Leeds trust trials PinPoint AI technology to improve early detection of cancer
Urgent cancer referrals could be accelerated with the help of a new blood test developed in Leeds that uses artificial intelligence to identify the risk that a patient has the condition.
Leeds Teaching Hospitals NHS Trust is trialling PinPoint as part of the West Yorkshire and Harrogate Cancer Alliance service evaluation of the test to see if it can improve early detection, cut waiting times, and reduce anxiety among those unlikely to have cancer.
It comes as secondary care services across England are inundated with urgent cancer referrals from GPs, meaning the two-week wait target to see a hospital consultant is missed in one in four cases.
But, despite a steady increase in referrals in recent years, just 7% of patients referred from primary care are ultimately diagnosed with the condition.
The PinPoint test is designed as a decision support tool to supply doctors with the information they need to triage patients more effectively when first presenting with symptoms.
Its machine learning algorithm searches for telltale signs of cancer in 31 standard markers in a blood sample, takes into account a patient’s age and sex, and aggregates these signals into a single probability score.
The underlying analysis is based on vast amounts of richly-detailed, anonymous medical data.
A patient seeing their GP with symptoms suggesting cancer would have the PinPoint test in the same way as any normal blood test.
The results would then be flagged as red, amber or green.
We need to start thinking differently about our cancer pathways because of huge demand and capacity issues causing bottlenecks across the NHS
‘Red’ patients with a high chance of cancer would have their referral accelerated, while ‘amber’ patients would be referred as normal, and ‘green’ patients, with a low chance of cancer, would see their GP to explore alternative diagnoses for their symptoms.
A large-scale retrospective study carried out in Leeds found that up to one in five referrals into the two-week wait pathway could be safely ruled out using the test.
And the study concluded the test was affordable and could be deployed rapidly to any NHS pathology laboratory with no additional hardware requirements.
The current evaluation in Leeds will see if the PinPoint matches or exceeds the success of the retrospective study.
It could then be deployed across the nine major cancer pathways: breast, gynaecological, haematological, head and neck, lower gastrointestinal, lung, skin, upper gastrointestinal, and urological.
Dr Nisha Sharma (pictured), consultant radiologist and director of breast screening at Leeds Teaching Hospitals NHS Trust, said: “We need to start thinking differently about our cancer pathways because of huge demand and capacity issues causing bottlenecks across the NHS.
The PinPoint test accurately calculates an individual’s risk profile based on historic data from more patients than a doctor could see in a lifetime and can become an important tool for supporting clinical decision making
“The PinPoint test has the potential to help clinicians to prioritise those at high risk and make the process less fraught for patients.”
Giles Tully, chief executive of PinPoint Data Science, added: “Our technology can transform the approach to diagnostics for cancer.
“The PinPoint test accurately calculates an individual’s risk profile based on historic data from more patients than a doctor could see in a lifetime and can become an important tool for supporting clinical decision making.”
The test was developed in Leeds by health tech company, PinPoint Data Science, in collaboration with Leeds Teaching Hospitals NHS Trust and the University of Leeds, with support from the Leeds Academic Health Partnership, Yorkshire and Humber Academic Health Science Network, and the West Yorkshire and Harrogate Cancer Alliance.
The project has received more than £1.7m in grants from SBRI Healthcare and the national NHS Cancer Programme to help roll out the test more widely.