Download PDF
CC BY-NC-ND 4.0 · Endosc Int Open 2022; 10(01): E112-E118
DOI: 10.1055/a-1591-0258
Original article

Initial application of deep learning to borescope detection of endoscope working channel damage and residue

Monique T. Barakat
Division of Gastroenterology and Hepatology, Stanford University School of Medicine, Stanford, California, United States
,
Mohit Girotra
Division of Gastroenterology and Hepatology, Stanford University School of Medicine, Stanford, California, United States
,
Subhas Banerjee
Division of Gastroenterology and Hepatology, Stanford University School of Medicine, Stanford, California, United States
› Author Affiliations
› Further Information
Also available at
   Permissions and Reprints

Referred to by:

Borescope inspection of endoscope working channels: Why and how?Endosc Int Open 2022; 10(01): E109-E111
DOI: 10.1055/a-1512-2813

Abstract

Background and study aims Outbreaks of endoscopy-related infections have prompted evaluation for potential contributing factors. We and others have demonstrated the utility of borescope inspection of endoscope working channels to identify occult damage that may impact the adequacy of endoscope reprocessing. The time investment and training necessary for borescope inspection have been cited as barriers preventing implementation. We investigated the utility of artificial intelligence (AI) for streamlining and enhancing the value of borescope inspection of endoscope working channels.

Methods We applied a deep learning AI approach to borescope inspection videos of the working channels of 20 endoscopes in use at our academic institution. We evaluated the sensitivity, accuracy, and reliability of this software for detection of endoscope working channel findings.

Results Overall sensitivity for AI-based detection of borescope inspection findings identified by gold standard endoscopist inspection was 91.4 %. Labels were accurate for 67 % of these working channel findings and accuracy varied by endoscope segment. Read-to-read variability was noted to be minimal, with test-retest correlation value of 0.986. Endoscope type did not predict accuracy of the AI system (P = 0.26).

Conclusions Harnessing the power of AI for detection of endoscope working channel damage and residue could enable sterile processing department technicians to feasibly assess endoscopes for working channel damage and perform endoscope reprocessing surveillance. Endoscopes that accumulate an unacceptable level of damage may be flagged for further manual evaluation and consideration for manufacturer evaluation/repair.



Publication History

Received: 11 August 2020

Accepted: 01 April 2021

Article published online:
14 January 2022

© 2022. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/)

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Herve RC, Keevil CW. Persistent residual contamination in endoscope channels; a fluorescence epimicroscopy study. Endoscopy 2016; 48: 609-616
    Article in Thieme ConnectPubMedGoogle Scholar
  • 2 Kovaleva J, Meessen NE, Peters FT. et al. Is bacteriologic surveillance in endoscope reprocessing stringent enough?. Endoscopy 2009; 41: 913-916
    Article in Thieme ConnectPubMedGoogle Scholar
  • 3 Verfaillie CJ, Bruno MJ, Voori n 't Holt AF. et al. Withdrawal of a novel-design duodenoscope ends outbreak of a VIM-2-producing Pseudomonas aeruginosa. Endoscopy 2015; 47: 493-502
    Article in Thieme ConnectPubMedGoogle Scholar
  • 4 Sorbello M, Di Giacinto I, Corso RM. et al. Prevention is better than the cure, but the cure cannot be worse than the disease: fibreoptic tracheal intubation in COVID-19 patients. Br J Anaesth 2020; 125: e187-e188
    CrossrefPubMedGoogle Scholar
  • 5 Barakat MT, Girotra M, Huang RJ. et al. Scoping the scope: endoscopic evaluation of endoscope working channels with a new high-resolution inspection endoscope (with video). Gastrointest Endosc 2018; 88: 601-611 e601
    CrossrefPubMedGoogle Scholar
  • 6 Ofstead CL, Wetzler HP, Heymann OL. et al. Longitudinal assessment of reprocessing effectiveness for colonoscopes and gastroscopes: Results of visual inspections, biochemical markers, and microbial cultures. Am J Infect Control 2017; 45: e26-e33
    CrossrefPubMedGoogle Scholar
  • 7 Thaker AM, Kim S, Sedarat A. et al. Inspection of endoscope instrument channels after reprocessing using a prototype borescope. Gastrointest Endosc 2018; 88: 612-619
    CrossrefPubMedGoogle Scholar
  • 8 Ofstead CL, Wetzler HP, Eiland JE. et al. Assessing residual contamination and damage inside flexible endoscopes over time. Am J Infect Control 2016; 44: 1675-1677
    CrossrefPubMedGoogle Scholar
  • 9 Barakat MT, Girotra M, Huang RJ. et al. Scoping the scope: endoscopic evaluation of endoscope working channels with a new high-resolution inspection endoscope (with video). Gastrointest Endosc 2018; 4: 601-611.e1
    CrossrefPubMedGoogle Scholar
  • 10 [Anonymous]. AORN Guideline for Processing Flexible Endoscopes. https://aornguidelines.org/guidelines/content?sectionId=173735349
    PubMedGoogle Scholar
  • 11 Visrodia K, Petersen BT. Echoing concerns related to endoscope reprocessing. Gastrointest Endosc 2017; 85: 398-400
    CrossrefPubMedGoogle Scholar
  • 12 ST91 AA. Flexible and semi-rigid endoscope processing in health care facilities. 2015. ISBN ISBN: 978-1-57020-585-9
    Google Scholar
  • 13 Rutala WA, Weber DJ. Healthcare Infection Control Practices Advisory Committee. Guidelines for disinfection and sterilization in healthcare facilities. 2008 https://www.cdc.gov/infectioncontrol/pdf/guidelines/disinfection-guidelines
    PubMedGoogle Scholar
  • 14 Barakat MT, Huang RJ, Banerjee S. Comparison of automated and manual drying in the elimination of residual endoscope working channel fluid after reprocessing (with video). Gastrointest Endosc 2019; 89: 124-132 e122
    CrossrefPubMedGoogle Scholar
  • 15 Collecchia G. [Human and artificial intelligence: comparison and clash of cultures]. Assist Inferm Ric 2018; 37: 212-217
    PubMedGoogle Scholar
  • 16 Dzobo K, Adotey S, Thomford NE. et al. Integrating artificial and human intelligence: a partnership for responsible innovation in biomedical engineering and medicine. OMICS 2019; DOI: 10.1089/omi.2019.0038.
    CrossrefPubMedGoogle Scholar
  • 17 Garwal A, Henkel R, Huang CC. et al. Automation of human semen analysis using a novel artificial intelligence optical microscopic technology. Andrologia 2019; 51: e13440
    PubMedGoogle Scholar
  • 18 Granter SR, Beck AH, Papke DJ. et al. Straw Men, deep learning, and the future of the human microscopist: response to “artificial intelligence and the pathologist: future frenemies?”. Arch Pathol Lab Med 2017; 141: 624
    CrossrefPubMedGoogle Scholar
  • 19 Lallas A, Argenziano G. Artificial intelligence and melanoma diagnosis: ignoring human nature may lead to false predictions. Dermatol Pract Concept 2018; 8: 249-251
    CrossrefPubMedGoogle Scholar
  • 20 Dorado-Diaz PI, Sampedro-Gomez J, Vicente-Palacios V. et al. Applications of artificial intelligence in cardiology. The future is already here. Rev Esp Cardiol (Engl Ed) 2019; 72: 1065-1075
    CrossrefPubMedGoogle Scholar
  • 21 Souza Filho EM, Fernandes FA, Soares CLA. et al. Artificial intelligence in cardiology: concepts, tools and challenges – “The horse is the one who runs, you must be the jockey”. Arq Bras Cardiol 2019; DOI: 10.36660/abc.20180431.
    CrossrefPubMedGoogle Scholar
  • 22 Misawa M, Kudo SE, Mori Y. et al. Artificial Intelligence-assisted polyp detection for colonoscopy: initial experience. Gastroenterology 2018; 154: 2027-2029 e2023
    CrossrefPubMedGoogle Scholar
  • 23 Byrne MF, Shahidi N, Rex DK. Will computer-aided detection and diagnosis revolutionize colonoscopy?. Gastroenterology 2017; 153: 1460-1464 e1461
    CrossrefPubMedGoogle Scholar
  • 24 Clarke J, Skoufalos A, Klasko SK. The human in the middle: artificial intelligence in health care summary proceedings symposium presentation and reactor panel of experts Thomas Jefferson University December 10, 2019. Popul Health Manag 2020; DOI: 10.1089/pop.2020.0030.
    CrossrefPubMedGoogle Scholar
  • 25 US Food and Drug Administration. Duodenoscope Surveillance, sampling & culturing: reducing the risks of infection. https://www.fda.gov/media/111081/download February 2018
    PubMedGoogle Scholar
  • 26 Weber DJ, Sickbert-Bennett EE, Kanamori H. et al. New and emerging infectious diseases (Ebola, Middle Eastern respiratory syndrome coronavirus, carbapenem-resistant Enterobacteriaceae, Candida auris): Focus on environmental survival and germicide susceptibility. Am J Infect Control 2019; 47S: A29-A38
    CrossrefPubMedGoogle Scholar