A groundbreaking blood test utilising artificial intelligence (AI) to determine the likelihood of cancer in patients has been developed in Leeds, offering hope for faster cancer diagnoses. The PinPoint test, currently being trialled by the Leeds Teaching Hospitals NHS Trust as part of the West Yorkshire and Harrogate Cancer Alliance service evaluation, aims to enhance early detection, reduce waiting times, and alleviate anxiety for patients unlikely to have cancer.
In recent years, secondary care services in England have faced an overwhelming influx of urgent cancer referrals from general practitioners (GPs), causing one in four cases to miss the two-week wait target for seeing a hospital consultant. Shockingly, only seven percent of patients referred from primary care are ultimately diagnosed with cancer, despite a significant rise in referrals over the years, reaching 2.8 million in the last year compared to one million in 2010.
The PinPoint test acts as a decision support tool for doctors, equipping them with crucial information to more effectively triage patients upon initial presentation of symptoms. By analysing 31 standard markers in a blood sample, considering factors such as age and sex, and utilising a machine learning algorithm, the test identifies potential signs of cancer and combines them into a single probability score. The underlying analysis draws from extensive, anonymised medical data.
When a patient visits their GP with cancer-related symptoms, they would undergo the PinPoint test, similar to a regular blood test. The test results are categorised into three color-coded flags: red, amber, or green. “Red” patients with a high likelihood of cancer would have their referral expedited, while “amber” patients would receive a standard referral. “Green” patients, who have a low probability of cancer, would be encouraged to consult with their GP to explore alternative diagnoses for their symptoms.
A large-scale retrospective study conducted in Leeds revealed that the PinPoint test could safely exclude up to one in five referrals to the two-week wait pathway. The study further confirmed the test’s affordability and its ability to be swiftly deployed in any NHS pathology laboratory without the need for additional hardware.
The ongoing evaluation in Leeds aims to determine whether the PinPoint test replicates or surpasses the success of the retrospective study. If successful, the test could be implemented across nine major cancer pathways, including breast, gynaecological, haematological, head and neck, lower gastrointestinal, lung, skin, upper gastrointestinal, and urological.
Dr. Nisha Sharma, consultant radiologist and director of breast screening at Leeds Teaching Hospitals NHS Trust, emphasised the need for innovative approaches to cancer pathways due to overwhelming demand and capacity constraints that lead to bottlenecks in the NHS. Dr. Sharma stated, “The PinPoint test has the potential to help clinicians prioritise those at high risk and make the process less stressful for patients.”
Giles Tully, CEO of PinPoint Data Science, highlighted the transformative potential of their technology in cancer diagnostics. Tully explained, “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 was developed through a collaboration between health tech company PinPoint Data Science, 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 received over £1.7 million in grants from SBRI Healthcare and the National NHS Cancer Programme to facilitate the wider implementation of the test.
