UK academics from the University of Nottingham along with ClinRisk Ltd have developed two new “QCancer” algorithms to help GPs detect both bowel and pancreatic cancers.
The simple tool cross-references both symptoms and risk factors of patients to ‘red flag’ those most likely to have the disease. Early diagnosis of pancreatic cancer is crucial so patients can be eligible for surgery – currently the only potential for a cure.
The research, published in the January edition of the British Journal of General Practice – the journal of the Royal College of General Practitioners – used patient data from 564 GP practices across the UK to develop the algorithm and to test its success at predicting which patients were likely to have pancreatic cancer. This was based on a combination of symptoms such as weight loss, appetite loss and abdominal pain along with risk factors such as age, chronic pancreatitis, smoking and diabetes.
The researchers found that the algorithm was successful in predicting over two thirds of all pancreatic cancers over the two year period which were in the top ten percent of patients predicted to be most at risk.
There is potential for these algorithms to be incorporated into existing GP computer systems to alert doctors of patients who may potentially be at risk of developing the disease.
Ali Stunt, Chief Executive of Pancreatic Cancer Action said; “Early diagnosis of pancreatic cancer is the key to improving survival rates for this disease and anything that can help doctors diagnose sooner is welcomed wholeheartedly and an algorithm that looks at both symptoms and a patient’s potential risk is an important step forward.
“We sincerely hope that these algorithms will have been designed to take into account the collection of vague and often overlooked symptoms of pancreatic cancer so early stage disease can be identified sooner as well as using the key alarm symptoms such as weight loss and abdominal pain which often are indicative of later stage pancreatic cancer.”