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

[00:00:00] [SPEAKER_01] 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?

[00:00:21] [SPEAKER_00] My personal belief is that primary care will be AI in the future, maybe 5 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're generating. And AI has a big role to play in that journey.

[00:00:41] [SPEAKER_01] So let's start with you introducing yourself to listeners.

[00:00:47] [SPEAKER_00] Hi, my name is Prashant Warier. I'm the co-founder and CEO of Qure. 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, IT Delhi. And went to the US at Georgia Tech, did a PhD in operations research.

[00:01:07] [SPEAKER_00] My PhD was optimizing trucking networks for the 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, demand forecasting, a bunch of retail and consumer products problems. This was all in the US.

[00:01:34] [SPEAKER_00] 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.

[00:02:03] [SPEAKER_00] And we'll talk about the Cure journey today.

[00:02:06] [SPEAKER_01] Yeah. And, and so talk about what cure AI was founded to do and how it has evolved.

[00:02:16] [SPEAKER_00] So we, when we started our hypothesis was that, that image recognition algorithms. I mean, this there's Alex net, but that was one of these neural convolutional neural networks that was released in 2012. Right. And our hypothesis was that can we sort of take some of those techniques applied to a lot of radiology images, billions of them. And would that enable us to then identify abnormalities on a X-ray or a CT scan?

[00:02:45] [SPEAKER_00] And that was the hypothesis when we started. And of course, I mean, we, we did that, uh, spent a lot of time collecting data because getting access to anonymized, uh, de-identified customer data, patient data is not easy. And, um, so spent almost the first year, uh, just working with hospital systems, especially we started out of India. So working with hospital systems in India, getting, uh, de-identified patient data, basically radiology images and the corresponding reports.

[00:03:13] [SPEAKER_00] And, uh, created a large database, more than a billion and a half images now. And that went into training these algorithms. And, uh, the, what we sort of focused on initially was detecting abnormalities on chest X-rays. Now chest X-rays, the most common imaging modality, more than 1.3 billion chest X-rays taken around the world. Uh, we focused on head CD scans. Head CT scans are one of those scans, uh, which require the fastest interpretation because you're looking for bleeds or stroke and you want to be able to treat the patient quickly. So speed is important.

[00:03:43] [SPEAKER_00] So high volume, uh, tasks, uh, we looked at things where real time processing is required, uh, and then sort of went on from there, built out, uh, solution portfolios for musculoskeletal X-rays, uh, chest CTs, uh, 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.

[00:04:11] [SPEAKER_00] You have to actually, uh, be participate in the end-to-end diagnostic process from the time a patient comes in, uh, 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? And, um, so we have now AI which runs on EMR data, which runs on the imaging AI imaging, vertical imaging, uh, radiology imaging data.

[00:04:35] [SPEAKER_00] And, um, uh, we have follow-up management tools which ensure that patients are followed up, uh, for the, for the next, uh, test. So, uh, multiple tools that, that bring together the patient's diagnostic journey and, uh, help patients, uh, get diagnosed earlier, detected earlier with conditions like tuberculosis, lung cancer, heart failure, COPD, and so on.

[00:04:56] [SPEAKER_01] Yeah. Yeah. And you're the, the customer for this are, uh, healthcare systems. Is that right? Not, it's not a customer-based product.

[00:05:08] [SPEAKER_00] It is not a consumer-based product. So one of the things that, uh, we are very careful about is that everything that we build and sell, uh, 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, uh, has those clearances.

[00:05:35] [SPEAKER_00] 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, uh, research around this. So we have been very focused on that. So we have today more than 200 plus publications at Cure and, uh, we have 26 FDA clearances. Uh, we have 65, uh, findings that are cleared in Europe and, uh, we are actually cleared for use in more than 105 countries.

[00:06:01] [SPEAKER_00] So it's, it's a, it's scaled, uh, quite broadly across the world as well. So that sort of, um, 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 decision. 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's one place where we are autonomous and I can talk about that in a bit.

[00:06:30] [SPEAKER_01] Yeah. Uh, and, and the, uh, the, the, the, the AI, uh, under the hood is evolved from supervised learning to, um, to integrating, uh, generative, uh, AI or, or, uh, uh, language models. Can you talk about how you, the, the underlying AI has evolved?

[00:06:56] [SPEAKER_00] So our underlying AI stack, I mean, so we, uh, integrate language models, vision models. So we have a combined vision plus language model and that's trained, um, on, I mean, uh, reports that we have, uh, for, so we have images, um, radiology images and the corresponding reports, but also we have, I mean, for a large number of, uh, scans, we have annotations, uh, where a radiologist has gone in and marked out where the abnormality lies. So, uh, a lot of it is supervised.

[00:07:25] [SPEAKER_00] 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, uh, pulmonary arterial hypertension, for example, or, uh, COPD, um, or, or a bunch of other conditions, lung cancer, lung nodule, malignancy risk, um, and a bunch of other conditions. Yeah.

[00:07:47] [SPEAKER_01] Yeah. And, uh, you were saying this is high volume. Uh, can, can you talk about the throughput and, and, and so what happens a doctor, uh, takes an x-ray and then it's uploaded to the system. Can just walk through the workflow, uh, from the doctor's point of view.

[00:08:08] [SPEAKER_00] So, uh, what happens is patient comes in, uh, takes an x-ray, x-ray is automatically uploaded to our system, right? Our patient comes in, takes the CT, CT is uploaded to our system. Um, we process it immediately. It takes, um, anywhere from a few seconds to maybe a minute to process those scans. Um, and the results are then available as a small widget on the radiologist's workflow.

[00:08:33] [SPEAKER_00] So, as a radiologist reading a scan, there'll be a small queue at the bottom of the screen where they can, uh, see the results of what cure has, um, uh, cure has processed for that particular scan, what the abnormalities that cure has identified. And they can click on that and they can go into further details. It will show you the nodules that we have, uh, picked up. You can go into details of those nodules. You can, um, see, compared to previous scans, there's a previous CT scan. You can compare to that.

[00:09:01] [SPEAKER_00] So, it then, it gets into that workflow from the, uh, radiologist 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, which many US health systems have.

[00:09:29] [SPEAKER_00] And so, in that program, what they do is they actually call this patient back in for a CT. And you do a load of CT scan to see if the nodule is, uh, 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, uh, benign. So, we manage that process as well. So, we have the solution called Q-Track, which manages that follow-up.

[00:09:57] [SPEAKER_00] 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 nodules, for example, all the nodule characteristics are automatically inserted into their report. 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.

[00:10:26] [SPEAKER_00] 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, is ex-US. I mean, it's not, not in the US, but this is around tuberculosis screening. Mm-hmm. Where, uh, tuberculosis is still, uh, uh, uh, uh, uh, it's still, I mean, affects more than 10 million people across the world every year.

[00:10:56] [SPEAKER_00] So, it's still very common, especially in the low and middle income countries. And, uh, tuberculosis screening protocols are that you take an x-ray. If the x-ray is positive, uh, you would do a sputum test, basically a 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.

[00:11:19] [SPEAKER_00] 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, uh, in 2021, WHO came out and said that AI, and specifically, specifically, they called out CURS algorithm, can interpret those x-rays autonomously to detect TB on that chest x-ray.

[00:11:44] [SPEAKER_00] 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 in those sites. So, it gets uploaded to our laptop, gets processed. Within 20 seconds, they get to know whether it's positive or not. And, uh, then if the x-ray is positive, then they go to and go into a sputum test. And that's how they continue testing.

[00:12:06] [SPEAKER_00] And today, we do this across maybe about 70, 75 countries across more than 15 million patients around the world who go through screening, uh, with the cure algorithm.

[00:12:17] [SPEAKER_01] Yeah. And from the doctor's, uh, point of view, uh, uh, are there metrics about how this can increase, uh, patient, uh, coverage? I mean, uh, how, how many, the time that it would take without cure AI as opposed to using cure AI to, to detect some of these anomalies?

[00:12:43] [SPEAKER_00] 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. Right. And, uh, we, we do those studies to show that radiologist operating alone and radiologist, radiologist operating with AI sort of, uh, what is the difference?

[00:13:13] [SPEAKER_00] 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 60 days, I mean, patient would be diagnosed more than 60 days early, sometimes even more, uh, because, because of cure being part of the diagnostic pathway.

[00:13:35] [SPEAKER_00] And so we do, uh, many of these kinds of studies which measure accuracy and measure improvement in the reporting of the radiologist and, uh, how, how, how much earlier you can detect, uh, lung cancer, for example.

[00:13:48] [SPEAKER_01] Uh, uh, uh, there's a CREAT study that, uh, that I've been told about, uh, what is the CREAT study and, uh, and, and, uh, how, how, uh, should U.S. healthcare experts interpret the results?

[00:14:08] [SPEAKER_00] So the CREAT study was, um, done, um, uh, so I, I, I sort of talk about what the CREAT 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 80% of lung cancer cases are diagnosed late, right?

[00:14:30] [SPEAKER_00] 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, 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 50, 55 years of age, depending on where you are, different countries have different rules.

[00:14:58] [SPEAKER_00] But heavy smokers and older, older people go through screening programs, right? They do annual screening based on low-dose CT scans. Now there are multiple challenges with that screening. One is that most people don't show up. That if you have 100 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? The second thing is that you look at something like that. Uh, the capacity for those CTs does not exist in most places.

[00:15:28] [SPEAKER_00] I mean, in a system like the NHS, for example, in UK, uh, I mean, elective surgery, elective procedures are already, I mean, um, uh, difficult to schedule, right? And, uh, doing low-dose CT scan screening is, I mean, there is not enough capacity. I mean, they are creating that capacity in the NHS 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-dose CT scans.

[00:15:52] [SPEAKER_00] So one of the things that we, we sort of looked at is we said there are 1.3 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 and identify the right patients who should go and get a CT? 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.

[00:16:21] [SPEAKER_00] 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 that hypothesis is that out of 100 X-rays, about 10 will have nodules.

[00:16:44] [SPEAKER_00] So not every nodule can be followed up because if you're sending 10 people for a CT out of 100, 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 score for identifying which nodules need a follow-up examination. That's how we created the lung nodule malignancy risk score. Now, this is not cleared for use in the U.S. right now. This is outside of the U.S. that we are doing this study.

[00:17:12] [SPEAKER_00] But we said out of those 10 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 CREAT study studied to see if that lung nodule malignancy risk score was effective at identifying the right patients for a follow-up, right?

[00:17:37] [SPEAKER_00] Now, the key result, one of the most important results of this is that out of 100 patients who were identified as high-risk nodule, high-risk by the lung nodule malignancy risk score, 54 patients were actually positive on a CT. So, all of them got a CT and 54 were actually positive on a CT, which means that it was extremely accurate at identifying the right patients for CT screening.

[00:18:01] [SPEAKER_00] 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 2. So, we are going from 2 out of 100 to 54 out of 100 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 95% positive. I mean, so sensitivity is more than 95%.

[00:18:30] [SPEAKER_00] And in fact, I mean, there are some people who might be positive on a CT. But in the CREAT 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 CREAT study, which basically is now creating a scoring system to identify the right patients who should get a follow-up CT.

[00:18:56] [SPEAKER_00] And based on routine chest X-rays, which enables early detection of lung cancer, our goal is to detect more than 50% of the lung cancer cases early. So, that 80% late, 20% early, you want to make that 50-50, 50% early, 50% 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 want to publish them.

[00:19:24] [SPEAKER_00] But we are seeing that more and more cases are getting diagnosed early with our solution.

[00:19:30] [SPEAKER_01] Yeah. And this is in the centers that are using Cure, obviously.

[00:19:36] [SPEAKER_00] This is in the centers that are using Cure. This is about, maybe about close to 700, 800 centers around the world who are using Cure for a lung cancer product, lung cancer pathway.

[00:19:47] [SPEAKER_01] 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, you have to find a provider that is using Cure? Or can your provider, is it an easy thing for them to adopt? Isn't it an expensive thing for them to adopt?

[00:20:12] [SPEAKER_00] It's not, it's not incredibly expensive to adopt, right? But the providers have to adopt this system. The, I mean, so again, I mean, we sort of have to go through a deployment process. We have to integrate with their. So what we do is 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 AMR systems, that integration with the PAC systems, that takes a few months, right? And the providers have to go through that process.

[00:20:42] [SPEAKER_00] So a 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. 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. And 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.

[00:21:00] [SPEAKER_01] Yeah. I'm just thinking for, I'm at an age where everyone's getting tests. All my friends. If you want to find somebody with Cure in their practice, is there a directory somewhere that Cure provides?

[00:21:20] [SPEAKER_00] You know, that's a good idea. What I will do is I'll ask my marketing, put up a list of sites that we deployed in on our website. So I think we should do that. Yeah. That's one place where you can look it up. Yeah.

[00:21:34] [SPEAKER_01] Yeah. So this is only one cancer that you're addressing, lung cancer. Can you talk about how many different cancers you've addressed? And is it all through x-ray or are you covering other kinds of tests?

[00:21:56] [SPEAKER_00] 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. So 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. Yeah.

[00:22:22] [SPEAKER_00] 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 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.

[00:22:51] [SPEAKER_00] So we do that. 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're able to detect. Now, some of these are not cleared in the US.

[00:23:14] [SPEAKER_00] So I mean, again, just wanted to clarify that some not all of the capabilities that we have are currently cleared by the FDA. 26 of them are.

[00:23:23] [SPEAKER_01] 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 a diagnostic tool for that.

[00:23:50] [SPEAKER_01] Is that do you do you address sort of esoteric fractures? We do. We do. Yeah. Are you familiar? I mean, can you talk about any of those?

[00:24:03] [SPEAKER_00] So we this is something which is still being launched. And we are we are sort of getting the FDA clearance for the solution right now. But detecting fractures, wrist 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 not use or other conditions.

[00:24:28] [SPEAKER_01] 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 malignancies or, you know, other kinds of disease?

[00:24:47] [SPEAKER_01] 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?

[00:25:03] [SPEAKER_00] It's both, actually. 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. What 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?

[00:25:32] [SPEAKER_00] 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 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. Right.

[00:26:01] [SPEAKER_00] 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 medical record data. But finally, all kinds of data have to then flow into helping make that diagnosis faster. And that's the focus. So we sort of do end-to-end diagnostics for a disease.

[00:26:31] [SPEAKER_00] And 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 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 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 earlier, diagnosing that patient earlier. And that's where the value gets created. Yeah.

[00:27:30] [SPEAKER_01] Is there any particular issue that makes that difficult?

[00:27:35] [SPEAKER_00] We have not, actually. We have not looked at pancreatic cancer. But we are looking at more types of cancers and seeing where we can sort of invest into and build those technologies. We have a team of about 200 data scientists and engineers who are working on research in many of these areas. But right now, nothing on pancreatic cancer.

[00:27:57] [SPEAKER_01] Yeah. Yeah. This is fascinating. Do you think the day will come when all medical records, all tests, whether it be x-ray, CT, or MRI, or whatever it might be,

[00:28:23] [SPEAKER_01] will be run through something like your AI to help doctors with their diagnosis?

[00:28:33] [SPEAKER_00] I think that, yeah, we are not too far away. Probably we are already there or getting there very soon. I think AI can add tremendous value to diagnostics. I think overall, I mean, we collect so much data about the body, right? We have sensors. I mean, heart rate sensors. We have got BP sensors. We have watches, we have watches, rings. I mean, and there is so much medical record data.

[00:28:59] [SPEAKER_00] 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. Maybe you don't even require medication. Maybe it can be treated by lifestyle changes, right?

[00:29:24] [SPEAKER_00] So 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.

[00:29:36] [SPEAKER_01] Yeah. I mean, currently, is your rollout primarily in countries that lack provision, that have a shortage of doctors? Or are you targeting the more affluent countries like the United States where there's plenty of doctors maybe?

[00:30:07] [SPEAKER_01] Yes.

[00:30:08] [SPEAKER_00] Yeah. So for 90% of our portfolio, the market is U.S. 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.

[00:30:34] [SPEAKER_00] But the rest of the product portfolio is more developed country focused.

[00:30:39] [SPEAKER_01] Yeah. And so in the U.S., what are the barriers to getting this into every medical practice?

[00:30:50] [SPEAKER_00] I think getting it into every practice is just about being there, I mean, being in front of them, presenting this portfolio to them. And 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 U.S. business only about a year and a half ago. So we are still scaling up.

[00:31:20] [SPEAKER_00] 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 the solution. 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 U.S. systems.

[00:31:36] [SPEAKER_01] Yeah. You know, one of the frustrations you mentioned, NHS, but one of the frustrations in the U.S. as well is getting appointments and getting tests scheduled or getting insurance to cover tests.

[00:31:55] [SPEAKER_01] And there's sort of the high end, this trend of testing, sort of elected testing that people can pay for directly. Why not make this available to the consumer?

[00:32:19] [SPEAKER_01] Because, yeah, the consumer can go to the doctor and say, hey, you know, you should get Cure AI because it'll give you an earlier and more accurate detection of anything that's going on with me.

[00:32:33] [SPEAKER_01] But it would be great if I could take my medical records and scans, upload them to a system that was trustworthy and vetted, as yours is, and get flagged that you need to see a doctor. There are nodules in your lung that should be taken, should have a professional look at.

[00:33:03] [SPEAKER_01] Why does it have to go through the medical establishment?

[00:33:10] [SPEAKER_00] I think where we operate, I mean, especially with scans, right? I mean, people don't have access to their scans. I mean, if you have taken a chest CT scan, you may not have access to that, right? And getting access to those scans is hard for people, for patients. 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.

[00:33:37] [SPEAKER_00] 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 ChatGPD for Health, I mean, they launched a direct patient-facing healthcare tool. Again, they're very careful about the disclaimers there because they cannot, I mean, they cannot provide a diagnosis to a patient. But yeah, I mean, I think there is value in providing these healthcare tools to patients. And I think we'll see that happen.

[00:34:07] [SPEAKER_00] 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 CT rather than from the patient.

[00:34:22] [SPEAKER_01] Yeah. Yeah. It just seems that with all of this, the trend is to put more and more power in the patient's hands or more and more knowledge in the patient's hands for them to direct their care.

[00:34:41] [SPEAKER_00] 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, that communication has to be done by a human, by a doctor, right? Because they communicate in the right way that this could be lung cancer, but there is 90% chance that it's not lung cancer, right? But you should go and do a CT.

[00:35:07] [SPEAKER_00] Now, when that patient gets that information from an AI algorithm, that could scare them, right? I mean, and that, again, I think the way this information is communicated, how the patients react, I think there is more to it than meets the eye. So, yeah, I think there is more research that needs to be done to make these algorithms patient-facing. But definitely, patients should have the power to get a second opinion from AI. I think for sure that should be available to them.

[00:35:37] [SPEAKER_01] I mean, I had an interview recently with a guy who had a skin cancer scare. And he's developed a system that scans. It's a hardware. It's a scanning room or portable scanning room that a doctor's office could set up.

[00:36:03] [SPEAKER_01] And you go in and it does a 360 very high-definition imaging. And then that's fed through an AI system that identifies potential cancerous lesions. And is the doctor's office of the future going to be a bunch of these systems? And the doctor kind of guides you.

[00:36:32] [SPEAKER_01] You do this x-ray. It's the AI, you know, 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. I mean, is healthcare moving in that direction?

[00:37:00] [SPEAKER_00] My personal belief is that primary care will be AI in the future, maybe five to ten 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, especially for a lot of basic conditions, will be AI.

[00:37:29] [SPEAKER_00] 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? 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 time that we talk to somebody will probably be AI.

[00:37:58] [SPEAKER_00] We don't talk to a doctor first. We'll talk to AI first before we interact with the doctor. So I think that's definitely coming our way in the next five to ten years.

[00:38:07] [SPEAKER_01] Yeah, well, that's exciting. And you said earlier that there is a fully automated part of your system, and you would talk about it.

[00:38:22] [SPEAKER_00] What is that? 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 is mainly because we don't have human readers available.

[00:38:51] [SPEAKER_00] 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. 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. And this particular use case is the use case that is, I think, the most scaled from an autonomous perspective. So most scaled autonomous AI use case in healthcare today.

[00:39:17] [SPEAKER_01] Is that right? Yeah. Are there other use cases that you could do that with? Malaria or, you know, there are all kinds of diseases in underserved populations where there aren't enough doctors.

[00:39:40] [SPEAKER_00] 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 the radiologist looks at that, right?

[00:40:01] [SPEAKER_00] 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, including multiple test results, right? But that X-ray to CT process automate just make sure that anybody who has a not evil, they get a CT, right? So there are steps that can be automated.

[00:40:25] [SPEAKER_00] But I think the healthcare is heavily regulated because, again, it's the first most important priority is patient safety. So, again, 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 things can be definitely automated.

[00:40:47] [SPEAKER_01] Yeah. Okay. I'm running out of questions, Prashant. Is there anything I haven't asked that you want to cover?

[00:40:57] [SPEAKER_00] No, I think that's about it. Thank you so much. Great talking to you.

[00:41:02] [SPEAKER_01] If a healthcare system wants to look at Cure AI, where would they find you?

[00:41:11] [SPEAKER_00] Partner at cure.ai, email, cure.ai website, cure on LinkedIn, X, Instagram.

[00:41:20] [SPEAKER_01] Yeah. And that's cure with a Q. Q-U-R-E, Q-U-R-E, not A-I, yeah. Okay. Great, Prashant. Thank you so much.