DELTA
Oesophageal cancer is the sixth most common cause for cancer related deaths worldwide. Compared to the rest of the European countries, UK has some of the worst outcomes mainly due to late diagnosis. The main risk factor for oesophageal cancer is chronic reflux and due to the high prevalence and non-specific nature of reflux symptoms, most patients are treated with acid-suppressant medications without referral for endoscopy. Three- to six- percent of individuals with reflux may have Barrett's oesophagus, which is a health condition that may cause oesophageal cancer. Barrett's oesophagus can be treated but only 20% of patients with Barrett's oesophagus are diagnosed. It is estimated that burden of oesophageal cancer could be reduced by up to 50% if all patients with chronic reflux are investigated. This is a formidable task since the NHS only has limited testing capacity and heartburn is common in the UK population. Currently, GPs are advised to treat their patients with antacid medications unless the patient present with "alarm" symptoms. Patient without alarm symptoms often continue to take the antacid medications life-long and there are increasing concerns about long-term side effects of antacids.
The output of this study will allow GPs to better identify patients who may benefit from endoscopy either as a result of early cancer detection or detection of Barrett's oesophagus, based on patterns of prescription acid-suppressant use as well as other characteristics of the patients.
Main Findings
The team developed the new tool by analysing the anonymised medical records from over 12 million patients from GP practices contributing to the QResearch database across England and identified over 16,000 cases of oesophageal cancer. The research incorporated key factors like age, lifestyle habits, medical history and medication use into the CanPredict algorithm.
Once developed, CanPredict was checked by testing it in a seperate set of QResearch practices (over 4 million patients) and the Clinical Practice Research Database (over 2.5 million patients). In testing, CanPredict accurately predicted an individual's risk of oesophageal cancer within the next decade. it outperformed existing models for estimating oesophageal cancer risk.
The study also highlighted the importance of factors such as age, body mass index, smoking, alchol consumption, and previous medical conditions in determining the risk of developing oesophageal cancer. The algorithm's ability to integrate these factors offers a comprehensive and personalised risk assessment for patients and can also help the NHS optimise the use of its resourses by targeting those at highest risj who are most likely to benefit from screening.
For more information on the results of DELTA please click HERE.