The development of the new broad-spectrum predictive algorithms ‘marks the first time oral cancer has been included’ in predictive modelling.
The algorithms are ‘much more sensitive than existing models’ and could potentially lead to earlier diagnosis of cancer according to researchers.
Previous models have used information about a patient’s age, family history, medical diagnoses, symptoms, and general health. The new algorithms build on this by incorporating the results of seven blood tests measuring full blood count and liver function as biomarkers to improve early cancer diagnosis.
‘Faster diagnosis and better survival outcomes’
Karen Coates, oral health educator for the Oral Health Foundation (OHF), said the foundation ‘strongly support investment in predictive algorithms that use routinely collected patient data to improve early cancer diagnosis’.
She continued: ‘This particular research is both timely and promising, offering a more accurate way to identify individuals with undiagnosed cancers, including mouth cancer, earlier than ever before.
‘When used appropriately, these tools could empower primary care professionals with better evidence to make faster and more targeted referrals – something we know is critical in improving outcomes for mouth cancer patients.’
She also stressed the importance of diagnosing mouth cancer at an early stage. She said: ‘Mouth cancer remains a disease with low survival rates, largely due to late-stage diagnosis. This study marks the first time oral cancer has been included in a broad-spectrum predictive algorithm. The addition of low-cost, widely available blood tests – combined with risk factors and symptom data – could increase the likelihood of identifying oral cancer earlier.
‘While the discrimination for oral cancer is not as strong as for some other cancers, it’s a step in the right direction. Earlier identification and referral could lead to faster diagnosis and better survival outcomes.’
Predictive algorithms ‘not a silver bullet’
However, Karen also identified some limitations of the predictive algorithm approach. She said: ‘While predictive algorithms like this are a valuable tool, they are not a silver bullet. Tackling mouth cancer requires a multifaceted strategy. Public awareness campaigns, routine opportunistic screening by dental professionals, better access to NHS dentistry, and training across the wider health system to recognise signs and symptoms early remain essential.
‘Algorithms can assist primary care but must be supported by broader systemic change – especially improved referral pathways between GPs and dental services.
‘Cases of mouth cancer in the UK have doubled over the last generation, yet awareness and early detection remain poor. Too many patients are still being diagnosed at later stages, when treatment is more invasive and survival rates plummet.
‘We must do more – through public education, professional training, and cross-sector collaboration – to reverse this trend. Innovative tools like predictive algorithms are welcome, but they must sit alongside stronger national efforts on prevention, education, and access to timely care.’
‘An affordable and efficient approach’
Julia Hippisley-Cox, professor of clinical epidemiology and predictive medicine at Queen Mary University of London, is lead author of the study. She 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 Dr 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 recorded in their medical records.
‘They offer the potential for enabling earlier cancer diagnoses in people from the age of 18 onwards, including for some rare types of cancer.’
Follow Dentistry.co.uk on Instagram to keep up with all the latest dental news and trends.
