is once again through to the french open women's final, where she will play jasmine paolini on saturday. paolini beat 17—year—old russian mirra andreeva in straight sets. swiatek beat coco gauff, despite the american saving three match points in the second set. the world number one eventually closed out victory 6—2, 6—4. she could join monica seles and justine henin as the only women to win three straight french open women's titles during the open era. just before we go, the latest match in cricket's t20 world cup has gone down to a thrilling finish. the united states and pakistan both ened up on the same total after their 20 overs, so it's gone down to a super over. the us made 18 from their over. pakistan are just about to start their over. an exciting fiinish, and that's all the sport for now. you are watching the context. it is time for our our new weekly segment, ai decoded. welcome to ai decoded, our regular weekly appointment with all things artificial intellligence. if you have watched this series before, you will know by now that in each of our programmes we like to focus on particular a theme. last time out, we looked at the different approaches to regulation in the us and here in europe. this week, we are going to focus on health. you no doubt have read that al is already delivering huge breakthroughs in medical science. tonight, we will show you how the technology is being used to deliver enormous advances in cancer therapy. it's about improving automation, improving efficiency, improving the confidence to deliver higher doses in fewer fractions so we can reduce waiting lists, which is particularly important in the uk right now. but how much investment is there in this new technology, and are we taking full advantage? a report this week from digital health that the government has slashed in half the investment it is putting into the nhs ai lab. we will speak tonight to the former nhs director of ai innovation, who these days is using the al to streamline regulation so our public services can more quickly make use of what is on offer. so let me set the context for you. currently here in the uk, there are 7.5 million people waiting for treatment in england. and in spite of all best efforts, it's only slightly down on a peak of nearly 7.8 million last september. but clearly not far enough. we spent in 2022—23 — the last year of confirmed final nhs spending data — total health spending in england was over £180 billion. spending has increased by an average of 5.5% a year in real terms since 2019—20. it stands to reason that we need a better solution. more spending does not necessarily deliver better outcomes, and that is where ai promises so much. our resident expert, priya lakhani, ai educator and ceo of century tech, is with us, and this week has been out on the road, focusing on one of the big medical tech companies here in the uk. where have you been? i where have you been? i have been to gatwick. is that — where have you been? i have been to gatwick. is that it? _ where have you been? i have been to gatwick. is that it? to _ where have you been? i have been to gatwick. is that it? to give _ where have you been? i have been to gatwick. is that it? to give you a - gatwick. is that it? to give you a buduet gatwick. is that it? to give you a budget and _ gatwick. is that it? to give you a budget and he — gatwick. is that it? to give you a budget and he went _ gatwick. is that it? to give you a budget and he went to _ gatwick. is that it? to give you a budget and he went to gatwick? | gatwick. is that it? to give you a - budget and he went to gatwick? was not much of — budget and he went to gatwick? was not much of a _ budget and he went to gatwick? —" not much of a budget. he went to a company called elekta who focuses on radiotherapy in it was an absolutely extraordinary demonstration of the technology. what you were going to see is al technology being used to track a tumour in the body. if the about prostate cancer, when a patient has prostate, the tumour moves, right? so you need to be able to track the tumour while you were treating it because otherwise he would have to give quite a margin of error and potentially could be treating healthy tissue. so imagine technology that can use life mri scanning that you are about to see track the tumour movement and then if you saw in the headline there potentially take the time to treat a patient down and therefore have a huge impact on waiting lists. super exciting. huge impact on waiting lists. super excitina. �* , ., ., huge impact on waiting lists. super excitina. �*, ., ., one in two people get cancer in their lifetime, and around half of those will be treated by radiotherapy as part of their treatment. i'm here at elekta to understand how radiation therapy works and look at their game—changing ai technology. so, dee, you're the managing director. can you show me how conventional radiotherapy works? of course, priya. and what you feel about it? so i'm going tojump on this machine. just mind your head as you go back down. so imagine if you will you're the patient. the first thing we do is make sure that you're lying in the same position every day. mm—hm. and you can stay still pretty well. what we've got here is a linear accelerator, and we electrically generate a therapeutic beam of radiation that comes out here. now what's important is that when the radiation beam comes out, it needs to be shaped. so in the radiation head here, we have something called a multileaf collimator which comprises 160 little metal leaves that move in real time to shape to the irregular tumour volume. so you'd be set up under the machine. we've got traditional kv imaging on this system, and as the machine is treating, you can image and the machine moves round the patient to deliver the therapeutic dose, effectively painting it to the tumour volume. so, dee, we know that patients really try and stay still on these machines, but the tumour moves inside. how have you developed cutting—edge ai technology to be able to solve that problem and have this precision beam not affect healthy tissue? this is soft—tissue imaging, so what we have here is an mri system, which we've developed in collaboration with our clinical partners to combine with state—of—the—art delivery systems i explained in order to get soft—tissue imaging at time of treatment. combining these two technologies has enabled us to precisely deliver, shaping the beam very precisely, at the same time as using mri imaging to get soft—tissue, crystal—clear vision of anatomy in real—time. what i'd like to show you is what we're doing with that information, so here you can see a lung volume. so the dark area here is the lung. what the mri imaging does is in real—time, it takes soft—tissue images and reconstruct them in three dimensions. so you're looking here at movement in all dimensions — in and out, side to side, backwards and forwards. the machine—learning algorithm, and where this really comes into play is as a training phase whereby the patient is set up on the system and the algorithm is watching the delineated target volume. that's the red bit here that the doctors created in the treatment plan. yeah. that's where you want your radiation to deposit all of its dose. you want to avoid the healthy tissue, so the template that's been generated by the algorithm using machine—learning is delineated in blue as i've said, and what your seeing along here at the bottom is a little trace of the movement in three dimensions of that target volume. as soon as the target volume that you want to radiate goes outside of that preset window, you can see that radiation beam is automatically turned off. are we going to be solely relying 100% on the ai when it comes to the treatment? or is there some sort of safety mechanism that we have if something goes wrong? yeah, that's a great question. there are always trained operators sitting at this control desk. they're the radiographers. they can be the physicists depending on the complexity of the treatment. so you don't100% rely on it, but what's so cool is that from an efficiency point of view, i showed you the set—up in the other room where we set the patient up. you can automate really large parts of the workflow, and that's our intention in the future. what is the actual impact in terms of treatment times with this technology? well, one of the most exciting impacts is the confidence it gives to the clinician and the people delivering the treatment, because if you can know absolutely where your radiation beam is painting your dose of real—time, you can have the confidence to shrink the margin around the target. traditionally, radiation therapy has margins around the target, margins of safety, margins of error. yeah. if you can shrink that, you can reduce side effects. interestingly as well, if you have confidence about where the radiation beam is going, you can escalate the dose. so imagine, for example, prostate treatments that previously were treated in upwards of 30 treatments every day. imagine with that level of technology available to you and that confidence, you could actually reduce the number of treatments down to five or even two. what is the future of using ai technology in radiation therapy? i think it's about improving automation, improving efficiency, improving the confidence to deliver higher doses in fewer fractions so we can reduce waiting lists, which is particularly important in the uk right now, but also across the world because we want to give hope to everyone with cancer. and the only way you can do that is to provide access to care. mind blown. mind blown! that is tracking in real time, increasing dosage in real—time, cutting the number of appointments. dosage in real-time, cutting the number of appointments.- dosage in real-time, cutting the number of appointments. yeah, you can change — number of appointments. yeah, you can change the _ number of appointments. yeah, you can change the radiotherapy - number of appointments. yeah, you can change the radiotherapy plan . can change the radiotherapy plan daily, right? because you have a visual on how the tumour�*s also reacting to that precision beam. so if you're in the uk and we had that really brave lady a couple of days ago say to the prime minister, say to serve keir starmer, is the nhs broke in and talked about how her friend lost her life on the waiting list? the impact is huge. you friend lost her life on the waiting list? the impact is huge. you can go throu~h so list? the impact is huge. you can go through so many _ list? the impact is huge. you can go through so many more _ list? the impact is huge. you can go through so many more patients - list? the impact is huge. you can go through so many more patients in i through so many more patients in such less time cutting the waiting list. of the problem is regulation and what many out there won't know is you helped co—write the review for metric —— ai is you helped co—write the review for metric —— a! with sir patrick melanson the former chief scientific adviser. . , , . melanson the former chief scientific adviser. , ., ., . ., adviser. last year, the chancellor asked us to _ adviser. last year, the chancellor asked us to review _ adviser. last year, the chancellor asked us to review regulation - adviser. last year, the chancellor asked us to review regulation of. adviser. last year, the chancellorl asked us to review regulation of ai across all sectors and i'm looking forward to having him come on to talk about the nhs but one of the points we learned was because we did not have overall regulation of ai in a case—by—case basis in the uk, one of the issues meant the saw that the regulators themselves are not actually up skilled in this area to be able to think... with; actually up skilled in this area to be able to think. . ._ actually up skilled in this area to be able to think... why would they be, it's be able to think... why would they be. it's so — be able to think... why would they be, it's so new? _ be able to think... why would they be, it's so new? the _ be able to think... why would they be, it's so new? the incentive - be able to think... why would they be, it's so new? the incentive is i be, it's so new? the incentive is not there- _ be, it's so new? the incentive is not there- if— be, it's so new? the incentive is not there. if you _ be, it's so new? the incentive is not there. if you are a _ be, it's so new? the incentive is| not there. if you are a regulator, you are trying it will save so you are trying to de—risk. now we are trying to treat people more and go the other way. i know he will shed somewhat on while the nhs might be struggling to do this at the moment. five years ago, the then health secretary matt hancock launched something called the nhs ai lab. there was an initial £250 million investment to work on challenges in health and care, including early cancer detection, new dementia treatments and more personalised care. but reports this week are thatjust as the technology leaps forward, the budget is being slashed. joseph connor, who was previously the nhs director of ai innovation and is now the ceo of carefulai ltd, is with us. we will talk about what you are doing to streamline the process shortly, but what were the main challenges you faced when you were in the nhs when it came to adopting new a! innovation and technology? 0k, ok, so if we go back to when that was which — ok, so if we go back to when that was which was _ ok, so if we go back to when that was which was about _ ok, so if we go back to when that was which was about 2017—2018,| ok, so if we go back to when that i was which was about 2017—2018, the challenges _ was which was about 2017—2018, the challenges at — was which was about 2017—2018, the challenges at that _ was which was about 2017—2018, the challenges at that time _ was which was about 2017—2018, the challenges at that time were - was which was about 2017—2018, the challenges at that time were not - challenges at that time were not 'ust challenges at that time were not just the — challenges at that time were not just the issue _ challenges at that time were not just the issue of _ challenges at that time were not just the issue of regulation. - challenges at that time were not just the issue of regulation. it. challenges at that time were not i just the issue of regulation. it was a relatively— just the issue of regulation. it was a relatively new _ just the issue of regulation. it was a relatively new area _ just the issue of regulation. it was a relatively new area of— just the issue of regulation. it wasj a relatively new area of awareness for the _ a relatively new area of awareness for the nhs, — a relatively new area of awareness forthe nhs, so— a relatively new area of awareness for the nhs, so there _ a relatively new area of awareness forthe nhs, so there is— a relatively new area of awareness for the nhs, so there is quite - a relatively new area of awareness for the nhs, so there is quite a i a relatively new area of awarenessj for the nhs, so there is quite a lot of difficult — for the nhs, so there is quite a lot of difficult if — for the nhs, so there is quite a lot of difficult if you're _ for the nhs, so there is quite a lot of difficult if you're able _ for the nhs, so there is quite a lot of difficult if you're able to - of difficult if you're able to understand _ of difficult if you're able to understand what _ of difficult if you're able to understand what it - of difficult if you're able to understand what it is. - of difficult if you're able to understand what it is. andj of difficult if you're able to - understand what it is. and there is to a large — understand what it is. and there is to a large degree _ understand what it is. and there is to a large degree a _ understand what it is. and there is to a large degree a lot— understand what it is. and there is to a large degree a lot of- understand what it is. and there is| to a large degree a lot of confusion as to _ to a large degree a lot of confusion as to the _ to a large degree a lot of confusion as to the value. _ to a large degree a lot of confusion as to the value, but _ to a large degree a lot of confusion as to the value, but when - to a large degree a lot of confusion as to the value, but when you - to a large degree a lot of confusionj as to the value, but when you raise awareness — as to the value, but when you raise awareness of — as to the value, but when you raise awareness of case _ as to the value, but when you raise awareness of case studies - awareness of case studies like you've — awareness of case studies like you've just— awareness of case studies like you've just done, _ awareness of case studies like you've just done, it _ awareness of case studies like you've just done, it becomes. awareness of case studies like - you've just done, it becomes obvious there _ you've just done, it becomes obvious there is— you've just done, it becomes obvious there is a _ you've just done, it becomes obvious there is a role — you've just done, it becomes obvious there is a role for— you've just done, it becomes obvious there is a role for things _ you've just done, it becomes obvious there is a role for things that - you've just done, it becomes obvious there is a role for things that can - there is a role for things that can provide _ there is a role for things that can provide predictive _ there is a role for things that can provide predictive analytics - there is a role for things that can| provide predictive analytics about what technologies— provide predictive analytics about what technologies can _ provide predictive analytics about what technologies can be - provide predictive analytics about what technologies can be used i provide predictive analytics about. what technologies can be used and applied _ what technologies can be used and applied to — what technologies can be used and applied to health _ what technologies can be used and applied to health care. _ what technologies can be used and applied to health care. i— what technologies can be used and applied to health care. i think- what technologies can be used and applied to health care. i think onel applied to health care. i think one of the _ applied to health care. i think one of the challenges _ applied to health care. i think one of the challenges that _ applied to health care. i think one of the challenges that i— applied to health care. i think one of the challenges that i faced - applied to health care. i think one of the challenges that i faced at l of the challenges that i faced at that time, — of the challenges that i faced at that time, which _ of the challenges that i faced at that time, which was _ of the challenges that i faced at that time, which was we - of the challenges that i faced at that time, which was we were l of the challenges that i faced at - that time, which was we were trying to get— that time, which was we were trying to get more — that time, which was we were trying to get more people _ that time, which was we were trying to get more people in _ that time, which was we were trying to get more people in the _ that time, which was we were trying to get more people in the nhs - that time, which was we were trying to get more people in the nhs to. to get more people in the nhs to actually— to get more people in the nhs to actually he — to get more people in the nhs to actually be the _ to get more people in the nhs to actually be the originators - to get more people in the nhs to actually be the originators of- to get more people in the nhs to actually be the originators of the| actually be the originators of the ai, actually be the originators of the al, it _ actually be