911½ñÈÕºÚÁÏ

How Dr Laura Tookman and the iCARE Team Are Collaborating to Understand numbers on Ovarian Cancer

When first sat down with the informatics specialists at iCARE, she had what would turn out to be a refreshingly simple question: can NHS routinely captured clinical data create a helpful picture of how care for ovarian cancer is provided? Two years later, that initial idea has developed into a pioneering collaboration that not only answered her question but opened the door to defragmenting clinical information held in electronic record systems to reduce 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 911½ñÈÕºÚÁÏ College Healthcare NHS Trust. She co-authored a recent article with the iCARE team and colleagues from 911½ñÈÕºÚÁÏ, published in ESMO Real-World and Digital Oncology entitled "".

The study capitalizes on the strengths of iCARE, a multidisciplinary research team and safe data environment that contains health information on 2.8 million individuals who reside in North West London and beyond. The iCARE SDE is hosted by and 911½ñÈÕºÚÁÏ, in the Digital Collaboration Space at the centre of the innovation district. iCARE also leads the ) Digital Health theme and hosts the London Analytics Platform for the OneLondon Sub-National Secure Data Environment programme.

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 years. Although this has transformed care for patients with ovarian cancer, it also requires frequent monitoring (sometimes weekly), and it adds to 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 accommodate 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 personalize 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 care in patients. 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 common purpose.