specificity were 70.21% and 100%, respectively, for LTP, and those both were 100% for TLUSG. For patients who could be assessed using both techniques, TLUSG had better accuracy than LTP (100% vs 80.33%, p = 0.0005).
CONCLUSIONS
The innovative intraoperative application of TLUSG is better for evaluating the laryngeal twitch response than LTP. This technique provides practical troubleshooting guidance for patients with no IONM signals during predissection vagus nerve stimulation.
Topics: Female; Humans; Male; Reproducibility of Results; Retrospective Studies; Thyroid Gland; Thyroidectomy; Ultrasonography; Vagus Nerve; Vagus Nerve Stimulation; Vocal Cord Paralysis; Vocal Cords
PubMed: 35213499
DOI: 10.1097/XCS.0000000000000053 -
Journal of Medical Systems Jan 2020The use of artificial intelligence, including machine learning, is increasing in medicine. Use of machine learning is rising in the prediction of patient outcomes....
BACKGROUND
The use of artificial intelligence, including machine learning, is increasing in medicine. Use of machine learning is rising in the prediction of patient outcomes. Machine learning may also be able to enhance and augment anesthesia clinical procedures such as airway management. In this study, we sought to develop a machine learning algorithm that could classify vocal cords and tracheal airway anatomy real-time during video laryngoscopy or bronchoscopy as well as compare the performance of three novel convolutional networks for detecting vocal cords and tracheal rings.
METHODS
Following institutional approval, a clinical dataset of 775 video laryngoscopy and bronchoscopy videos was used. The dataset was divided into two categories for use for training and testing. We used three convolutional neural networks (CNNs): ResNet, Inception and MobileNet. Backpropagation and a mean squared error loss function were used to assess accuracy as well as minimize bias and variance. Following training, we assessed transferability using the generalization error of the CNN, sensitivity and specificity, average confidence error, outliers, overall confidence percentage, and frames per second for live video feeds. After the training was complete, 22 models using 0 to 25,000 steps were generated and compared.
RESULTS
The overall confidence of classification for the vocal cords and tracheal rings for ResNet, Inception and MobileNet CNNs were as follows: 0.84, 0.78, and 0.64 for vocal cords, respectively, and 0.69, 0.72, 0.54 for tracheal rings, respectively. Transfer learning following additional training resulted in improved accuracy of ResNet and Inception for identifying the vocal cords (with a confidence of 0.96 and 0.93 respectively). The two best performing CNNs, ResNet and Inception, achieved a specificity of 0.985 and 0.971, respectively, and a sensitivity of 0.865 and 0.892, respectively. Inception was able to process the live video feeds at 10 FPS while ResNet processed at 5 FPS. Both were able to pass a feasibility test of identifying vocal cords and tracheal rings in a video feed.
CONCLUSIONS
We report the development and evaluation of a CNN that can identify and classify airway anatomy in real time. This neural network demonstrates high performance. The availability of artificial intelligence may improve airway management and bronchoscopy by helping to identify key anatomy real time. Thus, potentially improving performance and outcomes during these procedures. Further, this technology may theoretically be extended to the settings of airway pathology or airway management in the hands of experienced providers. The researchers in this study are exploring the performance of this neural network in clinical trials.
Topics: Adolescent; Algorithms; Bronchoscopy; Child; Child, Preschool; Female; Humans; Infant; Laryngoscopy; Machine Learning; Male; Neural Networks, Computer; Sensitivity and Specificity; Trachea; Vocal Cords; Young Adult
PubMed: 31897740
DOI: 10.1007/s10916-019-1481-4 -
Surgery Jan 2022Eliciting a normal electromyography signal has been the usual method to confirm the functional integrity of the recurrent laryngeal nerve during intraoperative nerve... (Comparative Study)
Comparative Study
Intraoperative trans-laryngeal ultrasound (LUSG) of the vocal cord is a novel method of confirming the recurrent laryngeal nerve (RLN) integrity during thyroid and neck surgery.
BACKGROUND
Eliciting a normal electromyography signal has been the usual method to confirm the functional integrity of the recurrent laryngeal nerve during intraoperative nerve monitoring. Given that oscillations of the vocal cord can be detected with trans-laryngeal ultrasound when the ipsilateral recurrent laryngeal nerve is stimulated with the endotracheal tube in situ, we aimed to compare the accuracy and cost of this novel method with the conventional electromyography method.
METHODS
Consecutive patients who underwent elective thyroid, parathyroid or neck dissection procedures were included. The NIM-Neuro 3.0 system was used. Endotracheal tube-based surface electrodes were utilized for electromyography signal recording. Standard anesthetic technique was adopted. Recurrent laryngeal nerve integrity was verified by both detection methods (laryngeal ultrasound and electromyography) independently. Vocal cord function was validated by flexible direct laryngoscopy postoperatively. For each method, concurrence with flexible direct laryngoscopy was defined as "true-positive" or "true-negative," based on the presence or absence of vocal cord paresis. Accuracy was calculated as the sum of all true positives and negatives divided by the total of nerves-at-risk. The cost of each method was calculated.
RESULTS
One hundred and four patients were eligible. Total number of nerves-at-risk was 155. Based on flexible direct laryngoscopy findings, the test sensitivity, specificity, positive predictive value, and negative predictive value of intraoperative laryngeal ultrasound were 75.0%, 99.3%, 85.7%, and 98.6%, respectively, while those of electromyography were 87.5%, 98.0%, 70.0%, and 99.3%, respectively. The prognostic accuracy in laryngeal ultrasound versus electromyography was comparable (98.1% vs 97.4%). The cost of the laryngeal ultrasound per operation was less than electromyography ($82 vs $454).
CONCLUSION
Laryngeal ultrasound has a similar detection accuracy to electromyography during intraoperative nerve monitoring. Apart from being a cheaper alternative, laryngeal ultrasound may be useful when there is unexplained loss of electromyography signals during surgery and may play a role in the intraoperative nerve monitoring troubleshooting algorithm.
Topics: Adult; Electric Stimulation; Electromyography; Female; Humans; Intraoperative Complications; Male; Middle Aged; Monitoring, Intraoperative; Neck Dissection; Parathyroidectomy; Prospective Studies; Recurrent Laryngeal Nerve Injuries; Thyroid Gland; Thyroidectomy; Ultrasonography; Vocal Cord Paralysis; Vocal Cords
PubMed: 34334213
DOI: 10.1016/j.surg.2021.05.062 -
The Annals of Thoracic Surgery Jul 2021We aimed to determine the incidence and contributing risk factors of vocal fold mobility impairment (VFMI) in postoperative cardiovascular patients and evaluate the...
BACKGROUND
We aimed to determine the incidence and contributing risk factors of vocal fold mobility impairment (VFMI) in postoperative cardiovascular patients and evaluate the impact of VFMI on health-related outcomes.
METHODS
This single-site prospective study enrolled adults undergoing sternotomy or thoracotomy procedures who underwent a fiberoptic laryngoscopy examination within 72 hours of extubation. Potential demographic and surgical risk factors and health-related outcomes were collected. A blinded laryngologist assessed VFMI and mucosal injury. Descriptives, univariate and multivariable regression analyses with odds ratios (OR) were performed.
RESULTS
Of 185 eligible examinations, VFMI was confirmed in 25% of patients (7 complete, 39 partial VFMI) with left-sided involvement in 83% of cases. Laryngeal mucosal injury included granuloma (38%), posterior cricoid hypertrophy (37%), edema (29%), bruising (23%), and hemorrhage (9%). Independent risk factors for complete VFMI were aortic arch procedure (odds ratio 6.1), body mass index less than 25 (OR: 7.2), and African-American or Hispanic race (OR: 6.0). Patients with two or more identified risk factors had a 33.0 increased odds of complete VFMI compared with patients not having two or more risk factors. Compared with patients having normal vocal fold motion, patients with complete VFMI had a 2.7 increased odds of pneumonia, 5.7 higher odds of reintubation, a 7.3 times higher odds of death, and increased length of hospital stay and cost of care (P < .05).
CONCLUSIONS
Interdisciplinary postoperative care and laryngoscopy examination are recommended for high-risk patients to facilitate early detection and improve patient outcomes.
Topics: Cardiac Surgical Procedures; Female; Florida; Follow-Up Studies; Humans; Incidence; Intubation, Intratracheal; Laryngoscopy; Length of Stay; Male; Middle Aged; Postoperative Complications; Prospective Studies; Vocal Cord Paralysis; Vocal Cords
PubMed: 33075318
DOI: 10.1016/j.athoracsur.2020.07.074 -
Vestnik Otorinolaringologii 2017The objective of the present study was to consider the currently available methods for the diagnostics and treatment of the patients presenting with bilateral paralysis... (Review)
Review
The objective of the present study was to consider the currently available methods for the diagnostics and treatment of the patients presenting with bilateral paralysis of the larynx of various etiologies. We undertook the analysis of the publications in the domestic and foreign scientific literature concerning diagnosis and treatment of bilateral paralysis of the larynx. It was found that despite the existing modern high-tech diagnostic technologies and the variety of surgical methods for the treatment of this condition, the problem of diagnostics, management, and rehabilitation of the patients suffering from bilateral paralysis of the larynx remains a serious challenge for the researchers and clinicians that requires further investigation of this pathology. For the correct and timely diagnosis of bilateral paralysis of the larynx, the comprehensive evaluation of the functional state of the neuromuscular apparatus of the larynx is necessary. The key prerequisites for the success of the surgical intervention are its timeliness and the choice of the optimal surgical modalities.
Topics: Early Medical Intervention; Humans; Laryngoscopy; Otorhinolaryngologic Surgical Procedures; Prognosis; Respiratory Insufficiency; Vocal Cord Paralysis; Vocal Cords
PubMed: 28980604
DOI: 10.17116/otorino201782477-82 -
The Laryngoscope Sep 2020To determine the natural history of vocal fold cysts, by undertaking a retrospective analysis of data from a single clinical institute.
OBJECTIVE
To determine the natural history of vocal fold cysts, by undertaking a retrospective analysis of data from a single clinical institute.
METHODS
All patients diagnosed with vocal fold cysts were identified from January 2006 to June 2018. A total of 87 patients that elected not to have surgery or who had an interval of observation greater than 90 days prior to surgical intervention were further analyzed. The primary outcome was whether the cyst enlarged, reduced in size, resolved or ruptured. The secondary outcome measures were whether cyst characteristics (translucent or opaque by gross appearance and/or the presence of inflammation), voice therapy or duration of follow up (≤/> 300 days) had an impact upon natural history.
RESULTS
There were 65 females and 22 males (47 years ±17). The mean duration of follow up was 589 days (Range 21 - 4523 days). The majority of cysts did not change (70.11%). The rest enlarged (12.64%), reduced in size (13.79%), resolved (1.15%) or ruptured (1.15%). There was no statistically significant relationship between the presence or absence of clinical signs of inflammation (P = .633) or voice therapy (P = .785) on natural history. There was an equivocal relationship between gross cyst appearance and natural history (P = .054), however there was a statistically significant relationship between the duration of follow up (P = .006) and natural history.
CONCLUSION
Most vocal fold cysts appear to remain static in size over time. About 30% change, with half of these enlarging and half shrinking. In addition to some possibility of change in size, there is a small chance of resolution or spontaneous rupture with potentially serious consequences to the voice.
LEVEL OF EVIDENCE
4. Laryngoscope, 130:2202-2207, 2020.
Topics: Adult; Aged; Cysts; Disease Progression; Female; Humans; Laryngeal Diseases; Male; Middle Aged; Retrospective Studies; Vocal Cords
PubMed: 31714601
DOI: 10.1002/lary.28377 -
A&A Practice Oct 2020Vagus nerve injury may complicate carotid endarterectomy (CEA). The recurrent laryngeal nerve (RLN) branches from the vagus nerve, innervating the ipsilateral vocal...
Vagus nerve injury may complicate carotid endarterectomy (CEA). The recurrent laryngeal nerve (RLN) branches from the vagus nerve, innervating the ipsilateral vocal cord. Vagus nerve injury can cause vocal cord dysfunction. Intraoperative vocal cord monitoring can detect vagus nerve injury during CEA. A patient with distorted neck anatomy from radiotherapy to treat oropharyngeal cancer and resultant right vocal cord paralysis required left CEA. Anticipating difficult neck dissection risking vagus nerve damage with associate RLN malfunction, we added vocal cord electromyography (EMG) to routine CEA electroencephalography (EEG). We recommend vocal cord EMG in anatomically complex CEA to avoid vagus nerve injury.
Topics: Endarterectomy, Carotid; Humans; Recurrent Laryngeal Nerve; Recurrent Laryngeal Nerve Injuries; Vocal Cord Paralysis; Vocal Cords
PubMed: 33094950
DOI: 10.1213/XAA.0000000000001331 -
The Laryngoscope Jan 2021Contemporary clinical assessment of vocal fold adduction and abduction is qualitative and subjective. Herein is described a novel computer vision tool for automated...
OBJECTIVES
Contemporary clinical assessment of vocal fold adduction and abduction is qualitative and subjective. Herein is described a novel computer vision tool for automated quantitative tracking of vocal fold motion from videolaryngoscopy. The potential of this software as a diagnostic aid in unilateral vocal fold paralysis is demonstrated.
STUDY DESIGN
Case-control.
METHODS
A deep-learning algorithm was trained for vocal fold localization from videoendoscopy for automated frame-wise estimation of glottic opening angles. Algorithm accuracy was compared against manual expert markings. Maximum glottic opening angles between adults with normal movements (N = 20) and those with unilateral vocal fold paralysis (N = 20) were characterized.
RESULTS
Algorithm angle estimations demonstrated a correlation coefficient of 0.97 (P < .001) and mean absolute difference of 3.72° (standard deviation [SD], 3.49°) in comparison to manual expert markings. In comparison to those with normal movements, patients with unilateral vocal fold paralysis demonstrated significantly lower maximal glottic opening angles (mean 68.75° ± 11.82° vs. 49.44° ± 10.42°; difference, 19.31°; 95% confidence interval [CI] [12.17°-26.44°]; P < .001). Maximum opening angle less than 58.65° predicted unilateral vocal fold paralysis with a sensitivity of 0.85 and specificity of 0.85, with an area under the receiver operating characteristic curve of 0.888 (95% CI [0.784-0.991]; P < .001).
CONCLUSION
A user-friendly software tool for automated quantification of vocal fold movements from previously recorded videolaryngoscopy examinations is presented, termed automated glottic action tracking by artificial intelligence (AGATI). This tool may prove useful for diagnosis and outcomes tracking of vocal fold movement disorders.
LEVEL OF EVIDENCE
IV Laryngoscope, 131:E219-E225, 2021.
Topics: Adult; Aged; Aged, 80 and over; Case-Control Studies; Computers; Deep Learning; Female; Humans; Laryngoscopy; Male; Middle Aged; Software; Video Recording; Vocal Cord Paralysis; Vocal Cords
PubMed: 32356903
DOI: 10.1002/lary.28669 -
European Archives of... Jul 2023Early-stage glottic cancer can be treated with radiotherapy only. Modern radiotherapy solutions allow for individualized dose distributions, hypofractionation and...
PURPOSE
Early-stage glottic cancer can be treated with radiotherapy only. Modern radiotherapy solutions allow for individualized dose distributions, hypofractionation and sparing of organs at risk. The target volume used to be the entire voice box. This series describe the oncological outcome and toxicity of individualized vocal cord-only hypofractionated radiotherapy for early stage (cT1a-T2 N0).
METHODS
Retrospective cohort study with patients treated in a single center between 2014 and 2020.
RESULTS
A total of 93 patients were included. Local control rate was 100% for cT1a, 97% for cT1b and 77% for cT2. Risk factor for local recurrence was smoking during radiotherapy. Laryngectomy-free survival was 90% at 5 years. Grade III or higher late toxicity was 3.7%.
CONCLUSION
Vocal cord-only hypofractionated radiotherapy appears to be oncologically safe in early-stage glottic cancer. Modern, image-guided radiotherapy led to comparable results as historical series with very limited late toxicity.
Topics: Humans; Vocal Cords; Squamous Cell Carcinoma of Head and Neck; Laryngeal Neoplasms; Retrospective Studies; Glottis; Head and Neck Neoplasms; Treatment Outcome; Neoplasm Recurrence, Local; Neoplasm Staging
PubMed: 36881167
DOI: 10.1007/s00405-023-07904-2 -
Journal of Voice : Official Journal of... Mar 2023The diffusion characteristics of water molecules were measured in the vocal folds of canines exhibiting unilateral vocal fold paralysis and unilateral cricoarytenoid...
OBJECTIVE
The diffusion characteristics of water molecules were measured in the vocal folds of canines exhibiting unilateral vocal fold paralysis and unilateral cricoarytenoid joint dislocation. These characteristics were used in conjunction with a histological examination of the microstructural changes of vocal fold muscle fibers to explore the feasibility of diffusion tensor imaging (DTI) in distinguishing unilateral vocal fold paralysis and unilateral cricoarytenoid joint dislocation as well as evaluating microstructural changes.
METHODS
Ten beagles were randomly divided into three groups: four in the unilateral vocal fold paralysis group, four in the unilateral cricoarytenoid joint dislocation group, and two in the normal group. Unilateral recurrent laryngeal nerve resection was performed in the vocal fold paralysis group. Unilateral cricoarytenoid joint dislocation surgery was performed in the dislocation group. No intervention was performed in the normal group. Four months postintervention, the larynges were excised and put into a magnetic resonance imaging (MRI) system (9.4T BioSpec MRI, Bruker, German) for scanning, followed by an analysis of diffusion parameters among the different groups for statistical significance. After MRI scanning, the vocal folds were cut into sections, stained with hematoxylin and eosin, and scanned digitally. The mean cross-sectional area of muscle fibers, and the mean diameter of muscle fibers in the vocal folds were calculated by target detection and extraction technology. Mean values of each measurement were used to compare the differences among the three groups. Pearson correlation analysis was performed on the DTI parameters and the results from histological section extraction.
RESULTS
The paralysis group had significantly higher Fractional Anisotropy (FA) compared to the dislocation group and normal group (P = 0.004). The paralysis group also had a significantly lower Tensor Trace value compared to the dislocation group and normal group (P = 0.000). The average cross-sectional area of vocal fold muscle fibers in the paralysis group was significantly smaller than the dislocation group and normal group (P = 0.000). Pearson correlation analysis yielded values of, r = -0.785, P = 0.01 between the average cross-sectional area of vocal muscle fibers and FA, and values of r = 0.881, P = 0.00 between Tensor Trace and the average cross-sectional area of vocal muscle.
CONCLUSION
FA and Tensor Trace can be used as effective parameters to reflect the changes of microstructure in vocal fold paralysis and cricoarytenoid joint dislocation. DTI is an objective and quantitative method to effectively evaluate unilateral vocal fold paralysis and unilateral cricoarytenoid joint dislocation, also capable of noninvasively evaluating vocal fold muscle fiber microstructure.
Topics: Animals; Dogs; Diffusion Tensor Imaging; Joint Dislocations; Laryngeal Muscles; Vocal Cord Paralysis; Vocal Cords
PubMed: 33388227
DOI: 10.1016/j.jvoice.2020.12.016