Real-World Validation of PinPoint Blood Tests in the NHS: Multivariable Machine Learning to Predict Cancer Risk in Primary Care Urgent Referrals

Objective To validate the UKCA-marked PinPoint blood tests, which use machine-learning models and routinely available blood analytes to estimate cancer risk in adults referred on urgent suspected cancer pathways in NHS England. Patients and Methods This work comprises a large-scale, prospective, observational, real-world NHS service evaluation of nine blood tests, carried out between December 2020 and July 2025. 16,481 patients with urgent suspected cancer (USC) referrals were enrolled across five secondary care Trusts and 170 GP surgeries. Real-world performance of the tests was evaluated using a range of diagnostic accuracy statistics. Results Five tests have performance indicating potential clinical utility. ROC AUC scores (95% CI) for these were: Upper GI=0.86 (0.81–0.90) Gynaecological=0.81 (0.77–0.85) Lung=0.79 (0.74–0.84) Head & Neck=0.73 (0.68–0.78) Lower GI=0.72 (0.67–0.78) Prioritisation of the 10% of highest-risk patients would reduce the number needed to investigate to detect one cancer by a factor of 2.6–6.1. Conclusion This work shows the potential of these tests to improve USC referral pathways. High-risk patients could be diagnosed more rapidly, leading to potential earlier-stage diagnosis and a better diagnostic experience. Low-risk patients could avoid unnecessary invasive medical testing for cancer. The software can be deployed rapidly across the NHS, without the need for additional hardware.