External UK validation of the ENDPAC model to predict pancreatic cancer risk: A registered report protocol

Abstract

AbstractIntroductionOverall cancer survival has increased over recent decades, but the very low survival rates of pancreatic cancer have hardly changed in the last 50 years. This is attributed to late diagnosis. Pancreatic cancer symptoms are non-specific which makes early diagnosis challenging. Data-driven approaches, including algorithms using combinations of symptoms to predict cancer risk, can aid clinicians. A simple but effective algorithm called Enriching New-Onset Diabetes for Pancreatic Cancer (ENDPAC) has been developed in the United States (US). ENDPAC has not yet been used in the United Kingdom (UK), our aim is to translate ENDPAC into the UK setting. The objectives are to validate ENDPAC and report its predictive utility within primary care.MethodsA retrospective cohort study of people with new-onset diabetes using the nationally representative Oxford-Royal College of General Practitioners Clinical Informatics Digital Hub (ORCHID) database. ORCHID holds over 10 million primary care electronic healthcare records. ENDPAC scores will be calculated for eligible people along with positive predictive value, negative predictive value, sensitivity and specificity of the algorithm. We will evaluate the optimal cut-off for defining people with high-risk of having pancreatic cancer.DiscussionOnce validated within the UK, ENDPAC could be implemented in practice to improve early pancreatic cancer diagnosis by using routine data. ENDPAC is currently being tested in the US in a clinical trial to evaluate its effectiveness. ENDPAC offers an automatable and inexpensive way to improve early diagnosis as part of a sequential approach to identify individuals at high-risk of having undiagnosed pancreatic cancer.How this fits inPancreatic cancer is a devasting disease which is hard to diagnose. An algorithm called ENDPAC has been developed in the United States to help clinicians identify people at risk of having undiagnosed pancreatic cancer. These people can be referred for an imaging investigation to diagnose or rule out cancer. This protocol outlines a United Kingdom (UK) validation of ENDPAC so that it could be used in clinical practice in the UK.