How Dr Laura Tookman and the iCARE Team Are Collaborating to Understand Numbers on Ovarian Cancer.
When Dr Laura Tookman first sat down with the informatics specialists at iCARE, she had what would turn out to be a refreshingly simple question: Can the NHS routinely capture clinical data to create a helpful picture of how care for ovarian cancer is provided? Two years later, that initial idea has evolved into a pioneering collaboration that not only answered her question but also opened the door to defragmenting clinical information stored in electronic record systems, thereby reducing the burden on clinicians’ time.
Dr Tookman is a specialist medical oncology consultant with an interest in gynaecological malignancy and is based mainly at Hammersmith Hospital, part of Imperial College Healthcare NHS Trust. She co-authored a recent article with the iCARE team and colleagues from Imperial, published in ESMO Real-World and Digital Oncology.
The study capitalises on the strengths of iCARE, a multidisciplinary research team and a secure data environment that contains health information for 2.8 million individuals residing in North West London and beyond. The iCARE SDE receives infrastructure support from the NIHR Imperial BRC.
“It was really thrilling to be able to see how we could combine clinical expertise and data science in this manner,” says Dr Tookman. “We always wish to be able to look back at our practice, to learn and improve, and this project was about sitting down and wondering whether we could develop a much more automated method of looking at data for patients with ovarian cancer.”
Research process
The research started by trying to understand what data points are most important to clinicians. “There is just so much information in NHS systems, but as a clinician, you need to know where to find it and what you are searching for,” she says. The groups together made a timeline of patient treatment, including key data points on diagnostics, surgery, systemic treatment, and pathology. “The vision was to learn about one patient’s pathway first and then extrapolate that out to thousands.”
Their study, over 1,581 patients treated between 2014 and 2022, had reassuring but also surprising findings. Established prognostic factors of disease stage and performance status were reaffirmed, but the researchers also monitored trends in treatment patterns over time. Among the surprises was the fast uptake of poly-ADP ribose polymerase inhibitors, oral maintenance therapies that became a standard part of treatment over the timeframe studied.
“Our figures demonstrate that once PARP inhibitors entered mainstream practice, their usage took off,” according to Dr Tookman. “It has made a huge difference in the way we treat patients. Instead of seeing someone, once they have completed their chemotherapy, for three months at a time for a blood test, we have people taking tablets over the years. Although this has transformed care for patients with ovarian cancer, it also requires frequent monitoring (sometimes weekly), and it adds to the workload across the entire multidisciplinary team.”
This degree of understanding is achievable only thanks to the infrastructure of iCARE. The SDE pull information from various electronic health record systems and accommodates semi-automatic curation workflows, enabling analysis at scale. The team-based method—clinicians and data scientists working together close at hand—is particularly well-suited. “We could not have done this without the iCARE team,” says Dr Tookman, “and vice versa too; you require health professionals to ensure the questions are clinically appropriate and ensure what we learn is correct.”
But it was not without challenges. “I foolishly thought the data would be readily available and more accurate,” she concedes. Missing data, for example, in ethnicity and genomic testing, made it difficult to study health disparities and personalise treatment. Most of the important information is hidden in free-text clinical notes. “The structured information—blood test results, dates—is fairly easy. But the gold is in the free text: surgical details, complications, subtleties of the tumour biology. We needed to employ AI and natural language processing to unlock that.”
Consolidation of genomic information is another matter of importance. Genetic mutations like BRCA are important determinants in the management of high-grade ovarian cancer. But these results tend to be in a format that is not readily available to researchers. “Genetic testing is coming on in leaps and bounds, but we have systems that can keep up and be flexible as new tests appear,” Dr Tookman says.
Aside from research, she believes that this piece of work will have a direct influence on patient care. Improved outcomes via benchmarking, the detection of inequalities, and improved planning of services are an immediate return. There is also a very personal angle. “Patients want data that is locally relevant, not national data from trials. They want to know what is best for people like them, in their area. That is something we can provide.”
In the future, Dr Tookman looks to extend this work into even more advanced analyses and more combined genomic and free-text data. She is also part of a companion project creating a dashboard for integrating significant patient data into one easy-to-use interface for clinicians to support decision making during multi-disciplinary team meetings.
It is all about enhancing care. The research, the planning of operations, the patient involvement—everything begins with putting the data that we already collect into context,” she says. “This partnership has demonstrated how well that works.”
With iCARE continuing to develop its capabilities through national projects, initiatives such as this are evidence of what can be achieved when clinicians and experts in data work together with a common purpose.
A study, published in The European Heart Journal, funded by the British Heart Foundation, National Institute for Health and Care Research, and the Medical Research Council, found that an AI algorithm can predict serious heart conditions years in advance using only ECG data
Researchers found that their AI could spot very early changes in the heart’s structure from an ECG, a common test which shows the heart’s electrical activity. The advanced algorithm could detect issues in the heart’s valves, which keep blood flowing in the correct direction through the heart’s chambers, even before the appearance of symptoms or physical changes that can be detected by ultrasound scans.
The AI could accurately predict who would go on to develop significant leaks in the heart’s mitral, tricuspid, or aortic valves – conditions known as regurgitant valvular heart diseases. It was able to correctly identify the risk of a leaky heart valve in the years following the ECG (from high to low) in around 69-79% of cases.
People flagged as ‘high-risk’ by the algorithm were up to 10 times more likely to develop these diseases than those classed as lower risk.
According to the team from Imperial College London and Imperial College Healthcare NHS Trust, their AI-enhanced predictions could potentially transform doctors’ approach to treating heart valve disease.
It’s estimated that 41 million people worldwide, including 1.5 million people in the UK, live with these heart valve diseases, which can lead to heart failure, hospital admissions and death. Early diagnosis is key for successful treatment. But the symptoms, which can include shortness of breath, dizziness, feeling tired and having heart palpitations, can be easily confused with other causes, while some patients don’t show any symptoms until the disease is advanced.
Earlier detection
Dr Arunashis Sau, one of the study leads, Academic Clinical Lecturer at Imperial College London’s National Heart and Lung Institute, and cardiology registrar at Imperial College Healthcare NHS Trust said: “Our hearts are incredibly complex and hard-working organs, but we rarely give them much consideration unless something goes wrong. By the time symptoms and structural changes appear in the heart, it may be too late to do much about it. Our work is harnessing AI to detect subtle changes at the earliest stage from a simple and common test, and we think this could be really transformative for doctors and patients. Rather than waiting for symptoms or relying only on expensive and time-consuming imaging tests, we could use AI-enhanced ECGs to spot those most at risk earlier than ever before. This means that many more people could get the care they need before their hidden condition affects their quality of life or becomes life-threatening.”
The study was part of an international collaboration led by researchers Drs Sau and Dr Fu Siong Ng and involving researchers in China, based at Shanghai’s Zhongshan Hospital. AI models were trained using nearly one million ECG and heart ultrasound (echocardiogram) records from over 400,000 patients in China. The technology was then tested on a separate group of more than 34,000 patients in the United States, showing that it works well across ethnically diverse populations and healthcare systems.
Issues with heart valves may first appear as very small changes to the heart’s electrical activity which are not apparent to doctors. These electrical changes become larger, but by this point, symptoms have often started to develop. The AI system can detect these subtle electrical patterns much earlier, hopefully before symptoms develop at all.
Dr Ng, the senior author, Reader in Cardiac Electrophysiology at the National Heart & Lung Institute at Imperial College London and a consultant cardiologist at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust, said:
“AI has enormous potential for improving healthcare around the world, but it requires huge amounts of data to train and test these algorithms. Our work is an example of the benefits of international collaboration in this fast-growing area. By training the model in an almost exclusively Chinese population and then testing in a US cohort, we can show that our AI tool has the potential to be applied in various countries and settings around the world. This ultimately means it has the potential to help even more patients.”
Continued work
The research builds upon the team’s development of the related AI-ECG risk estimation model, known as AIRE, which can predict patients’ risk of developing and worsening disease based on an ECG. Other AI models from this project have been trained to analyse ECGs to predict problems such as female heart disease risk, health risks including early death, high blood pressure and type 2 diabetes.
Trials of AIRE in the NHS are already planned for late 2025. These will evaluate the benefits of implementing the model with real patients from hospitals across Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust.
A new study found that children living near nuclear power stations in the UK are not at increased risk of childhood cancers.
The work was funded by the NIHR Health Protection Research Unit in Chemical and Radiation Threats and Hazards – a partnership between the UK Health Security Agency (UKHSA) and Imperial College London with infrastructure support provided by the NIHR Imperial BRC.
The research, led by scientists at Imperial College London and University of Bristol and commissioned by the UK Committee on the Medical Aspects of Radiation in the Environment (COMARE), found no evidence of increased risk of childhood cancers among children living near 28 nuclear installations between 1995 and 2016.
Researchers analysed cancer incidence data for nearly 50,000 cases of childhood leukaemia, non-Hodgkin’s lymphoma (LNHL), central nervous system (CNS) tumours, and other solid tumours in children aged 0–14 years.
They looked at data for communities living within 25 kilometres of installations, including those which have been linked to historical concerns about potential health impacts – such as Sellafield in Cumbria and Dounreay in northern Scotland.
Using these data and advanced statistical modelling, they found no increased incidence of childhood cancers in these areas compared to national averages.[1] They also found no evidence that cancer risk increased the closer children lived to the nuclear sites.
Dr Bethan Davies, from Imperial’s School of Public Health, a key member of the NIHR Imperial BRC SGE Theme and lead author of the study, said: “For many years there have been public concerns about the potential health impacts of living near nuclear installations. Our analysis suggests that children living near these sites today are not at increased risk.”
The latest study builds on decades of research following reports in the 1980s of clusters of cancer cases near nuclear facilities in England, Scotland and Germany[2] – following which, the UK Government set up COMARE to advise on the health effects of radiation.
Early investigations confirmed clusters of cases of some cancers near nuclear installations, particularly LNHL.
However, subsequent studies failed to show any direct link between these cases and radiation exposure from nuclear facilities.
In 2016, a COMARE report[3] suggested other potential explanations for these case clusters, including infections introduced due to population mixing in the areas.
The new findings come at a time of renewed interest in nuclear energy as part of the UK’s strategy to meet net-zero carbon targets and the government committing £14.2bn to build a new nuclear power station in Suffolk and develop small modular reactors.
The researchers say that while their study offers reassurance, they support COMARE’s recommendations for ongoing surveillance of cancer incidence near nuclear sites.
The authors acknowledge several limitations to their study, including the use of residential address at diagnosis as a proxy for exposure.
They were also unable to account for individual-level risk factors, such as genetic or medical conditions. However, they emphasise that the study’s design and comprehensive data make it one of the most detailed assessments to date.
Dr Davies added: “As the UK government announces a multibillion-pound investment for new nuclear energy infrastructure, our findings should provide reassurance that the historical clusters of childhood cancers reported near sites such as Sellafield and Dounreay are no longer evident.”
Professor Mireille Toledano, Mohn Chair in Population Child Health in Imperial’s School of Public Health, said: “These findings are both timely and important. As the UK and other countries expand their nuclear energy capacity, it’s vital that public health remains a central consideration. It’s reassuring that our study found that the historic case clusters have resolved, but it remains important we continue to monitor public health data around such sites across the UK for any emerging trends of concern
A major new study led by researchers at Imperial College London, including members of the NIHR Imperial BRC Cardiovascular Theme, has revealed that a simple blood test for inflammation could help predict long-term cardiovascular risk in individuals with high blood pressure, decades before any clinical event occurs.
Published in eBioMedicine, the research draws on longitudinal data from 5,294 participants in the UK arm of the Anglo-Scandinavian Cardiac Outcomes Trial (ASCOT Legacy). The investigators examined baseline levels of high-sensitivity C-reactive protein (hsCRP), a hepatic acute-phase protein that reflects systemic inflammation.
A Modest Elevation, a Major Risk
The analysis showed that individuals in the highest tertile of hsCRP levels faced a 25–30% greater risk of myocardial infarction, stroke, or all-cause mortality over the 20-year follow-up period compared to those in the lowest tertile. Notably, even a modest elevation in hsCRP at baseline conferred excess cardiovascular risk, despite participants appearing otherwise healthy at enrolment.
While hsCRP was not associated with stroke incidence over the long term, suggesting a different pathophysiological basis for cerebrovascular events, it was a powerful independent predictor of coronary and overall mortality. The authors highlight that the incorporation of hsCRP into conventional risk models improved prognostic discrimination by nearly 10%, supporting its potential utility in routine cardiovascular risk stratification.
The Synergy of Lipids and Inflammation
A particularly striking finding was that the concurrent elevation of both LDL-cholesterol and hsCRP conferred the highest risk of future adverse outcomes. In contrast, an isolated rise in cholesterol in the presence of low-grade inflammation (hsCRP < 2 mg/L) did not significantly raise risk. This supports the growing recognition that inflammation and lipid accumulation act synergistically in the atherogenic process and underscores the rationale for dual-pathway therapeutic strategies.
Towards Clinical Translation
The findings suggest that measuring hsCRP in patients with hypertension could inform earlier intervention strategies, including the initiation of statins or targeted anti-inflammatory therapies. Pilot studies are being considered to assess whether incorporating inflammatory profiling into hypertension management can reduce long-term cardiovascular events and mortality.
Professor Ramzi Khamis, Professor of Cardiology at the National Heart and Lung Institute, commented: “This important work underscores the need to identify and target residual inflammatory risk in patients with coronary artery disease. We are now moving beyond cholesterol alone. At the recent Imperial Vulnerable Plaque and Patient Meeting (VPM), we laid out a roadmap for future translational studies aimed at refining both diagnostic and therapeutic tools that address vascular inflammation. This study strengthens the case for integrating hsCRP-guided strategies into routine cardiovascular care, particularly in the context of hypertension.”
As cardiovascular medicine continues to evolve towards personalised prevention, the integration of simple, scalable biomarkers such as hsCRP into clinical workflows could play a critical role in identifying patients at greatest risk long before symptoms arise.
North West London (NWL) boroughs have high ethnic diversity, socioeconomic deprivation with large inequalities in health status and healthcare access. Capacity for community mental health research within the sector and in ARC NWL has historically been lacking in relation to need. Links between physical health, mental health, deprivation, ethnicity, education, and social care are well-recognised, yet a lack of centralised data has limited the development of a joined-up, population-based approach to identify and support children and young people (CYP) at risk of developing mental health (MH) conditions and those with existing conditions.
In 2021, we set out to address MH inequalities for CYP in NW London establishing ARC Outreach Alliance – an innovative project designed to address CYP MH research inequalities by:
- Creating a stakeholder network to advocate for policy changes and onboarding CYP as advisors to produce research relevant to, steered and informed by CYP.
- Collating and centralising big data on CYP MH service provision to improve research and service provision.
- Engaging with schools to explore barriers to accessing useful digital therapeutic tools to support early intervention for CYP MH.
In 2024 we have received further NIHR funding to continue our work on:
- Data driven discovery around health inequalities in access to CYP MH diagnostic services and interventions
- Understanding barriers to accessing care
- Improving the experience and reduce need for CYP MH crisis Care
- Growing ARC Outreach Alliance PPIE Engagement network – Listen to Act & YPAG
This project had a significant impact on the NWL landscape for CYP. Firstly, data driven discovery using routine data from primary and secondary care has identified inequalities in access to MH support for CYP in terms of referral pathways and access to specialised medication prescribing, as well as mapping gaps in mental health crisis care. These studies have highlighted systemic level inequalities as well as characterising specific populations at increased risk of mental health crises.
Secondly, the IMPACT study has improved awareness of MH support provided within schools, by offering evidence based digital solutions, and by identifying subpopulations of CYP least likely to access these interventions, setting the groundwork for better understanding the barriers that perpetuate inequalities in access to mental health interventions. These data have also provided a contemporary snapshot of unmet mental health need in school age young people in NWL and sets the groundwork for understanding likely barriers to uptake of our novel app co- designed with CYP integrating monitoring and real-time interventions to treat emotional dysregulation (in line with Imperial BRC objective). This work is currently subject to a randomised controlled trial.
Thirdly, involving young people has become integral to NWL mental health research as well as to the NWL ICB strategy for mental health. Demand for input from our YPAG exceeds capacity, despite the expanded number of young people involved.
AOA short film – created, filmed and edited by YPAG: https://www.youtube.com/watch?v=ToQrrS5N9ko
Winner of the inaugural PPIE Project competition announced
NHS England » Guidance on neighbourhood multidisciplinary teams for children and young people
