Multimodal assessment of tinnitus using functional near-infrared spectroscopy and psychophysiological measures

Abstract

Objective

To use a multimodal approach to classify individuals with tinnitus from controls, and individuals with mild versus severe tinnitus.

Design

We have previously shown feasibility of a non-invasive imaging technique called functional near-infrared spectroscopy (fNIRS) to detect tinnitus-related changes in cortical activity and classify individuals with tinnitus from controls, as well as individuals with mild versus severe tinnitus. In this study we have used a multimodal approach by recording heart rate, heart rate variability and skin conductance, in addition to fNIRS signals, from individuals with tinnitus and controls.

Study Sample

Twenty-seven participants with tinnitus and 21 controls were recruited.

Results

Our findings show, addition of heart rate measures can improve accuracy of classifying tinnitus severity, in particular loudness as rated subjectively. The f1-score, a measure of classification accuracy, increased from 0.73 to 0.86 when using a support vector machine classifier for differentiating low versus high tinnitus loudness.

Conclusions

Subjective tinnitus is a condition that can only be described by the individual experiencing it, as there are currently no objective measures to determine tinnitus presence and severity, or assess the effectiveness of treatments. Objective measurement of tinnitus is a critical step in developing reliable treatments for this debilitating condition.

Keywords:

• Tinnitus
• objective measurement
• fNIRS
• heart rate
• electrodermal activity
• machine learning

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The Bionics Institute acknowledges the support it receives from the Victorian Government through its Operational Infrastructure Support Program.