Team UW's hearing loss detection hack could change lives around the world

Team UW’s hearing loss detection hack could change lives around the world

Ninety-nine percent of infants in the United States are screened for hearing loss at birth. But when you look around the world, that number drops to just 40%. Failure to diagnose hearing problems early on can have major implications for these children. But a team of scientists from the University of Washington has created a way to solve this problem.

Shyam Gollakota is a professor at UW’s Paul G. Allen School of Computer Science and Engineering and director of its Mobile Intelligence Lab. KUOW’s Kim Malcolm told him about his team’s cheap and accurate test hack.

This interview has been edited for clarity.

Shyam Gollakota: As you mentioned, every child in the United States gets a newborn hearing screening test. Unfortunately, that’s not true with most of the rest of the world. The reason for this is that the medical equipment to do so is extremely expensive, which means that children born in India or Kenya don’t really have a newborn hearing test.

We have smartphones, we have headphones, we have all these devices. The question we asked is, can we reuse these cheap $2-$3 headphones to detect these hearing losses accurately?

Kim Malcolm: A very provocative question. What did you find?

We were able to do a great study. We used wired headphones connected to a smartphone. By running algorithms on the smartphone, we were able to hear these very faint sounds emitted from the ear and use them accurately to detect hearing loss to a standard similar to that of an FDA-approved medical device.

So these are measurements of something going on inside the ear that you can pick up with the smartphone and the earbuds?

Yes. Unlike a healthy adult, you can’t really ask a newborn if they can hear different audible tones. You can’t just ask them to raise their hands. Thus, it turns out that current practice uses the fact that a healthy ear generates its own sounds. It’s really fascinating because we usually think of the ear as something that receives sounds, but it turns out that the ear also generates sounds. So, if you have a healthy ear, the hair cells in your inner ear will vibrate in response to external sounds. We can detect these sounds from healthy ears. We cannot detect them when there is some sort of hearing loss problem. And we were able to do that just by using these $2-$3 headphones.

Is this test difficult to perform for a layman? Because it looks like you wanted to expand that.

All we have to do is put the earpiece in your ear and then turn on the app, which emits very low sounds. The whole test takes about 20-30 seconds to run.

So it looks like a parent or family member could run the test.

This is our ultimate goal. Currently, testing has been done with graduate students as well as nurses and clinicians. But from a usability perspective, it can potentially also be done by a parent or during a telehealth visit, and then a doctor can analyze the results. The whole thing potentially costs less than $10. It’s exciting because if you’re trying to set up a universal hearing screening program in India or Kenya or one of those countries where resources are limited, you might as well not invest too much money in paying medical devices and their maintenance. , but rather use these resources rather on human capital, for example, to hire nurses, hire people who can provide follow-up.

Which brings me to my next question. Suppose a family finds that their child is having an impact on their hearing that needs to be addressed. What do they do if they live in a country with fewer resources?

So that’s exactly the point. The first step we provide here is to detect that there really is a problem. The second step is potentially a follow-up. You need medical care and follow-up to make sure you have the right resources in terms of possibly hearing aids etc. This is where it becomes a political issue. How do you divide the finite amount of resources? Potentially, you can devote more resources to follow-up rather than the initial diagnosis itself.

So what is the next step in this process?

Here at the University of Washington, we created something called the TUNE program. There is a fairly large team spanning the UW Department of Computing, Departments of Global Health, Seattle Children’s, University of Nairobi, and the Kenyan Ministry of Health. The goal here is to help create technologies that can create the universal newborn hearing agenda in Kenya. We have also made the entire code of this project open source so that anyone in the world can download it and use it in their own context.

What kind of difference could it make in a child’s life if they had this early detection?

Many studies indicate that early detection of hearing loss could really help in terms of neurological development, and also to ensure that the child does not really see a difference in the way he perceives the world himself. This is why the United States is in a much better state for people with hearing loss than the rest of the world. I believe that by enabling the early detection of hearing loss for millions of children around the world, we can really make a big difference in their lives.

Why are you so interested in this job? What attracts you to it?

Growing up in India, my grandmother, who lived with us, had hearing loss. As we were from a low income family, we could not afford to have hearing care for her until later in her life. So it’s definitely an issue that’s pretty close to me. It’s truly amazing that I finally have the opportunity to work on this problem and use my skills to make a small difference.

What do you think she would have done with the work you do now?

I think she would have loved it. I think she would have basically asked me for the next step, which is for a cheaper hearing aid, for example.

Listen to the interview by clicking the play button above.

#Team #UWs #hearing #loss #detection #hack #change #lives #world

Leave a Comment

Your email address will not be published. Required fields are marked *