AI offers an opportunity to reimagine our approach to cancer diagnostics, leveraging data to build a more robust and efficient system for cancer referrals
COVID-19 brought into sharp focus the need for new solutions to old problems. Waiting lists in the NHS are by no means a new issue, but a combination of factors too complex to be explored here, has once again seen questions around capacity and staffing levels back in the news this year.
A system running at (near) full capacity is inevitably going to be vulnerable to shocks. Think of compression waves in traffic. Once the density of vehicles on a stretch of road nears or surpasses safe capacity levels, even tiny changes in speed by one can result in shock waves travelling backwards and queues appearing for no apparent reason.
The NHS is vulnerable in the same way: running at close to or over capacity with a limited bandwidth means that the more patients are in the queue, the more susceptible to external shocks the system becomes. That could be as simple as a single consultant falling ill and being unable to work or as massive as a global pandemic. Nowhere is this more true than in NHS cancer services, where demand in diagnostic pathways has been growing steadily for over a decade, without a corresponding increase in capacity.
The scale of the challenge in UK cancer referrals
The so-called ‘two week wait’ (2WW) cancer referral pathway, wherein suspected cancer cases are guaranteed to be seen for investigation in secondary care within 14 days, has become a victim of its own success. From 1 million patients per year at its inception in 2010, 2WW referrals have grown steadily at approximately 10% per annum to 2.8 million patients in 2022. The result is unsustainable pressure on the system and Trusts struggling to meet the 14-day target, sometimes delaying diagnosis by weeks.
The greater the backlogs, the further we get from a system capable of meeting the Government’s ambition of 75% of all cancers being identified early by 2028.
GPs are understandably keen to avoid missing the opportunity for early detection, so where symptoms occur, the 2WW is the obvious safest route. However, despite soaring patient numbers, only 7% of those referred are ultimately diagnosed with cancer.
The remaining 93% of patients (2.6 million people in 2022) do not have cancer at all.
“The two-week wait isn’t just 14 days, it’s 14 sleepless nights”
From a human perspective, every day ‘not knowing’ is a day of anxiety as patients wait for appointments, test results and diagnoses. Under the 2WW, the latter stages of the pathway are not captured but based on the recommendations of the 2015 Cancer Strategy, a transition is already underway to shift reporting to the ‘Faster Diagnostic Standard’ (FDS).
This requires that patients receive a diagnosis of cancer, or have cancer ruled out, within 28 days.
Within that window of time, a system for more accurately prioritising patients by individual risk could be transformational for supporting early detection and preventing unnecessary waits and testing for those in the 93% at negligible risk.
The PinPoint Test is an AI-driven, affordable blood test for cancer, designed to optimise NHS urgent cancer referral pathways. The test is a pure software solution which employs machine learning to analyse 31 standard analytes, plus the patient’s age and sex. It calibrates and aggregates these individual signals into one strong and highly accurate result: the chance that a patient has cancer.
The test is designed as a decision support tool to provide doctors with the information they need to more effectively triage patients when they first present with symptoms. Those at high risk can be prioritised for rapid investigation in Secondary Care, whilst those at lowest risk can be safely ruled out of the 2WW pathway for further consultation with their GP.
Our data suggests that up to 20% of current 2WW referrals could be safely ruled out, equating to 560,000 patients per year (based on 2021-22 data). That’s peace of mind delivered in the time it takes to run a blood test and an opportunity for your GP to identify the appropriate onward clinical path more quickly.
PinPoint’s potential for impact on secondary care clinics
In October 2022, a peer-reviewed paper modelling the potential impact of the PinPoint Test on capacity at the Leeds Teaching Hospitals NHS Trust Breast Clinic was published by BMC.
The paper showed that PinPoint improved compliance with 2WW referral targets from approximately 66% to over 98%. Overspill appointments, where patients are forced to reschedule, were reduced by 50%. In addition, PinPoint reduced pressure on the pathway significantly enough that one ‘low-capacity clinic’ per week could be removed from the schedule entirely.
These results suggest PinPoint will help to create a more robust, cost-effective and clinically impactful diagnostic pathway, capable of withstanding shocks whilst maintaining focus on high-risk patients. The paper on cancer referrals can be found in full here.
So, when can we expect to see PinPoint employed within NHS cancer referral pathways?
The test is currently undergoing a service evaluation run by the West Yorkshire and Harrogate Cancer Alliance, and in partnership with Mid Yorkshire Hospitals NHS Trust Pathology. This is being used to confirm its performance in a real-world setting and make sure it matches or exceeds the success of the original retrospective analysis, on which the PinPoint algorithm was developed.
The evaluation is the final step before being able to deploy across wider regions of England, in preparation for which PinPoint Data Science has received grants of over £1.7million from SBRI Healthcare and the NHS National Cancer Programme.
This means PinPoint is now working with AHSNs, Cancer Alliances and NHS Trusts in a total of five regions in England: West Yorkshire and Harrogate, Cheshire & Merseyside, Humber & North Yorkshire, Lancashire & South Cumbria, and Surrey & Sussex.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
More About Stakeholder
PinPoint Data Science – Streamlining Cancer Diagnostics in the NHS
Homegrown innovation in AI cancer diagnostics