Patients with superior canal dehiscence syndrome (SCDS) can present with a plethora of auditory and/or vestibular symptoms associated with a bony defect of the superior semicircular canal. While ...surgical repair is a reasonable option for patients with significant localizing symptoms, the degree of clinical improvement will vary among patients and poses challenges in outcome prediction. This study aims to assess the relationship between preoperative and postoperative symptoms and identify predictors of symptom persistence following repair.
Retrospective chart review.
Tertiary neurotology single-institution care center.
The primary outcome was to determine the proportion of resolved and persistent primary (most bothersome) and non-primary audiologic and vestibular symptoms following SCD repair. Secondary outcomes included comparison of patient, operative and radiologic characteristics between patients with resolved vs. persistent symptoms. Standardized patient questionnaires including 11 auditory and 8 vestibular symptoms were administered to patients at their preoperative and follow-up visits. Patient pre- vs. postoperative survey results, demographic and clinical characteristics, operative characteristics, audiometric data and cervical vestibular evoked myogenic potential (cVEMP) thresholds were compared via univariate χ
and multivariate binary logistic regression analyses between those patients reporting full postoperative resolution of symptoms and persistence of one or more symptoms. Radiologic computed tomography (CT) measurements of superior canal dehiscence (SCD) defect size, location, and laterality were also compared between these two groups.
Of 126 patients (132 ears) included in our study, 119 patients (90.2%) reported postoperative resolution (
= 82, 62.1%) or improvement (
= 37, 28.0%) of primary (most bothersome) symptoms, while 13 patients (9.8%) reported persistence of primary symptoms. The median (interquartile range) and range between surgery and questionnaire completion were 9 (4-28), 1-124 months, respectively. Analyzing all symptoms (primary and non-primary) 69 (52.3%) and 68 (51.1%) patients reported complete postoperative auditory and vestibular symptom resolution, respectively. The most likely persistent symptoms included imbalance (33/65/67, 50.8%), positional dizziness (7/20, 35.0%) and oscillopsia (44/15, 26.7%). Factors associated with persistent auditory symptoms included history of seizures (0% vs. 7.6%,
= 0.023), auditory chief complaint (50.0% vs. 70.5%), higher PTA (mean 19.6 vs. 25.1 dB,
= 0.043) and higher cervical vestibular evoked myogenic potential (cVEMP) thresholds at 1000 Hz (mean 66.5 vs. 71.4,
= 0.033). A migraine diagnosis (14.0% vs. 41.9%
< 0.010), bilateral radiologic SCD (17.5% vs. 38.1%,
= 0.034) and revision cases (0.0% vs. 14.0%,
= 0.002) were associated with persistent vestibular symptoms. Neither SCD defect size nor location were significantly associated with symptom persistence (P > 0.05).
Surgical repair for SCDS offers meaningful reduction in the majority of auditory and vestibular symptoms. However, the persistence of certain, mostly non-primary, symptoms and the identification of potential associated factors including migraines, PTA thresholds, cVEMP threshold, bilateral SCD, and revision cases emphasize the importance of individualized patient counseling and management strategies.
Background
The impact of close surgical margins on oncologic outcomes in HPV‐related oropharyngeal squamous cell carcinoma (HPV + OPSCC) is unclear.
Methods
Retrospective case series including ...patients undergoing single modality transoral robotic surgery (TORS) for HPV + OPSCC at three academic medical centers from 2010 to 2019. Outcomes were compared between patients with close surgical margins (<1 mm or requiring re‐resection) and clear margins using the Kaplan–Meier method.
Results
Ninety‐nine patients were included (median follow‐up 21 months, range 6–121). Final margins were close in 22 (22.2%) patients, clear in 75 (75.8%), and positive in two (2.0%). Eight patients (8.1%) recurred, including two local recurrences (2.0%). Four patients died during the study period (4.0%). Local control (p = 0.470), disease‐free survival (p = 0.513), and overall survival (p = 0.064) did not differ between patients with close and clear margins.
Conclusions
Patients with close surgical margins after TORS for HPV + OPSCC without concurrent indications for adjuvant therapy may be considered for observation alone.
Synthetic clinical images could augment real medical image datasets, a novel approach in otolaryngology-head and neck surgery (OHNS). Our objective was to develop a generative adversarial network ...(GAN) for tympanic membrane images and to validate the quality of synthetic images with human reviewers. Our model was developed using a state-of-the-art GAN architecture, StyleGAN2-ADA. The network was trained on intraoperative high-definition (HD) endoscopic images of tympanic membranes collected from pediatric patients undergoing myringotomy with possible tympanostomy tube placement. A human validation survey was administered to a cohort of OHNS and pediatrics trainees at our institution. The primary measure of model quality was the Frechet Inception Distance (FID), a metric comparing the distribution of generated images with the distribution of real images. The measures used for human reviewer validation were the sensitivity, specificity, and area under the curve (AUC) for humans' ability to discern synthetic from real images. Our dataset comprised 202 images. The best GAN was trained at 512x512 image resolution with a FID of 47.0. The progression of images through training showed stepwise "learning" of the anatomic features of a tympanic membrane. The validation survey was taken by 65 persons who reviewed 925 images. Human reviewers demonstrated a sensitivity of 66%, specificity of 73%, and AUC of 0.69 for the detection of synthetic images. In summary, we successfully developed a GAN to produce synthetic tympanic membrane images and validated this with human reviewers. These images could be used to bolster real datasets with various pathologies and develop more robust deep learning models such as those used for diagnostic predictions from otoscopic images. However, caution should be exercised with the use of synthetic data given issues regarding data diversity and performance validation. Any model trained using synthetic data will require robust external validation to ensure validity and generalizability.
Sentinel lymph node biopsy (SLNB) is widely used for Merkel cell carcinoma (MCC), however in SLNB positive MCC the role of completion lymph node dissection (CLND) with or without adjuvant radiation ...therapy is unclear.
Our goal was to determine the impact of CLND and adjuvant radiation therapy on survival in SLNB positive MCC.
We examined 447 patients with MCC with a positive SLNB in the National Cancer Data Base from 2012 to 2015. We compared patients who underwent CLND versus observation with or without adjuvant radiation.
Compared with CLND and adjuvant radiation (reference) treatment with observation (HR 3.54, CI 1.36–9.18) or CLND alone (HR 2.54, CI 1.03–6.27) were associated with worse overall survival after adjusting for clinicopathologic differences. In contrast treatment with adjuvant radiation alone without CLND was not associated with worse overall survival (HR 1.70, CI 0.74–3.92) compared with CLND and adjuvant radiation (reference).
In SLNB positive MCC, CLND alone is associated with worse survival compared with treatment with adjuvant radiation or both CLND and adjuvant radiation.
•Treatment after a positive SLNB for Merkel cell carcinoma remains a dilemma.•We analyzed 447 patients with a positive SLNB in a national cancer database.•We found that radiation with or without CLND improved survival.
High-definition video captured during transcanal endoscopic ear surgery (TEES) can serve as imaging data for computer vision algorithms. This report describes a proof-of-concept model for automated ...anatomy and instrument detection during TEES.
Background
American Society of Clinical Oncology guidelines recommend that the decision to give postoperative radiotherapy (PORT) for pN1 oral cavity squamous cell carcinoma (OCSCC) without other ...adverse features be based on the adequacy of the neck dissection (<18 or ≥18 nodes).
Methods
We conducted a cohort study of the National Cancer Database examining how PORT affects survival. We stratified analyses by the adequacy of the neck dissection and lymph node (LN) size.
Results
Our cohort comprised 1909 patients (898 received PORT). PORT conferred a survival benefit in the overall cohort (adjusted hazard ratio 0.82, 95% CI 0.72‐0.94). There was similar benefit in patients receiving inadequate and adequate neck dissections. Patients with >10 mm LN metastasis derived greater benefit compared with patients with smaller metastases.
Conclusions
In pN1 OCSCC without other adverse features, the size of the LN metastases may predict benefit from PORT, whereas the adequacy of the neck dissection may not.
Objective
Size, an important characteristic of a tympanic membrane perforation (TMP), is commonly assessed with gross estimation via visual inspection, a practice which is prone to inaccuracy. ...Herein, we demonstrate feasibility of a proof‐of‐concept computer vision model for estimating TMP size in a small set of perforations.
Methods
An open‐source deep learning architecture was used to train a model to segment and calculate the area of a perforation and the visualized tympanic membrane (TM) in a set of endoscopic images of mostly anterior and relatively small TMPs. The model then computed relative TMP size by calculating the ratio of perforation area to TM area. Model performance on the test dataset was compared to ground‐truth manual annotations. In a validation survey, otolaryngologists were tasked with estimating the size of TMPs from the test dataset. The primary outcome was the average absolute error of model size predictions and clinician estimates compared to sizes determined by ground‐truth manual annotations.
Results
The model's average absolute error for size predictions was a 0.8% overestimation for all test perforations. Conversely, among the 38 survey respondents, the average clinician error was a 11.0% overestimation (95% CI, 5.2–16.7%, p = 0.003).
Conclusions
In a small sample of TMPs, we demonstrated a computer vision approach for estimating TMP size is feasible. Further validation studies must be done with significantly larger and more heterogenous datasets.
Level of Evidence
N/A Laryngoscope, 134:2906–2911, 2024
Though size is central characteristic of tympanic membrane perforations (TMPs), its assessment is often subjective and inaccurate. A computer vision approach for identification and measurement of TMPs was developed and shown to be more accurate than sampled otolaryngologists at estimating TMP size in small subset of mostly dry, anterior and small perforations.
To review the historical circumstances that led to the emergence of corticosteroid therapy for idiopathic sudden sensorineural hearing loss (ISSNHL) and to discuss how this history has influenced ...current perspectives on the condition.
PubMed and Google scholar were used to identify articles of ISSNHL and oral corticoid steroid use. Historical articles accessed through our institutional medical library were also reviewed.
The use oral corticosteroids as a treatment for ISSNHL was seemingly influenced by three key historical circumstances that, together, provided the substrate for the treatment's use in ISSNHL. First, ISSNHL was a frustrating condition with uncertainty regarding its etiology and few reliable treatment options. Second, the discovery of corticosteroids was awarded the Nobel Prize in 1950, which led to widespread application of this therapy. Third historical circumstance was the evolution and emergence of more rigorous methodological study designs in clinical research. In 1980, these events culminated in a double-blind study evaluating the effectiveness of oral steroids for treatment of ISSNHL. Interestingly, this study is often misrepresented as a randomized controlled trial, which ultimately contributed to adoption of a new standard for treatment in ISSNHL. Research subsequent to these historical events has challenged the notion of corticosteroids as a gold standard but has not altered the historically established paradigm of corticosteroid treatment.
The use of steroids as a treatment for ISSNHL evolved from our specialty's need to address a complex condition, a novel therapeutic discovery, and a landmark study that met emerging methodological standards. Despite these strong historical foundations, ISSNHL remains a condition with an unknown etiology and the therapeutic value of corticosteroids remains unpredictable despite their gold standard label.
We compared the diagnostic performance of human clinicians with that of a neural network algorithm developed using a library of tympanic membrane images derived from children taken to the operating ...room with the intent of performing myringotomy and possible tube placement for recurrent acute otitis media (AOM) or otitis media with effusion (OME).
Retrospective cohort study.
Tertiary academic medical center from 2018 to 2021.
A training set of 639 images of tympanic membranes representing normal, OME, and AOM was used to train a neural network as well as a proprietary commercial image classifier from Google. Model diagnostic prediction performance in differentiating normal vs nonpurulent vs purulent effusion was scored based on classification accuracy. A web-based survey was developed to test human clinicians' diagnostic accuracy on a novel image set, and this was compared head to head against our model.
Our model achieved a mean prediction accuracy of 80.8% (95% CI, 77.0%-84.6%). The Google model achieved a prediction accuracy of 85.4%. In a validation survey of 39 clinicians analyzing a sample of 22 endoscopic ear images, the average diagnostic accuracy was 65.0%. On the same data set, our model achieved an accuracy of 95.5%.
Our model outperformed certain groups of human clinicians in assessing images of tympanic membranes for effusions in children. Reduced diagnostic error rates using machine learning models may have implications in reducing rates of misdiagnosis, potentially leading to fewer missed diagnoses, unnecessary antibiotic prescriptions, and surgical procedures.
In an era of vestibular schwannoma (VS) surgery where functional preservation is increasingly emphasized, persistent postoperative dizziness is a relatively understudied functional outcome. The ...primary objective was to develop a predictive model to identify patients at risk for developing persistent postoperative dizziness after VS resection.
Retrospective review of patients who underwent VS surgery at our institution with a minimum of 12 months of postoperative follow-up. Demographic, tumor-specific, preoperative, and immediate postoperative features were collected as predictors. The primary outcome was self-reported dizziness at 3-, 6-, and 12-month follow-up. Binary and multiclass machine learning classification models were developed using these features.
A total of 1,137 cases were used for modeling. The median age was 67 years, and 54% were female. Median tumor size was 2 cm, and the most common approach was suboccipital (85%). Overall, 63% of patients did not report postoperative dizziness at any timepoint; 11% at 3-month follow-up; 9% at 6-months; and 17% at 12-months. Both binary and multiclass models achieved high performance with AUCs of 0.89 and 0.86 respectively. Features important to model predictions were preoperative headache, need for physical therapy on discharge, vitamin D deficiency, and systemic comorbidities.
We demonstrate the feasibility of a machine learning approach to predict persistent dizziness following vestibular schwannoma surgery with high accuracy. These models could be used to provide quantitative estimates of risk, helping counsel patients on what to expect after surgery and manage patients proactively in the postoperative setting.
4 Laryngoscope, 133:3534-3539, 2023.
