Impact of real-time automatic quality control system on colorectal polyp and adenoma detection: a prospective randomized controlled study (with video).

BACKGROUND AND AIMS Quality control can decrease variations among colonoscopists' performance and improve colonoscopy effectiveness to prevent colorectal cancers. Unfortunately, routine quality control is difficult to carry out because of lacking a practical method. The aim of this study was to develop an automatic quality control system (AQCS) and assess whether it could improve polyp and adenoma detection in clinical practice. METHODS First, we developed AQCS based on deep convolutional neural network (DCNN) models for timing withdrawal phase, supervising withdrawal stability, evaluating bowel preparation, and detecting colorectal polyps. Next, consecutive patients were prospectively randomized to undergo routine colonoscopies with or without the assistance of AQCS. The primary outcome of the study was the adenoma detection rate (ADR) in AQCS and control groups. RESULTS A total of 659 patients were enrolled and randomized. Three hundred eight and 315 patients were finally analyzed in the AQCS and control group, respectively. AQCS significantly increased the ADR (0.289 vs 0.165, p<0.001) and the mean number of adenomas per procedure (0.367 vs 0.178, p<0.001) as compared with the control group. A significant increase was also observed in polyp detection rate (0.383 vs 0.254, p=0.001) and the mean number of polyps detected per procedure (0.575 vs 0.305, p<0.001). In addition, AQCS group were superior in sufficient withdrawal time (7.03 minutes vs 5.68 minutes, p<0.001) and adequate bowel preparation rate (87.34% vs 80.63%, p=0.023). CONCLUSIONS AQCS could effectively improve the colonoscopists' performance during withdrawal phase and significantly increase polyp and adenoma detection.

[1]  M. Wallace,et al.  Trainee participation is associated with increased small adenoma detection. , 2011, Gastrointestinal endoscopy.

[2]  P. Bossuyt,et al.  Polyp Miss Rate Determined by Tandem Colonoscopy: A Systematic Review , 2006, The American Journal of Gastroenterology.

[3]  Zhiyong Zhu,et al.  Same-Day Single Dose of 2 Liter Polyethylene Glycol is Not Inferior to The Standard Bowel Preparation Regimen in Low-Risk Patients: A Randomized, Controlled Trial , 2018, The American Journal of Gastroenterology.

[4]  Henry Horng-Shing Lu,et al.  Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. , 2017, Gastroenterology.

[5]  G. Ketwaroo,et al.  Quality measures and quality improvements in colonoscopy , 2015, Current opinion in gastroenterology.

[6]  J. Johanson,et al.  Colonoscopic withdrawal times and adenoma detection during screening colonoscopy. , 2006, The New England journal of medicine.

[7]  Nicolas Chapados,et al.  Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model , 2017, Gut.

[8]  T. Berzin,et al.  Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy , 2018, Nature Biomedical Engineering.

[9]  Christian Stock,et al.  Reduced risk of colorectal cancer up to 10 years after screening, surveillance, or diagnostic colonoscopy. , 2014, Gastroenterology.

[10]  P. Baldi,et al.  Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas , 2018, American Journal of Neuroradiology.

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  D. Rex,et al.  Colonoscopic withdrawal technique is associated with adenoma miss rates. , 2000, Gastrointestinal endoscopy.

[13]  A. Zauber,et al.  Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. , 2012, The New England journal of medicine.

[14]  Ahmedin Jemal,et al.  Trends in Colorectal Cancer Incidence Rates in the United States by Tumor Location and Stage, 1992–2008 , 2012, Cancer Epidemiology, Biomarkers & Prevention.

[15]  P. Baldi,et al.  Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy. , 2018, Gastroenterology.

[16]  Marcin Polkowski,et al.  Quality indicators for colonoscopy and the risk of interval cancer. , 2010, The New England journal of medicine.

[17]  C. Rees,et al.  UK key performance indicators and quality assurance standards for colonoscopy , 2016, Gut.

[18]  T. Berzin,et al.  Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study , 2019, Gut.

[19]  Robert Fletcher,et al.  Standardized colonoscopy reporting and data system: report of the Quality Assurance Task Group of the National Colorectal Cancer Roundtable. , 2007, Gastrointestinal endoscopy.

[20]  S. Moss,et al.  Longer mean colonoscopy withdrawal time is associated with increased adenoma detection: evidence from the Bowel Cancer Screening Programme in England , 2012, Endoscopy.

[21]  D. Lieberman.  A call to action--measuring the quality of colonoscopy. , 2006, The New England journal of medicine.

[22]  Christopher D. Jensen,et al.  Adenoma detection rate and risk of colorectal cancer and death. , 2014, The New England journal of medicine.

[23]  Henk Harkema,et al.  Applying a natural language processing tool to electronic health records to assess performance on colonoscopy quality measures. , 2012, Gastrointestinal endoscopy.

[24]  Christopher D. Jensen,et al.  Factors influencing variation in physician adenoma detection rates: a theory-based approach for performance improvement. , 2016, Gastrointestinal endoscopy.

[25]  Gheorghe Doros,et al.  The Boston bowel preparation scale: a valid and reliable instrument for colonoscopy-oriented research. , 2007, Gastrointestinal endoscopy.

[26]  A. Jemal,et al.  Cancer statistics, 2017 , 2017, CA: a cancer journal for clinicians.

[27]  J. Cubiella,et al.  Clinical practice Guidelines: quality of colonoscopy in colorectal cancer screening , 2012, Endoscopy.

[28]  D. Han,et al.  The Miss Rate for Colorectal Adenoma Determined by Quality-Adjusted, Back-to-Back Colonoscopies , 2012, Gut and liver.

[29]  Sabee Molloi,et al.  Detecting Cardiovascular Disease from Mammograms With Deep Learning , 2017, IEEE Transactions on Medical Imaging.

[30]  Thomas Rösch,et al.  Expert opinions and scientific evidence for colonoscopy key performance indicators , 2016, Gut.

[31]  Henrik Stovring,et al.  Proton Pump Inhibitor or Testing for Helicobacter pylori as the First Step for Patients Presenting with Dyspepsia? A Cluster-Randomized Trial , 2006, The American Journal of Gastroenterology.