Researchers in Australia have developed a new technology to objectively measure tinnitus, according to a recently published in the journal PLOS ONE.
Dr Mehrnaz Shoushtarian from the Bionics Institute led the research, along with collaborators from Deakin University.
Chronic tinnitus affects around 6–20% of adults with approximately 20% of these experiencing it in a severe form with symptoms such as depression, cognitive dysfunction and stress. However, despite its wide prevalence, there is currently no clinical test to objectively measure or assess tinnitus. Lack of an objective measure has made the development of effective treatments more challenging.
Measuring Tinnitus
The researchers investigated the sensitivity of functional near-infrared spectroscopy (fNIRS), a non-invasive brain imaging technique, to differentiate individuals with and without tinnitus and to identify fNIRS features associated with subjective ratings of tinnitus severity.
Resting state measures of connectivity between temporal regions and frontal and occipital regions of the brain were significantly higher in patients with tinnitus compared to controls. In the tinnitus group, temporal-occipital connectivity showed a significant increase with subject ratings of loudness. Also in this group, both visual and auditory evoked responses were significantly reduced in the visual and auditory regions.
Classifying patients with tinnitus from controls with an accuracy of 87.32% was achieved using Neural Networks (machine learning) to differentiate patients with slight/ mild versus moderate/ severe tinnitus.
According to the researchers, the findings “show the feasibility of using fNIRS and machine learning to develop an objective measure of tinnitus. Such a measure would greatly benefit clinicians and patients by providing a tool to objectively assess new treatments and patients’ treatment progress”.
Reference:
Shoushtarian M, Alizadehsani R, Khosravi A, Acevedo N, McKay CM, et al. (2020) Objective measurement of tinnitus using functional near-infrared spectroscopy and machine learning. PLOS ONE 15(11): e0241695. https://doi.org/10.1371/journal.pone.0241695
Source: PLOS ONE, Bionics Institute
