Cadmore media player playing video Doug Flora with Damian
Video Player
Accessibility
Using forms mode, you can utilize keyboard shortcuts to make usability more efficient.
Space bar will play and pause the video. Pressing escape will close all displays and pressing it again will jump to the end of the player.
You can press A to open the Keyboard Shortcut Dialog which also provides an audio description of the player and all of its features.
Language
1x
Play Speed
Adjust Volume
Transcript
Search
Result Count
of
Click to jump to result
Search
Re-center
Segments
Result Count
of
Click to jump to result
Search
Name:
Doug Flora with Damian
Description:
Doug Flora with Damian
Thumbnail URL:
https://cadmoremediastorage.blob.core.windows.net/436f8eb2-e120-4215-8641-917530c9f2f0/videoscrubberimages/Scrubber_1.jpg?sv=2019-02-02&sr=c&sig=%2FrCpEi3PMSfmOVW6bmmsfYCpFmx%2BWMheVSkVWWzwQ%2BA%3D&st=2024-12-26T22%3A45%3A45Z&se=2024-12-27T02%3A50%3A45Z&sp=r
Duration:
T00H24M04S
Embed URL:
https://stream.cadmore.media/player/436f8eb2-e120-4215-8641-917530c9f2f0
Content URL:
https://cadmoreoriginalmedia.blob.core.windows.net/436f8eb2-e120-4215-8641-917530c9f2f0/Doug Flora with Damian.mp4?sv=2019-02-02&sr=c&sig=jw6y1gjSPRYkKtjrz1FurPgA40RB42oeuDHbcCUVAyM%3D&st=2024-12-26T22%3A45%3A46Z&se=2024-12-27T00%3A50%3A46Z&sp=r
Upload Date:
2023-10-19T00:00:00.0000000
Transcript:
Language: EN.
Segment:0 .
DAMIAN DOHERTY: Hello and welcome to this IPM live. I'm Damian Doherty, your host for the next 30 minutes or so. I'm the editor in chief of Inside Precision Medicine, the world's only bi-monthly industry magazine focused solely on the new sciences and technologies driving this burgeoning precision medicine landscape. I'm delighted to say I'm joined by Dr. Doug Flora, the executive medical director of oncology services at St. Elizabeth Healthcare in Northern Kentucky and the founding editor in chief of AI in Precision Oncology, the pioneering peer-reviewed journal dedicated to advancing the applications of AI in precision oncology to a global community of oncologists.
DAMIAN DOHERTY: Now, this journal will launch early next year. And we'll be diving into that in a little while. But first off, Doug, welcome. And how the devil are you?
DOUG FLORA: Good morning. Good afternoon to you, I think, but good morning here. I'm doing quite well. Thanks for having me.
DAMIAN DOHERTY: Good. No, lovely to have you here. So look, let's dive in. Let's begin, if you will, Doug, by giving us a sense of the mission at St. Elizabeth and the work it is that you're doing for your community in Northern Kentucky, your role there, and maybe a snapshot, if you will, of a typical day, if such a thing, exists, of course, in the life of Doug Flora?
DOUG FLORA: Well, I'm a practicing oncologist, a medical oncologist. So I see patients in our clinic. I have an administrative role for our healthcare system as the chief clinical officer of our cancer programs and help lead a large team of people, over five or six different facilities, trying to take care of cancer patients really at ground zero for cancer in America. So Kentucky is a hotbed.
DOUG FLORA: It's number one in the country for colon cancer, number one for lung cancer, number one for both in deaths, late stage presentations, and whatnot. So we've got our hands full here and a lot of work being done, a lot of good work here at St. Elizabeth.
DAMIAN DOHERTY: OK, great. Now, as far as I can gather, you've been at St. Elizabeth's for, what, just over five years, right? Is that about right?
DOUG FLORA: I've been in practice for almost 20 years this year but in this role, for about five, six years. And--
DAMIAN DOHERTY: OK.
DOUG FLORA: --been with St. Elizabeth since I came out of training, it's been a real treat to work here. It's a very mission-driven place. It's a very kind place.
DAMIAN DOHERTY: OK. And since that new role in the last five years and the work that you're overseeing and maybe since the opening three years ago-- I think it's right-- of your new state-of-the-art cancer center, how has this new cancer center really enabled your ability to scale this new precision oncology approach that you're taking and the quality of care that you're providing to a region that, from what I understand, has a very high incidence of cancers, if not the highest in the US, is that right?
DOUG FLORA: We really do and very, very late stage presentations. And so we've thrown ourselves wholly into screening and prevention. So we have a prevention cancer clinic. We have a heavy emphasis on demonstration, teaching kitchen, and teaching people that food is medicine. We have a very avid precision medicine department, a center for precision medicine, genomic health with about a dozen genetic counselors, two pharmacogenomic pharmacists, and a number of other support staff.
DOUG FLORA: And we've really thrown ourselves into trying to use smart bombs instead of bunker busters. I'm really tired of giving chemotherapy to nice people.
DAMIAN DOHERTY: Right, OK. And I understand that you're a cancer survivor yourself, Doug. And so as a clinician focusing on oncology and being diagnosed with the disease, you're probably acutely aware of the importance of getting an early diagnosis so that we can detect and treat these cancers early and [INAUDIBLE] treat cancers more precisely, which, of course, is where the power of AI joins this narrative. Maybe following on to that.
DAMIAN DOHERTY: Maybe, could you give me a sense of when you had your road to Damascus moment, if you will, with AI's potential? And when did you realize this was something that you had to bring to St. Elizabeth's?
DOUG FLORA: That's a great question. As a clinician, I started to sense maybe a migration in medicine five years ago, six years ago, seven years ago, where it became a bit more transactional. Patients were in a high throughput. There were so many patients and so many time pressures on physicians with documentation and insurance approvals. And we just got away from that doctor-patient relationship that I had practiced with and loved my first 10 years in practice.
DOUG FLORA: And given the vast numbers of cancer patients coming through the wickets and fewer and fewer cancer providers and nurses and staff available, I realized we were going to have to figure something out. And tech is a very reasonable solution to that, to scale some of these kind employees, and take away some of the more mundane tasks from them. And AI is exceptional with that. So I started to lean into that pretty heavily back then, Damian.
DOUG FLORA: And it's only accelerated lately.
DAMIAN DOHERTY: OK. And you were with the like-minded colleagues that felt the same way? Who inspired you? Were the people that you had seen, that you'd seen speak-- or was this something you'd just been keeping an eye on over a period of time?
DOUG FLORA: Well, I'm a tech enthusiast, so I read everything. And I read Eric Topol's book in 2019, Deep Medicine, which I thought was just illuminating for me. And some of the things that he touched on later in the book especially were resonant with me in terms of repairing that doctor-patient relationship and using these tools to allow us to make care more human. And I think as I became more facile in AI, and I learned more about it, and I started to speak around the country on this, I realized that this was a real opportunity for us that we needed to grab quickly and try and get that patient-doctor relationship rebuilt by removing those other stressors that weren't productive for doctors or patients.
DAMIAN DOHERTY: Yeah, yeah. No, it's funny you mentioned Eric. I was literally reading an article he put out-- I think it was yesterday-- in science, talking about moving from this whole unimodal approach to this multimodal framework. Clearly, LLMs, Large Language Models, which maybe might touch upon in a minute, are based on a multimodal approach. But we're going to have to go a lot deeper and a lot wider, I think, to incorporate all those different omics data to get a much more holistic picture of disease risk.
DAMIAN DOHERTY: But the future is certainly mesmerizing. And I remember reading Deep Medicine as well and being-- it was a seminal book. Just thinking, gosh, the-- and of course, read that like you a few years ago before the rise of-- generative AI has come crashing into our worlds recently. But ultimately, the future is mesmerizing. It's going to be incredible to see what these models can do in pulling all that disparate data together.
DAMIAN DOHERTY: That's going to be the key, isn't it, to create that more comprehensive picture.
DOUG FLORA: I read that article last night too. And it's in science. He touched on all those points that were really in this unimodal phase, where it's really good at pattern recognition and reading digital pixelated slides for pathologists or image recognition for CT scans or chest x-rays and the like. But as we get into this next generation well beyond chatbot and into clinical decision-making, I think we're going to see more cures.
DOUG FLORA: I think we're going to find earlier identification and more patient saved, which is-- that's just music to my ears.
DAMIAN DOHERTY: No, absolutely. There's another chap called Tom Laurie that, in fact, interviewed Eric on a recent IPM live that we did. And he's just written a great book-- if you haven't read it-- called Hacking Healthcare. So I'll definitely send you a note on that. But he's just written an article for IPM. And he talks about this velocity of change that generative AI is bringing and the potential impacts it can have on healthcare, both positively and, of course, detrimentally so, this whole issue of amplifying human biases and, of course, the limitations we see in terms of diversity and representation.
DAMIAN DOHERTY: So I think the biggest issue we face-- and I'd love to get your thoughts on this-- is the fact that it's very hard for the clinical policy and regulatory frameworks to keep pace with this exponential change. So we've even had a recent call for a moratorium on AI to slow things down. And there's talk of these large language models being prone to hallucinations.
DAMIAN DOHERTY: So how do you think we're going to be able to keep all these stakeholders aligned and ensure that we're creating robust, unbiased, and safe AI systems?
DOUG FLORA: Yeah, I think that's the sweet spot, isn't it? I will tell you. That was the night is for starting the journal. So for me, as a clinician, I love this stuff. I read it. I'm interested in it. I talk about it. But I've got 59 other doctors in my building, most of whom don't know the difference between deep learning, machine learning, natural language, and processing.
DOUG FLORA: They just don't have time. They're really in the weeds, taking care of patients every day, and doing a fantastic job at it, and overwhelmed. At the same time, industry is hurtling forward, right? Our industry partners are 100% all-in on rapid development, sometimes for commercial gain, sometimes for the greater good. And I don't feel like the two groups are talking. And so what I thought for our journal, for AI in Precision Oncology, to combine those two forces.
DOUG FLORA: And so I've recruited a board of about 25 people on our editorial board right now that are maybe 40% academic heavyweights and 40% industry heavyweights and about 20% that are both. And I'm really enjoying the dialogue between the two as they start to discover unique skill sets and perspectives. And they're starting to blend those. And the articles that are starting to come in the manuscripts are starting to reflect those two teams communicating, which is exciting to me.
DAMIAN DOHERTY: Yeah, that's great. No, I've built a few editorial advisory boards in my time. And it's not a trivial task. I think if you have a great subject matter and you have something that's of the Zeitgeist and people are willing to support that. I think that's half the battle. And of course, you articulate it well, which I'm sure you have. But I think the key is as you say is to get that diversity, that real mix of board members that can bring completely different perspectives from not only different parts of the world but certainly bring that domain expertise.
DAMIAN DOHERTY: So I applaud you because I know it's not easy. But from what I can see, it looks like you've got some fantastic names on the board, which is wonderful. So listen, let's have a quick chat. And we'll circle back to the journal in a minute. I was keen to get a sense of how the procurement for new technology works at St. Elizabeth because I'm assuming that there must be a few tech companies arriving at your door, wanting to sell you transformative AI solutions.
DAMIAN DOHERTY: And I'm really intrigued to know-- how do you how do you pick out the wheat from the chaff? How is that process is done? I'm assuming it's been an evolving, learning process from within. But do you find you're getting bombarded these days? And how do you pass through what you deem to be relevant, what you deem to be necessary? And then really seeing, OK, well, this is a tool that we probably need to look at.
DOUG FLORA: Man, and that's the thing right now. And I'm struggling. And we are a forward-leaning system that cares about this and is looking into it heavily with very, very bright IT teams and very accommodating C-suite and board members that really believe in what we're trying to build at St. Elizabeth from a cancer perspective. We're in the process generation phase, which is, how do you do governance? Who is on that panel that will adjudicate this?
DOUG FLORA: Because you're right, especially since this became very public. And I'm all over LinkedIn sharing stuff about AI. Everybody in the industry is approaching, saying use this as an early adopter. And you just can't buy 200 programs at once. You don't have the IT muscle. We don't have the storage of terabytes of data. We'll blow up the building with the heat that will generate. So we have to adjudicate that carefully.
DOUG FLORA: And I think there's a user case right now for the things that have been validated. So we're looking at things like the natural language processing to remove documentation burdens for doctors.
DAMIAN DOHERTY: OK.
DOUG FLORA: I think there's things that are going on in that world with Microsoft and Nuance and Epic that were just announced last month.
DAMIAN DOHERTY: Mm-hmm.
DOUG FLORA: Lots of pattern recognition. So our radiologists have pushed through a mammography AI augmentation of their reads that's highly accurate and reduces workloads. And so some of those, we're dipping our toe in it, trying to gain experience. I have maybe been almost heretical here in my system. And I hope people aren't getting turned off by it because I keep banging the drum. To use your word, the velocity of change is not what we've seen before.
DOUG FLORA: And I had an email this morning to one of our chief strategic officers likening this to how we had to adapt to COVID. All of a sudden, the world was upended. And you had to build everything new. And we went to virtual health. And we went to quarantine and people working from home. And the whole system had to adapt immediately. I think, 18 months from now, that's where we're going to find ourselves with AI.
DOUG FLORA: I just think these tools are here. They are inevitable in a good way, in an authentic way. And we should be vetting them carefully. But we should view them as a tool that we can use, like a stethoscope or a CT scan, to help the patients.
DAMIAN DOHERTY: Yeah. OK, great. Well, I'm glad you mentioned NLPs there because I think-- I've often thought, they've been around a while. And it seems to be a distinct paucity of institutions that are still using them, certainly over here, this side of the pond. I haven't experienced anyone using it. And it's for me, it's a quick and easy win. To try and alleviate that administrative burden every day, I just see them as a really, really useful tool.
DAMIAN DOHERTY: So I'm really glad to hear that you're looking to implement that. And one assumes you're also probably looking or implementing AI on the digital pathology side as well, I assume.
DOUG FLORA: Yeah, I understand. Our pathology colleagues are digitalizing all our slides this year. And we're not there with the NLP for voice recognition. We do use a product of Nuance that we've used for many years in terms of dictating into our Dictaphones and our iPhones. And that's been NLP as you know from the very beginning. But it's refining now with this advent of generative AI that's really come to the masses.
DOUG FLORA: And so this next round of products is going to be hands-free, obviously. It'll just be able to take these large, unstructured data sets and make sense of them. We're not there yet. But certainly, I'm going to be one of those people who's asking for pilots and trials. And please let oncology have it first. I'd love to do that with my own division because my docs are-- they're ready.
DAMIAN DOHERTY: Yep, sure, sure, yeah, yeah. And look, so another really important part of this AI and precision oncology, precision medicine, is education, right? I think education around the technology fundamentally and, of course, the genomic literacy I think is clearly critical in advancing precision medicine. And let's face it. The vast majority of physicians that practice in the clinic at the moment, they weren't trained on genomics.
DAMIAN DOHERTY: And there's still a huge education gap. Even in residency, there's people clamoring for more information about genetics and genomics and how it works. And they need to be learning more about it. So even at the best of times, it can be rather confounding for physicians knowing what tests to order, which panels to use. Do I do whole genome?
DAMIAN DOHERTY: Do I do exome? How do I interpret variants of unknown significance? How do I even interpret the test reports? So there's still this huge educational piece to the pie. My question to you was-- I'm interested to know how you guys run that side of things in terms of-- have you created your own in-house panel, oncogene panel? Or do you use third party vendors?
DAMIAN DOHERTY: Or is a bit of a mix of the two? And how has that educational side-- how do you approached that at St. Elizabeth? Is it an ongoing developing thing that you're cognizant of it? You're aware that it's an issue. Or do you have an educational program within in terms of when physicians come to work with you?
DAMIAN DOHERTY: There's a training program, if you'd like, in terms of keeping up to date with the masses, as we know, the masses and masses of information that's being churned out every single day. It's hard for physicians to really keep on top of that. It's almost impossible with-- and that's probably why we're getting a lot of physician burnout. So just keen to get that idea of the educational component. And what your perspective on that is.
DOUG FLORA: Yeah, boy, I sure hope they're teaching it to our new med students because it is half of my life as a cancer doc. And the other half might be immunology these days, which we also didn't get heavy training on either.
DAMIAN DOHERTY: No.
DOUG FLORA: We're blessed in our system. So we do have this dedicated center for precision medicine and genomic health led by a very, very bright and dedicated medical oncologist. So Dr. Philips in our system did additional training in cancer genetics at City of Hope, trained at Cleveland Clinic. And she basically brought a lot of knowledge in-house and has been leading our charge. The director of our center is also very, very involved in education and vetting.
DOUG FLORA: And they're good for me, Damian, because, obviously, I'm on roller skates. I'm flying. And I'm on to the next thing. And they're both super adults. And so it's really, really important, I think, for me as an early adopter to listen to these counsels. They're wise counsels.
DOUG FLORA: And say, yeah, maybe what's being promised isn't quite what is there yet. And I might be ready to go on something and pick your product. And they're going to more carefully vet that and educate themselves and then the rest of us about it. So we have molecular tumor boards in the works. And we put on symposia with Markey Cancer Center in Kentucky, where I co-chair a precision medicine symposium each year that our whole team travels to.
DOUG FLORA: And it's a fun collegial thing too. We have genetics [INAUDIBLE] boards on Wednesdays. And that whole precision medicine department, all the GCS, and all the docs get together that are involved in that space. So I think it's a bit iterative because it hit us fast, again, just like this AI stuff has. But I think we're well-poised there. I think that the physicians certainly in oncology are ready.
DOUG FLORA: I think that now we're reaching out. And this precision medicine institute, if you will, is moving into cardiology and moving into full [INAUDIBLE] genomics for psychiatry drugs and opiates in our palliative care clinics. And I hope those doctors have time to get educated because it really will help impact patient care.
DAMIAN DOHERTY: But I suppose that comes back full circle to the reason that you're behind the journal, of course, because you'll have something there even in-house that you can distribute to your own team, which will be phenomenal, really, to have that resource. So let's quickly just step back and look at the journal again because I know we touched upon it. And you've given me a perspective there on the mission statement.
DAMIAN DOHERTY: And you've mentioned the editorial board members. Are there any little sneak previews you can give us? So what are we anticipating? So we've got a launch in January, correct? How are you getting on with most of these submissions here? Is it looking healthy? Anything you can tell us about it or--
DOUG FLORA: We opened for SCHOLAR-1 on, I think, Friday. And we had our first full manuscript of an original article five hours later.
DAMIAN DOHERTY: Oh, wow.
DOUG FLORA: We raced these things through because we were on a tight deadline for this October preview issue.
DAMIAN DOHERTY: Yeah.
DOUG FLORA: There will be some cool things. Obviously, there's going to be some interesting front matter in terms of education. To speak to what you have said, one of our goals is to help these oncologists get caught up. And so one of our managing editors or one of our editors, Scott Penberthy, is a director of applied AI for Google. And he's just going to do instructionals. Front matter each month, let's talk definitions.
DOUG FLORA: What is natural language processing? What is deep learning? What is multimodal, unimodal, all those things? And bring them along for maybe the first six issues. [INAUDIBLE] that everyone has the same chance to educate. And we'll be doing that in multiple rounds of media with multimedia and webinars as well since it is 2023, and we live on our phones. We have a good piece coming in from Lee Hood that we've asked for, some real perspective.
DOUG FLORA: Dr. Hood is, I think, 84 now, probably approaching 85 and has a 50-year perspective on this and has been talking about prevention and screening and personalization of medicine for half of my life. And so that will be an interesting piece. We've joked this. It's kind of an Andy Rooney piece because he's the only one who's been around this long who's seen everything from the very original automated DNA sequencing that he helped design to where we are now.
DOUG FLORA: He owns a company that's really digging into gigantic sets of data to try and introduce these concepts. And then simple, fun stuff. I think for me as a working clinician, I want digestible, easy-to-use tools that make my life easier. So we're going to do-- every month, there'll be front matter on prompt of the month or how to construct a generative AI prompt that helps you do your job, to fight an insurance company's denial, or to write a letter of recommendation for a fellow or a resident that we do all the time.
DOUG FLORA: How can we use these tools to use our voice but accelerate the efficiencies with which we work? And so there'll be a lot of user-friendly stuff in the journal as well.
DAMIAN DOHERTY: No, that's fantastic. Well, I'm very much looking forward to seeing it. As a closing question perhaps, what would you like to see? Or what would you perceive to be a measure of success? So when you look back on the next decade, a decade ahead, what would you like your legacy to be when you hang up your white coat for the last time, Doug? What would you like to say? Well, I've achieved this. And I've done this.
DAMIAN DOHERTY: Anything you'd like to offer on that side?
DOUG FLORA: Insightful question. So I don't know if you're a David Brooks fan. There's a book he's written called The Second Mountain.
DAMIAN DOHERTY: No, you mentioned it before. And I must-- I must read it, yeah.
DOUG FLORA: For listeners, it's a great way to gain context to that question, which is-- you're right. I'm at the point in my career where I've done most of the things that I always dreamed of doing. And now I'm trying to build something that is more impactful. And so I wake up each day. And I think, what levers can I pull that will reduce suffering the most or save the greatest number of patients with screening and detection or education?
DOUG FLORA: And I've realized, at 52, I might save more cancer patients as an administrator building screening programs or as an editor educating clinicians on tools that they could use to take better care of patients or make better clinical decisions. So I guess my goal is 5, 10 years from now that I will have added to the global happiness index because we've reduced the burden of cancer on society. And I think that these tools have a really high potential for doing so.
DOUG FLORA: I'm an eternal optimist. And I think that these things are here to help. I'm not worried about Skynet. I'm not worried about the AI turning on us. We need guide rails. We need really good legislation. And as you've mentioned, I think some of the leaders who understand this technology, most are the ones asking for help-- help rein this technology and before it gets unwieldy.
DOUG FLORA: And I think we're in a critical phase in that too, where we're going to figure this out in the next year or two.
DAMIAN DOHERTY: Yeah, I think I agree with you. I think the media has a responsible part to play. I think all too often it's pitting this sort of man against machine. And it's not helpful, quite frankly. I think we need to continue to espouse the narrative that it's going to augment. And it's going to help. And it's going to be a force for good. We obviously need guide rails.
DAMIAN DOHERTY: You're quite right. And we need to be vigilant. But ultimately, if we approach it the right way with oversight and we get the right people involved, then I think we'll be fine. But Doug, listen, it's been an absolute pleasure. I'm really excited about this new journal. I'm excited to be a fellow colleague. I'm obviously going to do whatever I can to help you in any capacity.
DAMIAN DOHERTY: And I watch you with great interest. And I'm sure it's going to be a huge success and look forward to seeing the preview issue and indeed the first issue in January. And I just wish you good luck with it all. And I appreciate you taking the time to speak to us.
DOUG FLORA: Likewise. Thanks for having me. We're excited to get it going. And good luck to you as well.
DAMIAN DOHERTY: Lovely. Thanks a lot, Doug. Cheers.
Segment:0 .
DAMIAN DOHERTY: Hello and welcome to this IPM live. I'm Damian Doherty, your host for the next 30 minutes or so. I'm the editor in chief of Inside Precision Medicine, the world's only bi-monthly industry magazine focused solely on the new sciences and technologies driving this burgeoning precision medicine landscape. I'm delighted to say I'm joined by Dr. Doug Flora, the executive medical director of oncology services at St. Elizabeth Healthcare in Northern Kentucky and the founding editor in chief of AI in Precision Oncology, the pioneering peer-reviewed journal dedicated to advancing the applications of AI in precision oncology to a global community of oncologists.
DAMIAN DOHERTY: Now, this journal will launch early next year. And we'll be diving into that in a little while. But first off, Doug, welcome. And how the devil are you?
DOUG FLORA: Good morning. Good afternoon to you, I think, but good morning here. I'm doing quite well. Thanks for having me.
DAMIAN DOHERTY: Good. No, lovely to have you here. So look, let's dive in. Let's begin, if you will, Doug, by giving us a sense of the mission at St. Elizabeth and the work it is that you're doing for your community in Northern Kentucky, your role there, and maybe a snapshot, if you will, of a typical day, if such a thing, exists, of course, in the life of Doug Flora?
DOUG FLORA: Well, I'm a practicing oncologist, a medical oncologist. So I see patients in our clinic. I have an administrative role for our healthcare system as the chief clinical officer of our cancer programs and help lead a large team of people, over five or six different facilities, trying to take care of cancer patients really at ground zero for cancer in America. So Kentucky is a hotbed.
DOUG FLORA: It's number one in the country for colon cancer, number one for lung cancer, number one for both in deaths, late stage presentations, and whatnot. So we've got our hands full here and a lot of work being done, a lot of good work here at St. Elizabeth.
DAMIAN DOHERTY: OK, great. Now, as far as I can gather, you've been at St. Elizabeth's for, what, just over five years, right? Is that about right?
DOUG FLORA: I've been in practice for almost 20 years this year but in this role, for about five, six years. And--
DAMIAN DOHERTY: OK.
DOUG FLORA: --been with St. Elizabeth since I came out of training, it's been a real treat to work here. It's a very mission-driven place. It's a very kind place.
DAMIAN DOHERTY: OK. And since that new role in the last five years and the work that you're overseeing and maybe since the opening three years ago-- I think it's right-- of your new state-of-the-art cancer center, how has this new cancer center really enabled your ability to scale this new precision oncology approach that you're taking and the quality of care that you're providing to a region that, from what I understand, has a very high incidence of cancers, if not the highest in the US, is that right?
DOUG FLORA: We really do and very, very late stage presentations. And so we've thrown ourselves wholly into screening and prevention. So we have a prevention cancer clinic. We have a heavy emphasis on demonstration, teaching kitchen, and teaching people that food is medicine. We have a very avid precision medicine department, a center for precision medicine, genomic health with about a dozen genetic counselors, two pharmacogenomic pharmacists, and a number of other support staff.
DOUG FLORA: And we've really thrown ourselves into trying to use smart bombs instead of bunker busters. I'm really tired of giving chemotherapy to nice people.
DAMIAN DOHERTY: Right, OK. And I understand that you're a cancer survivor yourself, Doug. And so as a clinician focusing on oncology and being diagnosed with the disease, you're probably acutely aware of the importance of getting an early diagnosis so that we can detect and treat these cancers early and [INAUDIBLE] treat cancers more precisely, which, of course, is where the power of AI joins this narrative. Maybe following on to that.
DAMIAN DOHERTY: Maybe, could you give me a sense of when you had your road to Damascus moment, if you will, with AI's potential? And when did you realize this was something that you had to bring to St. Elizabeth's?
DOUG FLORA: That's a great question. As a clinician, I started to sense maybe a migration in medicine five years ago, six years ago, seven years ago, where it became a bit more transactional. Patients were in a high throughput. There were so many patients and so many time pressures on physicians with documentation and insurance approvals. And we just got away from that doctor-patient relationship that I had practiced with and loved my first 10 years in practice.
DOUG FLORA: And given the vast numbers of cancer patients coming through the wickets and fewer and fewer cancer providers and nurses and staff available, I realized we were going to have to figure something out. And tech is a very reasonable solution to that, to scale some of these kind employees, and take away some of the more mundane tasks from them. And AI is exceptional with that. So I started to lean into that pretty heavily back then, Damian.
DOUG FLORA: And it's only accelerated lately.
DAMIAN DOHERTY: OK. And you were with the like-minded colleagues that felt the same way? Who inspired you? Were the people that you had seen, that you'd seen speak-- or was this something you'd just been keeping an eye on over a period of time?
DOUG FLORA: Well, I'm a tech enthusiast, so I read everything. And I read Eric Topol's book in 2019, Deep Medicine, which I thought was just illuminating for me. And some of the things that he touched on later in the book especially were resonant with me in terms of repairing that doctor-patient relationship and using these tools to allow us to make care more human. And I think as I became more facile in AI, and I learned more about it, and I started to speak around the country on this, I realized that this was a real opportunity for us that we needed to grab quickly and try and get that patient-doctor relationship rebuilt by removing those other stressors that weren't productive for doctors or patients.
DAMIAN DOHERTY: Yeah, yeah. No, it's funny you mentioned Eric. I was literally reading an article he put out-- I think it was yesterday-- in science, talking about moving from this whole unimodal approach to this multimodal framework. Clearly, LLMs, Large Language Models, which maybe might touch upon in a minute, are based on a multimodal approach. But we're going to have to go a lot deeper and a lot wider, I think, to incorporate all those different omics data to get a much more holistic picture of disease risk.
DAMIAN DOHERTY: But the future is certainly mesmerizing. And I remember reading Deep Medicine as well and being-- it was a seminal book. Just thinking, gosh, the-- and of course, read that like you a few years ago before the rise of-- generative AI has come crashing into our worlds recently. But ultimately, the future is mesmerizing. It's going to be incredible to see what these models can do in pulling all that disparate data together.
DAMIAN DOHERTY: That's going to be the key, isn't it, to create that more comprehensive picture.
DOUG FLORA: I read that article last night too. And it's in science. He touched on all those points that were really in this unimodal phase, where it's really good at pattern recognition and reading digital pixelated slides for pathologists or image recognition for CT scans or chest x-rays and the like. But as we get into this next generation well beyond chatbot and into clinical decision-making, I think we're going to see more cures.
DOUG FLORA: I think we're going to find earlier identification and more patient saved, which is-- that's just music to my ears.
DAMIAN DOHERTY: No, absolutely. There's another chap called Tom Laurie that, in fact, interviewed Eric on a recent IPM live that we did. And he's just written a great book-- if you haven't read it-- called Hacking Healthcare. So I'll definitely send you a note on that. But he's just written an article for IPM. And he talks about this velocity of change that generative AI is bringing and the potential impacts it can have on healthcare, both positively and, of course, detrimentally so, this whole issue of amplifying human biases and, of course, the limitations we see in terms of diversity and representation.
DAMIAN DOHERTY: So I think the biggest issue we face-- and I'd love to get your thoughts on this-- is the fact that it's very hard for the clinical policy and regulatory frameworks to keep pace with this exponential change. So we've even had a recent call for a moratorium on AI to slow things down. And there's talk of these large language models being prone to hallucinations.
DAMIAN DOHERTY: So how do you think we're going to be able to keep all these stakeholders aligned and ensure that we're creating robust, unbiased, and safe AI systems?
DOUG FLORA: Yeah, I think that's the sweet spot, isn't it? I will tell you. That was the night is for starting the journal. So for me, as a clinician, I love this stuff. I read it. I'm interested in it. I talk about it. But I've got 59 other doctors in my building, most of whom don't know the difference between deep learning, machine learning, natural language, and processing.
DOUG FLORA: They just don't have time. They're really in the weeds, taking care of patients every day, and doing a fantastic job at it, and overwhelmed. At the same time, industry is hurtling forward, right? Our industry partners are 100% all-in on rapid development, sometimes for commercial gain, sometimes for the greater good. And I don't feel like the two groups are talking. And so what I thought for our journal, for AI in Precision Oncology, to combine those two forces.
DOUG FLORA: And so I've recruited a board of about 25 people on our editorial board right now that are maybe 40% academic heavyweights and 40% industry heavyweights and about 20% that are both. And I'm really enjoying the dialogue between the two as they start to discover unique skill sets and perspectives. And they're starting to blend those. And the articles that are starting to come in the manuscripts are starting to reflect those two teams communicating, which is exciting to me.
DAMIAN DOHERTY: Yeah, that's great. No, I've built a few editorial advisory boards in my time. And it's not a trivial task. I think if you have a great subject matter and you have something that's of the Zeitgeist and people are willing to support that. I think that's half the battle. And of course, you articulate it well, which I'm sure you have. But I think the key is as you say is to get that diversity, that real mix of board members that can bring completely different perspectives from not only different parts of the world but certainly bring that domain expertise.
DAMIAN DOHERTY: So I applaud you because I know it's not easy. But from what I can see, it looks like you've got some fantastic names on the board, which is wonderful. So listen, let's have a quick chat. And we'll circle back to the journal in a minute. I was keen to get a sense of how the procurement for new technology works at St. Elizabeth because I'm assuming that there must be a few tech companies arriving at your door, wanting to sell you transformative AI solutions.
DAMIAN DOHERTY: And I'm really intrigued to know-- how do you how do you pick out the wheat from the chaff? How is that process is done? I'm assuming it's been an evolving, learning process from within. But do you find you're getting bombarded these days? And how do you pass through what you deem to be relevant, what you deem to be necessary? And then really seeing, OK, well, this is a tool that we probably need to look at.
DOUG FLORA: Man, and that's the thing right now. And I'm struggling. And we are a forward-leaning system that cares about this and is looking into it heavily with very, very bright IT teams and very accommodating C-suite and board members that really believe in what we're trying to build at St. Elizabeth from a cancer perspective. We're in the process generation phase, which is, how do you do governance? Who is on that panel that will adjudicate this?
DOUG FLORA: Because you're right, especially since this became very public. And I'm all over LinkedIn sharing stuff about AI. Everybody in the industry is approaching, saying use this as an early adopter. And you just can't buy 200 programs at once. You don't have the IT muscle. We don't have the storage of terabytes of data. We'll blow up the building with the heat that will generate. So we have to adjudicate that carefully.
DOUG FLORA: And I think there's a user case right now for the things that have been validated. So we're looking at things like the natural language processing to remove documentation burdens for doctors.
DAMIAN DOHERTY: OK.
DOUG FLORA: I think there's things that are going on in that world with Microsoft and Nuance and Epic that were just announced last month.
DAMIAN DOHERTY: Mm-hmm.
DOUG FLORA: Lots of pattern recognition. So our radiologists have pushed through a mammography AI augmentation of their reads that's highly accurate and reduces workloads. And so some of those, we're dipping our toe in it, trying to gain experience. I have maybe been almost heretical here in my system. And I hope people aren't getting turned off by it because I keep banging the drum. To use your word, the velocity of change is not what we've seen before.
DOUG FLORA: And I had an email this morning to one of our chief strategic officers likening this to how we had to adapt to COVID. All of a sudden, the world was upended. And you had to build everything new. And we went to virtual health. And we went to quarantine and people working from home. And the whole system had to adapt immediately. I think, 18 months from now, that's where we're going to find ourselves with AI.
DOUG FLORA: I just think these tools are here. They are inevitable in a good way, in an authentic way. And we should be vetting them carefully. But we should view them as a tool that we can use, like a stethoscope or a CT scan, to help the patients.
DAMIAN DOHERTY: Yeah. OK, great. Well, I'm glad you mentioned NLPs there because I think-- I've often thought, they've been around a while. And it seems to be a distinct paucity of institutions that are still using them, certainly over here, this side of the pond. I haven't experienced anyone using it. And it's for me, it's a quick and easy win. To try and alleviate that administrative burden every day, I just see them as a really, really useful tool.
DAMIAN DOHERTY: So I'm really glad to hear that you're looking to implement that. And one assumes you're also probably looking or implementing AI on the digital pathology side as well, I assume.
DOUG FLORA: Yeah, I understand. Our pathology colleagues are digitalizing all our slides this year. And we're not there with the NLP for voice recognition. We do use a product of Nuance that we've used for many years in terms of dictating into our Dictaphones and our iPhones. And that's been NLP as you know from the very beginning. But it's refining now with this advent of generative AI that's really come to the masses.
DOUG FLORA: And so this next round of products is going to be hands-free, obviously. It'll just be able to take these large, unstructured data sets and make sense of them. We're not there yet. But certainly, I'm going to be one of those people who's asking for pilots and trials. And please let oncology have it first. I'd love to do that with my own division because my docs are-- they're ready.
DAMIAN DOHERTY: Yep, sure, sure, yeah, yeah. And look, so another really important part of this AI and precision oncology, precision medicine, is education, right? I think education around the technology fundamentally and, of course, the genomic literacy I think is clearly critical in advancing precision medicine. And let's face it. The vast majority of physicians that practice in the clinic at the moment, they weren't trained on genomics.
DAMIAN DOHERTY: And there's still a huge education gap. Even in residency, there's people clamoring for more information about genetics and genomics and how it works. And they need to be learning more about it. So even at the best of times, it can be rather confounding for physicians knowing what tests to order, which panels to use. Do I do whole genome?
DAMIAN DOHERTY: Do I do exome? How do I interpret variants of unknown significance? How do I even interpret the test reports? So there's still this huge educational piece to the pie. My question to you was-- I'm interested to know how you guys run that side of things in terms of-- have you created your own in-house panel, oncogene panel? Or do you use third party vendors?
DAMIAN DOHERTY: Or is a bit of a mix of the two? And how has that educational side-- how do you approached that at St. Elizabeth? Is it an ongoing developing thing that you're cognizant of it? You're aware that it's an issue. Or do you have an educational program within in terms of when physicians come to work with you?
DAMIAN DOHERTY: There's a training program, if you'd like, in terms of keeping up to date with the masses, as we know, the masses and masses of information that's being churned out every single day. It's hard for physicians to really keep on top of that. It's almost impossible with-- and that's probably why we're getting a lot of physician burnout. So just keen to get that idea of the educational component. And what your perspective on that is.
DOUG FLORA: Yeah, boy, I sure hope they're teaching it to our new med students because it is half of my life as a cancer doc. And the other half might be immunology these days, which we also didn't get heavy training on either.
DAMIAN DOHERTY: No.
DOUG FLORA: We're blessed in our system. So we do have this dedicated center for precision medicine and genomic health led by a very, very bright and dedicated medical oncologist. So Dr. Philips in our system did additional training in cancer genetics at City of Hope, trained at Cleveland Clinic. And she basically brought a lot of knowledge in-house and has been leading our charge. The director of our center is also very, very involved in education and vetting.
DOUG FLORA: And they're good for me, Damian, because, obviously, I'm on roller skates. I'm flying. And I'm on to the next thing. And they're both super adults. And so it's really, really important, I think, for me as an early adopter to listen to these counsels. They're wise counsels.
DOUG FLORA: And say, yeah, maybe what's being promised isn't quite what is there yet. And I might be ready to go on something and pick your product. And they're going to more carefully vet that and educate themselves and then the rest of us about it. So we have molecular tumor boards in the works. And we put on symposia with Markey Cancer Center in Kentucky, where I co-chair a precision medicine symposium each year that our whole team travels to.
DOUG FLORA: And it's a fun collegial thing too. We have genetics [INAUDIBLE] boards on Wednesdays. And that whole precision medicine department, all the GCS, and all the docs get together that are involved in that space. So I think it's a bit iterative because it hit us fast, again, just like this AI stuff has. But I think we're well-poised there. I think that the physicians certainly in oncology are ready.
DOUG FLORA: I think that now we're reaching out. And this precision medicine institute, if you will, is moving into cardiology and moving into full [INAUDIBLE] genomics for psychiatry drugs and opiates in our palliative care clinics. And I hope those doctors have time to get educated because it really will help impact patient care.
DAMIAN DOHERTY: But I suppose that comes back full circle to the reason that you're behind the journal, of course, because you'll have something there even in-house that you can distribute to your own team, which will be phenomenal, really, to have that resource. So let's quickly just step back and look at the journal again because I know we touched upon it. And you've given me a perspective there on the mission statement.
DAMIAN DOHERTY: And you've mentioned the editorial board members. Are there any little sneak previews you can give us? So what are we anticipating? So we've got a launch in January, correct? How are you getting on with most of these submissions here? Is it looking healthy? Anything you can tell us about it or--
DOUG FLORA: We opened for SCHOLAR-1 on, I think, Friday. And we had our first full manuscript of an original article five hours later.
DAMIAN DOHERTY: Oh, wow.
DOUG FLORA: We raced these things through because we were on a tight deadline for this October preview issue.
DAMIAN DOHERTY: Yeah.
DOUG FLORA: There will be some cool things. Obviously, there's going to be some interesting front matter in terms of education. To speak to what you have said, one of our goals is to help these oncologists get caught up. And so one of our managing editors or one of our editors, Scott Penberthy, is a director of applied AI for Google. And he's just going to do instructionals. Front matter each month, let's talk definitions.
DOUG FLORA: What is natural language processing? What is deep learning? What is multimodal, unimodal, all those things? And bring them along for maybe the first six issues. [INAUDIBLE] that everyone has the same chance to educate. And we'll be doing that in multiple rounds of media with multimedia and webinars as well since it is 2023, and we live on our phones. We have a good piece coming in from Lee Hood that we've asked for, some real perspective.
DOUG FLORA: Dr. Hood is, I think, 84 now, probably approaching 85 and has a 50-year perspective on this and has been talking about prevention and screening and personalization of medicine for half of my life. And so that will be an interesting piece. We've joked this. It's kind of an Andy Rooney piece because he's the only one who's been around this long who's seen everything from the very original automated DNA sequencing that he helped design to where we are now.
DOUG FLORA: He owns a company that's really digging into gigantic sets of data to try and introduce these concepts. And then simple, fun stuff. I think for me as a working clinician, I want digestible, easy-to-use tools that make my life easier. So we're going to do-- every month, there'll be front matter on prompt of the month or how to construct a generative AI prompt that helps you do your job, to fight an insurance company's denial, or to write a letter of recommendation for a fellow or a resident that we do all the time.
DOUG FLORA: How can we use these tools to use our voice but accelerate the efficiencies with which we work? And so there'll be a lot of user-friendly stuff in the journal as well.
DAMIAN DOHERTY: No, that's fantastic. Well, I'm very much looking forward to seeing it. As a closing question perhaps, what would you like to see? Or what would you perceive to be a measure of success? So when you look back on the next decade, a decade ahead, what would you like your legacy to be when you hang up your white coat for the last time, Doug? What would you like to say? Well, I've achieved this. And I've done this.
DAMIAN DOHERTY: Anything you'd like to offer on that side?
DOUG FLORA: Insightful question. So I don't know if you're a David Brooks fan. There's a book he's written called The Second Mountain.
DAMIAN DOHERTY: No, you mentioned it before. And I must-- I must read it, yeah.
DOUG FLORA: For listeners, it's a great way to gain context to that question, which is-- you're right. I'm at the point in my career where I've done most of the things that I always dreamed of doing. And now I'm trying to build something that is more impactful. And so I wake up each day. And I think, what levers can I pull that will reduce suffering the most or save the greatest number of patients with screening and detection or education?
DOUG FLORA: And I've realized, at 52, I might save more cancer patients as an administrator building screening programs or as an editor educating clinicians on tools that they could use to take better care of patients or make better clinical decisions. So I guess my goal is 5, 10 years from now that I will have added to the global happiness index because we've reduced the burden of cancer on society. And I think that these tools have a really high potential for doing so.
DOUG FLORA: I'm an eternal optimist. And I think that these things are here to help. I'm not worried about Skynet. I'm not worried about the AI turning on us. We need guide rails. We need really good legislation. And as you've mentioned, I think some of the leaders who understand this technology, most are the ones asking for help-- help rein this technology and before it gets unwieldy.
DOUG FLORA: And I think we're in a critical phase in that too, where we're going to figure this out in the next year or two.
DAMIAN DOHERTY: Yeah, I think I agree with you. I think the media has a responsible part to play. I think all too often it's pitting this sort of man against machine. And it's not helpful, quite frankly. I think we need to continue to espouse the narrative that it's going to augment. And it's going to help. And it's going to be a force for good. We obviously need guide rails.
DAMIAN DOHERTY: You're quite right. And we need to be vigilant. But ultimately, if we approach it the right way with oversight and we get the right people involved, then I think we'll be fine. But Doug, listen, it's been an absolute pleasure. I'm really excited about this new journal. I'm excited to be a fellow colleague. I'm obviously going to do whatever I can to help you in any capacity.
DAMIAN DOHERTY: And I watch you with great interest. And I'm sure it's going to be a huge success and look forward to seeing the preview issue and indeed the first issue in January. And I just wish you good luck with it all. And I appreciate you taking the time to speak to us.
DOUG FLORA: Likewise. Thanks for having me. We're excited to get it going. And good luck to you as well.
DAMIAN DOHERTY: Lovely. Thanks a lot, Doug. Cheers.
Form Title Download
Transcript
Form Title Bookmark
Entire Media
Segment(s)
Custom Clip
Start At:
End At:
Form Title Share
Entire Media
Segment(s)
Custom Clip
Start At:
End At:
Form Title Accessibility and Keyboard Shortcuts
The cadmore media player is a professional video and audio player experience designed to deliver media as well as relevant transcript, segmentation, and metadata. On the screen is a traditional html video player with buttons such as play, pause, forward, captioning, language and play speed selection and more. Adjacent to the video player are generally tabs, one of which shows a scrolling transcript of the video and the other shows any segmentation of the media, sometimes referred to as chapters. At the top of the video is a menu bar containing an Explore button and Tools button. The Explore button allows you to dig deeper into the video by opening up an explore dialog which contains tabs for a visual navigation of the video using thumbnails, an about tab which contains rich metadata about the media, a segments tab which contains further information about the video, and a related tab which contains links to other media related to this media. The tools button opens a menu with options for sharing the media on social media, creating bookmarking links, creating embed codes for your website, generating citations, and more.
Keyboard Shortcuts
Keyboard shortcuts only work while you are in forms mode. By entering forms mode, you will be able to quickly access portions of the media player with single key commands.
Spacebar: Play/Pause Toggle
I: Info Menu,
O: Tools Menu
T: Transcript Tab,
S: Segments Tab
F: Forward 15,
R: Rewind 15
L: Languages,
P: Playspeed
M: Mute Toggle,
V: Volume Bar
N: Video Only Toggle,
B: Full Screen Toggle
C: Captions Toggle
Escape: Closes dialogs and menus / Exits Player
Z: Next Transcript Chapter
X: Previous Transcript Chapter
Q: Next Transcript Paragraph
W: Previous Transcript Paragraph
Entire Media
Segment(s)
Custom Clip
Start At:
End At:
Embed Size
-
You Size - Responsive
-
We Size - Responsive
-
Picture Overlay Popup
-
400 x 225
-
512 x 288
-
400 x 700
-
768 x 1024
-
1024 x 512
-
1280 x 608
Form Title Cite
No citation provided.
Info
Segments
Related
Thumbnails
Exit Clip Mode
You have requested to see a portion of the video outside of the clip.
Click OK to switch to the full video or click if you would like to stay inside the clip. You can always go back to the clip with Tools and Clip Mode