Screening patients with sensorineural hearing loss for vestibular schwannoma using a Bayesian classifier

Abstract

Objectives: Selecting patients with asymmetrical sensorineural hearing loss for further investigation continues to pose clinical and medicolegal challenges, given the disparity between the number of symptomatic patients, and the low incidence of vestibular schwannoma as the underlying cause. We developed and validated a diagnostic model using a generalisation of neural networks, for detecting vestibular schwannomas from clinical and audiological data, and compared its performance with six previously published clinical and audiological decision‐support screening protocols. Design: Probabilistic complex data classification using a neural network generalization. Settings: Tertiary referral lateral skull base and a computational neuroscience unit. Participants: Clinical and audiometric details of 129 patients with, and as many age and sex‐matched patients without vestibular schwannomas, as determined with magnetic resonance imaging. Main outcome measures: The ability to diagnose a patient as having or not having vestibular schwannoma. Results: A Gaussian Process Ordinal Regression Classifier was trained and cross‐validated to classify cases as ‘with’ or ‘without’ vestibular schwannoma, and its diagnostic performance was assessed using receiver operator characteristic plots. It proved possible to pre‐select sensitivity and specificity, with an area under the curve of 0.8025. At 95% sensitivity, the trained system had a specificity of 56%, 30% better than audiological protocols with closest sensitivities. The sensitivities of previously‐published audiological protocols ranged between 82–97%, and their specificities ranged between 15–61%. Discussion: The Gaussian Process ORdinal Regression Classifier increased the flexibility and specificity of the screening process for vestibular schwannoma when applied to a sample of matched patients with and without this condition. If applied prospectively, it could reduce the number of ‘normal’ magnetic resonance (MR) scans by as much as 30% without reducing detection sensitivity. Performance can be further improed through incorporating additional data domains. Current findings need to be reproduced using a larger dataset.

Pure-Tone Hearing Asymmetry: A Logistic Approach Modeling Age, Sex, and Noise Exposure History

“…B, Saliba et al (2009). C, Welling et al (1990) /Nouraei et al (2007). Outside of the Schlauch et al (1995) method, this group has a higher false-positive rate than the pure-tone average methods.…”

Findings on 7000 MRI of the IAM: To scan or not to scan?: A retrospective cohort study

“…In the UK, the most common include Oxford, Sunderland and Charing Cross . Nouraei et al summarise various pickup rates of VS from 0.5% to 4.3%, dependent on the criteria and population studied. Other papers suggest the importance of certain frequencies, such as Mangham et al rank‐order rule and Saliba's Rule 3 kHz …”

“…Patient safety is a priority; consequences of undiagnosed VS can be debilitating or life threatening. Conversely, given the low pickup rates of VS, the costs associated with MRI and the number of incidental radiological findings, one could debate the request rate. Additionally, there is the ethical dilemma associated with incidental findings.…”

Audiologist-led screening of acoustic neuromas in patients with asymmetrical sensorineural hearing loss and/or unilateral tinnitus: our experience in 1126 patients

“…There is ongoing debate regarding who should be screened with MRI. The reported sensitivity of audiological criteria outlined in internationally published protocols ranges between 82 and 97 per cent, and specificity is between 15 and 61 per cent 9 . In one study, Obholzer et al .…”