
Transformation in Trials
A podcast about the transformations in clinical trial. As life science companies are pressured to deliver novel drugs faster, data, processes, applications, roles and change itself is changing. We speak to people in the industry that experience these transformations up close and make sense of how the pressure can become a catalyst for transformation.
Transformation in Trials
How early diagnostics of lung cancer can lead to better survival rates with Chris Wood
Chris Wood discusses how early diagnostics of lung cancer through artificial intelligence and medical imaging can lead to better survival rates through early intervention.
• Lung cancer takes more lives than breast, prostate and colon cancer combined, with approximately 70% of cases caught at late stages
• The National Lung Screening Trial showed that screening high-risk populations reduced mortality by 20%
• I-ELCAP research demonstrated an 80% twenty-year survival rate for early-stage cancers detected with CT scans and treated surgically
• Preventive healthcare is shifting from general advice to personalized screening protocols based on individual risk factors
• AI applications in medical imaging now assist with detection, characterization, and triage of disease
• Lung biopsies have a 22% complication rate, making non-invasive diagnostic methods particularly valuable
• AI-powered imaging can provide additional information to help clinicians decide whether to perform biopsies
• In clinical trials, AI imaging analysis could improve patient selection and help trials reach endpoints more efficiently
• Medical imaging gives patients visual information about their bodies that can motivate healthier lifestyle changes
• The future of healthcare will likely focus on improving quality of life rather than simply extending lifespan
If you have a suggestion for a guest for our show, reach out to Sam Parnell or Ivanna Rosendal on LinkedIn. You can find more episodes on Apple Podcasts, Spotify, Google Podcasts or in any other player.
________
Reach out to Ivanna Rosendal
Join the conversation on our LinkedIn page
Welcome to another episode of Transformation in Trials. I'm your host, ivana Rosendahl. In this podcast, we explore how clinical trials are currently transforming so we can identify trends that can be further accelerated. We want to ensure that no patient has to wait for treatment and we get drugs to them as quickly as possible. Welcome to another episode of Transformation in Trials. Today we're going to focus on the topic of how early diagnostics of lung cancer can lead to better survival rates, and today in the studio with me I have Chris Wood. Chris, would you mind introducing yourself to my audience?
Speaker 2:Sure, I'm a medical physicist by training, but I've been working in the medical imaging industry for about 35 years, and my current company is using artificial intelligence to help accelerate, hopefully, the diagnosis of lung cancer.
Speaker 1:That is awesome, chris, and I'm very excited to be talking to you today, maybe just setting the stage for our audience. What is the state of lung cancer treatment today?
Speaker 2:Yeah, unfortunately, lung cancer is quite often caught at later stages.
Speaker 2:I think the number is about 70% of the time In the United States anyway, it's caught at the late stage and a late stage diagnosis of lung cancer has a very, very poor prognosis of lung cancer has a very, very poor prognosis.
Speaker 2:Early stage lung cancer is asymptomatic, which is why quite often these patients are silently fighting lung cancer and you don't know it until they're at advanced stages. So the treatment unfortunately is not accelerating. But we are finding some success by accelerating the diagnosis and downstaging patients. So we're finding more patients at an early stage. We're starting to see survival take up in the broader population. And this all started with the results out of the National Lung Screening Trial, which were about 2012, which showed that you could reduce mortality in high-risk populations by 20% by screening for lung cancer, catching it at the early stage, intervening surgically, and there's been decades of research after that that have really sort of backed up that hypothesis. So now we know that if we can get more people screened, we know who these people are, we know who is at high risk generally, and if we can get more people screened, we can make an impact on this disease.
Speaker 1:That sounds hopeful for a cancer. That is a very serious one, and you actually told me during our pre-call that this is one of the cancers that kill most people out there, to my surprise.
Speaker 2:Right Colon cancer takes more lives than breast, prostate and colon cancer combined every year, and partly because the diagnosis is typically late and partly because it's just a really difficult disease to treat. So early intervention is really what you need and, like I said, since the National Long Screening Trial data came out, a group called IL-CAB has been tracking patients for decades and two years ago they published some remarkable data that if you act on these early stage cancers surgically, the 20 year survival rate for these early stage cancers that are detected with CT scans is 80%. So they started using words like cure to describe this treatment. So we have this extremely sensitive test CT scanning that can find these early stage cancers, and we know if you act on those cancers when they're caught early, you can essentially cure the disease. So that's exciting for those of us who are coming at this problem from this early diagnosis angle. Of course, you know, if somebody invented some sort of miracle cure drug that could actually just cure lung cancer, we'd all be thrilled.
Speaker 1:But right now, it appears as if the best tool we have for combating this disease is detecting it early and acting on it surgically. So, chris, we're kind of touching upon the area of preventive health care, right, and if you were to try to explain what this means to someone who is still in high school, a 17-year-old person?
Speaker 2:what is preventive health care? Well, you know, I think people have gotten a lot of conflicting information over the years about how to make themselves healthy right. Lots of epidemiology-based studies where they're looking at the impact of sugar or fat or some other variant in your diet and you know, one year they'll tell you one thing and one year they'll tell you another. But I think, as this field has progressed, we're starting to tease out the things that really matter, and one of the things that I think all people should be aware of is whether or not they're at high risk for certain conditions. Obviously, with lung cancer, we know that smokers are at high risk for getting lung cancer much, much higher risk than the general population. But we're also starting to see that there could be genetic markers Women who have the BRCA gene, for example. They need different screening protocols Depending on your upbringing, depending on your diet, depending on lots of different factors. What might be indicated either now or in the future right is a different type of screening regimen for you, because if we can find out what you're at high risk of developing, we can catch it early and intervene early.
Speaker 2:So preventive medicine is sort of morphing from this sort of global, you know sort of approach where you say everyone should do this one thing to live longer, everyone should do this one thing to live longer, to more of this personalized approach where you know, you find out what you're specifically at high risk for. And imaging plays a big part in that because you know those folks who are at high risk. The way to determine oftentimes you know whether or not they have a condition and they're still asymptomatic is through imaging. As it is with lung cancer. Right, I would expect that we were going to get more and more groups identified as high risk, perhaps even folks who live in Seattle like me, because you know we have a lot of wildfires out here that for the last few summers have been turning the sky orange, and you know we may find that that is introducing enough risk into these populations where those folks who are exposed to those wildfires should get screened for lung cancer as well.
Speaker 1:So I think that's some passive smoking there.
Speaker 2:I don't know if a 17 year old would get all that, but I think I think that's, in general where it's going is that we're trying to figure out what people's risk factors are and what is the best intervention to take, and that can lead to some prevention, at least prevention of advanced stage disease.
Speaker 1:That is interesting. I think thinking about risk for people who are not necessarily statisticians does require a mindset of understanding. Well, this is something you need to deal with now so that you avoid bigger problems later, and that is a hard thing to do than necessarily getting a diagnosis. You have this right now getting a diagnosis.
Speaker 2:you have this right now, right? The extremes are usually the worst approach, right? So doing nothing is usually a bad approach. And also sort of going in and getting your whole body scanned. You know MRI every year also a bad idea, right? Because you know you're going to end up spending most of your time and money dealing with incidental findings. That may or may not matter, but, like I said, as genetic profiling or testing becomes more sophisticated, we're going to know what you're at risk for and we're going to be able to take reasonable steps to try to detect those conditions when they pop up.
Speaker 1:Very cool. Detect those, those conditions when they pop up very cool. So if we get into some of the specifics, how do we recognize a lung cancer using ai, based on scans?
Speaker 2:yeah, I think that, um, you know, like a lot of medicine, some of the breakthroughs that are made in other areas of science, they get applied to us, right. So you know, it wasn't fundamental research that really kind of led medical imaging down this path. It was actually in 2012 when Jeffrey Hinton's group you know the guy who just won the Nobel Prize, His group created this classifier called Supervision, which made this quantum leap in object recognition by employing deep learning to that task humans. There's been several billion dollars, maybe a few billion dollars, invested into medical imaging companies that are trying to apply this sort of deep learning, object recognition, computer vision technology to medical imaging and the original thought was, oh, we're just going to replace radiologists. A lot of venture capitalists thought that was what's going to happen. But the field has matured and evolved and now you find that there are quite a few applications that help detect disease. There are only a handful that help characterize disease. Those are called CAD-X. Cad-e is the detection. X CAD E is the detection. There are a few applications in medical imaging that are called CAD T, which triage and essentially put certain exams on the top of a radiologist's work list because they might have an emergent condition right, Some sort of emergency action needs to be taken with this patient and that's been detected by AI. So you want to have a radiologist look at that first.
Speaker 2:But the original thought was to apply some of these deep learning techniques just the way you apply them to any other vision task, and that didn't quite work out. Medical imaging has to be very reproducible, Um. It has to be reliable, uh. And false positives mean a different thing for us than they do for somebody, kind of detecting cats in a video, Um. So we tend to now in medical imaging use a curated somewhat curated list of features as opposed to letting the AI figure out what it's going to look for.
Speaker 2:And we've started to kind of migrate more sort of away from detection which is what you see in computer vision, a lot towards more characterization, because we can add a lot more value if we can help the radiologists do a better job than they normally would Not just a faster job, but a better job. So in a way we're still kind of at the early stages, to be honest, of how medical imaging is going to impact radiology. We have some promising results. We've got some really cool core technologies that we can leverage. Medical imaging is going to impact radiology. We have some promising results.
Speaker 1:We've got some really cool core technologies that we can leverage, but the story is not completely written yet on how AI is going to impact medical imaging. It's exciting to be in the forefront of that story. Everything, chris, this is kind of what we're trying to do today recognize some of the early symptoms using AI. The traditional way is with biopsies, so why can't we just take biopsies of everyone's lungs?
Speaker 2:Yeah, if only it were that easy. The lung, as I'm sure you know, is a special place to biopsy, right, and the complication rate for intervention into the lung is 22%, so it's quite high. You can do needle biopsies and get lower numbers for certain things that you want to biopsy in the lung, depending on where it is. Numbers for certain things that you want to biopsy in the lung, depending on where it is. There's bronchoscopy, there's robotic bronchoscopy now, which is a newer type of intervention, and, of course, thoracic surgery, right. But if you have a patient, you know who's coming in for a lung biopsy. They probably have, maybe not probably, but frequently will have comorbidities like emphysema and other conditions, and they may end up getting something like a collapsed lung, which could cause them to be admitted to the hospital. And you know you're talking about five to $10,000 for some of these complications that occur, as well as difficulty for the patient, right. So you don't want to biopsy more than you have to in the lung, but you're also faced with this wildly aggressive disease where, if you don't catch it early, the patient's prognosis is extremely poor.
Speaker 2:So we're trying to provide as much information as we possibly can. We're not trying to replace biopsies. Maybe 20 years down the road we'll be able to do that, maybe with a combination of radiomics, which is what we're doing, looking at CT scans combined with, maybe, blood-based biomarkers or something like that. But right now we're just trying to provide more information to help clinicians reasonably decide what the best care is for the patient right in front of them. Any piece of information they get is going to be helpful for them, because these are really difficult decisions. Do you send the patient in who's 78 and maybe has comorbidities and it's going to be a hard nodule to get? Do we do the biopsy today or do we wait six months? That is an incredibly complicated clinical decision and if we can just shine a little bit more light on, you know, some of those features of that nodule that would help them make the best decision for the patient, then we've done our job.
Speaker 1:So potentially just narrowing down how many patients may need a biopsy or pointing out, like where this biopsy should be targeted, it would already be helpful to make that clinical decision a little bit easier.
Speaker 2:Yeah, right now, basically what happens is that nodules are kind of identified and tracked and after they get to a certain size at least at a lot of institutions, once they get to a certain size then they're sent to a tumor board or a nodule clinic and the team of physicians decide what to do. And a lot of it is just very subjective and we're trying to provide a little piece of objective information for them and that might cause them to send maybe some additional nodules that they might not normally send to tumor board, and at that tumor board they have this additional information. So it might impact what they do. You know, I think, like I said, that we've got clinical studies that are out there that show that we can have this positive impact.
Speaker 2:But the specific way that these physicians use our information that we provide is probably going to vary from institution to institution, depending on their needs, their patient population, what their goals are as an institution.
Speaker 2:Maybe they're trying to pursue earlier diagnosis, maybe they're finding that in their practice they're catching too many cancers at the later stage and they really want to do something to help the community to catch them at an earlier stage. They might use our technology and our information differently than another group who's finding a lot of early cancers. But maybe they're, you know, maybe they're doing surgery on patients who are benign nodules more frequently than they would like, right, so how they use our information is kind of up to them. Our job as a vendor is to provide information to them about what the information is right, an explanation of what the information is, and kind of consult with them on how they might want to use that information. And as our studies, as more and more studies come out on the use of this type of radiomic features, you know, over the long term that'll have an impact on patient care you know, over the long term that'll have an impact on patient care.
Speaker 1:So if we look at how this may be applicable when it comes to clinical trials, it's a different situation. Right, we're not necessarily treating yet. Are there any other ways that this form of diagnostic could be helpful when trying to understand some of these cancers better?
Speaker 2:Well, I think you know, certainly, one of the things I've heard from folks who are trying to perform clinical trials for early detection of lung cancer, maybe blood-based detection. These trials can involve thousands and thousands of patients, right, and one of the things that we may be able to do to impact these trials is help with patient selection. Right, you know, we can go in and perform CT scans on these patients. We can see whether or not they have nodules. We can then characterize the features of those nodules and ultimately that might help the clinical trial get to an endpoint more efficiently if we can create a subset of patients that would be useful for that particular trial.
Speaker 2:There's other things that quantitative analysis can do in clinical trials. Quantitative analysis of medical imaging right, we can track the volume of things by scanning patients, maybe more reasonable than a lot of clinical trials take, where they just use the old WHO or resist criteria to try to figure out how big something is. Nowadays, medical imaging workstations all have the ability to measure volumes pretty much. So there are things you can do quantitatively looking at texture, looking at volumes, counting pixels, you know, to find these secondary endpoints perhaps, but in terms of our specific technology we would probably be more upstream.
Speaker 1:Yeah.
Speaker 2:Until we get to the point where we're doing clinical trials that involve both the imaging markers that we're finding and other markers that are found in the blood.
Speaker 1:That would be interesting.
Speaker 2:Yeah, I think ultimately people think that's where this is going to go. Probably it'll go there, even if vendors don't do it right. They'll take our product, they'll figure out how to make our product work with other products that are out there that are looking at blood tests, and they'll figure out how to combine the two pieces of information that are provided. Maybe there's an opportunity in the future for a company to create a combined solution. Right now it's more of a research topic than anything else.
Speaker 1:Yeah, that makes sense when it comes to discovering some of these diseases early on. There is also, I guess, a societal question here. Do we invest enough in our healthcare models to find these issues before they actually arise, or could we potentially reroute some of our treatment funding to actually earlier diagnosis? I would be curious to hear your thoughts on this.
Speaker 2:Yeah, I think that that's certainly a trend. Most of the studies that you see say that if you can catch diseases early certainly lung cancer the cost is going to be greatly reduced. Just since we've rolled out lung cancer screening in the United States, we've saved quite a bit of money from downstream elimination of downstream treatment, right. Whether or not it makes sense for everything is a tough question. It's more on a case-by-case basis, right, whether or not you want to screen for a specific condition. If you've got a really good treatment for that condition, maybe you don't necessarily need to catch it earlier. From a financial standpoint, maybe from other perspectives it does make sense. But, like I said, I do think that in the future you're going to go more to a screening clinic and you're going to get a screening protocol that's designed for you.
Speaker 2:Right now, everybody gets a colonoscopy at a certain age. You get lung cancer screening. If you were a smoker, you look at genetic markers and you see whether or not you need a specific sort of bespoke design breast cancer screening protocol. You want to incorporate MRI or you want to incorporate ultrasound into your screening protocol. These things are getting more and more personalized. So I this is a sort of a guess on my part, but I do think that, ultimately, your general, your primary care physician, is going to work with you to figure out what your screening protocol is based on your markers and your needs, and then you're going to probably go to a screening clinic and get all those things done, maybe in a single day, which would be great, right?
Speaker 1:That would be amazing. But also it's a shift for the individual and us as a society to think more about well. How can we figure out the general advice for the individual, rather us as a society to think more about? Well, how can we figure out the general advice for the individual rather than, as you mentioned in the beginning, like these, general advice for how do you live healthy as people in general, but more like which risks do you have and what sort of care do you need to take?
Speaker 2:Yeah, I mean, I personally got you know when I was 50, I went and got a coronary CTA right and it it was impactful for me because I changed my diet pretty dramatically after that. Um, because I found out that I was even though I exercise a lot, I was kind of at the same stage as the average average American when it comes to my coronaries and I thought, oh my goodness, that's terrible. Like the average American is, you know, probably going to die from heart disease. So, yeah, so it can be impactful that way too is that if you're doing this imaging and you're screening somebody, you can also get these other markers which might impact specific lifestyle changes that they can make. And a lot of times when people see things in a medical image, it is much more impactful than some sort of blood test where, oh, maybe it was elevated today or you don't necessarily believe it, but when you can see something with your own eyes, I think it can impact patient behavior pretty profoundly.
Speaker 1:I recently had an ultrasound of my own heart. Everything was fine, but still it was indeed a very impactful experience, just like seeing what is happening on the inside on a screen. Somehow it caught me by surprise how profound an experience that actually was.
Speaker 2:Yeah, and I think in some ways it kind of gives you an appreciation of your own body, what it's, yeah, what it's doing. I think we kind of take it for granted, right. But, um, when you see your arteries and veins and you see your heart pumping and you see all these functions happening inside your body, you maybe you think a little bit more about how I could take care of those functions.
Speaker 1:Yeah, it suddenly seems very fragile, somehow like whoa, this thing is actually operating inside of me. Okay, Well, Chris, I would be curious to learn more about. How did you get into this space in the first place?
Speaker 2:Well, I studied physics in college and then I had two ways I could get funded for graduate school. One was Department of Defense funding. We were essentially building lasers to do guidance systems for missiles, and the other one was medical imaging. And you know, I chose medical imaging because I thought that it was a little bit better to try to help people than to blow them up. That was about the extent of my you know, 22 year old brain thought process. And then, similar to the conversation we just had when I started, I started working at Moffitt Cancer Center in Tampa and some of the first images I saw that popped up on the screen. I was just completely amazed, like we, we were working with magnetic resonance imaging and, yeah, I just thought it was the coolest thing I'd ever seen. So I've been.
Speaker 2:Then I transitioned to work in industry. I didn't ever practice as a medical physicist in a hospital or anything like that, I just went right into industry and I happened to come in at a time when we were replacing film with computer monitors, so the entire software sort of explosion in radiology was happening right around the time I entered or shortly after the time I entered industry. So I was able to always find a job because there's been a ton of software that's needed to be written and with that disruption in radiology, there were a lot of opportunities to make things better. Honestly, I thought when I started we would be a little further along now than now. There are still people using really old-fashioned techniques to assess disease. Mostly, radiology is completely just a visual art.
Speaker 2:Radiologists Art radiologists are extremely good at what they do, but this sort of influx of quantitative tools and analysis didn't really happen the way I thought it was going to happen. But now, with deep learning, I think we have an opportunity to kind of bring it to the next level, maybe, and surpass human performance on a couple of these key tasks. That'll add value to the radiology report. Ultimately and that's what radiologists need in order to thrive in a value-based world, right Is their report needs to be as valuable as possible. So if we can use artificial intelligence and some of these other tools to help them create more value, that's impactful downstream, that impacts how much money essentially medical imaging is worth, and that'll be good for the whole field. I don't think any radiologists are worried about losing their jobs anymore because it's just not going to happen. No, but it is important for them to continuously try to increase the value that their reports create, and AI has got the potential to do that.
Speaker 1:That does seem to be kind of the general trajectory of AI. It's not necessarily about replacing work. The way that I see it, it's more about, for example, when it comes to imaging. We can have more imaging now, so we can apply it in different ways, because potentially we can just use the scarce time of radiologists better.
Speaker 2:Yeah, we've had similar things happen, like pap smears, for example. Only, I think, 20-30% I may be wrong here, but a relatively small percentage of those are looked at by human. There's AI-based tools that essentially just triage those things and then the ones that are questionable are sort of sent up to a pathologist to look at, so similar models might pop up in radiology. There are a lot of barriers to that right now, including malpractice insurance and including just general insurance. If you get paid a professional fee of $55 to look at a chest CT by Medicare, who gets paid if it's read by AI? Or does anybody?
Speaker 1:Right, that's a good question yeah.
Speaker 2:There's lots of sort of tactical things that need to be worked out, as well as some technology that needs to advance.
Speaker 2:But I think people see that there's a potential that down the road we could look at some of these things and some of these exams and we could say, look, you know, especially in a screening world, maybe some of these we can triage out and not even have anyone look at them. It would be a big disruption but it's like a self-driving car. As soon as you're as good as the average driver, you can replace some of those tasks right. As soon as you're as good as the average radiologist at looking at a relatively simple exam, maybe you can automate reading some of those relatively simple exams. That's down the road. You can automate reading some of those relatively simple exams, that's down the road. But I don't think I've ever met a radiologist who would be upset if I reduced the number of chest X-rays they needed to look at every day, right, they're usually trying to avoid those. So you know, I think if we could say, look, you're only going to look at the hard ones, they'd all be happy with that.
Speaker 1:Yeah, then they can also spend more time on the ones that really matter.
Speaker 2:Yeah, and some of the 3D you know MR and CT are harder to read. Those you know 3D data sets, not the projection data sets. There's a lot of time and effort associated with that. A chest CT, for example, can take, you know, 12 minutes to read. A chest CT, for example, can take 12 minutes to read and so, as a radiologist, if you could start maybe getting some time back from the AI, you could spend a little bit more time on some of these things and also have fewer interruptions. Radiologists right now are really hyper subspecialized, so this kind of enables that to a certain degree, because some of these easier exams in a rad practice, sometimes they share the burden of reading them and you can become more, you can work more in your subspecialty if you have AI taking some of those tasks off your plate, and I think radiologists would generally like that. The quality of a subspecialist is higher, they read faster and they like to read within their subspecialty.
Speaker 1:I actually did not know that they were hyper-specialized within an area.
Speaker 2:Well, they are, because radiology groups have gotten very, very big. As a consequence of switching to digital, you don't need to physically be in a location anymore to read an exam. You used to have to be in the basement of a hospital and you'd read everything that came out of the scanners regardless, and all sorts of types of diseases came out of the scanners regardless, and and all sorts of types of diseases. And now everything's digital. So you can have a 800 person radiology group and you can have people who specialize in a specific type of exam and they can read all of those all day. Um. But some of the exams that are um exams that maybe no one wants to read, maybe, maybe we can automate some of those, like I said, down the road, so that 50% of them they won't need to look at. But we've got a lot of tactical things to work out around that for that type of change to take place.
Speaker 1:Did that make sense? Well, chris, as we start rounding off our conversation, I always ask my guests the same thing towards the end. Okay, and that is, if I gave you the transformation trials magic wand that has the ability to change one thing in the life sciences industry, what would you wish to change?
Speaker 2:In life sciences in general. Yes, that's a big, big question. Oh, that's a big, big question. But I think the theme that we've been talking about is more emphasis on prevention of disease, and I think I would probably fall into that camp of detecting disease early and how you can treat patients easily, cheaply, more effectively with these early detections. And I think if I were to wave a magic wand, it would be specialized screening based on individual needs, followed by early detection of all sorts of diseases, and also reducing the burden on radiologists and having them add more value through artificial intelligence. I don't know how far we're going to get with that, but we're doing our little part here at RevealDx to try to move that ball a little further in that direction.
Speaker 1:I think that's a great wish and I hope that that is the way that we're going, not just with your push, but generally the industry as a whole moving in that direction.
Speaker 2:Yeah, yeah, I think, and, like I said, I think imaging can play a part in this, because we can have this impact on patients by showing them what's going on in their body. Because we can have this impact on patients by showing them what's going on in their body, we can convince them to take those steps necessary to live healthier lives and get you know more of their years to be quality years. That's one of the things I think is a good trend is people are emphasizing more years of quality life as opposed to just extending lives has been kind of maybe the focus for for a little too long. Um, now we're switching more to our towards a better goal, I think yeah, yeah, I, I agree.
Speaker 1:Um well, chris, if my listeners want to learn more about you or your company, where can they find you?
Speaker 2:um, we're mostly active on LinkedIn. They can go to revealeddxcom there's a dash in the URL there revealed-dxcom. But following us on LinkedIn is probably the best choice and certainly anybody wants to connect with me, that's where they can find me.
Speaker 1:Excellent. I'll make sure to include that in the show notes too. Thanks, ivana. People can click a link. Well, chris, it's been a pleasure to have you today. I've learned new things about radiology. Great, I appreciate that a lot.
Speaker 2:All right, it's fun to be on. Thank you.
Speaker 1:You're listening to Transformation in Trials. If you have a suggestion for a guest for our show, reach out to Sam Parnell or Ivana Rosendahl on LinkedIn. You can find more episodes on Apple Podcasts, spotify, google Podcasts or in any other player. Remember to subscribe and get the episodes hot off the editor.