The Bionics Institute Claim They Have Found a Way of Objectively Measuring Tinnitus

[Ed209]

Dr Mehrnaz Shoushtarian claims she has found a way to objectively measure tinnitus severity and whether a person has tinnitus or not via fNIRS (functional near-infrared spectroscopy).

I've read a few articles on this already. I'll link two below:

Technology lets clinicians objectively detect tinnitus for first time

I found this statement rather interesting:

fNIRS revealed a statistically significant difference in the connectivity between areas of the brain in people with and without tinnitus. Moreover, the brain's response to both visual and auditory stimuli was dampened among patients with tinnitus. When a machine learning approach was applied to the data, a program could differentiate patients with slight/mild tinnitus from those with moderate/severe tinnitus with an 87.32% accuracy. The authors conclude that fNIRS may be a feasible way to objectively assess tinnitus to assess new treatments or monitor the effectiveness of a patient's treatment program.

AI that can diagnose tinnitus from brain scans may improve treatment

Their study can be found here:

Objective measurement of tinnitus using functional near-infrared spectroscopy and machine learning

@Markku @Hazel, maybe you could reach out to her and see if she would be interested in doing an episode for the Tinnitus Talk Podcast?

From @Hazel:​

Good news: We have now published our interview with the Bionics Institute as the next episode of the Tinnitus Talk Podcast!

For now, it's available to Patreon supporters only, but never fear, it will be publicly available soon. Patreons will also have exclusive access to the video recording of the podcast. You can become a Patreon supporter for as little as $2 USD per month.

It was a very interesting interview with a clearly very dedicated and capable brain researcher, Mehrnaz Shoushtarian (PhD). We spoke about the technical ins and outs of the objective measure, the underlying theories the work is based on, the future commercialisation of the technique, the ultimate impact the Bionics Institute is hoping for, and much more.

We hope you will find the episode informative; let us know down below once you've had a listen!

 

[Ed209]

Just found this:

 

[Pitseleh]

NOW we're talking.

This actually brought tears to my eyes.

Some form of diagnosis was the change we needed. We're closer than it has ever got.

 

[PeterPan]

This was discussed on Australian Radio National this morning.

An means of objectively measuring tinnitus would be of great assistance in determining the effectiveness of treatments. They only used 25 people in their study; it would be interesting if more were used.

Abstract
Chronic tinnitus is a debilitating condition which affects 10–20% of adults and can severely impact their quality of life. Currently there is no objective measure of tinnitus that can be used clinically. Clinical assessment of the condition uses subjective feedback from individuals which is not always reliable. We investigated the sensitivity of functional near-infrared spectroscopy (fNIRS) to differentiate individuals with and without tinnitus and to identify fNIRS features associated with subjective ratings of tinnitus severity. We recorded fNIRS signals in the resting state and in response to auditory or visual stimuli from 25 individuals with chronic tinnitus and 21 controls matched for age and hearing loss. Severity of tinnitus was rated using the Tinnitus Handicap Inventory and subjective ratings of tinnitus loudness and annoyance were measured on a visual analogue scale. Following statistical group comparisons, machine learning methods including feature extraction and classification were applied to the fNIRS features to classify patients with tinnitus and controls and differentiate tinnitus at different severity levels. Resting state measures of connectivity between temporal regions and frontal and occipital regions 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 of interest respectively. Naïve Bayes classifiers were able to classify patients with tinnitus from controls with an accuracy of 78.3%. An accuracy of 87.32% was achieved using Neural Networks to differentiate patients with slight/ mild versus moderate/ severe tinnitus. Our 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.

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0241695

 

[Mentos]

Some clinics, like brai3n.com already uses qEEG to objectively measure tinnitus, so it's not fully true that fNIRS would be the first of brain imaging techniques used to measure tinnitus. Still, the more methods, the better.

 

[DebInAustralia]

I rang the Bionics Institute in Melbourne this morning.

They are taking names of interested prospective participants.

I mentioned that it would be great to interview Dr Mehrnaz Shoushtranan for the Tinnitus Talk community. They seemed receptive to this, and said they will forward this request to their marketing director. I dropped your names:

@Hazel
@Markku

Also, Channel 7 are featuring a story on this tonight EST.

 

[Orions Pain]

It would be cool to see a study utilizing this + Lenire. Also to see how the brain may change if a treatment is a placebo.

 

[DebInAustralia]

 

[Markku]

Hi @DebInAustralia and @Ed209!

This would, for sure, make for an interesting Tinnitus Talk Podcast episode. Let's try to coordinate this.

 

[Pitseleh]

Some clinics, like brai3n.com already uses qEEG to objectively measure tinnitus, so it's not fully true that fNIRS would be the first of brain imaging techniques used to measure tinnitus. Still, the more methods, the better.

I may be misunderstanding what Brai3n is doing, but I believe the difference with fNIRS lies in that the AI also makes a distinction in tinnitus severity, which is of great importance.

 

[DebInAustralia]

Hi @DebInAustralia and @Ed209!

This would, for sure, make for an interesting Tinnitus Talk Podcast episode. Let's try to coordinate this.

The plan is to speak to the Doctor this coming Monday morning.

I have invited @Samantha R to join us.

She sounds receptive to sharing her research with us.

 

[Ed209]

The plan is to speak to the Doctor this coming Monday morning.

I have invited @Samantha R to join us.

She sounds receptive to sharing her research with us.

That's awesome news.

 

[xyz]

Some clinics, like brai3n.com already uses qEEG to objectively measure tinnitus, so it's not fully true that fNIRS would be the first of brain imaging techniques used to measure tinnitus. Still, the more methods, the better.

I think there are different approaches to objectively measure tinnitus, but none of them have been approved so far. Hopefully the one which works in the end doesn't involve an MRI scan.

 

[Gb3]

I think there are different approaches to objectively measure tinnitus, but none of them have been approved so far. Hopefully the one which works in the end doesn't involve an MRI scan.

Why not MRI?

 

[Orions Pain]

Why not MRI?

MRIs are dangerously loud. Lots of people here have tinnitus that was either caused by or worsened by one and it would be far from ideal for any of us as a way of measuring our tinnitus.

 

[chinup]

Why not MRI?

It can spike noxacusis and likely spike tinnitus as well. It's super loud.

 

[Chriscom]

Hi @DebInAustralia and @Ed209!

This would, for sure, make for an interesting Tinnitus Talk Podcast episode. Let's try to coordinate this.

That's great, so thanks for looking into this and thanks to the others who learned of this and proposed it.

 

[xyz]

Why not MRI?

Because they are bloody loud.

 

[weab00]

Why not MRI?

If you're lucky enough you'll walk into it with a mild case and walk out with a brand slappin' new acoustic trauma.

 

[UKBloke]

Why not MRI?

Volume.

 

[Chriscom]

If you're lucky enough you'll walk into it with a mild case and walk out with a brand slappin' new acoustic trauma.

It's a risk but it's not automatic. I needed an MRI to rule out acoustic neuroma last year. I did some research to find one of the quieter machines in my area (major metropolitan area, so I had more choices than many), had it done (no neuroma, yay!), and escaped without any increase in my tinnitus. Nevertheless, it absolutely is a risk, and you have to weigh one risk against another. I wouldn't do an MRI to measure tinnitus.

 

[Gb3]

If you're lucky enough you'll walk into it with a mild case and walk out with a brand slappin' new acoustic trauma.

I had an MRI about 8 months ago and it wasn't loud at all. The old machines maybe.

 

[wwtsai]

I had an MRI about 8 months ago and it wasn't loud at all. The old machines maybe.

It definitely depends on the type of machine used and hearing protection provided. I had an MRI two months ago and while they used earplugs and cushioning over my ears, the machine was still extremely loud and unpleasant. Didn't affect my tinnitus but I swore from then on I'd never go for another MRI lol.

 

[Orions Pain]

I had an MRI about 8 months ago and it wasn't loud at all. The old machines maybe.

I think it comes down to how sensitive your ears are.

Some have tons of MRIs with hardly any protection and don't have any issues. Some have issues from new machines with double protection. Just like some play in heavy metal bands for 40+ years without issues vs someone going to one concert and coming out with permanent tinnitus.

If you have hearing loss perhaps 100 dB doesn't seem as bad vs someone who has hyperacusis but the point is even new machines can go to 100 dB and 100 dB is dangerous for our ears, regardless of how it's perceived.

 

[Soren]

With this I could finally get compensation from the work injury that gave me tinnitus.

 

[Danny B]

Huuuge news. A major breakthrough on the path to a cure. Very exciting times!!

 

[DebInAustralia]

I spoke to Bionics today.

They've already tested 30 people prior to COVID-19. They're looking to test a further 70. They're recruiting now.

I've put my hand up. It sounds like I'm in, once I sign on a dotted line.

They're focusing on testing chronic, constant tinnitus. They're excluding anyone with additional neurological conditions.

Subjects are exposed to quiet, visual and auditory stimuli (pink noise 65 dB).

I'm waiting on more info to share.

 

[PeterPan]

They're recruiting now.

Is Sydney OK or is it Melbourne only?

Also, is your tinnitus mild, moderate, severe etc?

 

[DebInAustralia]

Is Sydney OK or is it Melbourne only?

Also, is your tinnitus mild, moderate, severe etc?

If you mean, are they recruiting interstate, I didn't ask that as I live locally.

I'm not sure how to classify my tinnitus, but it's very vocal.

 

[DebInAustralia]

I'm in the trial - 10th December.