New algorithms to help GPs predict which patients have undiagnosed cancer
Two new advanced predictive algorithms use information about a person’s health conditions, and simple blood tests, to predict patients’ chances of having a currently undiagnosed cancer, including hard to diagnose liver and oral cancers. The new models could revolutionise cancer detection in primary care, and make it easier for patients to be treated at much earlier stages.
The NHS currently uses predictive algorithms (eg: QCancer scores) to combine information from patient data and identify individuals deemed at high risk of having a currently undiagnosed cancer, enabling GPs and specialists to call them in for further testing.
WIPH and University of Oxford researchers used the anonymised electronic health records from over 7.4 million adults in England to create two new algorithms, which are much more sensitive than existing models, and could lead to better clinical decision making and potentially earlier cancer diagnoses. In addition to information about patient age, family history, medical diagnoses, symptoms, and general health, the new algorithms incorporate results from seven routine blood tests (measuring full blood count and testing liver function) as biomarkers to improve early cancer diagnosis.
Compared with QCancer algorithms, the new models identified four additional medical conditions associated with an increased risk of 15 different cancers, including those affecting the liver, kidneys, and pancreas. Two additional associations were also found for family history with lung cancer and blood cancer, and seven new symptoms of concern (including itching, bruising, back pain, hoarseness, flatulence, abdominal mass, and dark urine) were identified as being associated with multiple cancer types. The new algorithms offer much improved diagnostic capabilities, and are the only current tests that can be used in primary care settings to estimate the likelihood of having a current but as yet undiagnosed liver cancer.
Julia Hippisley-Cox, WIPH Professor of Clinical Epidemiology and Predictive Medicine and study lead author said: “These algorithms are designed to be embedded into clinical systems and used during routine GP consultations. They offer a substantial improvement over current models, with higher accuracy in identifying cancers - especially at early, more treatable stages. They use existing blood test results which are already in the patients’ records, making this an affordable and efficient approach to help the NHS meet its targets to improve its record on diagnosing cancer early by 2028.”
Co-author Carol Coupland said: “These new algorithms for assessing individuals’ risks of having currently undiagnosed cancer show improved capability of identifying people most at risk of having one of 15 types of cancer, based on their symptoms, blood test results, lifestyle factors and other information in their medical records. They offer the potential for enabling earlier cancer diagnoses in people from age 18 onwards, including for some rare types of cancer.”’
J Hippisley-Cox, C Coupland. Development and external validation of prediction algorithms to improve early diagnosis of cancer. Nat Commun 16, 3660 (2025). https://doi.org/10.1038/s41467-025-57990-5