Application of a Computer Vision Tool for Automated Glottic Tracking to Vocal Fold Paralysis Patients

2021 ◽  
pp. 019459982198960
Author(s):  
Tiffany V. Wang ◽  
Nat Adamian ◽  
Phillip C. Song ◽  
Ramon A. Franco ◽  
Molly N. Huston ◽  
...  
Keyword(s):  
Vocal Fold ◽  
Assessment Tool ◽  
Medical Center ◽  
Characteristic Curve ◽  
Academic Medical Center ◽  
Vocal Fold Paralysis ◽  
Control Group ◽  
Large Patient ◽  
Patient Reported ◽  
Before And After

Objectives (1) Demonstrate true vocal fold (TVF) tracking software (AGATI [Automated Glottic Action Tracking by artificial Intelligence]) as a quantitative assessment of unilateral vocal fold paralysis (UVFP) in a large patient cohort. (2) Correlate patient-reported metrics with AGATI measurements of TVF anterior glottic angles, before and after procedural intervention. Study Design Retrospective cohort study. Setting Academic medical center. Methods AGATI was used to analyze videolaryngoscopy from healthy adults (n = 72) and patients with UVFP (n = 70). Minimum, 3rd percentile, 97th percentile, and maximum anterior glottic angles (AGAs) were computed for each patient. In patients with UVFP, patient-reported outcomes (Voice Handicap Index 10, Dyspnea Index, and Eating Assessment Tool 10) were assessed, before and after procedural intervention (injection or medialization laryngoplasty). A receiver operating characteristic curve for the logistic fit of paralysis vs control group was used to determine AGA cutoff values for defining UVFP. Results Mean (SD) 3rd percentile AGA (in degrees) was 2.67 (3.21) in control and 5.64 (5.42) in patients with UVFP ( P < .001); mean (SD) 97th percentile AGA was 57.08 (11.14) in control and 42.59 (12.37) in patients with UVFP ( P < .001). For patients with UVFP who underwent procedural intervention, the mean 97th percentile AGA decreased by 5 degrees from pre- to postprocedure ( P = .026). The difference between the 97th and 3rd percentile AGA predicted UVFP with 77% sensitivity and 92% specificity ( P < .0001). There was no correlation between AGA measurements and patient-reported outcome scores. Conclusions AGATI demonstrated a difference in AGA measurements between paralysis and control patients. AGATI can predict UVFP with 77% sensitivity and 92% specificity.

Effect of Medialization on Dyspnea Index in Unilateral Vocal Fold Paralysis

2021 ◽  
pp. 019459982110565
Author(s):  
Matthew R. Hoffman ◽  
Beau Vandiver ◽  
Natalie Derise ◽  
Edie R. Hapner ◽  
Glen Leverson ◽  
...  
Keyword(s):  
Cardiac Disease ◽  
Vocal Fold ◽  
Assessment Tool ◽  
Upper Airway ◽  
Severity Index ◽  
Vocal Fold Paralysis ◽  
Voice Handicap Index ◽  
Unilateral Vocal Fold Paralysis ◽  
Function Index ◽  
Patient Reported

Objective Patients with unilateral vocal fold paralysis commonly report dysphonia and dysphagia. Dyspnea also occurs, with studies on treatment-related change producing mixed results. Studies including patient-reported outcomes have focused on single-question global scales. The Dyspnea Index (DI) includes 10 questions, is specific to upper airway–related dyspnea, and may better capture these patients’ symptoms. We evaluated change in DI after treatment. Study Design Retrospective review. Setting Academic medical center. Methods Forty-three patients with unilateral vocal fold paralysis underwent injection augmentation (n = 25) or framework surgery (n = 18). DI was recorded preprocedure, 2 to 4 weeks afterward, and at approximately 3 months afterward in 19 patients. Voice Handicap Index–10, Glottal Function Index, Cough Severity Index, and Eating Assessment Tool–10 were also recorded. Change in parameters and correlations were assessed. Obesity, cardiac disease, pulmonary disease, and procedure (injection vs framework surgery) were evaluated for effect on DI. Results Twenty-four patients had an abnormal baseline DI (>10). DI decreased from 14.9 ± 13.8 to 6.5 ± 9.3 after treatment ( P < .001; 95% CI, 4.7-12.1). Twenty-eight scores decreased, 9 remained unchanged, and 6 increased. Change in DI was influenced by the presence of cardiac disease. Decreased DI persisted at 3-month follow-up. Voice Handicap Index–10, Glottal Function Index, Cough Severity Index, and Eating Assessment Tool–10 scores decreased and were correlated with change in DI. Conclusion Upper airway–related dyspnea is common in unilateral vocal fold paralysis, occurring in half of this cohort. Correcting glottic insufficiency may alleviate symptoms. Treatment decision making should consider postprocedural change in dyspnea, especially in patients for whom dyspnea is a motivating factor for seeking treatment.

scholarly journals Comorbid Dysphagia and Dyspnea in Muscle Tension Dysphonia: A Global Laryngeal Musculoskeletal Problem

OTO Open ◽  
2018 ◽  
Vol 2 (3) ◽  
pp. 2473974X1879567 ◽  
Author(s):  
Patrick O. McGarey ◽  
Nicholas A. Barone ◽  
Michael Freeman ◽  
James J. Daniero
Keyword(s):  
Assessment Tool ◽  
Medical Center ◽  
Academic Medical Center ◽  
Muscle Tension ◽  
Retrospective Chart Review ◽  
Clinical History ◽  
High Rate ◽  
Musculoskeletal Problem ◽  
Muscle Tension Dysphonia ◽  
Patient Reported

Objective To characterize the associated symptoms of dysphagia and dyspnea among patients presenting with muscle tension dysphonia (MTD). Study Design Retrospective chart review performed over a 14-month period from October 2014 to December 2015. Setting Voice and swallowing center of a tertiary academic medical center. Subjects and Methods Thirty-eight patients with MTD were included for analysis. Clinical data were collected and analyzed, including perceptual voice evaluation and patient-reported outcomes measures. Results Among patients with a diagnosis of MTD, the incidence of reported dysphagia during clinical history and examination was 44.7%. Among patients with MTD, 60.5% had an EAT-10 (10-item Eating Assessment Tool) score ≥3 (ie, abnormal). Patients who reported dysphagia and/or had abnormal EAT-10 score (≥3) had significantly greater voice impairment than that of patients without dysphagia ( P = .02). Patients who reported dysphagia also had significantly higher Clinical COPD Questionnaire scores than those of patients who reported only dysphonia ( P = .002). Conclusions Patients presenting for dysphonia who are diagnosed with MTD have a high rate of comorbid dysphagia. Patients who reported dysphagia had significantly higher self-reported voice impairment and greater severity of breathing dysfunction as measured by the Clinical COPD Questionnaire. The coincidence of these symptoms in this patient cohort may suggest an underlying pathophysiology that has yet to be elucidated. Further prospective studies are needed to clarify the underlying cause of dysphagia and breathing dysfunction in the setting of MTD and to investigate diagnostic and therapeutic paradigms.

scholarly journals Uncovering the important acoustic features for detecting vocal fold paralysis with explainable machine learning

2020 ◽  
Author(s):  
Daniel M. Low ◽  
Gregory Randolph ◽  
Vishwanatha Rao ◽  
Satrajit S. Ghosh ◽  
Phillip C. Song
Keyword(s):  
Machine Learning ◽  
Vocal Fold ◽  
Characteristic Curve ◽  
Case Series ◽  
Vocal Fold Paralysis ◽  
Acoustic Parameter ◽  
Control Group ◽  
Acoustic Features ◽  
Level Of Evidence ◽  
And Task

AbstractObjectivesTo detect unilateral vocal fold paralysis (UVFP) from voice recordings using an explainable model of machine learning.Study DesignCase series - retrospective with a control group.MethodsPatients with confirmed UVFP through endoscopic examination (N=77) and controls with normal voices matched for age and sex (N=77) were included. Two tasks were used to elicit voice samples: reading the Rainbow Passage and sustaining phonation of the vowel /a/. The eighty-eight extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) features were extracted as inputs for four machine learning models of differing complexity. Training and testing were performed using bootstrapped cross-validation. SHAP was used to identify important features.ResultsThe median Area Under the Receiver Operating Characteristic Curve (ROC AUC) score ranged from 0.79 to 0.87 depending on model and task. After removing redundant features for explainability, the highest median ROC AUC score was 0.84 using only 13 features for the vowel task and 0.87 using 39 features for the reading task. The most important features included intensity measures, mean MFCC1, mean F1 amplitude and frequency, and shimmer variability depending on model and task.ConclusionUsing the largest dataset studying UVFP to date, we achieve high performance from just a few seconds of voice recordings while discovering which acoustic features are important across models. Notably, we demonstrate that the models use different combinations of features to achieve similar effect sizes. Overall the categories of features related to vocal fold physiology were conserved across the models. Machine learning thus provides a mechanism to detect UVFP and contextualize the accuracy relative to both model architecture and pathophysiology.Level of EvidenceType 3

Implementation and Evaluation of a Smartphone Application for the Perioperative Care of Neurosurgery Patients at an Academic Medical Center: Implications for Patient Satisfaction, Surgery Cancelations, and Readmissions

2017 ◽  
Vol 14 (3) ◽  
pp. 303-311 ◽  
Author(s):  
Daniel R Felbaum ◽  
Jeffrey J Stewart ◽  
Amjad N Anaizi ◽  
Faheem A Sandhu ◽  
Mani N Nair ◽  
...  
Keyword(s):  
Postoperative Complications ◽  
Medical Center ◽  
Academic Medical Center ◽  
Smartphone Application ◽  
Control Group ◽  
Pain Scores ◽  
Phone Calls ◽  
Academic Medical ◽  
Number Of Patients ◽  
Before And After

Abstract BACKGROUND Smartphone applications (apps) in the health care arena are being increasingly developed with the aim of benefiting both patients and their physicians. The delivery of adequate instructions both before and after a procedure or surgery is of paramount importance in ensuring the best possible outcome for patients. OBJECTIVE To demonstrate that app-based instructions with built-in reminders may improve patient understanding and compliance and contribute to reducing the number of surgery cancellations and postoperative complications and readmissions. METHODS We prospectively accrued 56 patients undergoing routine neurosurgery procedures who subsequently downloaded the app. The median age was 54 (range 27-79). Patients were followed for successful registration and use of the app, compliance with reading instructions before and after surgery, and sending pain scores and/or wound images. The number of surgeries cancelled, postoperative complications, 30-d readmissions, and phone calls for surgery-related questions were examined. RESULTS Fifty-four of the 56 patients successfully registered, downloaded, and used the app and read and complied with instructions both before and after surgery. There were no cancelled surgeries. There was 1 postoperative complication. There were no readmissions. Eight of the 54 patients (14.8%) called the office on a single occasion for a surgery related question. CONCLUSION We demonstrate the utility of a smartphone application in the perioperative neurosurgical care setting with regard to patient compliance and satisfaction as well as surgery cancellations and readmissions. Further study of a larger number of patients with a control group is warranted.

scholarly journals A Multimodal Curriculum With Patient Feedback to Improve Medical Student Communication: Pilot Study

2019 ◽  
Vol 21 (1) ◽  
pp. 115-121
Author(s):  
Nicole Dubosh ◽  
Matthew Hall ◽  
Victor Novack ◽  
Tali Shafat ◽  
Nathan Shapiro ◽  
...  
Keyword(s):  
Communication Skills ◽  
Assessment Tool ◽  
Medical Center ◽  
Academic Medical Center ◽  
Effective Means ◽  
Intervention Group ◽  
Control Group ◽  
Communication Assessment ◽  
Patient Feedback ◽  
Fourth Year Medical Students

Introduction: Despite the extraordinary amount of time physicians spend communicating with patients, dedicated education strategies on this topic are lacking. The objective of this study was to develop a multimodal curriculum including direct patient feedback and assess whether it improves communication skills as measured by the Communication Assessment Tool (CAT) in fourth-year medical students during an emergency medicine (EM) clerkship. Methods: This was a prospective, randomized trial of fourth-year students in an EM clerkship at an academic medical center from 2016-2017. We developed a multimodal curriculum to teach communication skills consisting of 1) an asynchronous video on communication skills, and 2) direct patient feedback from the CAT, a 15-question tool with validity evidence in the emergency department setting. The intervention group received the curriculum at the clerkship midpoint. The control group received the curriculum at the clerkship’s end. We calculated proportions and odds ratios (OR) of students achieving maximum CAT score in the first and second half of the clerkship. Results: A total of 64 students were enrolled: 37 in the control group and 27 in the intervention group. The percentage of students achieving the maximum CAT score was similar between groups during the first half (OR 0.70, p = 0.15). Following the intervention, students in the intervention group achieved a maximum score more often than the control group (OR 1.65, p = 0.008). Conclusion: Students exposed to the curriculum early had higher patient ratings on communication compared to the control group. A multimodal curriculum involving direct patient feedback may be an effective means of teaching communication skills.

Vocal Fold Paralysis after Esophagectomy for Carcinoma

2016 ◽  
Vol 155 (1) ◽  
pp. 122-126 ◽  
Author(s):  
Michael J. Loochtan ◽  
Daniel Balcarcel ◽  
Elizabeth Carroll ◽  
Eileen M. Foecking ◽  
Eric J. Thorpe ◽  
...  
Keyword(s):  
Vocal Fold ◽  
Medical Center ◽  
Academic Medical Center ◽  
Tertiary Care ◽  
Vocal Fold Paralysis ◽  
Delay In Diagnosis ◽  
Lengths Of Stay ◽  
Academic Medical ◽  
Mean Time ◽  
Routine Assessment

Objectives (1) To recognize factors that contribute to vocal fold paralysis (VFP) after esophagectomy. (2) To describe the morbidity associated with VFP after esophagectomy. Study Design Retrospective cohort study. Setting Tertiary care academic medical center. Subjects and Methods The medical records of 91 patients undergoing esophagectomy for malignancy were reviewed (2008-2014). Twenty-two patients with postoperative VFP were compared with 69 patients without VFP with regard to preoperative variables, surgical approach (transcervical vs other), and postoperative outcomes. A subset analysis of cervical approaches was performed, including those where an otolaryngologist assisted. Results There were no significant differences in preoperative variables between patients with and without VFP. Cervical approaches were associated with increased VFP ( P < .0001). Recurrent laryngeal nerve (RLN) identification was associated with increased VFP ( P = .0001). RLN dissection by head and neck surgeons was associated with decreased VFP ( P = .0223). Patients with VFP had longer lengths of stay ( P = .0078), higher rates of tracheotomy ( P = .0439), and required more outpatient swallow evaluations ( P = .0017). Mean time to diagnosis of VFP was 45.6 days (median, 7.5 days). Conclusions Cervical approaches are associated with increased VFP in patients undergoing esophagectomy for malignancy. When cervical approaches and mobilization are required, the inclusion of an experienced cervical surgeon to identify the RLN may improve the rate of postoperative VFP. Patients with VFP after esophagectomy experience significantly more morbidity. Due to the potential delay in diagnosis and treatment of postoperative VFP, routine assessment of inpatient vocal fold function may be beneficial.

Benign Vocal Fold Lesions in Patients with Chronic Cough

2020 ◽  
Vol 162 (3) ◽  
pp. 322-325 ◽  
Author(s):  
Michelle Adessa ◽  
Roy Xiao ◽  
Darcey Hull ◽  
Andrew J. Bowen ◽  
Claudio F. Milstein ◽  
...  
Keyword(s):  
Chronic Cough ◽  
Vocal Fold ◽  
Medical Center ◽  
Academic Medical Center ◽  
Case Series ◽  
Patient Characteristics ◽  
Control Group ◽  
Benign Vocal Fold Lesions ◽  
Leicester Cough Questionnaire ◽  
Significant Difference

Objective The objective of this study was to determine the prevalence of benign vocal fold lesions (BVFLs) in patients with chronic cough over a 1-year period. Study Design Case series with chart review. Setting Tertiary academic medical center. Subjects and Methods A retrospective cohort study of patients with chronic cough seen in our tertiary multidisciplinary cough clinic from 2016 to 2017 was conducted. Patient characteristics, presence of BVFLs by laryngoscopy, and Leicester Cough Questionnaire (LCQ) were recorded. Results A total of 419 patients were included (average age: 61 years), and 67% of patients were female. Ten percent of patients had BVFLs: granuloma (5%), leukoplakia (3%), nodules (2%), and polyps (1%). Median cough duration was 2.9 years (interquartile range [IQR], 0.7-8.5); no significant difference in median cough duration was observed between patients with BVFLs and those with no lesions (2.6 vs 3.0 years, P = .86). In total, 178 patients (42%) had available LCQ data: median score of 10.2 (IQR, 7.9-13.9); no significant difference in median LCQ was observed between patients with BVFLs and those with no lesions (10.5 vs 10.1, P = .54). Conclusion Prevalence of BVFLs in our cohort of patients with chronic cough was 10%, with posterior glottic lesions—granuloma—being the most common (5%). Prevalence of midmembranous lesions was as follows: vocal fold nodules (2%) and vocal fold polyps (1%). BVFLs were not associated with longer cough duration or more severe cough. We cannot determine a causative or noncausative relationship between BVFLs and chronic cough at this time due to lack of a control group.

Assessing Patient Symptoms Due to Nasal Septal Perforation: Development and Validation of the NOSE-Perf Scale

2021 ◽  
pp. 019459982199201
Author(s):  
Cullen M. Taylor ◽  
Stephen F. Bansberg ◽  
Michael J. Marino
Keyword(s):  
Nasal Obstruction ◽  
Discriminant Validity ◽  
Assessment Tool ◽  
Tertiary Care ◽  
Control Group ◽  
Septal Perforation ◽  
Specific Symptom ◽  
Nose Scale ◽  
Nasal Septal Perforation ◽  
Patient Reported

Objective Reporting patient symptoms due to nasal septal perforation (NSP) has been hindered by the lack of a validated disease-specific symptom score. The purpose of this study was to develop and validate an instrument for assessing patient-reported symptoms related to NSP. Study Design Validation study. Setting A tertiary care center. Methods The Nasal Obstruction Symptom Evaluation (NOSE) scale was used as an initial construct to which 7 nonobstruction questions were added to measure septal perforation symptoms. The proposed NOSE-Perf instrument was distributed to consecutive patients evaluated for NSP, those with nasal obstruction without NSP, and a control group without rhinologic complaints. Questionnaires were redistributed to the subgroup with NSP prior to treatment of the perforation. Results The study instrument was completed by 31 patients with NSP, 17 with only nasal obstruction, and 22 without rhinologic complaint. Internal consistency was high throughout the entire instrument (Cronbach α = 0.935; 95% CI, 0.905-0.954). Test-retest reliability was demonstrated by very strong correlation between questionnaires completed by the same patient at least 1 week apart ( r = 0.898, P < .001). Discriminant validity was confirmed via a receiver operating characteristic ( P < .001, area under the curve = 0.700). The NOSE-Perf scale was able to distinguish among all 3 study groups ( P < .001) and between NSP and nasal obstruction ( P = .024). When used alone, the NOSE scale could not discriminate between NSP and nasal obstruction ( P = .545). Conclusions The NOSE-Perf scale is a validated and reliable clinical assessment tool that can be applied to adult patients with NSP.

Implementation of a Leeches + Antimicrobial Prophylaxis Order Panel to Optimize Medicinal Leech Use at a Tertiary Care Academic Medical Center

2021 ◽  
pp. 089719002199368
Author(s):  
Nicole M. Palm ◽  
Jill C. Wesolowski ◽  
Janet Y. Wu ◽  
Pavithra Srinivas
Keyword(s):  
Antimicrobial Prophylaxis ◽  
Medical Center ◽  
Academic Medical Center ◽  
Tertiary Care ◽  
Medicinal Leech ◽  
Aeromonas Species ◽  
Leech Therapy ◽  
Before And After ◽  
Timing Of Initiation ◽  
Medicinal Leeches

Medicinal leech therapy promotes vascular flow and can be used to salvage grafts. Medicinal leeches have a symbiotic relationship with Aeromonas species and can therefore present a risk of bacterial transmission to patients. Antimicrobial prophylaxis is warranted for the duration of leech therapy, however, an institutional evaluation of 40 patients receiving medicinal leech therapy demonstrated poor adherence with recommendations. An electronic medical record order panel for antimicrobial prophylaxis with medicinal leech therapy was implemented, leading to a subsequent improvement in adherence to prophylaxis use, including significant increases in the ordering of antibiotics and the appropriate timing of initiation in the subsequent 10 patients receiving medicinal leech therapy after panel implementation. Aeromonas infections were rare before and after panel implementation, and developed only in the patient subset with non-optimized prophylaxis.

scholarly journals Multidimensional acoustic analysis of pathological voice

2009 ◽  
Vol 137 (5-6) ◽  
pp. 234-238
Author(s):  
Mirjana Petrovic-Lazic ◽  
Snezana Babac ◽  
Zoran Ivankovic ◽  
Rade Kosanovic
Keyword(s):  
Vocal Fold ◽  
Acoustic Analysis ◽  
Control Group ◽  
Acoustic Parameters ◽  
Vocal Rehabilitation ◽  
Voice Treatment ◽  
Before And After ◽  
The Voice ◽  
Vocal Fold Nodules ◽  
Pathological Voice

Introduction. There are subjective and objective ways to examine the effects of vocal therapy in voice disorders. The most precise and objective check-up is the use of computer voice analysis. Objective. The aim of the research was to perform a detailed analysis of acoustic structure of the vowel A before and after voice treatment in patients with vocal fold nodules in order to obtain objective verification of the vocal rehabilitation success. Methods. We examined 30 female patients, aged 34.6?6.69 years, with vocal fold nodules. Acoustic parameters of voice were compared with the control group consisting of 21 subjects without voice pathology. In all persons the vowel A was recorded and analyzed before and after a month of vocal therapy. The success of the vocal therapy was tracked using computer analysis of vocal structure. Signal, noise and tremor parameters were processed. Results. Of the analyzed vowel A parameters: STD, PER, JITA, JITT, RAP, vFO, ShdB, SHIM, APQ, VTI, SPI, F0, NHR, FTRI, eleven improved (p<0.05 and p<0.01). Three parameters (F0, NHR, FTRI) changed showing improvement, but the obtained differences were not statistically significant (p>0.05). Conclusion. Based on the obtained results it was concluded that vocal therapy gave satisfactory results, but that it should be continually applied until full stabilization of the voice.

Sign in / Sign up

Export Citation Format

Share Document