Now then, tuberculosis remains the world's deadliest infectious disease, and here in South Africa the numbers are staggering four hundred and sixty eight out of every one hundred thousand people affected. But despite this, TB remains massively underdiagnosed in our health and wellness segment. Today, we're focusing on a groundbreaking new initiative from Stellenbosch University, where researchers are helping lead a global trial using AI artificial intelligence to improve TB diagnoses,
particularly at primary care level. The project, involving ten institutions across Africa and Europe, aims to develop a diagnostic tool that uses handheld ultrasound devices and smartphones to help detect TV quickly and more accurately, even in rural or low resource settings. Joining us now to explain more is Professor Grant Thron, Professor and Clinical Microbacteriology and Epidemiology at Stellenbosh Universities, also the char coordinator for this innovative study. Good to
have you with us this afternoon. Thanks for making time.
Thank you, mich Thank you so much. Sarah Jane, Good afternoon to you and your listeners.
It's incredible to think that although it is the world's sort of most deadliest infectious disease, it's still underdiagnosed. Why is that.
Rov The main reason is that TB has such a diverse way of presenting. Most TB, in fact, probably about half TB is in people who don't yet feel sick enough to seek care. These are people who do not yet have full blown symptoms, and traditionally we've unfortunately relied on symptoms to trigger TB testing. But with projects such as this one, we are trying to test people earlier and earlier before they are even actually aware that they may have TB disease.
So what would and what would that look like? Then? How did how? How does that work?
So how that would look like? Is that you would move away from a symptom based approach to really a risk factor based approach. Right, So, regardless of how someone is feeling, if they are in a certain area, or they have maybe a clinical condition like diabetes or HIV that increases their risk of TV, you would evaluate them using a two step process. The first process is really just working out would that person actually benefit from TV testing?
And that is called a screening tool where you take someone who is healthy and you see, do they actually need that crucial yet really expensive follow on commatory testing or can they go about dead with their day and we can be confident they don't have TV. So this project is really aiming to target people in those risk groups to make sure that we get the scarce but expensive tests that we have applied to the right combination of people in an efficient manner.
For a while testing the wrong people at the wrong time. I suppose that's what you were saying just then, is that this is about getting to people before the point at which they're presenting with symptoms exactly.
This is one of the paradoxes in TB care is that most people who we test for TB do not actually have TV. But at the same time, we just never test and laugh people for TV. So we need to make TB testing itself more efficient, so make sure that we don't waste unnecessary resources testing people who would probably not benefit, and then at the same time use those freed up resources to expand the knit for TV
testing as wide as possible. But in people who have those risk factors that mean that the odds are finding someone are the highest that they can be.
You mentioned some people who are more predisposed than others. Who else might be on that list who is particularly at.
Risk for TV, So it depends, right, I think the most important thing is traditionally people who have some form of compromised immunity are at risk of TB. But crucially that is not just HIV. It can also be malnutrition. It can also be poor health for other reasons because of smoking or you're exposed to pollution. It can also be the fact that you maybe had TB before and that itself increases your risk for future episodes. So the
risk factors for TB are diverse. But having said that, I'm really much just emphasized is that TB, even though it's more likely to be found in certain people, there are many people who themselves lead act active, healthy, normal lives who actually start to come down with a cough and often TB is not suspected in those people because they don't fit that stereotypical picture. But they often turn out to have had full blown TV all along. So
there's nothing absolute with TV. It can affect everyone to different extents.
Yeah, South Africa is now part of this major international project. So what's involved in the study and what exactly is the main goal.
The main goal of the study is to catalyze on recent advances in ultimo ultrasound technology. So ultrasound technology which many of us are may be familiar with when it comes to you know, ultrasounds in trolleys on hospitals that are maybe used for looking at pregnancy. Those devices have become miniaturized and have become handheld. They can be moved over the body to acquire images to look for small
early signs in the anatomy of people for TV. And where AI comes in is that traditionally to acquire those ultrasilved images is a lot of information that's generated and there is a very high level of training and specialized expertise that is required to analyze that large amount of information, and that is quite frankly expertise, but we do not have available in South Africa at the scale that we
need it. So the AI comes in and being able to process that information as it is captured by these point of care ultrasolt machines to say that this person perhaps has a shadow on their legs, or there's evidence of tissue damage in their body, and whether or not that specific signal or that specific type of damage that is seen is itself indicative of TV And so this project will try and show that as a proof of concept and generate the evidence to say that this is
a technology or maybe it would not be a technology that really requires large scale adoption because it helps us to tist more people and importantly, it may not be constrained by the huge shortage of people with irrelevant training mast the health workers in South Africa that are in such a shortage.
So I was wondering how this could then, what would this sort of look like in local clinics, And I mean how soon this type of technology might be available to be rolled out in local clinics, But how would it help with with the challenges that we face here in South Africa.
So the visionire is that in approximately five years or so, anyone who's coming into a clinic primary care clinic like in other words, their local community clinic, anyone who is coming in there for any reason, the seas this ultrasound scan which can potentially be done through the clothes, and it can be done by someone with only a few
days of training. So perhaps while you're in the queue, while you're waiting for other clinical services, you could receive this scan of your body and that could tell you whether or not you need to be prioritized for other further testing. But that's the initial use case that we are targeting, where we are able to check anyone who's
coming into the facility. And then further down the line, we know that there's a lot of TV in communities that never comes into facilities and you can maybe deploy these devices in communities where people check the torso for signs or TV and use that to refer people on it.
It's really exciting stuff, isn't it. And I wonder, I mean, what if we were to look forward, what might be the long term hope for how guess AI. That's the the buzzword at the moment. How AI could transform TB care or even more broadly broader healthcare diagnostics, particularly in resource limited environments like ones that we see here in South Africa.
So this is a tool that is by no means going to replace doctors or right yeah, it's a tool to simply support them where people with very specialized expertise of skits. It also is something that almost democratizers access to new diagnostic technologies because that patient to benefit from for example, the advances in ultrasound does not need to go to a university hospital perhaps where a professor who is a specialist in ultrasound is based, where easily orchese
level of expertise is required to interpret that ultrasound. So it's allowed their access to new technologies by removing these bottlenix that we have in terms of human capacity and importantly, AI, even though itself is relatively complex, a lot of that
complexity is behind the scenes. In other words, there I itself can be in a very user friendly tool which can simplify what would otherwise be fairly complex decision making and also importantly help frontline health workers at faster with also greater accuracy.
RAP appreciate your time this afternoon, what a fascinating area of work and certainly looking forward to seeing how that is rolled out across South Africa. Speaking to Professor Granthron, professor in Clinical Microbacteriology and Epidemiology at Stelleinbosh University talking about this project that researchers at Stelleinbosh University are involved in leading really a global trial using artificial intelligence to improve tuberculosis diagnosis. As we heard there, the idea that
that could be rolled out at primary care level. Number of institutions across the continent and in Europe aiming to develop a tool that essentially is a handheld ultrasound device and which could help detect TB more quickly and more accurately, particularly in rural or low resource settings. What a fascinating conversation.