Ram Yalamanchili: Hey, Dr. Barkett, how are you? Good, good. How are you? I'm doing good. Uh, thanks for, uh, making time. Uh, so today I wanted to talk about the, I think an aspect which you and I spent a bunch of time talking about. Uh, I know you're really excited about some of the future technologies coming out from AI and, uh, related technologies.

So, uh, let's get started. Right. So, uh, first off, uh. Tell me a bit about yourself and, uh, uh, you know, and your, your introduction to how you got into research, how you got into ophthalmology. I'd love to hear a little bit more, more of your background. Oh,

Dr. Mark Barakat: yeah, no, yeah, sure. No, thanks for having me. So, so, yeah, I, um, I'm, uh, founder, director of Retina Medical Institute, uh, of Arizona here in Arizona.

And, um, you know, uh, retina specifically have been doing research for the better part of. Probably 10, 15 years at this point. Uh, clinical trials are, um, very in interesting to me. They're, they're kind of stimulating, fascinating. It's, it's, it's uh, it's a nice way of not making the same widget over and over and over and over.

And it gives us access in my patients access to newer cutting edge therapies. And, and which kind of dovetails nicely into this conversation 'cause it's all about, you know, getting access to cutting edge, um, cutting edge technology, cutting edge therapies, and, and, and here we are, so. Um, yeah.

Ram Yalamanchili: Great. And, uh, just, just briefly, right, uh.

I know you've mentioned that you have some background in computer science, which is kind of unique, uh, when we first spoke, but, uh, tell us more about that. Uh, you know, just from the background,

Dr. Mark Barakat: I mean, so yes, absolutely. Um, I, I come from, from, from a line of math people. My, my dad is an engineer. His father was a PhD mathematics, so, you know, I, I'm, I'm the kind of person that, that unfortunately, or fortunately, however you look at it, thinks of numbers.

And so, yes, computer science major in college, I found it fascinating. Um, but at the same time, um, found that I, you know, enjoy interacting with patients as well. So, um, I kind of found my way into medicine, but, uh, never kind of looked at, uh, you never kinda lose that outlook, that, that way of thinking about, you know, problem solving, things like that.

Ram Yalamanchili: Yeah. Yeah. No, it's fascinating. Uh, that makes us two, two people coming from computer sciences into healthcare, but obviously you, you, you took the tough route. So, uh, no. Great. I'm really excited to hear about your thoughts on what's, what's happening today, right. And, uh, where we are with ai. So maybe to start off right, uh, tell us more about, you know, where, where do you see AI AI's role in.

Um, you know, generally maybe like applicable to the ophthalmology and the clinical trial space. And then we'd love to hear more about your particular practice and uh, uh, yourself, right?

Dr. Mark Barakat: Oh, no, sure. So, you know, I mentioned the reason why I like, and why I actually love doing research. Um, what I don't mention is all the other stuff that comes with it.

So there's a, there's a, there's a high burden that comes with, you know, obviously regulatory burden, oversight in terms of data entry, you name it. I mean, there are many, many different steps along the way to assure of the quality of the data that goes in. And it's, it's, uh, that's critical, but it also takes, that takes a lot of, uh, man hours and, and frankly, repetitive tasks.

Um, so. That's the sort of the underpinnings of getting to do all the fun stuff, all the cool stuff of bringing new therapies, uh, to patients. And so I, I think that is where there's a unique, um, potential and possibility for artificial intelligence, right? Because artificial intelligence, as, as you know better than I do, um, helps to, um.

Offset some of that burden, but also helps to, um, basically collaborates with, with whoever's using it. Um, it makes, it, makes, makes it easier to do, makes it more complete, makes it more reliable. More accurate, has the potential to sort of revolutionize the. Underpinnings of research. So there's a lot of pain points here that can be addressed by, by, by ai.

Ram Yalamanchili: And what do you say when people say, Hey, research has been one of the slower parts of the, uh, industry, which in terms of technology option, right? I think there's even pre ai, there's been other technologies which have kind of, uh, uh, come in. Uh, do you see anything different in, in terms of what's happening right now?

Or do you have a different view on what's, uh, what's maybe about to happen?

Dr. Mark Barakat: Well, you know, I, I haven't thought about that, but since you bring it up, I would say it makes, it makes some, it makes sense that in research there's gonna be a slower adoption curve, um, only because it's not just. The head of clinic saying, well, I, I want to try a different software or something like that, is, there's many, many different stakeholders here, right?

So there's the clinical trial status, there's the investigator, there's the coordinator team, there's the, uh, central research organization, there's the, the sponsor themselves. And of course everything has to be, uh, audit ready, um, uh, if and when the FDA or the sponsor wants to look at all this stuff. So there's many, many different, um.

Barriers, I, I guess you'd call it. Um, but at the same time, there's, for that very reason, there's a lot of opportunity because if you have to please that many, um, stakeholders, uh, that's, that's kind of tough. That's kind of tough. Yeah. And so, um, I, I think that is an opportunity.

Ram Yalamanchili: And do you think that these sort of barriers have, uh.

You know, in some ways curtail the amount of research we could do. Do you see that at all in, uh, in practice?

Dr. Mark Barakat: No, I think so. I think so. I mean, I mean, you can do anything, um, in a haphazard and um, manner, but if you want to do something, um. In a reliable and consistent manner that that's it. It takes a lot of time, a lot of man hours and a lot of effort.

And of course you are limited by, by, by that, right? So, um, if I have the staff to run a. Five trials by definition, I don't have time to run the six and it, it may not be the amount of time it takes to actually see the subjects of the patients within those trials. It may also be all the, all the backend stuff that needs to happen, right?

So for every, every single visit you have, you have hours upon hours of data entry and query resolution and, and, and paperwork. And that's, that's the stuff that. Is a limiting factor in terms of, well, how many subjects within a trial or for that matter, how many trials you can accept at the site. Mm-hmm.

Ram Yalamanchili: Mm-hmm. And have there been like, historically challenges around managing this, you know, status quo, right? Like, I, one, one area I'm thinking about is, uh, what you just said, which is how do you, how do you enable staff to do all this work in, uh, in, in some kind of a, a scalable way? And, uh, do you have any like, insights around how that worked or how that worked out for you or, you know, places in the past?

Dr. Mark Barakat: It, it, it's, I mean, honestly, if you, if you talk to other clinical trialists that, that is one of the biggest problems that we have is, is, is finding and training. I. Good and great staff and then, and then keeping them because there's, there's a, there's a bottleneck there. There's only So as, as you know, in any field, we talked about computer science, we, we talked about medicine.

In any field, you're, you are limited by the number of good people that you have, and I think that will always be the case. Right? And so really what you have here is, is kind of like a force multiplier. With ai. So you, you have good people, you wanna keep training good people. I'm not saying, I'm not suggesting in the least that you wanna replace good people, but you wanna enable them to do what they're doing well at a faster, more reliable manner.

Ram Yalamanchili: Yeah, and that kind of comes back to, uh, I think a, something which gets a lot of soundbite lately, which is. You know, what is AI's place in society? And, uh, I don't know where you sit, but I'm more excited about the abundance which is coming. I think there is an, like you said, it's a force multiplier for all the things we would want to do and couldn't do for all this.

Well, right. And, uh, you know, there's, there's so many opportunities to do better research, more research, more, you know, more drugs to market like I. There's definitely an area where, um, I mean, I could definitely see the world turning towards a place where there's just a lot more opportunity than there is today, and we're able to manage that kinda opportunity.

And today we're, we're bottlenecked 'cause of many, many other resources or whatever it might be. Right. Um, so it's interesting that you mentioned, uh, there's an aspect of training and then there's an aspect of retention. Why did you say that? I'm, I'm curious, you, you sort of, uh, brought up the retention of keeping them around.

Uh, and is there a reason why, why That's sort of a, uh, top of mind, I guess. Um,

Dr. Mark Barakat: uh, quite simply, uh, knowing how to, um, work within the conference of a clinical trial is a very specific skillset that's in, that's in high demand, right? So there are, um, only so many people that are well trained and are able to do that.

And these people are being courted as they should be, are being courted by clinical sites. They're also being courted, quote, uh, accorded by CROs, possibly even by sponsors. And so there, there. They're in high demand, right? And so, um, you constantly have to try to replenish that pipeline as best as you can.

But I don't have to tell you, turnover is a killer. So much better to maintain the staff that you have and enable them to be productive. In the least amount of, you know, stressed environment as possible. And, you know, sometimes anything can, can get hectic, right? And so you're trying to figure out, you know, staff burnout's.

Another thing, for example, we we're seeing more and more trials coming out, which is, hey, that's fantastic, that's why we're doing it, right? We, we are getting these, these cool new mechanisms of actions and, and by the same time, the, the burden has begun to increase. Right.

Ram Yalamanchili: You're talking about burden on the staff, on, on your staff,

Dr. Mark Barakat: bur burden on, well, uh, on the, on the system as a whole, uh, system as a whole.

Right. Uh, a burden on the staff, but also sponsors are looking for more sites. Uh, there's more concurrent trials going on right now. Um, so it's the entire system is trying to. Accommodate a higher demand than it appears was in the past, which is great. That means there's a lot of innovation in this field, which is fa fascinating.

How do we accommodate that, that innovation and, and how do we make sure that we don't limit innovation should be limited only by your imagination, not by the logistics on the ground. Makes sense?

Ram Yalamanchili: Yeah. So that it comes to, one of the point is. How did you end up saying, you know, yes, we're in research, yes. I have to be mindful of the technology I'm bringing in, but let's, let's sort of try out something in the AI space.

You know, you obviously are, uh, sort of an innovator yourself. Um, but I'm curious like how you think about adopting new technology even potentially, like, you know, why, why work with companies like ourselves in this space? Right.

Dr. Mark Barakat: Well, I mean. Ultimately we will come back to where we're right now. But I mean, ultimately it's either, either you adapt and you adopt or you get left behind.

And I think the writing is on the wall. Um, um, AI already in other fields, e even in, in day-to-day areas, AI has already made a hu made huge inroads in, in, you know, facilitating what, what we do on a daily basis. So I cannot imagine that. This little niche of clinical trial research is, is, is immune, uh, to that sort of thing.

Right? And so, and then, I mean, frankly, going back to this particular case as, as, as I mentioned. There's many things that I love about clinical trials. There's many, otherwise, why, why would you bother doing it? There's also many things that are quite painful that are pain points. Now, I'm, I'm very lucky. I have, I have dedicated staff and they're, they're amazing.

And, uh, I wouldn't be able to do what I do without them. Um, but I also. Know that what they're doing is not very, very efficient. I mean, you have primary source and you have to document that, and then from the primary source you have to put in data capture. And that then, then afterwards you get, you know, 15,000 queries and you have to resolve those.

It's um. You know, we all know the principle of touch it once. This is, this is, touch it 15 times before, you know, any one particular data point is, is finally accepted. And, you know, um, if there is a possibility of reducing that, why wouldn't I try it Now, granted. It'll be, uh, there'll be learnings along the way, so there'll probably be some bumps in the road, but I'm not afraid of a few bumps in the road.

If, if I can be one of the first people to actually learn how to, um, you know, introduce that into clinical trials.

Ram Yalamanchili: Right. And what was staff reaction like? I'm curious because you're obviously, uh, you know, bringing something which is new and um, uh, you know, it's, it's, uh, you know, it's something people may or may not be okay with in terms of like the change, right.

So how, how do you handle that and where, how do you handle that?

Dr. Mark Barakat: It's a, it's a learning curve, right? So, um, you know, you have a conversation with, with a team saying, you know, initially it, initially it may seem to you like it's more work because we're, what we're trying to do is we're trying to lay the foundation for something I.

Here, but basically we all need to get on board with, here's the reason. I mean, do you love spending this much time, uh, sitting in front of your screen doing manual data entry, whereas you could be following up with patients or, or maybe setting up another screen or, or doing something that's actually, in essence, uh, I feel like more productive or, or, so I'll say a, a, a more valuable use of your time.

And so as long as you sort of lay out the vision, um, I, I, I think we can all be on the same

Ram Yalamanchili: team. Makes sense. And in terms of just coming back to the type of AI or the type of technology we're like looking at. Right. So I've. I've sort of thought about it as there are, there are certain types of problems you can solve today with ai and it's fairly high accuracy, high consistency, and then there's some, which are, I would say much higher value, but it might be a little bit further away, uh, because you might need more validation.

You might, you might need regulation, uh, regulatory approvals, things like that. So are you seeing things. Uh, in the similar review. And what would some of these examples be? Uh, if, if, if I were to ask specifically in the ophthalmology space?

Dr. Mark Barakat: Yeah, I mean, you, you are right. You have to learn how to walk before you can run.

Um, and so right now you look for the low hanging fruit. You look for things that are more actionable. So, so some of the things that I, I mentioned right now, right? So the, the filling out the, the, the forms, the 1570 twos, the, the, uh, a killer is informed consent. Uh, the, the informed consents, uh, they go through several iterations throughout the trial, and even though the subject may already be in the trial for months, um, all of a sudden they need to be recons consented.

And it's, it's not rocket science, but you need to keep track of which form it is. 'cause otherwise as a deviation and, and the less deviations they are, the, the better trial we conduct and, and hopefully the cleaner our data is. So there's, uh, you know, DOA logs, for example. All, all those things, it basically boils down to.

There's many actionable things that AI can help us with, um, that are the important but still minutia of the day-to-day aspects of, of, of, uh, the clinical trial. The, the other thing is, um, I. I cannot tell you how many times I've run back to find those, those little folders they have that print the protocol and, and, and, and find fonts that you need a magnifier to even be able to see because, well, what's the inclusion exclusion again?

Or, or what's, what's the exact, you know, rescue treatment criteria And hey, listen, it works. Is it efficient though? No, of course. It's not efficient. So all those things I think would be squarely within Bailey league of something that we can do now. I think that's something that AI can, can address now and make things run more smoothly.

So rather than me, you know, hitting the pause button saying, I don't know if I'm supposed to treat you or not, then running to look at the form or, or frankly, picking up the phone and calling the CRO or, or, or calling the sponsor. This is something that can be answered now. Now you, you're absolutely right.

I mean, the, the, the sky's the limit. So, um, would it be great to have ai, you know, search and find patients for me or, or, or, you know, uh, be part of the discussion about informed consent or, you know, all those things that we may have thought was science fiction, just, uh, you know, a couple decades ago, I, I think they're feasible, but this, this is harder to do.

So let's, let's, for the time being. So the concept works. Let's see. AI is a, is is a, a safe partner in, in the clinical trial space. And then once you've established that, I think you can slowly expand the functionality and and usefulness. I.

Ram Yalamanchili: So it's interesting how you, um, stratified it, right? There's a certain set of tasks and workflows, which are, I would say, not entirely patient facing.

In, in, in, in how you describe it. It could be preparing your documentation, basically managing your regulatory overhead. Um, you know, finance is another one we see quite often, right? We are. That's fair. Yeah. You know, just, just managing all the invoices, all the billing, like, you know, there, there's, there's a certain amount of like overhead there, which requires, uh, you know, uh, a lot of time to do well.

Um, and then of course all the manual, uh, chores like data entry and double data capture, things like that. I certainly think there is a, a taller ask in terms of putting an AI in front of a patient and having it interact with a patient. I think that we're entering a very different territory if we, if we go there, but somewhere in between.

But, but wouldn't that be awesome?

Dr. Mark Barakat: Wouldn't that be awesome? I dunno, is

Ram Yalamanchili: it, I'd love,

Dr. Mark Barakat: I mean, again, that's, that's thinking way, way ahead, but I mean, you're right, but right now you, you focus on, on, on the tasks that. I would love to outsource if I could, but I can't. Right. And then slowly, incrementally increase.

That's right. Yeah.

Ram Yalamanchili: And what about like things where, you know, uh, because especially retina tends to be very image heavy, uh, in terms of uh, you know, just the modalities involved. Uh, I think there's some exciting areas where AI can take us potentially. Um, I'm just curious, like, have you seen anything interesting, anything you're excited about and, uh Oh, for sure.

Where are we on constant timeline to be actually like adopting these things?

Dr. Mark Barakat: I mean No, no, absolutely. I mean, when it comes to that, when it looks to biomarkers on OCTs, for example. They, they've done, they've done some really good work on, on ai, you know, segmenting like subretinal fluid versus retinal fluid, or the presence or absence thereof.

They, it's already, uh, being used in, in, in, in some trials, not notably, um, with, um, uh, notable vision auto television. They, they, they have their own way of segmenting as well. And this is, I'll use in the Truckee trial, for example, following patients that are used a farb in the real world. I know there's many, many other, um, imaging centers, uh, across the country that are, that are looking at this also with their own proprietary, uh, artificial intelligence, uh, modules and Yeah.

Yeah, I mean, the, this, again, the sky's the limit. I'm, I'm sure as we speak, um, multiple, um, labs, multiple teams are looking at, uh, the use of AI and, for example, measurement, uh, measuring, uh, geographic atrophy or, or predicting the progression thereof. That's something that's really useful because. You know, as a field we can tell you the averages and can tell you certain risk factors for progression, but you know, when you see that one patient, that one subject in front of you, do you really know what the rate is going to be?

No. That's why many times you, you see them back and even in some of these trials and you look for, for the progression, it, it sure would be nice if you had. Um, uh, greater confidence like an AI module telling you, well, this is, this was most likely the rate of progression and these, these are the patients that are most likely to benefit from treatment versus not.

So yes, I mean, we're definitely knocking on that door. Uh, it is very imaging heavy and so, um, yeah.

Ram Yalamanchili: Got it. And are you seeing this in clinic as well? I mean, I know we, we spoke about it in the clinical trial context, but, you know, have you adopted or have you like, started to see practitioners bring this into your regular, um, you know, standard of care practice?

Dr. Mark Barakat: You know, I haven't seen too much of it in, in the clinic yet. Uh, at least AI in terms of, uh, imaging. But, um, I wouldn't be surprised if it, it was slowly be, become introduced. Right. So, I mean, for that matter. It is being introduced, uh, again, with, with the recent FDA approval of the home OCT device. That, that home OCT device, you cannot separate that from the AI module that's running in the background.

So, um, I guess I'm behind the times when I say no, I haven't seen in the clinic. It, it, it, it will be in the clinic.

Ram Yalamanchili: Okay. So it's making inroads. You, you think that'll, that'll happen? I guess it's happening right now. In in it, it, it is, it is, it is happening as we speak. Interesting. Great. Um, so in terms of like, just, just to fast forwarding this, right, uh, specifically talking about clinical trials, uh, one area which I, I find myself, you know, thinking quite a bit is when we speak to sponsors, I mean, you're on the clinician, you're on the, uh, trial side, but.

Speaking to sponsors. Some of the common things they talk about is, Hey, I, I have a tough time staying on track with my, with my program. I can't find enough sites, uh, who are, uh, you know, able to recruit, able to do the work. Um, and it always seems very similar. Like they, all, the problems seem very similar in terms of like how they describe these, uh, uh, the challenges with the trials.

Um, do you think that changes at some point, uh, you know, where could this go and how, how could this change?

Dr. Mark Barakat: Um, you know, some of it will never change. Um, if, if sponsors saying, um, boy, I wish we had, um, more sites or, or, uh, more activity or faster recruitment, I, I don't think will ever change, um, a clinical trialist saying, boy, I, I, you know, I wish I, my, my staff, uh, had more or less turnover that some of that will never change.

Right. But, um, I think when it comes to this in particular, um. What, what AI is uniquely positioned to do is help level the playing field. So, um, trying to put on my sponsor head right now and, and, you know, never been one, so I don't know if this is accurate or not, but I would assume that you have, let's say, a hundred sites for a trial.

Of those a hundred sites, I would say maybe 50 of them are really active. The other 50 may not be. So that's, that's number one. Can AI help those other 50 sites be more productive? Well, the question is, why are they not productive? Is, is it something that is manageable? Uh, is it something that they're spending so much time on, on these other tasks that, that AI could take care of 'em?

Who knows, right? That that's, that's one of the pain points. Then the other, uh, other question is of those sites that are active, what's the quality data that you're getting? I can tell you this right now, it, it is gonna be a, a wide range. You, you'll get some sites that, um, are very proficient, um, and you get some sites that provide high quality data and sometimes those two come in combinations and sometimes they don't.

And so it, it, I would say, would behoove me as a sponsor to know. Throughout the trial that we're doing these quality assessments and quality assurances rather than at the tail end when, let's say some of these patients at these sites have already finished and well, what happened here? Where's the documentation?

Or, or, or these things are missing or, or that's missing, right? So I think, um, to answer your question. There will, if, if you ever hear a sponsor or clinical trialist tell you that something's perfect, they're not looking hard enough. You will, there will always be some issue that needs solving. But I, but I think some of those are solvable.

Ram Yalamanchili: Yeah. And you bring up an interesting point about, uh, sort of discrete versus continuous, uh, management, right. Of your site quality or, uh, you know, data. Um, I do see the argument for you have to do more, more maybe like more frequent checks on what's happening in terms of your data coming in. But then, right now that also directly correlates the cost you have to invest into the trial.

So, you know, you've, you've, you've gotta make a balanced choice, I suppose. And, uh, I think that's, uh, that's one of the challenges for many, many organizations, right? And especially if you're in some form of a scale more with lots of sites, lots of patients, then it becomes even more challenging. So this issues I.

Uh, I can see the scale which AI brings in could be another excellent in terms of like, what you can do in, in more, more real time than where we are today. Right. So that, that's another exciting part of it. Um, great. Thanks for, thanks for your, uh, time, uh, Dr. Bar. It's been exciting to talk to you about, uh, where you see AI and where you're adopting ai, uh, in your clinic and, uh, where, where things are going.

So, uh, excited to see. Yeah. It's, it's been, it's been a

Dr. Mark Barakat: pleasure. Thanks for having me. Im exciting to see where, where this, where this takes us.

Ram Yalamanchili: Yeah, absolutely. Have a good one then. Thanks,