Thousands of women could be spared painful and invasive cancer examinations thanks to a new AI-powered blood test being trialled by the UK's National Health Service. The PinPoint blood test, developed by Leeds-based company PinPoint Data Science, uses machine learning to analyse 30 blood markers and determine a patient's risk of cancer with remarkable precision.
Around 90,000 postmenopausal women in England are referred by their GP each year for suspected womb cancer due to heavy bleeding. Currently, all must undergo a transvaginal ultrasound scan — a procedure many find uncomfortable or painful — followed by biopsies if cancer is still suspected. Yet only about one in ten of those referred actually has the disease.
The PinPoint test achieved 99% accuracy in both detecting gynaecological cancers and ruling them out during a trial involving 16,481 patients, including 3,313 women referred for womb cancer concerns. Based on these results, the test could spare approximately 18,000 women annually from unnecessary invasive procedures.
Two NHS trusts — Mid Yorkshire Teaching NHS Trust and Leeds Teaching Hospitals NHS Trust — are now planning to implement the test. Prof Sean Duffy, the company's chief medical officer and a former NHS England national clinical director for cancer, called the 99% accuracy rate 'remarkable by any clinical standards.'
'This has the potential to spare thousands of patients from painful invasive procedures they do not need,' Duffy said. Cancer Research UK described the test as 'promising' while calling for further research.
Dr Jacinta Walsh, a GP in West Yorkshire, noted that it often takes up to six GP visits to rule out cancer, and the blood test 'will help shortcut that process to deliver peace of mind earlier.'
