This website is intended for healthcare professionals only.

Hospital Healthcare Europe
Hospital Pharmacy Europe     Newsletter          

Press Releases

Take a look at a selection of our recent media coverage:

AI study reveals prostate cancer consists of two distinct subtypes

13th March 2024

Prostate tumours evolve in two distinct disease types, a new artificial intelligence (AI) study by the Pan Prostate Cancer Group has revealed, which may lead to better diagnosis and tailored treatments in future.

This international consortium of researchers, led by the universities of Oxford and Manchester, analyses genetic data from thousands of prostate cancer samples across nine countries and is aiming to develop a genetic test that, when combined with conventional staging and grading, can provide a more precise prognosis for each patient, allowing tailored treatment decisions.

For this particular study, they used AI neural networks to process data on changes in the DNA of prostate cancer samples from 159 patients in the UK.

Samples were taken after radical prostatectomy in patients with intermediate or lower risk prostate adenocarcinoma who were otherwise treatment naive.

Published in the journal Cell Genomics, the results generated an evolutionary tree that took multiple routes to two ‘evotypes’, or subgroups, of prostate cancer.

These two prostate cancer subtypes were confirmed by using two other mathematical approaches applied to different aspects of the data, as well as being validated in other independent datasets from Canada and Australia.

It is hoped that these findings could save thousands of lives in future by revolutionising how prostate cancer is diagnosed and providing tailored treatments to individual patients according to a genetic test, which will also be delivered using AI, the researchers said.

Professor Colin Cooper, professor of cancer genetics at the University of East Anglia’s Norwich Medical School, who was involved in the research, said: ‘This study is really important because until now, we thought that prostate cancer was just one type of disease. But it is only now, with advancements in artificial intelligence, that we have been able to show that there are actually two different subtypes at play.

‘We hope that the findings will not only save lives through better diagnosis [of prostate cancer] and tailored treatments in the future, but they may help researchers working in other cancer fields better understand other types of cancer too.’

Prof David Wedge, lead researcher and professor of cancer genomics and data science at the Manchester Cancer Research Centre, added: ‘This realisation is what enables us to distinguish the disease types. This hasn’t been done before because it’s more complicated than HER2+ in breast cancer, for instance.

‘This understanding is pivotal as it allows us to classify tumours based on their evolutionary trajectory rather than solely on individual gene mutations or expression patterns.’

As well as this project in prostate cancer, AI is being used in a number of new clinical studies into disease areas such as cardiovascular disease.

And neural networks in particular have previously been used, for example, in an AI study of Parkinson’s disease, which revealed four subtypes of the disease.

AI clinical trial aims to reduce blood cultures in emergency departments by 30%

27th February 2024

A clinical trial at Amsterdam UMC is aiming to show that an artificial intelligence (AI) algorithm can reduce the number of blood cultures taken in emergency departments (EDs) worldwide by almost a third.

The algorithm takes data from the electronic health record of patients with suspected sepsis, such as body temperature and other standard lab results that provide information about possible infections, to identify patients with a low risk of infection or inflammation.

The clinician uses this prediction, together with their own observation, to then consider whether a blood culture is required.

Dr Prabath Nanayakkara, professor of internal medicine at Amsterdam UMC, whose work focuses on increasing efficiency in acute care, said: ‘Of all the blood cultures that are done in the emergency room, only 15% indicate that something is wrong, and it’s even more interesting if you take a closer look at those positive results. Then about half of the positive blood cultures turn out to be false positives. We’re used to doing it this way but that doesn’t mean the analysis is necessary. Certainly not when you look at the numbers.’

The new clinical trial – known as the ABC study – will test the algorithm in practice and is one of the first randomised controlled trials worldwide to consider such an algorithm in acute care.

It was previously developed by Amsterdam UMC’s acute AI team and extensively tested and validated nationally and internationally, the team said.

The AI’s prediction is now built into the electronic patient record at Amsterdam UMC, so the healthcare provider is shown this prediction on the computer screen when requesting a blood culture in the intervention group, which the researchers say is a ‘unique’ approach.

‘With tailor-made advice for each patient, we expect to drastically reduce unnecessary cultures, hopefully by up to 30%,’ said Professor Nanayakkara.

‘If this study is successful, we will not only reduce the number of blood cultures – and therefore the costs – but also ensure that the number of false positive blood tests decreases and thus, no patients will be treated unnecessarily.

‘False positive results lead to uncertainty among patients and doctors, extra procedures, excessive treatment with antibiotics and, longer hospital admissions and even higher mortality in that group.’

He added: ‘We shouldn’t do things in healthcare that aren’t necessary [and] this is pre-eminently an issue in which AI can be used. In doing so, we are showing that AI can really change healthcare.’

In October 2023, a study presented at the European Society of Emergency Medicine congress led to calls for increased sepsis awareness as two of the four internationally recommended sepsis screening tools used by emergency medical services were deemed inadequate for recognising the condition.

And in February 2024, updated guidance from the National Institute for Health and Care Excellence on identifying and managing sepsis in over-16s recommended better targeting of antibiotics for suspected sepsis.

AI and genetics underpin project to speed up CVD diagnosis and personalise treatment

16th February 2024

A new international project aiming to use artificial intelligence (AI) and genomics data to personalise therapies for patients with cardiovascular disease (CVD) has been announced.

The Next Generation Tools for Genome-Centric Multimodal Data Integration in Personalised Cardiovascular Medicine (NextGen) project aims to build AI-supported novel and synergistic tools to enable portable multimodal, multiomic and clinically oriented research in high-impact areas of cardiovascular medicine.

The tools will benefit researchers, innovators and healthcare professionals by identifying and overcoming health data linkage barriers in exemplar cardiovascular use cases that are complex or intractable with existing technology.

The ultimate goal is to provide faster diagnosis and better, more personalised treatments for patients while capitalising on increasing innovations and trends in AI technology.

The NextGen project will be delivered by a 21-member consortium of academic, clinical, technical and commercial partners from across Europe and the US, including the European Society for Cardiology, and led by University Medical Center (UMC) Utrecht and Queen Mary University of London.

Project coordinator Professor Pim van der Harst, interventional cardiologist and head of the department of cardiology at the UMC Utrecht, said: ‘No two people are exactly the same, and so it makes sense that each person needs a slightly different strategy to optimise their health. Personalised medicine is, therefore, the way forward for preventing heart disease, speeding up diagnosis, and monitoring and treating people with CVD.

‘To develop individualised therapies, we need to compile as much information as possible about individuals, and that’s where NextGen comes in. The unique picture we generate will then form the basis for improving cardiovascular health and wellbeing.’

Several real-world pilots will demonstrate the effectiveness of NextGen tools and will be integrated in the NextGen Pathfinder network of five collaborating clinical sites as a self-contained data ecosystem and comprehensive proof of concept.

The work will complement the ‘1+ Million Genomes’ initiative, which aims to enable secure access to genomics and clinical data across Europe, and the European Health Data Space – a European Commission governance framework for the safe and secure exchange, use and reuse of health data.

Consortium member Professor Panos Deloukas, professor of cardiovascular genomics and dean for Life Sciences at Queen Mary University of London’s William Harvey Research Institute, added: ‘This is a tremendous opportunity and a challenge we have in building the right toolbox that will allow [us] to unite CVD patient data across Europe and implement precision medicine to improve cardiovascular healthcare.’

The NextGen project has received €7.6 million from the EU’s Horizon Europe programme.

In August 2023, a genetic study revealed how the use of clopidogrel in British patients of south Asian ancestry appears to be less effective at preventing recurrent myocardial infarction than in those of European descent.

And earlier in 2023, single cell and spatial genomics combined with computational techniques were used to develop a comprehensive Heart Cell Atlas to better understand the heart and how it responds to treatments.

Are blood tests, robotics and AI the secrets to earlier lung cancer diagnosis?

4th January 2024

With the results of the lung cancer screening SUMMIT study expected imminently, Helen Gilbert caught up with consultant respiratory physician Dr Neal Navani to discuss this research, promising new innovations in lung cancer diagnostics and what they might mean for the future of lung cancer care.

As Cancer Research UK’s Lung Cancer Centre of Excellence, University College London and University College London Hospital (UCLH) have been at the forefront of lung cancer innovations, pioneering diagnostic modalities such as endobronchial ultrasound.

This diagnostic focus is particularly pertinent as lung cancer is Europe’s biggest cancer killer, with 380,000 deaths across the continent in 2020 – a fifth of all cancer deaths.

In England, more than 60% of lung cancer patients are diagnosed at either stage three or four, and this late diagnosis is a frustration for Dr Neal Navani, lead consultant respiratory physician for lung cancer services at UCLH, as he says cure rates can be as high as 80-90% for patients whose small, early-stage lung cancer is detected.

Dr Navani, who is also the clinical lead of the UK National Lung Cancer Audit and clinical director for the Centre for Cancer Outcomes at the North Central London Cancer Alliance, has long been involved in pioneering research at UCLH to improve early detection and diagnosis.

And recent projects suggest there are further innovations on the horizon that have the potential to improve patient outcomes.

The SUMMIT study

In May 2023, the largest lung cancer screening study of its kind in the UK drew to a close.

The four-and-a-half-year SUMMIT study was a collaboration between researchers from UCLH, University College London (UCL), the National Institute for Health Research, UCLH Biomedical Research Centre and GRAIL – a US healthcare company focused on the early detection of cancer.

Their aim was to identify lung cancer early among at-risk Londoners and support the development of a new blood test for the early detection of lung and multiple cancer types.

More than 13,000 people aged 55-77 from north and east London who had a significant smoking history were offered a blood test and a low-dose CT scan of their lungs. They were followed up at three months or immediately if a cause for concern was identified.

Dr Navani describes the research – results of which are expected imminently – as ‘a really fantastic, rich data set on which we can look to answer a lot of questions about detecting cancer early’.

He is particularly interested in developing a model that incorporates PET-CT scans to predict malignancy in screen-detected lung nodules. Often these appear like freckles on the lung, which may or may not be cancerous.

The challenge, he says, is working out whether they are malignant or benign, and currently this is done using a risk calculator developed in 2005.

It involves an injection of radioactive sugar before a PET-CT scan to see whether the nodule – or anything else for that matter – takes up the sugar. This then correlates with the risk of malignancy.

However, Dr Navani describes the current tool, which was developed in 2005, as out of date and prone to underestimating the risk of cancer in lung nodules.

Updated lung cancer risk and diagnosis tools

Data from the SUMMIT trial are set to be used to develop and test a new risk calculator that takes into account more than 10 factors including family history, smoking and the size and appearance of nodules. It aims to accurately predict the chance of a nodule being cancerous.

‘We’re able to see whether sugar is taken up by that nodule in the lung – the idea being that small cancers use up more sugar than nodules that are not due to cancer,’ Dr Navani says.

‘Data for that work are being collected and developed. We’re pulling together data through other trials doing a similar thing and hopefully we’ll be able to clarify the role of PET-CT scanning for nodules in the next two years.’

The risk calculator will be compared against the existing model as well as others that do not include PET-CT scanning.

If found to be more accurate, the potential benefits are numerous and may include fewer patient investigations at lower cost, earlier treatment and reduced anxiety for those called in, Dr Navani explains.

UCL researchers are also using blood samples from the SUMMIT study to evaluate a blood test that can diagnose tumours earlier and detect 50 types of cancer, including lung cancer, with high accuracy.

Developed by GRAIL and an international team of researchers co-led by UCL, the test looks for tell-tale chemical changes to bits of genetic code – cell-free DNA – that leak from tumours into the bloodstream.

It was developed using artificial intelligence (AI) after researchers fed data on methylation patterns from the blood samples of thousands of cancer patients into a machine learning algorithm. It is said to identify many types of cancer, including bowel, ovarian and pancreatic, and can diagnose in which tissue the cancer originated with 96% accuracy.

Revolutionary robotics

But the potential of technology in bolstering cancer diagnosis doesn’t stop at AI. Another promising area of innovation is robotics.

Dr Navani is intrigued by the potential of this kind of diagnostic ability, and he is aware of robotic techniques that will be ‘the subject of research over the next year or two’.

He says: ‘We need to understand the cost effectiveness of robotic diagnosis of lung nodules. It’s potentially exciting.’

Earlier this year NHS clinicians at the Royal Brompton and St Bartholomew’s Hospital in London began a clinical study trialling a robotic-assisted bronchoscopy system.

Each hospital site is aiming to recruit around 50 patients with small lung nodules located in areas that are challenging to reach via traditional bronchoscopy.

The system combines software, robotic assistance and a flexible catheter with a camera to create a 3D roadmap of the lungs – much like a car’s sat-nav.

Doctors are directed to deep and hard-to-reach areas in each of the 18 segments of the lung, with the aim of removing tissue samples for biopsy with greater precision and accuracy.

The benefits of diagnosing a lung nodule accurately with a tiny camera could ‘open up a world of possibilities in terms of drug delivery, or ablation [to destroy cancerous nodules] in a controlled and accurate way,’ says Dr Navani. ‘I think in the next five to 10 years we’re going to see novel diagnosis and treatment options for our patients with early-stage lung cancer in particular.’

Endobronchial ultrasound

Another key development Dr Navani anticipates is the continued and increasing importance of collaboration, particularly when it comes to technology.

Endobronchial ultrasound (EBUS), one of the biggest innovations in respiratory medicine over the last 15 years, evolved from endoscopic ultrasound used in other clinical areas.

EBUS was trialled in the early 2000s by the UCLH research team, of which Dr Navani was a leading player, and uses a bronchoscope with a light, camera and integral ultrasound scanner to produce a detailed image inside the chest.

It enables doctors to take targeted needle biopsies of any enlarged lymph nodes and suspicious lesions while avoiding areas such as blood vessels.

Prior to this, patients at-risk of lung conditions required incisions to the chest under general anaesthetic, resulting in hospital stays and the possibility of complications or even death.

The arrival of EBUS in clinical practice in 2007 meant the diagnostic procedure could be performed on outpatients in under 30 minutes, with patients able to leave just one or two hours later.

‘It’s a very safe technique [and] in the last 10-15 years it’s really become a mainstay of diagnosis in respiratory medicine,’ Dr Navani acknowledges. ‘It started off very slowly but now in the UK there are 140 centres that are doing this technique and it’s been adopted globally for diagnosing lung conditions.’

Dr Navani believes the adaption of tools and techniques used in other clinical fields will continue to play a pivotal role in the advancement of lung cancer diagnostics and treatment. He points out, for example, that tumour ablation, which is used to treat lung and liver cancer, is now happening at a research stage for pancreatic cancer.

And this collaboration doesn’t just extend across clinical specialities. Imaging and information providers, including the likes of Fujifilm, also serve a vital purpose by providing increasingly innovative imaging solutions.

In June 2023, NHS England announced the national rollout of a targeted lung cancer screening programme to help detect cancer sooner and speed up diagnosis.

The rollout followed a successful pilot phase in which lung cancer scanning trucks carrying out on-the-spot chest scans operated from convenient locations such as football stadiums, supermarket car parks and town centres.

In September, NHS England announced that more than one million people had been invited for a lung cancer check via the scheme and almost 2,400 cancers had been caught – an impressive 76% of which were diagnosed at stage one or two.

‘That’s going to hopefully need innovative imaging solutions, particularly low-dose scanners, and I think we need to work with industry in terms of the use of artificial intelligence to help with the reporting of those scans,’ Dr Navani says.

Innovative diagnostic imaging techniques are certainly in development, and Dr Navani sees huge potential in new technologies for treating patients, too.

‘In terms of delivering novel therapies, in the future there may be a role for delivering drugs directly into the lungs, the pleural space or endobronchially, lymph nodes, or primary lung lesions,’ he says.

Addressing unmet needs in lung cancer

Dr Navani describes working in a hospital that is attached to a world-class university as ‘fantastic’ because it grants access to ‘extraordinary expertise’ spanning science, sociology, data science, computer science and engineering.

‘The research into lung cancer at UCL is really incredibly broad and, dare I say it, world leading, right the way through the basic science, biology and understanding how cancer develops and spreads and changes over time… to understanding the societal impact, equality and equity of care,’ he says.

According to Dr Navani, there appears to be a big difference in the outcomes of lung cancer patients based on socio-economic status.

‘We’ve really tried to address this in the National Cancer Audit, but it remains a significant challenge,’ he says. “A lot of this comes down to local resources… access to healthcare, equality and subsequent diagnosis and treatment in a timely fashion.’

Another major unmet need, Dr Navani says, is the 15% of patients with lung cancer who have never smoked and it’s here that ‘urgent research is needed’.

‘Given the high burden of lung cancer care, that’s a significant number of people – if you consider [non-smoking-related lung cancer] as a cancer in its own right it would be the seventh most common cause of cancer death,’ he says.

‘We’re really starting to get to grips with lung cancer in smokers but we are still at the early stages of understanding why people who’ve never smoked develop lung cancer. It would be important to predict who these people might be so that we can identify them at an earlier stage so hopefully their outcome will be better.’

Looking to the future

The most pressing issue facing the NHS is limited resources, according to Dr Navani.

‘We simply don’t have enough scanners, radiologists, or space to do bronchoscopies,’ he states. ‘We’ve talked a lot about innovation but actually the most important thing that can be done to improve lung cancer care is for each hospital and primary care setting to have the appropriate resources to deliver what we know is already appropriate care, to drive out inequalities and drive everybody up to the best possible standards.’

While the future of funding for lung cancer care in the UK remains in flux, one thing is for certain: the research, expertise and drive to support the early diagnosis of patients remains, and Dr Navani’s commitment to supporting patients through innovative routes is stronger than ever.

EADV: Improvement in AI skin cancer detection as software identifies all melanoma cases

13th October 2023

The use of artificial intelligence (AI) software has shown a 100% detection rate for melanoma and saved over 1,000 face-to-face secondary care consultations during a 10-month period, according to a study presented at the recent European Academy of Dermatology and Venereology (EADV) Congress 2023.

The study was able to able to correctly detect all 59 cases of suspected melanoma between April 2022 and January 2023, as well as 99.5% of all skin cancers (189/190 cases) and 92.5% of pre-cancerous lesions (541/585).

The software assessed 22,356 patients with suspected skin cancers using three versions of an AI software. The first version tested in 2020-21 had an 85.9% detection rate for melanoma (195/227), 83.8% for all skin cancer (903/1,078) and 54.1% for pre-cancerous lesions (496/917).

Lead author Dr Kashini Andrew, a specialist registrar at University Hospitals Birmingham NHS Foundation Trust, commented: ‘The latest version of the software has saved over 1,000 face-to-face consultations in the secondary care setting between April 2022 and January 2023, freeing up more time for patients that need urgent attention.‘

The research team noted that the data is ‘incredibly encouraging‘, however, co-author and colleague, Dr Irshad Zaki, consultant dermatologist, said: ‘We would like to stress that AI should not be used as a standalone tool in skin cancer detection and that AI is not a substitute for consultant dermatologists.‘

Evidence of the need for appropriate clinical oversight was shown among the basal cell carcinoma cases as a single case was missed by the AI tool and later identified at a second read by what the researchers termed ‘a dermatologist “safety net“‘.

Dr Kashini Andrew added: ‘This study has demonstrated how AI is rapidly improving and learning, with the high accuracy directly attributable to improvements in AI training techniques and the quality of data used to train the AI.

‘The role of AI in dermatology and the most appropriate pathway are debated. Further research with appropriate clinical oversight may allow the deployment of AI as a triage tool. However, any pathway must demonstrate cost-effectiveness, and AI is currently not a standalone tool in dermatology. Our data shows the great promise of AI in future provision of healthcare.’

This supports the findings of previous studies including a 2022 systematic review in which the researchers concluded that ‘the performance of artificial intelligence in melanoma is satisfactory and the future for potential applications is enormous‘.

Need for patient education on AI in healthcare to build trust revealed in new survey

9th October 2023

Almost two thirds of patients are comfortable with using healthcare settings that use artificial intelligence (AI), but only if they are familiar with the technology, according to a new survey from GlobalData.

The results revealed that 60% of patients who were familiar with AI were either very or quite comfortable with attending an AI-enabled healthcare setting. When it came to people who weren’t familiar with the technology, this level of comfort fell to just 7% of patients.

A lack of in-person interaction was the top patient concern associated with physicians using AI in clinical practice, and most patients felt more comfortable with physicians using it to automate administrative tasks compared to directing patient care.

Faster healthcare delivery and mitigation of healthcare staff shortages were identified as the main benefits associated with AI use in clinical practice.

The survey data also reveals that those aged 18-55 years were more likely to be familiar with AI than those aged 56 years and over, with more than 50% of the younger group rating their knowledge as moderately or very familiar.

Commenting on the important and evolving use of AI to detect image-based diseases such as cancer, Urte Jakimaviciute, senior director of market research at GlobalData, said: ‘Together with the development of a robust regulatory framework, it is imperative to prioritise patient education regarding the technology.

‘This education should aim to enhance comprehension of AI’s utilisation, its potential advantages, and associated adoption risks, ultimately fostering increased trust in AI. Enhanced knowledge empowers individuals to make informed decisions and mitigate biases linked to this technology.’

Similar issues around trust have been identified in previous studies. For example, a 2021 study looking at patient apprehensions about the use of AI in healthcare, published in the journal NPJ Digital Medicine, identified concerns relating to its safety, threats to patient choice, potential increases in healthcare costs, data-source bias and data security.

These authors also concluded that ‘patient acceptance of AI is contingent on mitigating these possible harms’.

The new GlobalData survey, Thematic Intelligence: AI in Clinical Practice – Patient Perspective 2023, saw 574 patient respondents from the US, France, Germany, Italy, Spain, the UK, Japan, Brazil, Canada, India and Mexico.

The patients were diagnosed with conditions such as heart diseases, diabetes, multiple sclerosis, cancer, chronic respiratory conditions, rheumatoid arthritis, psoriasis and inflammatory bowel disease. They were surveyed between July and August 2023.

Artificial intelligence technologies could speed up contouring in radiotherapy

24th August 2023

Artificial intelligence technologies could be utilised to reduce the time needed for contouring during radiotherapy treatment planning, according to draft guidance from NICE.

In June 2023, NICE guidance suggested lower intensity and shorter duration radiotherapy in breast cancer did not impact on breast cancer-related mortality or disease recurrence and therefore served as a suitable alternative to the current standard care.

Now, related draft guidance proposes that artificial intelligence (AI) technologies have the potential to help healthcare professionals to produce contours more quickly, which could improve workflow efficiency.

AI technologies and contouring

Evidence made available to NICE’s independent medical technologies advisory committee indicates how AI technologies generally produce similar quality contours of organs at risk as those carried out manually, with most only needing minor edits.

Currently, following a CT or MRI scan, a radiographer has to manually contour an image to highlight organs at risk of radiation damage, lymph nodes and the site of the cancer. The dose of radiotherapy is not only calculated to target the tumour site but also to prevent organs and healthy tissue from being damaged.

Clinical experts advising the independent NICE committee estimated a time saving of 10-30 minutes per plan, depending on the amount of editing needed, while the clinical evidence presented to the committee suggests it may range between three and 80 minutes of time saved per plan.

Sarah Byron, programme director for health technologies at NICE, said: ‘NHS colleagues working on the front line in radiotherapy departments are under severe pressure with thousands of people waiting for scans.

‘The role imaging plays in radiotherapy treatment planning is quite pivotal, so recommending the use of AI technologies to help support treatment planning alongside clinical oversight by a trained healthcare professional could save both time and money.‘

Health and social care secretary Steve Barclay added: ‘It’s hugely encouraging to see the first positive recommendation for AI technologies from a NICE committee, as I’ve been clear the NHS must embrace innovation to keep fit for the future.

‘These tools have the potential to improve efficiency and save clinicians’ thousands of hours of time that can be spent on patient care. Smart use of tech is a key part of our NHS Long Term Workforce Plan, and we’re establishing an expert group to work through what skills and training NHS staff may need to make best use of AI.‘

AI tool aids heart attack diagnosis speed and accuracy, say researchers

30th May 2023

Heart attack diagnosis could be achieved quicker and more accurately via the use of a new artificial intelligence algorithm developed by the University of Edinburgh.

Tested on 10,286 patients in six countries, the algorithm – named CoDE-ACS – was able to rule out a heart attack in more than double the number of patients compared to guideline-recommended pathways, and with an accuracy of 99.6%.

The tool was also found to identify those whose abnormal troponin levels were due to a heart attack rather than another condition.

It performed well regardless of age, sex or pre-existing health condition, which the authors say reduces the potential for misdiagnosis and inequalities across the population.

‘Enormous potential

Funded by the British Heart Foundation (BHF) and the UK’s National Institute for Health and Care Research, the study was published in the journal Nature Medicine.

Its lead author, Professor Nicholas Mills, BHF professor of cardiology at the Centre for Cardiovascular Science, University of Edinburgh, said: ‘For patients with acute chest pain due to a heart attack, early diagnosis and treatment saves lives. Unfortunately, many conditions cause these common symptoms, and the diagnosis is not always straight forward. Harnessing data and artificial intelligence to support clinical decisions has enormous potential to improve care for patients and efficiency in our busy emergency departments.’

CODE-ACS was developed using data from 10,038 patients in Scotland who had arrived at hospital with a suspected heart attack. It uses routinely collected patient information, such as age, sex, ECG findings and medical history, as well as troponin levels, to predict the probability that an individual has had a heart attack. The result is a probability score from 0 to 100 for each patient.

Clinical trials are now underway in Scotland to assess whether the AI tool can help doctors reduce pressure on overcrowded emergency departments.

Tailoring diagnosis and treatment pathways for complex lung disease

11th May 2023

Dr Anjali Crawshaw shares insights into her work on idiopathic pulmonary fibrosis and how AI may be able to extend the survival rates of people living with complex lung disease.

University Hospitals Birmingham NHS Foundation Trust has recently launched what it understands to be a world-first project aiming to improve the survival rates of people living with fibrotic lung disease, including idiopathic pulmonary fibrosis (IPF).

Lung disease clinicians and researchers will use sophisticated algorithms developed by the Cambridge medical data company Qureight to read patient lung scans. The goal is to help improve understanding of fibrotic lung diseases and make more accurate and earlier diagnoses, facilitating earlier treatment.

In addition, the project will analyse significant volumes of data from ethnic minority groups to address health inequalities in the system and allow for a tailored approach to treatment for these individuals.

Dr Anjali Crawshaw is consultant respiratory physician lead, Birmingham Interstitial Lung Disease Unit, University Hospitals Birmingham NHS Foundation Trust. Here, she explains why complex inflammatory and fibrotic lung diseases – her area of specialism – can be challenging to manage in clinic and how the research will help unlock valuable insights from existing patient data.

What is idiopathic pulmonary fibrosis?

Idiopathic pulmonary fibrosis (IPF) is the most common type of fibrotic lung disease that affects roughly 50 in every 100,000 people. It causes the lungs to become scarred, leading to cough, severe breathlessness and progressive respiratory failure. It currently has a survival time worse than most cancers.

Why is inflammatory fibrotic lung disease so difficult to diagnose?

It can be difficult to classify the disease due to the complex and varied patterns seen. In addition, deciding if this is responding to treatment, is stable or getting worse can be challenging. It is currently necessary for specialist radiology doctors to analyse CT scan images of lungs as part of the diagnosis and monitoring process, but the process can be open to interpretation bias. One of the widely accepted and published difficulties in this field, is that if you have multiple doctors looking at the same scan, you won’t always get the same answer. One of the advantages of having good quality computer standardised algorithms is that you will.

In addition to a lung doctor specialising in such lung conditions, our multidisciplinary teams involve radiologists, pathologists, specialist nurses and pharmacists who currently make a diagnosis based on the patient history, blood tests and CT imaging. In more complex cases, invasive investigations such as a telescope test into the lungs may be required, which is not without risk. This allows a biopsy to be taken, although sometimes a more invasive biopsy is still required to make a clear diagnosis. Improved imaging techniques have reduced the number of biopsies required.

There’s a shortage of specialists, which can make this process slow and difficult.

What are the limitations with the current healthcare dataset?

One of the problems in healthcare in general is that a lot of our data comes from white people of European descent. There’s partly an assumption that this is the data set we’ve got, and everybody’s healthcare can be extrapolated from this.

That’s not quite right, but we don’t know how that’s not quite right. For example, the lung function of a person of Indian origin born in the US may be better than a relative the same age and build born in India. We don’t really know why that is. There are lots of sociological and environmental factors that are at play here, and we don’t understand what those are.

Idiopathic pulmonary fibrosis – just one of a huge number of fibrotic lung diseases – is another example where unconscious bias may come into play. The ‘typical’ IPF patient is a 70-year-old white man, so a patient from an ethnic minority background presenting with the same symptoms may be at risk of delayed diagnosis.

I look after a lot of people with sarcoidosis who can also develop fibrotic lung disease. They are often much younger and of working age. There’s a greater prevalence in people who are black, and their disease is often more severe, but we just don’t fully understand why that is – the data is not there.

How will the AI tool work for diagnosing lung disease?

All the patients who come through our service get CT scans as part of their diagnostic process. The study algorithm will combine the data from patient scans – for example, their lung and airway volume – with lung function data from tests, blood results and demographic records.

This information will be securely and anonymously processed to deliver insights into the presentation, development and progression of IPF. We will look specifically at the similarities and differences for ethnic minority patients.

Why is Birmingham so uniquely placed to collect this patient data?

We’re a young, super-diverse city. We’re home to people from 187 different nationalities, and more than half the population is from an ethnic minority, so we are perfectly placed to be leading on this work.

Part of the reason we’re missing this data is because you need a certain amount of money and funding to conduct studies. If research is happening in rich countries that have good access to CT imaging that will, by virtue, skew the population of patients in the database as you’re using data from the patients in front of you. Places in other parts of the world have the expertise and drive to do the research, but they don’t have the funding or access to good CT imaging so it doesn’t get done. 

This partnership with Qureight marks a very significant moment for our team. Patient data that truly reflects the unique diversity of Birmingham’s population will be invaluable to the planning and delivery of more equitable patient care – not just in Birmingham and the UK but internationally.

The role of AI in transforming lung cancer care 

Dr Sumeet Hindocha has a passion for artificial intelligence, with his work focusing on radiomics and deep learning in lung cancer. He speaks to Hospital Healthcare Europe about his latest research and the uses and considerations of AI-enabled diagnostics in medicine.

Dr Sumeet Hindocha is a clinical oncology specialist registrar at The Royal Marsden NHS Foundation Trust and a researcher in artificial intelligence (AI). He is currently leading the trust’s OCTAPUS-AI study to investigate how this technology can help identify which patients with non-small cell lung cancer are at higher risk of recurrence.

Why are you interested in lung cancer and AI?

Lung cancer is the leading cause of cancer deaths worldwide. Non-small cell lung cancer (NSCLC) is behind almost 85% of cases and is often curable when detected early enough. Radiotherapy is a key treatment modality for it, but, unfortunately, recurrence can occur in over a third (36%) of patients treated with radiotherapy.

We know that the earlier we detect recurrence the better the outcomes generally are for patients. It means we can get them on to the next line of treatment or offer the best support as soon as possible. This could reduce the impact the disease has on their lives and help patients live longer.

The aim of our study is to see whether AI could help identify the risk of cancer returning in these patients using CT scans. The study addresses the National Institute of Healthcare and Clinical Excellence’s call for further research into using prognostic factors to develop risk-stratification models to inform optimal surveillance strategies after treatment for lung cancer.

Where does your enthusiasm for AI stem from?

Artificial intelligence has had a big impact in improving various aspects of our lives and work, from automating routine tasks to even things like the programmes recommended to us on Netflix or smart home devices like Siri or Alexa. What’s really exciting about its application in healthcare is its significant potential to improve patient outcomes and experience. We have a huge amount of data from imaging and electronic patient records that can be readily applied to AI. It gives us the ability to detect patterns of disease that would otherwise be difficult to uncover, to develop new drugs and even streamline how we deliver healthcare.

Who are you working with on the OCTAPUS-AI study?

Researchers from the Institute of Cancer Research, Imperial College London and the Early Diagnosis and Detection Centre, which aims to accelerate early diagnosis of cancer and is supported by funding from the Royal Marsden Cancer Charity and the National Institute for Health and Care Research. 

What did the first phase of the study involve?

We compared different models of machine learning (ML) – a type of type of AI that enables computer software to learn complex data patterns and automatically predict outcomes – to determine which could most accurately identify NSCLC patients at risk of recurrence following curative radiotherapy.

Anonymised, routinely available clinical data from 657 NSCLC patients treated at five UK hospitals was used to compare different ML algorithms based on various prognostic factors such as age, gender and the tumour’s characteristics on scans to predict recurrence and survival at two years from their treatment. We then developed and tested models to categorise patients into low and high risk of recurrence, recurrence-free survival and overall survival.

A patient’s tumour size and stage, the type and intensity of radiotherapy, and their smoking status, BMI and age were the most important clinical factors in the final AI model’s algorithm for predicting patient outcomes.

The results suggested that this technology could be used to help personalise, and therefore improve, the surveillance of patients following treatment based on their risk. This could lead to recurrence being detected earlier in high-risk patients, ensuring that they receive urgent access to the next line of treatment that could potentially improve their outcomes. 

Results from the second phase of the study were recently published. Can you tell us more about this work?

In this phase, as well as clinical data, we used imaging data describing the tumours’ characteristics – a technique known as radiomics – taken from radiotherapy treatment planning CT scans on over 900 NSCLC patients in the UK and Netherlands.

Radiomic data can also be linked with biological markers. We believe it could be a useful tool in both personalising medicine and improving post-treatment surveillance. This data was used to develop and test ML models to see how accurately they could predict recurrence. 

The TNM staging system, which describes the amount and spread of cancer in a patient’s body, is the current gold standard in predicting prognosis. However, our model was found to better correctly identify which NSCLC patients were at a higher risk of recurrence within two years of completing radiotherapy than a model built on the TNM staging system.

How could your findings benefit patients?

We are at an early stage, and there’s a lot more work to do before we have a tool ready for use in the clinic. However, our results suggest that our AI model could be better at predicting tumour regrowth than traditional methods. This means that, using our technology, clinicians may eventually be able to identify which patients are at a higher risk of recurrence and offer them more targeted follow up. If recurrence did occur, this would be detected earlier so patients could be offered the next line of treatment as soon as possible. Meanwhile, low-risk patients could potentially be spared unnecessary follow-up scans and hospital visits.

This is also an exciting project because we don’t have to put patients through extra procedures for the model to work, as the data is routinely collected during the course of their normal treatment. Furthermore, in theory, there’s no reason why we can’t adapt the same tool to predict recurrence for other cancers.

What are the next steps?

So far, we’ve looked at CT scans and clinical data. We know from other areas of research [see next question] that some models have been developed using other patient data, for instance previous biopsy results or blood markers.

The next stage would look to improve the performance of the algorithm with more advanced AI techniques, such as deep learning or multimodal approaches, that incorporate different forms of data. Once the model is optimised, the next stage would likely be a prospective study to see if it can accurately predict risk of recurrence in patients currently starting radiotherapy treatment.

Have you published any other papers on AI recently, and what were the conclusions?

Our group has published a review paper that provides an overview of how AI is being used across the spectrum of cancer care, from screening and diagnosis through to treatment and follow up. We explore its implementation in primary care, radiology, pathology and oncology.

AI application in healthcare data has the potential to revolutionise early cancer diagnosis and may provide support for capacity concerns through automation. It can also allow us to effectively analyse complex data from many modalities, including clinical text, genomic, metabolomic and radiomic data.

In the review, we discuss myriad convolutional neural network – or CNN – models that can detect early-stage cancers on scan or biopsy images with high accuracy. Some had a proven impact on workflow triage. Many commercial solutions for automated cancer detection are becoming available, and we are likely to see increasing adoption in the coming years.

What other advantages could the adoption of AI bring to the sector, and what are some of the cons?

One of the biggest challenges facing healthcare right now is increasing demand, more complex cases and a shortage of workers. AI could augment our workflow, not replacing people, but doing some of the easier jobs so staff can focus on the more challenging tasks.

In the setting of patient decision-support, caution is needed to ensure that models are robustly validated before use.

In our review, we also highlight several challenges around the implementation of AI, including data anonymisation and storage, which can be time-consuming and costly for healthcare institutions.  

We also discuss model bias, including the under-reporting of important demographic information, such as race and ethnicity, and the implications this can have on generalisability.

In terms of how study quality and model uptake can be improved going forwards, quality assurance frameworks, such as SPIRIT-AI, and methods to standardise radiomic feature values across institutions, as proposed by the image biomarker standardisation initiative, may help. Moreover, disease-specific, gold-standard test sets could help clinicians benchmark multiple competing models more readily. 

Despite the above challenges, the implications of AI for early cancer diagnosis are highly promising, and this field is likely to grow rapidly in the coming years.

×