Colorectal cancer is the second leading cause of cancer-related deaths in the US, claiming about 50,000 lives in 2015. Colonoscopy is currently the preferred screening modality for colorectal cancer; in theory colonoscopy should prevent most colorectal cancers. However, recent data suggest that there is a significant miss-rate associated with colonoscopy for the detection of even large polyps and cancers. Indeed, reports from Canada and Germany fail to show any protection of colonoscopy for right-sided and only about 70% protection for left-sided colorectal cancer. Reports from the US show that prevention of colorectal cancer related death is at best 53-68% in carefully controlled longitudinal studies. Furthermore, patients of endoscopists with the highest rate of detection of premalignant polyps had the lowest rate of colorectal cancers in subsequent years. In 2015, the American College of Gastroenterology and the American Society of Gastroenterology renewed consensus guidelines defining a good quality colonoscopy but adherence to these guidelines varies among endoscopists and there is growing concern that these guidelines do not reflect true quality. We hypothesize that real-time objective feedback during the withdrawal phase of colonoscopy will improve quality of colonoscopy. We have created software that in real-time evaluates the technique of the endoscopist, categorizes technique into different degrees of quality (similar to software in airplanes that warns pilots against stalling) within milliseconds and via heads-up display technology can inform the endoscopist about the level of measured quality. In other words, we have created a system that has the potential to improve endoscopic technique during a procedure in a live patient. Using this system, we propose to address two Specific Aims. First, to determine the optimal method of real-time feedback for four features of colonoscopy related to the amount of stool in the colon and the effort of the endoscopist to inspect as much as possible all mucosa of the colon. And second, to test whether real-time feedback during colonoscopy improves quality of colonoscopy and the adenoma detection rate in three endoscopy centers. Successful evaluation and implementation of the proposed real-time analysis and feedback system has the potential to improve the quality of care of over 14 million US citizens ? the approximate number of people undergoing colonoscopy ? on an annual basis. In addition, the technology lends itself for rapid adaptation to other endoscopic medical procedures such as upper gastrointestinal endoscopy, cystoscopy, arthroscopy and bronchoscopy.

Public Health Relevance

Our long-term objective is to ensure that all endoscopic examinations of the colon, so called colonoscopies, are of excellent quality. Unfortunately, at present this is not the case and ?missed lesions?, i.e. large polyps or colorectal cancer, sometimes are detected shortly after a ?negative? colonoscopy. Several patient-, equipment- and endoscopist-related factors may be responsible for this. We and most colorectal cancer experts believe that the endoscopist-related factors, in particular endoscopist technique, are most important as the endoscopist can mitigate unfavorable conditions related to patient- or equipment-related conditions. We have developed software able to derive quality metrics about endoscopist-related factors from streaming video during colonoscopy and immediately inform the endoscopist about the results, i.e., provide real-time feedback. In other words, we have created a system that has the potential to improve endoscopic technique during a colonoscopy in a live patient. Now we propose to optimize the method whereby we provide feedback related to technique to the endoscopist and then to test whether giving feedback indeed results in better technique and at the same time in the discovery and removal of more polyps. This year, approximately 14 million US citizens will undergo colonoscopy for a total cost of around $24 billion and about 50,000 patients will die of colorectal cancer. We strongly believe that use of our software will improve detection and prevention of colorectal cancer.

Agency
National Institute of Health (NIH)
Institute
National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)
Type
Research Project (R01)
Project #
1R01DK106130-01A1
Application #
9173952
Study Section
Nursing and Related Clinical Sciences Study Section (NRCS)
Program Officer
Hamilton, Frank A
Project Start
2016-08-01
Project End
2020-05-31
Budget Start
2016-08-01
Budget End
2017-05-31
Support Year
1
Fiscal Year
2016
Total Cost
Indirect Cost
Name
Mayo Clinic, Rochester
Department
Type
DUNS #
006471700
City
Rochester
State
MN
Country
United States
Zip Code
55905