A predictive Bayesian network that risk stratifies patients undergoing Barrett's surveillance for personalized risk of developing malignancy.

BACKGROUND: Barrett's esophagus is strongly associated with esophageal adenocarcinoma. Considering costs and risks associated with invasive surveillance endoscopies better methods of risk stratification are required to assist decision-making and move toward more personalised tailoring of Barrett's surveillance. METHODS: A Bayesian network was created by synthesizing data from published studies analysing risk factors for developing adenocarcinoma in Barrett's oesophagus through a two-stage weighting process. RESULTS: Data was synthesized from 114 studies (n = 394,827) to create the Bayesian network, which was validated against a prospectively maintained institutional database (n = 571). Version 1 contained 10 variables (dysplasia, gender, age, Barrett's segment length, statin use, proton pump inhibitor use, BMI, smoking, aspirin and NSAID use) and achieved AUC of 0.61. Version 2 contained 4 variables with the strongest evidence of association with the development of adenocarcinoma in Barrett's (dysplasia, gender, age, Barrett's segment length) and achieved an AUC 0.90. CONCLUSION: This Bayesian network is unique in the way it utilizes published data to translate the existing empirical evidence surrounding the risk of developing adenocarcinoma in Barrett's esophagus to make personalized risk predictions. Further work is required but this tool marks a vital step towards delivering a more personalized approach to Barrett's surveillance.

Pre-diagnostic delays caused by gastrointestinal investigations do not affect outcomes in pancreatic cancer.

BACKGROUND: Pancreatic ductal adenocarcinomas are poor prognostic cancers accounting for 3% of all cancer cases in the UK. They often present late in the course of the disease process with non-specific symptoms, including gastro-intestinal(GI) symptoms. Delays in diagnosis occur when investigations are carried out in a primary care setting for GI symptoms. The aim of this study was to assess delays in pancreatic cancer diagnosis when patients were referred for GI investigations and evaluate its effect on survival. METHODS: Retrospective cohort study of all patients diagnosed with pancreatic adenocarcinoma in a Scottish district general hospital over a seven year period from January 2010 to December 2016. Patients were divided into two groups, those who had a GI investigation 18 months prior to the pancreatic cancer diagnosis and those who did not have GI investigations. Data on demographics, symptoms on referral, stage of disease at diagnosis, treatment undergone and length of survival collected and analysed. RESULTS: One hundred and fifty-three patients were diagnosed with pancreatic cancer in the study period. Forty (26%) of the 153 underwent gastrointestinal investigations in the 18 months prior to diagnosis. The remaining 113 (74%) had no gastro-intestinal investigations in the same time period. Demographic data were comparable. Significant delays occurred from referral to diagnosis in the GI investigated group compared to those who did not have GI investigations. (64.5days vs 9 days, p = 0.001). No difference was noted in disease stage or treatments undergone between the groups. There was no difference in the average survival after diagnosis between the two groups with median of 108 days for those who underwent GI investigations to 97 days for those who did not.(U = 2079.5, p = 0.454). CONCLUSION: Delays caused by pre-diagnostic GI investigations do not appear to contribute to the poor prognosis of pancreatic cancer. Recently updated NICE Guidelines recommends early ultrasound or CT in patients with GI symptoms and weight loss which may reduce delays in diagnosis. Screening tests in future may become cost effective and diagnose this condition at a curable stage which in turn may improve survival rates.