AI Is Reading 15 Million X-Rays a Year With No Human in the Loop | Prashant Warier, Qure.ai

Eighty percent of lung cancer cases are diagnosed too late, not because the signals aren't there, but because nobody was looking at the right moment. Prashant Warier, co-founder and CEO of Qure.ai, joins Craig Smith to explain how his company is changing that using a tool most people already encounter: the routine chest X-ray. Cure's Lung Nodule Malignancy Risk Score - validated in the CREATE study - analyzes X-rays people get for unrelated reasons, identifies high-risk nodules, and flags which patients need follow-up CT scans. The result is a detection rate of 54 positive patients out of 100 flagged as high-risk, compared to the 2 out of 100 found by standard CT screening programs. That's not a marginal improvement. That's a different category of outcome. The conversation covers the full landscape of where AI diagnostics actually stands today: the 15 million TB screening X-rays that Cure reads autonomously every year across 70 countries with no radiologist in the loop, because in many of those countries there are only two radiologists for the entire nation; the 26 FDA clearances and 200-plus published studies that underpin the company's clinical credibility; and the regulatory barriers that currently prevent patients from uploading their own scans and getting an AI read directly. Warier also makes his sharpest prediction: within 5 to 10 years, primary care will be AI-first, the first conversation you have when something feels wrong won't be with a doctor, it will be with an AI. Based on what Cure is already doing at scale today, that timeline is harder to dismiss than it might sound. Subscribe to Eye on A. I. for weekly conversations with the people building and deploying the future of AI.

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Craig S. Smith?

  Is the doctor's office of the future going to be a bunch of these systems? And the doctor kind of guides you? The AI gives the doctor a cheat sheet on what he should pay attention to. You go in and get a body scan. The doctor gets a report on what he should pay attention to. Is healthcare moving in that direction?

• 0:21Speaker 01

  My personal belief is that primary care will be AI in the future. Maybe five to 10 years from now. We have to be more proactive about diagnostics and we'll see algorithms play a role in that. I think that's where definitely the world is headed where diagnostics will happen much earlier through the amount of data that we are generating. And AI has a big role to play in that journey.

• 0:41Craig S. Smith?

  So let's start with with you introducing yourself to listeners.

• 0:46Speaker 01

  Hi, my name is Prashant Warrior. I'm the co-founder and CEO of Cure. I've been building AI algorithms for the last 25 years. I did a bachelor's in technology out of in engineering out of India from one of the IITs, IIT Delhi. And went to the US at Georgia Tech, did a PhD in operations research. My PhD was optimizing trucking networks for for the for US trucking organizations. And spent, I mean, did that, went on to work for SAP where I was basically doing price optimization for retail, so price optimization, markdown optimization,

• 1:28Speaker 01

  demand forecasting, a bunch of retail and consumer products problems. This was all in the US. I came back to India about 14 years ago and set up an advertising technology startup, which was using AI to to basically collect consumer behavior from a lot of e-commerce sites in India. And then use that to target the right ads for customers. And then that got an exit for that about 10 years ago. And started Cure slightly less than 10 years ago, focused on AI in the healthcare space. And yeah, we'll talk about the Cure journey today.

• 2:07Craig S. Smith?

  Yeah. And and so talk about what Q R I was founded to do and how it has evolved.

• 2:17Speaker 01

  So we, when we started, our hypothesis was that that image recognition algorithms, I mean, this, there is Alex Net, but that was one of these neural convolution neural networks that was released in twenty twelve, right? And our hypothesis was that can we sort of take some of those techniques, apply it to a lot of radiology images, billions of them? And would that enable us to then identify abnormalities on a X-ray or a C T scan? And that was the hypothesis when we started. And of course, I mean, we we did that, spent a lot of time collecting data because getting access to anonymized, we identified customer data, patient data is not easy.

• 2:59Speaker 01

  And so spent almost the first year just working with hospital systems, especially we started out of India. So working with hospital systems in India. Getting the identified patient data, basically radiology images and the corresponding reports. And created a large database, more than a billion and a half images now. And that went into training these algorithms. And the, what we sort of focused on initially was detecting abnormalities on chest X-rays. Now, chest X-ray is the most common imaging modality, more than one point three billion chest X-rays taken around the world. We focused on head C T scans. Head C T scans are one of those scans which require the fastest interpretation because you're looking for bleeds or stroke.

• 3:41Speaker 01

  And you want to be able to treat the patient quickly. So speed is important. So high volume tasks. We looked at things where real time processing is required. And then sort of went on from there, built out solution portfolios for musculoskeletal X-rays, chest C Ts. And a lot more. I mean, over the years, we evolved into an early detection company. So we went beyond just radiology imaging. We said, radiology imaging or detecting abnormalities on a radiology image is not enough. You have to actually be participate in the end to end diagnostic process from the time a patient comes. To all the way to the time they get diagnosed with the disease, how can you infuse AI into that patient journey at multiple steps?

• 4:25Speaker 01

  And so we have now AI which runs on EMR data, which runs on the imaging, AI imaging, medical imaging, radiology imaging data. We have follow-up management tools which ensure that patients are followed up for the for the next test. So multiple tools that that bring together the patient's diagnostic journey and help patients get diagnosed earlier, detected earlier with conditions like tuberculosis, lung cancer, heart failure, COPD and so on.

• 4:56Craig S. Smith?

  Yeah, and you're the the customer for this are healthcare systems, is that right? Not it's not a cus- a consumer-based product.

• 5:08Speaker 01

  It is not a consumer-based product. So one of the things that we are very careful about is that everything that we build and sell is a software, we only sell AI software, but it gets it gets classified as a software as a medical device. So it's a medical device and when you deploy it at a hospital, anywhere in the world, you have to go through a regulatory clearance. It's an FDA clearance in the US, you have to go through CE marking in Europe and every other country has those clearances. And second thing I think is that these devices sort of are, I mean, you have to show evidence of the efficacy of these devices as well. So you have to publish research around this. So we have been very focused on that.

• 5:47Speaker 01

  So we have today more than two hundred plus publications at Cure and we have twenty-six FDA clearances. We have sixty-five findings that are cleared in Europe and we are actually cleared for use in more than hundred and five countries. So it's it's a scaled quite broadly across the world as well. So that's sort of our focus has always been on making sure that we sort of we we get those clearances. And this the product that we deliver is used by a physician in making the right decisions. So it's a decision support tool and at no place are we directly diagnosing something for a patient. And one place we do, I'll talk about that, there is one place where we are autonomous and and I can talk about that in a bit.

• 6:31Craig S. Smith?

  Yeah, and and the the the AI under the hood has evolved from supervised learning to to integrating generative AI or or language models. Can you talk about how the the underlying AI has evolved?

• 6:57Speaker 01

  So our underlying AI stack, I mean, so we integrate language models, vision models. So we have a combined vision plus language model and that's trained on, I mean, reports that we have. First, we have images, radiology images in the corresponding reports. But also we have, I mean, for a large number of scans, we have annotations where a radiologist has gone in and marked out where the abnormality lies. So a lot of it is supervised, there is some unsupervised part, but it's a mix of both of those that goes into the vision language model, which is then what we use for, which is then what we fine tune for specific use cases. We will we'll fine tune that for detecting pulmonary arterial hypertension, for example,

• 7:38Speaker 01

  or COPD, or a bunch of other conditions, lung cancer, lung nodule malignancy risk, and a bunch of other conditions.

• 7:47Craig S. Smith?

  Yeah, and you were saying this is high volume. Can you talk about the throughput? And and so what happens? A doctor takes an X-ray and then it's uploaded to the system. Can just walk through the workflow from the doctor's point of view?

• 8:08Speaker 01

  So what happens is patient comes in, takes an X-ray, X-ray is automatically uploaded to our system, right? Our patient comes in, takes a CT, CT is uploaded to our system. We process it immediately. It takes anywhere from a few seconds to maybe a minute to process those scans. And the results are then available as a small widget on the radiologist's workflow. So as a radiologist reading a scan, there will be a small queue at the bottom of the screen where they can see the results of what. Cure has, um, uh, cure has processed for that particular scan, what the abnormalities that cure has identified. They can click on that and they can go into further details. It will show you the nodules that we have picked up.

• 8:53Speaker 01

  You can go into details of those nodules. You can, um, see compared to previous scans, there is a previous CT scan. You can compare to that. So it then it gets into that workflow from the radiologist's workstation. So this is one part, right? Now, what we also allow them to do is that they can add this patient into a lung nodule workup program. So basically, if they suspect that this patient could have a lung cancer risk, which is something that we can provide. They can now add this patient to a lung nodule follow-up program, typically called an IPN, incidental pulmonary nodule program, uh, which many US health systems have. And so in that program, what they do is they'd actually call this patient back in for a CT.

• 9:34Speaker 01

  And you do a load of CT scan to see if the nodule is potentially malignant or not, right? And sometimes what happens is that nodule is too small. So then they have to call them back again three months later for another CT to see if the nodule has grown. If the nodule has grown, then, uh, it is likely malignant, otherwise it's benign. So we, we manage that process as well. So we have the solution called QTRAC, which manages that follow-up. So not only do we interpret, uh, the X-rays and the CT scans using AI, we also, uh, manage that follow-up program. And, uh, the other capabilities that we have, some of the capabilities we have is that as the radiologist is reporting these nodule, for example, all the nodule characteristics are automatically inserted into their report.

• 10:16Speaker 01

  So they don't have to report it now. It's basically part of the report and that's a very complex task. It takes time to measure each nodule, to measure, to identify where it is. And so we do all of that and we, and also identify the characteristics of the nodule, right? We do all of that and we insert that into the, uh, into the report for the radiologist. Now, this is one use case. This is one use case. Uh, one of the other use cases that has become very big for us is XUS. I mean, it's not, not in the US. But this is around tuberculosis screening. Where tuberculosis is still, uh, uh, uh, it's still, I mean, affects more than ten million people across the world every year. So it's still very common, especially in the low and middle income countries.

• 11:00Speaker 01

  And tuberculosis screening protocols are that you take an X-ray. If the X-ray is positive, uh, you would do a sputum test, basically microbiological test of the patient's sputum. Now, the bottleneck for this becomes the fact that the X-ray interpretation, which is, uh, which requires a radiologist. And, uh, many countries that we work in, uh, in Africa, for example, rural parts of India, uh, there is, there are not enough radiologists. So there is nobody reading those X-rays. It takes sometimes days, sometimes weeks to get those X-rays read. And in twenty twenty-one, WHO came out and said that AI, and specifically, they called out cure algorithm, can interpret those X-rays autonomously to detect TB on that chest X-ray.

• 11:44Speaker 01

  So today, the protocol there is that X-ray gets taken, gets automatically uploaded to our, so this is, again, we have to do local processing. So we have laptops that are, are, uh, in those sites. So gets uploaded to our laptop, gets processed. Within twenty seconds, they get to know whether it's positive or not. And then if the, if, if the X-ray is positive, then they go to and go and do a sputum test. And that's how they continue testing. And today, we do this across maybe about seventy, twenty-five countries, across more than fifteen million patients around the world who go through screening, uh, with the cure algorithm.

• 12:17Craig S. Smith?

  Yeah, and from the doctor's, uh, point of view, uh, are there metrics about how this can increase, patient, uh, coverage? I mean, uh, how, how many, the, the time that it would take without cure AI as opposed to using cure AI to, to detect some of these anomalies?

• 12:44Speaker 01

  So you know, I think in in many ways, I mean, there is there is studies that we have done to show that um cure plus, I mean, and you have to do those studies for the FDA clearances where we show that cure uh algorithm plus the radiologist is way more accurate than the radiologist or more accurate than the radiologist alone, right?

• 13:04Craig S. Smith?

  Hmm.

• 13:04Speaker 01

  And we we do those studies to show that radiologist operating alone and radiologist radiologist operating with AI sort of uh what is the difference and uh we we have those studies. Uh again, I mean, reporting time, I mean, we have done studies which show that we can significantly improve the lung cancer detection. So almost by more than sixty days, I mean, patient could be diagnosed more than sixty days early, sometimes even more uh because because of cure being part of the diagnostic pathway. And so we do uh many of these kinds of studies which measure accuracy, measure improvement in the reporting of the radiologist and how how how much earlier you can detect uh lung cancer, for example.

• 13:49Craig S. Smith?

  Uh there's a create study that uh that I've been told about. Uh what is the create study and uh in in how how uh should US healthcare experts interpret the results?

• 14:08Speaker 01

  So the create study was um done um uh so I I'll sort of talk about what the create study is and the relevance of that, right? And then talk about the results. So the the basic challenge with detecting lung cancer is that uh a lot of by lung cancer, about eighty percent of lung cancer cases are diagnosed late, right? And the reason for that is, I mean, you have these nodules that grow in the lungs and I'm not a doctor, so I'm also speaking from

• 14:36Craig S. Smith?

  Yeah.

• 14:37Speaker 01

  uh talking to people, right? But basically, uh these nodules, I mean, when when they are small, you don't have any symptoms. So you get symptoms when it's already quite late, right? And that's why you have to do screening. So especially people who are at risk, uh people who are smokers, heavy smokers. Uh above fifty fifty five years of age depending on where you are different countries have different rules but heavy smokers and older for older people go through screening programs right they do annual screening based on low do C D scans now there are multiple challenges with that screening one is that most people don't show up that if you have hundred people who are eligible for screening typically about five people show up so people don't show up because they've I mean they feel like they're healthy why should you go out and do the screening right

• 15:21Speaker 01

  the second thing is that you look at something like that uh the capacity for those cities does not exist in most places I mean in a system like the N H S for example in U K uh the I mean elective surgery elective procedures are diffi- already I mean um uh difficult to schedule right and uh doing low do C D scan screening is I mean there is not enough capacity that I mean they are creating that capacity in the N H S definitely but when you look at the low and middle income countries there is not enough capacity at all to uh do those uh low do C D scans so one of the things that we we sort of looked at is we said there are one point three billion people who go through a chest X ray every year right and on that chest X ray you can see nodules now can you identify malignancy risk on those nodules

• 16:06Speaker 01

  and identify the right patients who should go and get a C T that was the basic hypothesis right so can you sort of do a pre-screening for that screening and we are not here trying to go out and screen people with X rays what we're saying is just use routine X rays all of us take X rays for routine reasons we take X rays for annual checkups you have some infectious condition you have a cough you have a cold you do a pre-surgery X ray I mean N number of reasons that you would do an X ray and we said on those routine X rays can we detect nodules and can those nodules then be followed up right now that was the hypothesis now the challenge with with that hypothesis is that out of hundred X rays about ten will have nodules so not every nodule can be followed up because if you're doing ten sending ten people for a C T out of hundred

• 16:50Speaker 01

  there is not enough capacity for that right so then we said we have to find the right nodule that needs a follow up so we have to figure out which is a high risk nodule so we said let's figure out a risk core for identifying which nodules need Follow-up examination. That's how we created the lung nodule malignancy risk score. Now, this is not cleared for use in the US right now. This is outside of the US that we are doing this study. But we said, out of those ten patients who have a nodule, maybe one has a high-risk nodule. And then the question was, how accurate is that risk score, the lung nodule malignancy risk score? How accurate are we at that risk score? That is what the Create Study studied.

• 17:30Speaker 01

  To see if that lung nodule malignancy risk score was effective at identifying the right patients for a follow-up, right? Now, the key result, one of the most important results of this is that, out of hundred patients who were identified as high-risk nodule, high-risk by the lung nodule malignancy risk score, fifty-four patients were actually positive on a CT. So, all of them got a CT. And fifty-four were actually positive on a CT, which means that it was extremely accurate at identifying the right patients for CT screening. And just to give you an example, if you do a CT by screening program, the number of patients who are positive on that CT will be about two.

• 18:08Speaker 01

  So, we are going from two out of hundred to fifty-four out of hundred with this lung nodule malignancy risk score. And the other thing is, what is the false negative rate? I mean, are we missing any nodules, right? And there also, are we missing any cancer cases? And there also, we identified that we are more than ninety-five percent positive. I mean, sensitivity is more than ninety-five percent. And in fact, I mean, there are some people who might be positive on a CT. But in the Create Study, there was nobody who we recommended as low-risk, who was actually then diagnosed with lung cancer. So, everybody did not. I mean, so, anything that was negative was finally negative from a cancer perspective. So, that was the high-level results from the Create Study,

• 18:50Speaker 01

  which basically is now creating a scoring system to identify the right patients who should get a follow-up CT. And based on routine chest X-rays, which enables early detection of lung cancer, our goal is to detect more than fifty percent of the lung cancers cases early. So, that eighty percent late, twenty percent early, you want to make that fifty-fifty, fifty percent early, fifty percent late. And we are seeing that movement happening, actually, as we're looking at data coming out of multiple sites. We are seeing that we are enabling that stage shift. And I can't talk today about some of those results because we're going to publish them. But we are seeing that more and more cases are getting diagnosed early with our solution.

• 19:30Craig S. Smith?

  Yeah, and this is in the centers that are using cure, obviously.

• 19:36Speaker 01

  This is in the centers that are using cure. This is about, maybe about close to seven and eight centers around the world who are using cure for a lung cancer product, lung cancer pathway.

• 19:48Craig S. Smith?

  And how do you, if you're a patient and you get an X-ray, how do you encourage your provider to run it through cure? Is it, is, is you have to find a provider that is using cure? Or, or can your provider is an easy thing for them to adopt? Is it an expensive thing for them to adopt?

• 20:13Speaker 01

  It's not, it's not incredibly expensive to adopt, right? But the providers have to adopt this system. It the, I mean, so again, I mean, we sort of have to go through a deployment process. They have to integrate with their. So what we do is we, we collect imaging data, but we also collect medical records. So we are able to then combine the medical record data with imaging data to make the right prediction. So that integration with the MR systems, that integration with the PAC systems, that takes a few months, right? And the providers have to go through that process. So patient cannot use this. I mean, they can, of course, go to a provider who's using cure. They can ask the provider if they're using cure. Uh, but the patient cannot, I mean, right now, we don't have a patient program where they can send us a scan and we can process it.

• 20:54Speaker 01

  And I, I don't think it's also legal for us to do it right now. So I think based on FDA regulations, we cannot do it.

• 21:01Craig S. Smith?

  Yeah, uh, I'm just thinking for, I'm at an age where everyone's getting tests of all my friends. If you want to find somebody with cure in their practice, is there a directory somewhere that cure provides?

• 21:21Speaker 01

  You know, that's a good idea. What I will do is I'll, I'll ask my marketing and put up a list of sites that we deployed in on our, on our website. So I think we should do that.

• 21:31Craig S. Smith?

  Yeah.

• 21:31Speaker 01

  That's one place that you can look it up, yeah.

• 21:34Craig S. Smith?

  Yeah. So, uh, this is only one, uh, cancer that you're addressing, lung cancer. Can you talk about, uh, how many different cancers you've addressed? And is it all through X-ray, uh, or, or are you covering other kinds of tests?

• 21:56Speaker 01

  So we also have a CT solution for lung cancer where the same nodules that I spoke about, we can detect them on a CT, we can characterize those nodules, we can measure their progression, measure the size. So that's again a solution we have, again focused on lung cancer. We don't currently do other types of cancers, but we have similar solutions for tuberculosis like I spoke about. We can detect signs of heart failure on chest X-ray and we can follow that up. We detect coronary artery disease from routine chest CT scans. So on a chest CT scan, you can see the calcification of the coronary artery and that is basically an indicator of

• 22:39Speaker 01

  coronary artery disease. So again, when you do these lung cancer screening programs, you can actually find signs of coronary artery disease and then those patients can then be followed up for heart disease and so they can then be tested for that, right? So we do that.

• 22:55Speaker 01

  Then we have a solution which can detect bleeds and multiple abnormalities and stroke on head CT scans and CT angios and then we detect fractures on musculoskeletal X-rays. So about 16 different kinds of fractures that we are able to detect. Now, some of these are not cleared in the US. So I mean, again, just wanted to clarify that some, not, not all of the capabilities that we have are currently cleared by the FDA. 26 of them are.

• 23:23Craig S. Smith?

  Yeah. And on the, on the skeletal fractures, I have a friend who's a orthopedic surgeon and he's talked about certain fractures, one in the wrist that are extremely hard to diagnose. And I know that there have been groups working on developing diagnostic tool for that. Is that, do you, do you address sort of esoteric fractures?

• 23:56Speaker 01

  We do, we do.

• 23:58Craig S. Smith?

  Yeah. Are you familiar? I mean, can you talk about any of those?

• 24:03Speaker 01

  So we, this is something which is still being launched and we are, we are sort of getting the clearance for this solution right now, but detecting fractures, these fractures is common, I mean, across different body parts and the idea is simple. I mean, you, if you take a musculoskeletal x-ray, I mean, the algorithm will sort of mark out that fracture for the radiologist to see before they report it, very similar to how you do nodules or other other conditions.

• 24:28Craig S. Smith?

  Yeah. Where is this headed for you? I mean, are you building out, are you covering more and more types of anomalies, either fractures or, or malignancies or, or, you know, other kinds of disease? Or is your focus on integrating other kinds of AI into the system to make it easier to use from the doctor's point of view?

• 25:04Speaker 01

  It's both actually, so it's both. I mean, we are, so we have an LLM research team that is looking at, I mean, research on what can you interpret from the patient's medical records, which is mostly text data, report data, pathology reports, right? How can you interpret from there? Then we have a vision research team, which is looking at vision models or basically vision language models, but then they are looking at what more abnormalities can you detect? And as we sort of are growing, what we're realizing is that the real value is in detecting conditions that are very hard to diagnose, right? I mean, COPD diagnosis is very poor, lung cancer, like I said, early diagnosis is bad, right? So those are areas where AI can

• 25:49Speaker 01

  play a very important role and so sort of we are expanding our capability there. But one thing that we are very clear about is that We focus on diagnosis of a disease, right? And the biomarkers for that can come from pathology tests, can come from radiology, can come from medical records, right? And we also have a tool which basically scribes doctor-patient conversation. So we have a note-taking tool as well. So again, that allows us to get access to some, some medical record data. But finally, all kinds of data have to then flow into helping make that diagnosis faster. And, and that's, that's the focus. So we, we sort of do end-to-end diagnostics for a disease.

• 26:31Speaker 01

  And that's, that's what we have been doing for the last two and a half, three years. Before that, we were more of a, before that, we were just doing what you were asking for, that, asking about, right? That can you do more and more findings on a scan? And we were doing more, but then we realized that, I think, doing more, more findings on a scan is good. But then we sort of have to do the, make sure that we are enhancing that patient journey and finding that patient that earlier, diagnosing the patient early. And that's where the value gets created.

• 27:01Craig S. Smith?

  Yeah. Uh, I have to ask because, uh, you know, early detection of lung cancer is, is so important. Uh, the, the other one that, uh, requires early detection and is notoriously asymptomatic until it's too late is pancreatic cancer. Uh, have you worked at all on, on pancreatic cancer detection? And if not, is there a particular issue that makes that difficult?

• 27:35Speaker 01

  We have not actually, we have not looked at pancreatic cancer. But we are looking at more types of cancers and seeing what, where we can sort of invest into and, and build those technologies. We have a team of about 200 data scientists and engineers who, who are working on, on, on research in many of these areas. So, but right now, nothing on pancreatic cancer.

• 27:58Craig S. Smith?

  Yeah, yeah. Uh, this is fascinating. Do you think, uh, the day will come when all medical records, all tests?

• 28:13Craig S. Smith?

  Whether it be X-ray, C T, or, or M R I, or what, what, whatever it might be, will be run through uh, something like Q R A I to, to help doctors with their diagnosis.

• 28:34Speaker 01

  I think that, yeah, we are not too far away. Probably we are already there or getting there very soon. I think A I can add tremendous value to diagnostics. I think overall, I mean, we, we collect so much data about the body, right? We have sensors, I mean, heart, uh, uh, I mean, heart rate sensors, we have got B P, B P sensors, we've got watches, rings, I mean, and there is so much medical record data. So I think in general, the diagnostics has to move earlier and earlier. So we have to be more proactive about diagnostics. And we'll see algorithms play a role in that. I mean, how can algorithms ingest all the data about the body that we are producing and then sort of come to the, come to a diagnosis very early so that we can treat.

• 29:18Speaker 01

  Maybe you don't even require, require medication, maybe it can be treated by lifestyle changes, right? So I think that's, that's where, uh, definitely the world is headed where diagnostics will happen much earlier through the amount of data that we are generating and A I has a big role to play in that, in that journey.

• 29:37Craig S. Smith?

  Yeah, uh, I mean, currently, uh, is, is your rollout primarily in uh, countries, uh, that, that are, that lack pro, uh, provision that are uh, have a shortage of doctors or are you targeting uh, the, uh, the, the more affluent countries like the United States where there's plenty of doctors, uh, maybe? Uh, yes, yeah.

• 30:09Speaker 01

  So for ninety percent of a portfolio, the market is US and some European countries. There is a small part of a portfolio, which is what I spoke about tuberculosis, which is more prevalent, I mean, in the low and middle income countries. That product again has its own market, it's scaled up across Africa, Asia, LatAm. But the rest of the product portfolio is more developed country focused.

• 30:39Craig S. Smith?

  Yeah, and so in the US, what are the barriers to getting this into every medical practice?

• 30:50Speaker 01

  I think getting it into every practice is just about being there, I mean, being in front of them, presenting this portfolio to them. What we are seeing is that most times when we are in front of the right stakeholders in a hospital system, they see the value in a lung cancer portfolio and we are seeing very high win rates from a deal perspective. So if we are in front of them, so again, we sort of started our US business only about a year and a half ago. So we are still scaling up, we are still sort of scaling up across the country. But one of the things we are seeing is that everybody that we speak to is interested and they want to deploy this solution.

• 31:29Speaker 01

  So it's a matter of time, I think, in the next one or two years, they should be scaled up across most of the US systems.

• 31:36Craig S. Smith?

  Yeah, you know, one of the frustrations, you mentioned NHS, but one of the frustrations

• 31:44Craig S. Smith?

  in the US as well is getting appointments and getting tests scheduled or getting insurance to cover tests. And there is sort of the high end, this trend of testing,

• 32:05Craig S. Smith?

  sort of elected testing that people can pay for directly.

• 32:12Craig S. Smith?

  Why? Not make this available to the consumer. Uh, because yeah, the consumer can go to the doctor and say, hey, you know. You should get cure AI because it'll. Give you a earlier and more accurate detection of anything that's going on with me. Uh, but it would, it would be great if I could take my medical records and scans. Upload them to a system that I. That was trustworthy and vetted, but as yours is. And and get flagged that you need to see a doctor. There are nodules in your.

• 32:55Craig S. Smith?

  Lung that that should be taken. Uh, should have a professional look at. Uh, that you why is is does it have to go through the medical. Uh, establishment.

• 33:10Speaker 01

  I think where we operate, I mean, especially with scans, right? I mean, people don't have access to their scans. I mean, if I, if you have taken a chest CT scan, you may not have access to that, right? And getting access to those scans. Uh, is hard for people, for for patients. Um, and then if they have to give it to us, we have to process it. Of course, if they have it, we can process it. But then there is the regulations also FDA regulations which don't allow us to directly interact with a patient or provide a diagnosis to a patient. So I think multiple steps, I think. There is definitely tremendous value in making this available to patients, right? And I think if you look at. Um, chat G P T for health, I mean, they launched a direct patient facing.

• 33:52Speaker 01

  Uh, healthcare tool. Again, they're very careful about the disclaimers there because. Uh, they cannot, I mean, they cannot provide a diagnosis to a patient. Uh, but yeah, I mean, I think I think there is value in. Uh, providing the these healthcare tools to patients and I think we'll see that happen. Um, right now, I think one of the bottlenecks is that. Patients may not have access to their imaging information. And so if we have to process that, we have to take it from the provider. Where they took that X-ray or C T, uh, rather than from the patient.

• 34:22Craig S. Smith?

  Yeah, uh, yeah, it just seems that with with all of this. Uh, the trend is to put more and more uh power in the patient's hands or more and more. Knowledge uh in the patient's hands for them to direct their care.

• 34:40Speaker 01

  I there is one more point there actually which I want to talk about. I think the point that you made about knowledge, right? That is also a difficult one because if I go out and tell a patient that you have a nodule which could be potentially lung cancer. Um, that communication has to be done by a human, by a doctor, right? Because they they communicate in the right way that this could be lung cancer, but there is ninety percent chance that it's not lung cancer, right? But you should go and do a C T. Now, when that patient gets that information from an A I algorithm, that could scare them, right? I mean, um, and and that again, uh, I think the way this information is communicated, how you uh, how the patients react?

• 35:20Speaker 01

  I think there is more to it than meets the eye. So we, yeah, I think there is more research that needs to be done to. Make these algorithms patient facing, but definitely patient should have the power to uh, get a second opinion from A I. I think for sure uh, that should be available to them.

• 35:37Craig S. Smith?

  I mean, I had a uh, uh, interview recently with a guy who who had a skin cancer scare. And he's developed a system uh, that scans, it's a hardware, it's a a scanning. Room or portable scanning room that a uh, doctor's office could set up. And you go in and it it does a three sixty very high definition uh, imaging. And then that's fed through an A I system that identifies potential uh, cancerous legion lesions.

• 36:21Craig S. Smith?

  And is the is the doctor's office of the future going to be a bunch of these? Systems and the doctor kind of guides you, you you do this X ray. It's the A I, you know, gives a uh, the doctor of.

• 36:43Craig S. Smith?

  A cheat sheet on what he should pay attention to. You go in and get a body scan. The doctor gets a report on what he should pay attention to. I mean, is, is, is healthcare moving in that direction?

• 37:00Speaker 01

  My personal belief is that primary care will be AI in the future. Maybe five to 10 years from now, that what a primary care physician does, which is interact with the patient, identify symptoms, recommend tests, maybe diagnose disease, recommend treatment. I think a lot of that, for especially for a lot of basic conditions, will be AI. I think we'll have specialists who handle, I mean, somebody has lung cancer, the kind of treatment they should go through will require expertise, and I think if you are doing surgery, that will require expertise, but again, maybe there are some basic surgeries that AI can do, right?

• 37:45Speaker 01

  So I think more and more will be automated. I think definitely primary care is one of those areas where I see a lot of automation coming in. And our first, first time that we talk to somebody will probably be AI. We don't talk to a doctor first, we'll talk to AI first. Before we interact with a doctor. So I think that's, that's definitely coming our way in the next five to 10 years.

• 38:07Craig S. Smith?

  Yeah, well, that's exciting. And, and the, you, you said earlier that there is a fully automated part of your system and you would talk about it. What is that?

• 38:23Speaker 01

  So that is a TB screening product that I spoke about where when these x-rays, about 15 million x-rays every year are taken in Africa and Asia and Latin America, we are the final algorithm that is interpreting that x-ray. There is no human in the loop. X-ray is taken, interpreted by a cure, and we recommend if that patient is positive or not, and then they go through a sputum test. And that, that is mainly because we don't have human readers available, we don't have radiologists available, so AI has to play that role. You're talking about countries where there are two radiologists for a whole country. Right, so it's just not enough to read hundreds of thousands of scans. And that's where AI is playing a very, very significant role.

• 39:07Speaker 01

  And this, this particular use case is the use case that is, I think, the most scaled from an autonomous, autonomous perspective. So most scaled autonomous AI use case in healthcare today.

• 39:17Craig S. Smith?

  Is that right? Yeah. Are there other use cases that, that you could do that with malaria or?

• 39:27Craig S. Smith?

  You know, there are all kinds of diseases in, in underserved populations that, where there aren't enough doctors.

• 39:40Speaker 01

  There are definitely more areas where this kind of automation could come in, right? Especially when you're recommending further testing. For example, you see something on an X-ray and the algorithm sees something and says, this patient should get a CT. And that CT can be called for autonomously without a radiologist looking at it. Because anyway, you're going to get a CT and maybe that radiologist looks at that, right? So I think some of this can be made autonomous because finally, the diagnosis is done by a physician with a lot of information about that patient, about that patient, including multiple test results, right? But that X-ray to CT process automate, just make sure that anybody who has a nodular, they get a CT, right? So there are steps that can be automated.

• 40:26Speaker 01

  But I think the healthcare is heavily regulated because again, it's the first, most important priority is patient safety. So again, those, those changes will be a little bit slow because finally you want to ensure that any change you make is not causing harm to patients. But I can see that more, more, more things can be definitely automated.

• 40:49Craig S. Smith?

  Okay, I'm running out of questions, Prashant. Is there anything I haven't asked that you want to cover?

• 40:57Speaker 01

  No, I think that's that's about it. Thank you so much. Great talking to you.

• 41:02Craig S. Smith?

  If if a healthcare system wants to look at Cure AI, where would they find you?

• 41:10Speaker 01

  Partner at cure.ai, email, cure.ai website, cure on LinkedIn, X, Instagram.

• 41:21Craig S. Smith?

  Yeah, and that's cure with a Q.

• 41:23Speaker 01

  Q U R E, Q U R E dot AI, yeah.

• 41:26Craig S. Smith?

  Okay, great, Prashant.