Biofeedback, AI, and Anxiety

What if the most effective treatments for children looked nothing like traditional medicine?

In this episode, three innovators share how games, biofeedback, and AI are being used to treat some of the most overlooked conditions in pediatric healthcare.

Juliette Hawa, pediatric physical therapist and founder of PFRx, describes how a gamified biofeedback device is helping children with pelvic floor dysfunction (a condition affecting around 10 million kids) learn to control muscles that cause constipation, incontinence, and pain. Designed with Children's Hospital Colorado and built for home use, PFRx turns muscle training into a video game children can play from the couch.

Dika Vilic, Senior Clinical Scientist in AI at Guy's and St Thomas' NHS Foundation Trust in London, shares what it looks like to build AI from the inside of a health system, including why pediatric AI is uniquely challenging, why children's hospitals tend to produce more innovators than adult hospitals, and what happens when a drug calculator accidentally attracts 10,000 users and has to be taken offline for regulatory compliance.

Raj Amin, CEO and co-founder of Arcade Therapeutics, explains how a game called StarStarter for Anxiety is using attention bias modification (a subconscious, neuroscience-backed form of cognitive behavioral therapy) to reduce anxiety symptoms in children and adults. A published clinical study showed a 68% reduction in symptoms within 30 days. And a depression version is now in clinical trials, funded by an NIMH grant.

Episode Resources:

Children's Hospital Colorado

StarStarter for Anxiety, App by Arcade Therapeutics

Attention Bias Modification (ABM)

Connect with Juliette Hawa:

Juliette Hawa LinkedIn

Connect with Dika Vilic:

Dika Vilic LinkedIn

Guy's and St Thomas'​ NHS Foundation Trust Website

Guy's and St Thomas'​ NHS Foundation Trust LinkedIn

Connect with Raj Amin:

Raj Amin LinkedIn

Arcade Therapeutics Website

Arcade Therapeutics LinkedIn

Arcade Therapeutics Instagram

Dr. Tracy Dennis-Tiwary

Connect with us:

KidsX Website

KidsX LinkedIn

Children's Hospital L.A. Website

Children's Hospital L.A. Instagram

Children's Hospital L.A. LinkedIn

Transcript

0:01

Welcome to the Dose of Optimism, where I talk to the optimists in healthcare. My name is Omkar Kulkarni, and I work at one of the world's best children's hospitals where I lead innovation. I started Kids X, which is a premier international startup accelerator for pediatric innovation, and over the years I've met thousands of startups, investors, and innovators. Every one of them has a story, and every one of them is optimistic about the problems they're solving. On this podcast, you'll meet amazing people who will share their stories and what makes them optimistic about the future of healthcare. A little note before we get into this episode. All right, let's get started. My first guest today is Juliet Hawa. Juliet Hawa is a pediatric physical therapist and an entrepreneur specializing in pelvic health with nearly two decades of clinical experience at Children's Hospital, Colorado. She has advanced expertise in areas such as biofeedback, urology, and developmental therapy. I hope you'll enjoy my interview with Juliet Hawa. So PFRX, tell me more about what that project has been about. Sure. So PFRX is a pelvic floor trainer designed specifically with kids in mind. So about 10 million kids suffer from pelvic floor dysfunction every year. And there are just not really good options out there for pediatric pelvic health. And so PFRX decided we were going to take this into our own hands and make the first marketable at-home pelvic floor biofeedback device. So let's start with the 10 million kids who have a need for this. So what causes pelvic floor disorders or problems amongst children and what are common reasons for it? Sure. So they're not 100% sure why some kids have pelvic floor dysfunction and other kids do not, but they can speculate that the environment and diet, also stressors, anxiety, and limitations for bathroom breaks at school kind of play a role into pelvic floor dysfunction. So when you think about pelvic floor dysfunction, you can think of constipation, urinary and stooling incontinence, abdominal pain, pelvic pain. So anything that causes those pelvic flocks to tighten, and then they end up a lot of times weakening. And so tell me about your solution, the PFRX, and how that helps these kids with their daily needs. So our solution, and me as a 20-year veteran of pediatric physical therapy, designed along with Children's Hospital Colorado and CU Innovations, a pelvic floor trainer. So what we do is we use gamification, external electrodes, and a Bluetooth capability to your smartphone or your smart tablet. So basically the child wears the device with external electrodes. What we do is we look at pelvic floor contracting and the pelvic floor relaxing, and then they get to play a video game. So this video game and the external sensors senses these EMG contractions of the pelvic floor muscles. So basically they can turn the pelvic floor muscles on by doing a contraction and the character responds. And then they turn the pelvic floor muscles off and the contraction lessens or the EMG signal shuts off and the character responds. So we've developed about eight levels of games that these kids can play over an eight-week period of time in order to make progress in their strength training and learning how to recruit their muscles better, learning how to relax their muscles, which translates to better body control when you're in the bathroom or you sense that you need to use the bathroom. So the kids can have less accidents, better bowel movements, and less pain. Wow. And they do this from home, or do they have to be in the clinic or at where can they use this tool? Yeah. So they can use the tool at home. So it's the device is about as big as a smartphone. The electrodes hook into that device. And then you just use your smartphone to get the games. And then basically you can sit on your couch or you can sit in a chair anywhere at home and play this video game. So this is designed after what a biofeedback device looks like in the clinic. And generally, those biofeedback devices tend to be pretty big or they're they're clinician tools. So they're not very user-friendly to the child. So we've developed PFRX to be very easy to use, very user-friendly, and straightforward. So they know exactly what goals are expected of them on that given day. So we've been using the device about five to seven times a week in our clinical trials to see where the best outcomes are gained. So we're saying five to seven times a week for eight weeks and checking in with your clinician during the time of use. Wow. So is the outcome you're hoping for that these children use this device and they're able to then regain their ability? Yes. So the outcome is basically it's symptom-based. So we're hoping for less urine accidents, less stooling accidents, better bowel movements overall. So the pelvic floor is a muscle that moves pressure in the body. And so if you can recruit these this muscle group better, then you can have better elimination of your bowel and bladder. So that's what we're looking at is we're in we're helping the kids gain better control of this pelvic floor muscle group. Remind me again, how old are these kids typically that are the target age for this app? Right now we're targeting under 22. Generally speaking, about five years old is a good age to start and up to 22. But the reason we're targeting kids right now is because we are a children's hospital and that's primarily who we treat. But really, anybody with a pelvic float can use this device. Adults, children, men, whoever wants to try it can use it. But primarily right now we're marketing five to 22. Thank you so much for joining us today and telling us all about your great new PFRX. I think it's a very novel approach towards a seemingly a really big problem with millions of kids to stand to benefit from this if and when you're successful. My next guest is Dika Vielich. Dika works in London at Guys and St. Thomas's NHS Foundation Trust. It's one of the UK's leading academic health systems. She has a strong academic background. She's from the King's College of London, and she has deep expertise in health information technology and AI and how it can interface really well with hospital IT systems to deliver really innovative solutions. I hope you'll enjoy this interview with Dika. Dika, thank you for joining us. You have a really cool job. What do you do? Tell us. I completely agree. This is absolutely my dream job. So I run a team, and what we make is we're an in-house team that is owned by the NHS, so the national healthcare provider in national healthcare service in the UK. I work in London in Guys and St. Thomas's Hospital, Hospital Foundation Trust. And we are an in-house AI team. We make our own software as a medical device, and we have built multiple clinical AI products that we have been able to launch into our clinical pathways. And why is that so different than other hospitals in the UK? First of all, is because GST actually invested in having an in-house AI resource. And I think that over time, other hospitals will have no choice but to do the same. Having a software engineer be part of the healthcare provision team is not very common at all. We're definitely at like the forefront of that. But we're not the only ones. There are other clinical scientific computing teams, for example, in Southampton and their hospital, there's a very good clinical scientific computing team as well. It's definitely something that is only on the horizon now. And a huge reason for that is the software as a medical device becoming a bigger and bigger part of healthcare delivery. And you need to be able to understand it, to regulate it, to implement it appropriately, and also to do all the work around it, that you have to make sure that it's clinically safe and also financially viable. I think, in my experiences, the children's hospitals have a lot more innovators and a lot more researchers than any other hospital. And primarily is because their patients are healthier and there's fewer patients. So they have a little bit more time and they tend to be a lot more creative because the market doesn't cater to them the same way that it caters to the adult population or the adult patients. So there's probably quite a lot of entrepreneurs in hospitals that are for children, but I don't think that they get the same kind of support that we do. Give me an example of a project where you've got an internal pediatric innovator who you're partnering with to build out a solution, perhaps a software as a medical device, that is improving some sort of outcome that is relevant to your hospital or to children generally in the NHS. So we've had a few projects that have started and they didn't go very far. And one of those is for bowel perfer perforation detection in neonates. It was such a good idea. It was led by a doctor called Hamat Khan, and the project was called Carnax, like it had a logo, it had everything. And we were looking at it in mobile x-rays, but AI was struggling with that because we didn't have enough data. And all the data was too different, basically. There wasn't like a common thread between them. They were different quality, they were differently collimated, they were the babies also were anywhere between 20 and 40 weeks destined. So the variability was too big. So we tried that, it massively failed. Currently, we are working with MELD team, and that's MRI Epilepsy Lesion Detection, who hopefully will come on this podcast to talk about their AI. But it they're using AI to find the lesions in the first MRI they've taken when symptoms of epilepsy show up. They have been extremely successful in that and they're ready for the regulation to label it with a CE mark to be able to deploy it in multiple different hospitals appropriately as a software as a medical device rather than as a research tool. But I'll let them talk about more about that. But we're working together on that. And then right now, also what we're helping with is to get the CE mark for a South Thames retrieval service. And what that is, just a drug calculator for emergency medicine. But the way that it went is that Evelina wrote it, they built it. It's not AI, it's just a drug calculator. And then they put it online so they could use their staff could use it in emergency situations. But they ended up with about 10,000 users by accident very quickly. And because it's software as a medical device, it's giving you drug doses, therefore impacting patient outcomes. They had to take it offline so that we can develop it properly within the appropriate regulation, make sure that all of those clinical safety checks are closed loops, and then get the C mark and then put it back up. So it's mostly that so far. How do you start one of these projects? Does somebody come to you, a clinician or researcher come to you? Do you scour the data to figure out where their opportunities may be? So most of them have come from clinicians who have identified a need, or they said, I need this, and it could be solved with tech, or this is a problem that I have that is recurring. I need to solve it with tech. When people come to me without a project, I normally just ask, what is the part of your job that you hate the most that you would love to just be able to have somebody else do or have something else do it? Because most of the time people hate things that are repetitive, things that are boring, things that are happening a lot. It's almost never, oh, seeing really interesting cases. Nobody's ever gonna hate that. So in the past, we've always had clinical needed to be identified. Some of it also came from narrow events or complications that we were seeing or things like that, where there was a big investigation or where things have gone wrong, and then you end up like analyzing your entire process and then you see where the process needs to be bolstered or improved. But in the future, I think we're gonna be changing that more into us seeing a need and seeing an opportunity and then offering our services. And the reason for that is that a lot of the times when somebody comes with an unidentified need or a newly identified need rather, or a clinical problem, almost always it is not a technical solution that is needed. It's almost always a change management needed or more people needed and things like that, or it's just the problem is complex or it's mismanaged and things like that. So I think it would be we could be a lot more productive if we knew what our strengths were and we were offering it as a service. So I'm hoping that changes over time. But for now, it's very much clinicians come to us with ideas and then we see what we can do with them. You work with pediatric data and pediatric AI products and also with products designed around AI solutions for adults. Is there a difference? That is such a great question. The first thing that is always going to be different is that all of your pediatric populations are by de facto vulnerable populations. They are underrepresented, they have very little power of advocacy, and everything has to go through a proxy. Usually their parents, not necessarily. The other thing is that the data is going to be always a lot more sparse and it's always going to be a lot more variable because we say pediatric, but we mean anywhere between just born to the age of 18. And then between 16 and 18, I think there's a bit of a gray area, and some services will move 17-year-olds to adult care and some won't, and it all depends. So that's another uncertainty. So a lot of the times people will say pediatric data is actually everybody under the age of 16 and not 18, which is also murky. But the biggest problem by far is that the data quality is always going to be a bit more questionable because if you're working with things like x-rays, you're not going to be working with a lot of CTs at all because most of the time you're not going to refer a child for a CT because of the radiation dose. And all of those images are going to be lower quality. Also, if you have children and you're scanning them on something like an MRI, they will move. They will not necessarily be it lying down completely still for 45 minutes. So the quality is a problem, the quantity is a problem, and the fact that your patient population is going to be much, much smaller. So to try to sell it to a higher app as to why you're spending a year improving something, it needs to have a really big impact. It can't just be something that is a very small, nice to have. Also, the market isn't serving the pediatric population, in my opinion, at all compared to how many products are coming out for adult population, which basically means that for teams like ours and similar teams who are trying to service pediatric populations, don't have the market providing examples of what actually works and what doesn't work, while you have that in adult radiology. And my last guest today is Raj Amin. Raj is the CEO of Arcade Therapeutics. He's a tech entrepreneur with lots of experience building new products in companies that have scaled with positive social impact. He has previously co-founded three venture-backed companies. He's led product innovation initiatives for big Fortune 500 companies in healthcare, online media, entertainment, transportation. And importantly, he's the CEO of Arcade Therapeutics, which we're going to talk about, which is delivering really innovative therapy through games for kids and teenagers. Tell me more about Arcade Therapeutics and what you guys are working on. Sure. Yeah. So Arcade Therapeutics is a therapeutic game company. We're developing clinical grade wellness products that act as interventions for mental health. We've based our interventions on real science. My co-founder here is actually a neuroscientist named Dr. Tracy Dennis Tawari. And a lot of our early interventions are based upon her work with NIH-funded studies around a process called attention bias modification, which is an attention training mechanism that's built into gameplay. So it's subconscious, so you don't really have to think about it. It's built into the game and it allows us to engage patients, but also reduce anxiety symptoms. Can you give me an example of what that would look like? Yeah, sure. So, you know, you may know that there's all kinds of different kinds of games. Mobile phone-based games are actually the most popular. It's the most type of downloaded app. And so it's naturally engaging. For example, our currently released product is called Star Starter for Anxiety. And you can search for it on the App Store and you'll find it. It is a game that embeds this attention biased modification training into the game. And the game is basically there's a ship that is moving across a game board. So think about it like pinball-like. The faster you get to the ship, the more energy your ship has to collect stars on a game board. So it's very simple. There's a tutorial that shows you how to do it. But as you play the game over six-minute sessions, it's really training your attention to focus less on negative information and more on positive. It does that by focusing your attention away from negative and angry faces and focusing them on happy faces. Seems very simple, but our clinical studies show that it really works. And is there positive reinforcement if you do the right thing? Yeah. So what happens if you get to the ship quickly, you know, which is which is the goal of the game, the ship moves faster and so it can bounce off more of the walls and collect more of the stars. As you continue to play, it gets a little bit more difficult if you're moving faster. And so it kind of gives you a little bit more of a challenge as you play through the session. Now, this is part of the broader realm of cognitive behavioral therapy, right? It fits underneath the umbrella of cognitive behavioral therapy, but it's actually a subconscious version. You could think about CBT often as being conscious top-down reprogramming. And essentially what this is doing, it's operating bottoms up. So against the subconscious biases that we have to automatically seek out negative information. And so by changing that orientation with against something called threat bias, what it does is it makes us more open and flexible, it increases what's called neuroplasticity, which allows us to see the other paths that are available and get less stuck in negative thinking patterns. That's cool. And so this is early on designed to focus on kids with anxiety, right? Yeah, so it's it's kids, it's adults. We actually did our clinical studies initially for adults 18 to 65. We've tested with kids as well. Today it's available for kids 13 plus. Interestingly enough, some of our most enthusiastic users are actually moms of teenagers who really appreciate the gameplay and think about it often like a game they can play with the family. So, what's next for you guys? Yeah, so a lot of what we're doing now is getting the product out in people's hands. So we've recently released a direct-to-consumer subscription model, just $4.99 a month right now for people to just get access to this offering. In addition, we're working with our healthcare partners and partners like universities to make it available more broadly through enterprises. So in those models really being used often as a first line of defense to help triage and figure out who needs to be escalated so that the right resources can get to them. So, yeah, we're excited with the new APA Labs badge to have that extra stamp of credibility. But the goal is now to get it out in people's hands and keep adding features. And you've got more missions coming and that are built into the game and more exciting features. We're excited about that. And then also we have a depression version that's going through clinical trials now that is actually funded by an NIMH grant that is um being what it's being implemented with University of Texas Austin at Clinical Trial for a Depression product that's based on a similar methodology, but really tuned and optimized for depression. So we're really excited about that too. Rod, thanks for joining the show and excited to see this take off. All right, thank you for joining us for your dose of optimism. Make sure to check out our show notes to get more information about our guests and the work they're doing. Visit our podcast page on the Kids X website to join our podcast community and to learn more about pediatric innovation. Thank you to our sponsors and to our presenting partner, Kids X. Please subscribe wherever you get your podcasts. And remember, it takes a village to make sure our kids grow into healthy adults. So volunteer at your local library, help out at the community center, and if you're so inspired, donate to your local children's hospital. Alright, see you next time. The content, views, opinions, and information presented on this podcast do not reflect the views of Children's Hospital Los Angeles or of the sponsors of the podcast.