Abstract
Introduction: Overall cancer survival has increased over the recent decades, but the dismal survival rates of pancreatic cancer have hardly changed in the last 50 years. This is attributed to late diagnosis. Early pancreatic cancer symptoms are non-specific which makes diagnosis challenging. Data-driven approaches, including prediction algorithms that use a combination of symptoms, have been developed to aid earlier detection and diagnosis. One such algorithm is ENDPAC (Enriching New-Onset Diabetes for Pancreatic Cancer). ENDPAC was developed is the US primary care setting. The aim of this project is to validate ENDPAC for the UK setting and make invisible cases of pancreatic cancer visible using routinely collected healthcare data. Methods: A retrospective case-control study using the nationally representative Oxford-Royal College of General Practitioners Clinical Informatics Digital Hub (ORCHID) database will be undertaken. ORCHID holds over 10 million primary care electronic healthcare records including nearly 14,000 people diagnosed with pancreatic cancer (cases). Healthcare records of cases will be compared with matched controls and the predictive power of ENDPAC for the detection of pancreatic cancer will be evaluated. Discussion: Routinely collected primary care data are a rich resource that should be used to improve healthcare. However, they are currently underutilised in research due to restricted access as well as privacy and ethical implications. Using a trusted research environment to conduct analysis ensures data security and privacy. The validation of ENDPAC will serve as a case study to support the safe and trustworthy use of patient data in research. Conclusion: Data-driven algorithms using routine primary healthcare data may be an inexpensive and systematic approach to enhance identifying individuals who are at high-risk of conditions that would benefit from additional screening. Thorough validation is required to ensure these tools are fit for purpose before they can be adopted in clinical practice.