103: AI in Dentistry: How Pearl AI Is Enhancing Diagnosis and Case

Welcome everybody, to another episode of the Dental Boardroom podcast. It's Wes Reed, cpa, cfp, host of the show and owner of Practice cfo. Today we continue our series on AI in dentistry. And I think this is going to be a great show because I am interviewing Mike Buckner with Pearl AI, which is one of the leading AI technologies in the space of dentistry and sort of clinical analysis. So, Mike, welcome to the show.

Thanks so much for having me.

I want to dive in and I think we're going to have a little bit of a unique show because unlike some of the other episodes I've done, we're actually going to do a little show and tell so people can jump on the YouTube version of my podcast and actually see in action how Pearl AI can help a dentist. So before we get there, let me give a little background on you and fill in the gaps here. But you, you have spent essentially your whole career, or most of your career at least, in dental technology. A lot of big names that I absolutely am familiar with and I bet most of our listeners as well. Solution Reach, which is all about automated client communication, right, Mike?

That's correct.

So you were at Solution Reach for four years, then you were at Dental intel. And a lot of my clients are on Dental Intel. We actually have a strategic kind of partnership with them to provide some discounted benefits and packages for, for our clients of Dental Intel. And you were there for a little over a year and then you were at Weave for three years. We've also another technology. All of these, if I'm correct, Mike, have come out of Utah, right, Which is where you are.

I don't know what it is about Utah, but there's a lot of dental technology companies that come out of Utah.

For some reason, I think, if I recall, BYU is the number one feeder into dental school. So you just got a lot of, a lot of, lot of dentists in Utah when they migrate back. And also you have this sort of tech hub there in the Thanksgiving Point area. I was gone after I graduated in 2005. I was gone for like 10 years. And I came back. I barely even recognized the place with all the tech that companies that have now grown out of that area. And so the merging, the, the merging of technology and dental in Utah makes a little bit of sense, but Utah seems to be this, this epicenter of dental technology. And now it continues, it sounds like with, with Perl AI.

That's correct.

Yep.

Pearl now since, since 21. So.

Well, let's, let's dive in to, to Perl AI a little bit. I want to start off before we go into the specifics of your tech and just talk about AI in dentistry in general. You've been with these various software companies and for our listeners who are learning about AI and they may know this or not know this, this concept, but AI is a entirely different type of technology. Historically we've had SaaS software software as a service, which is a software that's coded and then it's put on a website as, as a web based app as opposed to the old desktop based apps where you launch them from your, your computer. And these softwares were very process specific. The coding basically told it exactly what to do at every point along the journey of whatever the function is of that software. AI now comes in and introduces a brain along that pathway that can think very intelligently and analytically and very quickly to do what historically has been a human element of that process. And it can empower the humans, I. E. In this case the dentists, to be able to get data better, faster, more accurate, to then spend more time with the patient and kind of work on the things ultimately clinically applying to helping their, their, their patients. So AI just absolutely transformative, absolutely revolutionary in the way that it works. I don't even understand it. You know, these tokens and neural networks, it's all a bit foreign to me. We're all trying to understand it. But let's now talk about what you're seeing in the landscape of AI in dentistry. Are you finding that dentists are open to exploring AI in their offices? And how well do you think the industry is adopting this new technology? What are you seeing out there?

Are you looking to buy or sell a dental practice? If you're a seller, how do you find a strong list of potential buyers?

There's no MLS or Zillow for dental practice sales.

In such a fragmented market, many dentists selling their practice feel discouraged.

That's why I built practiceOrbit.com practice orbit.

Is modernizing how dental practices are bought and sold. It's a platform technology. Y' all know them. Zillow, Airbnb, Uber, and OpenTable, just to name a few.

These technologies do two things.

First, they help match buyers and sellers, and by centralizing the marketplace. Second, once the match between buyer and seller is made, these technologies help them navigate the sale to a successful close. Here are a few of the features.

Inside a Practice Orbit users can determine.

A reasonable sale price for a practice in just minutes.

All they need is the most recent business tax return.

Practice owners can use the directory to find important service providers like practice brokers, attorneys, accountants and bankers. Practice owners and their brokers can invite those service providers into the platform. So all parties are coordinating the sale together.

Practice owners will have a beautiful digital.

Listing of their practice like a home on Redfin. And importantly, the listing will be anonymous and personal information like your address, name and pictures are only released after an NDA is signed and approved by you or your broker. Practice buyers can create saved searches to.

Be auto notified when new listings come.

On the platform that fit their desired specialty and location. And hey, dental practice brokers, you can list all your practices on the site for free. By doing so, you'll get access to Practice Orbit's large pool of buyers, all of whom have created profiles and saved searches to be autonotified.

When new listings come for sale, you can use the platform to introduce your.

Listings to a targeted search of buyers. Additionally and optionally, you can use the.

Platform tools such as a built in.

NDA, a customizable LOI and a workflow tool to navigate the sale from LOI to closing.

In fact, you can manage all your.

Listings on the system from listing the practice to NDA to LOI and finally.

To closing the deal.

Create your free account today at www.practiceorbit.com foreign.

That's a really good question. I think, I think early on when there was talk about artificial intelligence, there, there was a lot of hesitation, but there was a lot of different types of artificial intelligence. And so you had a lot of people that were sitting on the sidelines wanting to see what, how it all plays out with, with the various types of artificial intelligence. We started seeing, you know, companies that were, that were pulling in and implementing various aspects of AI. One of those being, you know, computer vision and the ability to have AI help break things down, that typically, you know, could be recognized, you know, that it could recognize pictures and images and, and learn from, from that input. But that's not all. I mean all of the different, the different aspects from, from voice recognition, from learning language models, you know, to be able to really increase the efficiency in practices. I think it came to a point where practice owners are now seeing that, that this is truly a gift to this industry. In, in dentistry, there's only a few ways that you can grow your practice. I mean, you can, you can add operatories, you can, you know, add locations, you can, you can grow your dental practice, you can bring in new patients. But at some point there reaches kind of this max capacity unless you start leaning into technologies and efficiencies that can help you do more with less. And that's really where AI comes in. When leveraged appropriately and in the right ways, AI can help practice owners really do more with less and be more efficient and really just elevate the standard of care across the board.

Yeah. Adding to that, I think there's, I think a lot of dentists have really felt disheartened over the past, say, five to ten years as pressures on the private practice have increased dramatically. And this is a, this is something that can help them battle that trend, that, that, that emerging challenge with compression on profits within, within dental. How do you, how do you reduce, how do you increase your collections or how do you reduce your expenses? And AI has the potential to affect both of those. And so I'm encouraging our clients to adopt these, even if in the beginning they're sort of clumsy about it, and even if some of the companies aren't fully there yet, and it may not necessarily right off the bat, increase efficiencies or increase revenue. Maybe it does, maybe it doesn't. I'm trying to understand to what extent is AI truly ready to create those efficiencies and how much of it is still in this sort of beta phase of its evolution. I think Pertle, having been around one of the longest, is gotta be the farthest along in so many ways towards actually producing valuable, effective results. And the fact that you guys have grown so dramatically and have so many dentists is I think, evidence that, that you're a leading, that you're a leader in this, in this space which we're going to get into what it does and do a little demo about what it does. But the other thing too is we, you know, we patients of dental offices have a hard time sometimes visualizing or sort of mentally ingesting what is the clinical issue that we're having because we can see an X ray, but it usually doesn't tell us a great story or dentists sometimes struggle to communicate a, because they don't know how to get out of their clinical box of communication. And it's, it's too, maybe technical or doesn't quite move them to, to accept a treatment plan. My understanding is that AI is helping in case presentation to help patients better understand what is the clinical need that they, that they have. Is, Is Perl helping in case acceptance?

Absolutely. So the, the aspect of artificial intelligence that we're going to focus on when talking about Perl is truly that computer vision aspect where we are going back and we are, we are looking at x Rays, we're looking at these, these 2D images and, and those that have even been taken historically. So we can go back over the last 18 months and we can scan all of those X rays and we're gonna, we're gonna basically surface everything that the AI is finding, all the patterns that it's learned. What does caries look like, what does calculus look like, what does a periapical radiolucency look like, like. And it's going to surface all those on those X rays and then it's also going to compare everything that's in the practice management software going back those 18 months. So if there are things that the AI is flagging and saying, hey, this is, this is something that we found, but you've never treatment planned that it's going to kind of have that as a flag for, for the team, alerting the team and the clinicians to take a look at those specific areas, especially, especially when those patients are coming back in. And so.

Even if practices and clinicians don't miss anything, the game changing aspect of helping the patients to truly see what is going on on those X rays, because we're overlaying those DICOM files, those X rays, those digital X rays, we're overlaying that with color, showing what's going on and, and giving a quantitative measurement. So now they can see how far into the dentin, how far into the enamel the decay is compared to last time. So when the patients are seeing this and truly understanding what's going on, it gets them to a yes, faster and easier because they see it and they understand it. Half of the time the patients are thinking, well, if it doesn't hurt and I don't really understand what's going on, but if it doesn't bother me, it's fine. But when they truly see it and they get it, we're seeing an average increase in case acceptance of between 20 and 30% in practices, you know, just from the fact that they can understand what's going on.

And speaking of the, the effect on the economics of the practice. So I'm the, I'm the money guy, I'm the finance guy, the cpa. What I like to do is try to tether the outcomes of the, this clinical side back to the P and L, essentially back to the financial aspect of owning a dental practice. And as much as my dentist, I know, love being a dentist and it's a huge fulfilling aspect of their life, at the end of the day, it's to support their life personally and the goals that they have in their life. And so I do want to translate the efficiencies gained by new technologies into financial success for the dentist. So ideally, it's not only benefiting the patient, but it's also, of course, benefiting the doctor. And everyone's benefiting by that. The the nature of the economics of a dental practice is for those who listen to my podcast a lot, they know I talk about this subject that you've got about 75 to 85% of your costs in a dental practice are fixed costs. Now, over time, everything is variable. If you go from a $1 million practice to a $5 million practice, you're going to need a lot more employees. You're going to need more, more more facility costs. You're probably going to be doing more marketing. You're going to have just more, more up and down the P and L. Everything is goes up or down with collections over a longer period of time. But from month to month and even year to year, 80% of the costs of a dental practice are fixed. And 20%, largely labs and supplies and a few other small things are variable costs that go up and down directly as collections go up or down. And the reason why I bring this up as it relates to case acceptance is because up until you've met your fixed costs, which is your labor, your facility costs, your admin costs, you know, 75 to 85% are fixed costs. Until you've met those fixed costs and then your labs and supplies, the variable cost, your profit margin is zero. So if you think about it this way, you may go for the first three and a half weeks of the month and every dollar of collections is just paying your fixed and variable costs. You haven't paid yourself anything. And if the month ends and you just got done only paying your fixed and variable costs and not paying you, you might as well go work in and out burger, you're going to take home more money. So it's really once you pierce or break through the fixed and variable cost that now you start to get into something more meaningful. But even then, now you got to pay your, you got to pay your debt payments and you got to pay your taxes. And once you get through those, okay, now you're paying yourself and now you're saving for your future self. And so I bring this up to say, if you can get your case acceptance increase up, let's say by 10%, because that 10% is most likely after you've broken through the fixed and variable costs, 80% of that new 10% case acceptance, 80% of that money goes right down to the bottom line into the doctor's pocket. So this is where the doctor makes their, what I'll simply call their living and financial freedom bucket is you got to get past that. And so over the years that I've been doing this, I always emphasize, can you open up another morning, can you open up one weekend if your chairs are full? Because that extra little amount is where you make all your money. And this is where I think AI and helping increase case acceptance can have a massive increase on the bottom line. If they can go from, let's say a 30 to 40% case acceptance up to a 50 or 60 case acceptance or wherever you are, if you can increase that by 20%, that 20% is going to go straight to your pocket and it may increase your take home income by 80%. So it has this leveraged compound effect. You increase your case acceptance by 20%, it's going to increase your take home by 80 to 100%. That's why those extra yeses are so important. And this is where a pearl can come in and have a significant effect on the doctor's profitability. Anything you want to share about that relationship between the clinical and the financial. I love it.

In fact, it kind of, you know, it reminds me of a book that I, you know, I highly recommend. It's Dan Martel's book, buy back your time. Because in a dental practice, the thing that we were up against is time. It's that one thing that we cannot get back. How well are we using our time? That's how well we're using our time in the practice. That's how often our chairs are left open and, and that's how well we're maximizing our team. And if we're, if we're hiring team members and office managers to come in and to do certain things, let's really break that down. Now in his book, he kind of breaks this down into four quadrants and it's like, what, what are you doing? Or each team member should go through this exercise. What are the things that they like to do do? It lights them up. That's why they chose that profession. And what are the things that they like to do? But that also makes the practice a lot of money. Those are the areas that we should be spending our time in. The other areas that truly just suck the life out of you, right, you just, you hate doing, you dread doing, and it really, when you break it down, does it really make the practice a lot of money? Those Are the areas that we need to be thinking, thinking about how do we leverage technology, how do we outsource that, how do we get that off our plate so that we can spend more time doing what makes the practice a lot of money and what lights us up if we can do that. He goes in and he talks about kind of a formula here where if you can outsource for a fourth of the cost, something that really doesn't make the practice, a lot of money needs to be done, maybe, but also that nobody likes to do. Those are the areas that if you can outsource that for a fourth of the cost, you now just bought back another hour somewhere else that you can be more profitable. That's really how we got to be thinking of, you know, about. In as far as business owners or in a practice of. If I'm. I'm going to give you an example here. If I'm. If I'm paying, you know, a treatment coordinator, an office manager, insurance coordinator, if I'm paying them, I'm just gonna say 20 bucks an hour, right? 20, 25 bucks an hour to be going through and verifying and calling insurance companies to see what patients are eligible for and what their remaining benefits are. Let's add that up, because the cost and depending on how much time they spend on the phones, that adds up. And, and now there are better tools and there are better ways to do certain things like that that you can outsource for a fraction of the cost. You could leverage artificial intelligence to be doing a lot of that, which now just buys back additional time for those team members to be doing something else. That's really, you know, when you break it down, that's really where AI comes into play is, is helping practices, you know, do more with less, be more efficient, but also making a difference on that, that case acceptance and helping the patients, you know, see what's being presented and understand that.

So I want to. I have a few comments on this subject of time. Time being the most valuable thing we have. And I think sometimes the thing we mistreat the most. A few comments on this. Number one is Warren Buffett.

Said that successful people say no to a lot of things. Really successful people say no to almost everything. Because when you, as a business owner and as a human being, honestly, but especially as a business owner and a dental, you have an incredible amount of people vying for. For their time. Vying for their time. And it's very common for dentists and CPAs like me as well, to naturally want to do things Ourselves, we are consummate Diyers, really, and we're consummate Diyers. And one thing I had to learn over the years is that diying can be beneficial in some areas, but it can be incredibly detrimental in other areas. Because what patients come in the practice for isn't for small talk. It's not to get a nice chair that gives you a little massage. It's not to watch the TV on the top of the roof in the operatory. It's, it's none of those things. It's, they want no pain, they want a nice smile, they want good oral health. Those are the things they come in for. Anything that a dentist is doing that isn't promoting that desired job that a patient wants to be done for, for their life, anything that isn't that is a less or an under productive use of the doctor's time, but because they can do it and they can think, oh, I can save $100 if I do this, I can save a little bit of money if I do this instead of having somebody else, instead of hiring somebody else. Now I get, in certain situations, like when you start up a practice, you know, you're probably going to be doing your own hygiene for a little while. As a dentist, I get it. So I don't want this to be taken to the extreme. But as dentists want to become a truly successful practice, getting to one, you know, 1.3, 1.82, two and a half, $3 million as a dental practice, there's no way to do that unless they figure out how to use their time with increasingly more.

Do you ever feel lost in your practice finances? And how about your personal finances? Ever wonder where your hard earned money goes and, and why you're not seeing the financial progress you've worked so hard for? If so, listen up. As a dental CPA and financial planner, I've created our company Practice CFO just for you. With almost two decades of experience, Practice CFO integrates great CPA services like accounting and tax with customized financial planning, both business and personal.

Think of it this way.

Our dental focused CPA services give us the X rays we need to clinically plan your global finances and be effective financial planners. It's a highly customized approach we call the CFO model. Historically, having a CFO or Chief Financial Officer was an advantage of large corporations only. But today, Practice CFO gives that same advantage to private dental practice owners. As a client of Practice cfo cfo, you'll be assigned one of our dedicated CFO advisors. You'll receive insightful financial reports each month, have regular financial review meetings, reduce taxes, grow your wealth, and feel more in charge of your numbers. Because we believe that in the competitive landscape of dental practice ownership today, you have to be an effective business owner, not just a capable clinician. Reach out to learn more at www.practicecfo.

Productivity out of IT and the productivity that I emphasize as critical is what the patients consider valuable. And anything behind the curtain that leads up to the clinical diagnosis and the treatment planning and the communication and the, the actual work, the, the treatment, anything behind that sort of that, that assembly line that is before getting to the patient should be delegated. And a great dentist is not only going to delegate that, but they're going to hire really well and find a great people and establish a great culture of energy and positivity that those people that are delegated to can really be elevated in their role and produce that part of the assembly line really effectively. So by the time it gets the doctor's cue, when they're presenting with a patient, the doctor can do that extremely well. And then when they're done, the front office can collect very well from the insurance companies and the patient to ultimately get money in the bank out of that whole, that whole process. And so one, you know, one, one doctor I heard say it on a, on a former podcast, he goes, I've had to learn how to fire myself from a bunch of jobs so that I could focus on the jobs that actually make me money. And one of the things I emphasize to doctors a lot, especially new doctors who just bought a practice, is less is more. And what I mean by that is if you can live off less in your personal life, it frees you up to retain capital or money in your practice, which will then allow you to hire good people. It'll allow you to have a good, maybe practice management consult or allow you a little extra money to get pearl going in your office. Because a lot of times these things are investments that don't immediately on day one turn a profit. Like you hire a good employee, even if they're good, they may take six months to a year to become really effective at that. Or you get a new technology, it may be a few months or more before you understand how it works. It's, you're using it effectively, your team adopts it, and then you start turning a profit on that. So less is more. Try to live as a financial planner. Mike I'm always weaving in financial planning advice into almost whoever I'm talking to. Dennis Try to live through. If you don't have resources in your practice to invest in those things that are going to grow your practice, try to figure out a way to live on a less in order to free up space to have more in your practice, because that will then generate significantly more later in order for you to have a really good life today and saving for the future. It's like, who's that financial planning guy, really popular financial planning guy who wrote the book Total Money Makeover. He said, if you live like no one else now, later you'll live like no one else. Dave Ramsey.

Yes.

If you live like nobody else now, later you'll live like nobody else, meaning live really frugally now, and later on you don't have to live frugally anymore. So, anyways, just a few thoughts there, and one of the, one of the areas that I think the doctor should not delegate, but in fact, they need to delegate to do more of this. It's communication, culture, management, sales. Those are the things my doctors who do $3 million a year as a single doctor, practice, maybe an associate. Those doctors on almost every case, they communicate really, really well. And they're good. They're good leaders. They're good leaders in their practice. And dentists naturally love to really continually hone the clinical, as they should, But I really try to encourage them to also hone in the, the, the soft skills as well, because the soft skills, at the end of the day, I found, end up making more money than the clinical skills. And I know that may not sound welcomed by a lot of listeners, but patients typically just don't know. They don't know exactly that you're 30% better than the dentist down the street. But they will know how they feel when you communicate to them the treatment plan that you're presenting. And that's what they go off of is, is that feeling. All right, that was a little bit of a, of a tangent there, but let's, let's get back on track here. Let's jump into Pearl, and I'd love for you to share your screen, Mike. And let's give us a demo. So listeners, we feed our podcast into YouTube and some of our YouTube shows will actually do a demo or a PowerPoint. So we're going to do that. And Mike, if you could explain what we're looking at for those who are not on YouTube, that would be. So go ahead and kick it off with us with this demo.

All right, so. So what we're looking at here, this is Pearl's second opinion. And this, this is truly designed to be able to give like an AI second opinion on real time X rays. So a patient comes in, gets their X rays taken. Our system will pull the, the DICOM file or the digital images, run them through our AI software and then it will put them into Pearl's platform like this. So looking at this, let's just say Ryan just barely came into the practice. I can click on this and it's going to give me and I love this view here. This is kind of what I consider like a 30,000 foot view. You've got the, the full mouse series, the FMX and, and you're seeing little indicators in the bottom left hand side of each of these images which is really the system telling you that AI has surfaced or AI is detecting that there is something to be seen in, in each of these X rays. So right here, you know, each of these colors represent something different. But I can click in here and I can see that you know, there are, there are progressed carries and in fact not only are these areas that should be looked at, but it's giving that quantitative measurement. So it's showing you that 19% is in the enamel, 81% is in the dentin.

Okay.

In these areas here, it's showing you the bone level measurements from the CEJ to the crest, areas of subgingival calculus, areas of notable margin. Okay. But then also in a different color, it's showing those areas that, that are incipient and these are the ones that typically, you know, we, we watch or we keep an eye on. We might be able to remineralize, use cured on or something else in order to arrest that. But this is really helping the patients see and understand this. So first of all, without the, the overlay, right. I can some of this, it's pretty obvious, you can see what's popping up. But then when we're talking to the patient, we're going to give a little bit more color, a little bit more context. So I'm going to have AI actually analyze everything that's going on, break that down, all the anatomy of the tooth so that I can then explain what it means when it's progressed into the dentin and what it means when we say that it's incipient and that, that it has not yet progressed or that we, we might be able to, to stop that from progressing.

Right.

And then I can also show a view of how much, how much of that tooth is affected. So right here this helps especially when making decisions that. Okay, I've got 82% of that tooth that's affected.

You know, or you've got carries, you've got a restoration on here. So we might now be to the point where we may need to proceed with a crown. So it's showing you how much of the tooth is affected there. It's really giving that additional context to the patients. Okay, now one more thing that I just want to show is, is oftentimes, and I'm going to come back here, but oftentimes we may have those patients that come in and we were watching something, you know, the last time that they were in. We. Let me just pull this, this image up here. I'm going to compare this, this, this X ray that we just took with the last X ray that was in. So this here shows that, okay, it was, you've got 47% of that, that's in the dentin, 53% of the enamel. And now when they've come in and we've taken a new X ray that we've got 56% of that in the Dentin, 44% of that is in the enamel. And you can see that difference there. So it really helps kind of paint that picture to the, to the patients of truly what is, is needed to be taken care of while that patient's in the chair. So that is, that's really kind of the, the, the nuts and bolts of how our system works. We're going to provide those visuals. We're going to also provide a PDF with all of that kind of broken down so that when they're submitting their insurance claims, they have evidence for claims. They can, they can show all the measurements on there. Now I want to go back just for a second and talk about this concept of time and making the most of our time while the patients are in the chair. The CDC recently, they've got a study that shows that 43% of caries like on an X ray, 43% of caries go missed on an X ray. 20% of caries that are diagnosed are not actually caries. And then you've got about 49% of periapical radiolucencies that go missed on an X ray. So where this really comes into play is that if we are making the most of when that patient's in the chair and ensuring that we're catching everything before that patient comes in, the system's going to look at their last set of X rays, compare what's in that practice management software to provide those insights. Okay, so that we can, we can get the whole team on the same page, and we can make those calls to say, all right, the AI is detecting that there was something right over here. Let's get another set of X rays. Let's compare that with the last set of X rays when that patient was in. Okay. So it's now we're planning ahead. We're also able to have the, what we call pre check. It's AI driven insurance verification so we can get the full breakdown. We know what that patient is eligible for. Okay. Now, prior to artificial intelligence really coming into the dental space, we were leveraging and I worked at a few of these companies where we were sending out automated text messages to bring patients back into the, into the practice when there was an opening.

Right.

And that's great because now it's automatic automated communication. We're bringing patients back in. This, this is what really excites me. This is where we can get very laser focused on bringing the right patients back in for certain, certain openings in the chair. So now we can go through and say, okay, AI is saying that here is a patient that has, you know, three to $5,000 worth of treatment that we have never even diagnosed. We've never even talked to the patient about, and here's what's remaining on their insurance benefits. So we know that if we can plan ahead, get that patient into the chair, we know what they're eligible for, we know what the AI is showing. We can see it now. We can be a little bit more proactive and a little bit more intentional to make sure that we're not just bringing somebody that's coming back in for a cleaning that, you know, might be low production value. And that patient, you know, they might be one of those patients that just is very hesitant to proceed with treatment. We're bringing the right patients back at the right time, making the most of the time in the chair.

All right, couple questions on this. Thank you for that demo. That was fantastic. So are you saying that Pearl can take a radiograph that was done on a former patient that maybe you didn't have Pearl at the time that you did those X rays, and it can run it through its process and give recommendations or illustrate areas of need that weren't previously uncovered in the original radiograph? Am I understanding you right?

Yeah. So it might be saying, okay, you've got a patient coming back in today for a cleaning, and they've got something, you know, they've got some, some unscheduled treatment. However, this patient, based upon sub gingival calculus, based upon know, bone level Measurements, you know, and the percentage per quadrant. This is probably a good candidate for scaling and root planing. So it's going to surface these things saying, you might want to take a look here, or here's a patient that's coming in for a cleaning. But you didn't, you never, you never talked to them about this periapical radiolucency. They probably need a root canal. So it's going to surface those things from previous patients or from the last time that those patients were in. It's going to pull those X rays in as well.

So the AI is detecting something that the dentist is not detecting. Is that a correct understanding?

I would say the AI is detecting what most of the time the dentist is detecting as well. And I love that you said detecting. It's not diagnosing. The AI is simply saying, based upon the pixels that we see in this image, there is a high likelihood that carries is present right here. Now, I would say most of the time when, when looking at it, the, the dentist will say, oh yeah, I can see it right here. Now. Maybe I didn't know that it was, I didn't see or didn't think that it was that far progressed. And sometimes, I mean, we're in an industry where a lot of these dentists, they're, they're practicing solo. They are, they're the only dentist in the practice. And so sometimes when they're on the fence about something and they may want to watch it, this can provide that second set of eyes where it's really just looking at the data. It's, it's not making any sort of emotional judgment calls. It's just saying based upon the data, here's what's going on, but it is not substituting the clinician's decision.

So speaking of the data, the power of a, an AI solution is commensurate with the depth of its data. Are you crow crowdsourcing your data across existing Perl users across hundreds of dental offices to have a larger data set within the LLM that the, that Pearl will dip into when it does its, its analysis to produce its recommendations, or it's, it's, it's detections, its trends? How and how well is it using that to kind of forecast the development of the things it is detecting? So I guess that's two questions. One is how, how is Perl building out the strength of its LLM, which these things are very much effective only as a function of the depth of their, of their data. That's number one. And number two is is not only saying, here's some additional things we've detected now that may help you as a dentist diagnosing this, but also here's how we believe this is going to develop over, over time based on this massive pool of data from other patients historically.

So I'm going to go back to when this process really started. We started this process back in 2015, really going through with the largest data set of anonymized dental X rays. Okay. And having, first of all, having dentists having human annotators go through and look at and train what they see on those X rays. So this truly comes down to, you can equate this to the power of a thousand dentists, you know, basically looking at your X ray and giving their assessment of it. Okay, so it's, it was several years in the process of training these modules to detect into, look at patterns, and it's really breaking down what is seen on those X rays pixel by pixel. You know, the human eye has, has limitations. We can only see so much, but computers can really break down thousands of different shades and tones of gray to catch things earlier and to help define how far something has progressed. And so if there is something now with and I, it's important to note that with each of these images that the AI is, is going to kind of overlay or detect certain things. There is always an edit button in there and there may be something that the dentist says, you know what, I, I can see why the AI might think that this is carries or might think that this is calculus, but I've looked here and I'm going to just, I'm going to delete that and they can go in and they can delete that annotation. There's also an indicator on there where they can go and they can say, you know what, something is off and they can click on that and that, you know, after, after so many of. Let's say that we've gotten a number of calculus that seems off after so many. Our team really goes to work to look at the models to see, okay, where, where are we missing? We need to maybe improve certain models. We are constantly improving and the AI is, is constantly getting more and more accurate.

Thank you. So, yeah, in the beginning there was some human training. It's almost like there's always going to be some, some human training. And it's not just aggregating data across a lot of users, but it's also the users continually training that data and correcting it when it's wrong. And then you have the Collective brain, using your example, which I think really clarified for me as a non clinician, exactly how that's working. It's like the collective mind of a thousand dentists all looking at a single X ray together. That's, that's a really powerful explanation of how AI is working. And as you know, with like GPT for example, periodically it will give me two answers and ask me which one I like more. So it's constantly trying to self educate along the way and the more educated it becomes, the faster it probably continues to self educate. Almost like this geometric curve of learning. And that's where, you know, that's where the whole world is asking will it ever get to a point where it's, its curve is so steep, it's learning is so fast, its neural networks so good that essentially those neural networks become like a human brain and then even better and they become self aware and AGI kicks in. Artificial general intelligence. Who knows where that will go. But I think that's the concept here, that these things get smarter and smarter, smarter with data and they learn on themselves the smarter they get. So who knows where the end of that curve is of self learning in these large language models. So it actually is, I think, going to be really exciting to see how effectively these things help doctors over time become more and more accurate as clinicians communicating a treatment plan to their patients. Now you also mentioned verification. Do you get, does Pearl get involved in areas outside of the operatory room, I. E. A revenue cycle, management with verification or submitting EOBs, dealing with rejections, that whole process?

Yeah, there's, there's some really exciting things that we are just about to, to be launching where we're not just focused on the X rays in the practice, we're not just focused on, on looking and, and highlighting detections. We're taking that to the next level of knowing that it's surfacing a lot of data. How do we capture on that, how do we make the most of that for the practice? So we are obsessed right now looking at the whole process from, from when the patient comes in to when the patient leaves, you know, and, and when the claims are submitted, we are looking at how we can leverage artificial intelligence in every step of the way to help practices really increase their efficiency and, and to do more.

So starting off with radiograph analysis and then expanding into some operational processes which at the end of the day they all relate. The radiograph analysis is one step in this assembly line of the patient experience. And I know that there's other AIs that are really kind of starting on the RCM side, the revenue cycle management side. And then they're considering going into the, the clinical side and the operatory. It'll be interesting to see how the various sort of leading companies out there evolve themselves across the different chain of, of AI inside of a dental office and how much they're going to specialize in one particular aspect of AI use in, in an office. I think that'll be interesting. Okay, now the other, I think that one of the final questions. I know we're running out of time here, but explain how Perl is compared to other AI radiograph analysis out there. Like for example, Overjet, who I've also done an interview with as well. Yeah.

You know, a lot of these companies have a lot of similarities. We're probably more similar than we are different in most cases. You know, as far as Pearl goes, right now Pearl has the largest list of FDA cleared detections. We are the only company right now that is cleared for 3D imaging for CBCT and we are in the process of finalizing our product to be released. But we needed the FDA clearance on that first. So we, we're several steps ahead of looking at CBCT and having the FDA clearance for that. That's going to be a massive game changer. I would say another area that we're, that we're different is that we are focused on, on that workflow in the practice. So we have the largest list of native integrations. So that if it's, for example, if you're the practice, practice is using eaglesoft right there within eaglesoft. You don't have to open up another browser. It's just available right there in the image reader. They can go in and click and see Pearl's detections in there. And we've got several others that are natively integrated. The largest list of natively integrated capabilities. So a lot of different ways that we are, that we're different, a lot that were similar. But we started with the mindset of creating a tool for the practices for the clinicians. And we went to the providers first, we went to the clinicians first and saying, look, of course AI is being utilized with insurance companies. We want to provide a tool that helps you on the same level playing field. We want to give you the same capabilities that insurance companies are using so that when you're submitting these claims, you know, you're essentially you're, you're on the same level playing field and you can provide the evidence for claims, show that it's been ran through, you know, artificial intelligence, FDA cleared AI detections to ensure that they are accurate.

Great. Okay, so how do people get to know Pearl and how do they go about doing a demo and determining if this is a good fit for their practice?

Yes. So you can go to helloperl.com and if you go to hellopearl.com you can go on there. You can do a, you can click to get a demo of our product and kind of see how it works. And our team will be able to do a zoom meeting, kind of walk you through, show you, you know, how it would work in your practice and really determine the right, you know, we've got different offerings, but really help determine the right offering for your practice.

Awesome. Well, Mike, this has been fantastic. Pearl's been out there for one of the longest company, maybe even the longest, in this particular space of radiograph analysis. That was really impressive demo. I can see why this would be so powerful for a dentist. Very exciting to see how these things are evolving and what they're doing for dentists. So thank you for taking the time to join on the show and give us an illustration of priority Pearl AI.

Thank you. Thank you for having me.

It'll be great and say a couple years to, to say, hey, Mike, let's do this again. Where is AI now? In. In. In Perl. What's the power like now? Because it's, it will definitely become more and more powerful. And, and if. If you add other AI areas around the revenue cycle management and, and other areas of the practice, the more that that integration works, just the overall, the overall processes can be more efficient and helpful for a doctor. So thanks again for joining on the Dental Boardroom podcast.