|
1
|
Feng L, Xu J, Ji X, Chen L, Xing S, Liu B, Han J, Zhao K, Li J, Xia S, Guan J, Yan C, Tong Q, Long H, Zhang J, Chen R, Tian D, Luo X, Xiao F, Liao J. Development and validation of a three-dimensional deep learning-based system for assessing bowel preparation on colonoscopy video. Front Med (Lausanne) 2023; 10:1296249. [PMID: 38164219 PMCID: PMC10757977 DOI: 10.3389/fmed.2023.1296249] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Accepted: 12/01/2023] [Indexed: 01/03/2024] Open
Abstract
Background The performance of existing image-based training models in evaluating bowel preparation on colonoscopy videos was relatively low, and only a few models used external data to prove their generalization. Therefore, this study attempted to develop a more precise and stable AI system for assessing bowel preparation of colonoscopy video. Methods We proposed a system named ViENDO to assess the bowel preparation quality, including two CNNs. First, Information-Net was used to identify and filter out colonoscopy video frames unsuitable for Boston bowel preparation scale (BBPS) scoring. Second, BBPS-Net was trained and tested with 5,566 suitable short video clips through three-dimensional (3D) convolutional neural network (CNN) technology to detect BBPS-based insufficient bowel preparation. Then, ViENDO was applied to complete withdrawal colonoscopy videos from multiple centers to predict BBPS segment scores in clinical settings. We also conducted a human-machine contest to compare its performance with endoscopists. Results In video clips, BBPS-Net for determining inadequate bowel preparation generated an area under the curve of up to 0.98 and accuracy of 95.2%. When applied to full-length withdrawal colonoscopy videos, ViENDO assessed bowel cleanliness with an accuracy of 93.8% in the internal test set and 91.7% in the external dataset. The human-machine contest demonstrated that the accuracy of ViENDO was slightly superior compared to most endoscopists, though no statistical significance was found. Conclusion The 3D-CNN-based AI model showed good performance in evaluating full-length bowel preparation on colonoscopy video. It has the potential as a substitute for endoscopists to provide BBPS-based assessments during daily clinical practice.
Collapse
Affiliation(s)
- Lina Feng
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jiaxin Xu
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xuantao Ji
- Wuhan United Imaging Healthcare Surgical Technology Co., Ltd., Wuhan, China
| | - Liping Chen
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Shuai Xing
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Bo Liu
- Wuhan United Imaging Healthcare Surgical Technology Co., Ltd., Wuhan, China
| | - Jian Han
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Kai Zhao
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Junqi Li
- Changzhou United Imaging Healthcare Surgical Technology Co., Ltd., Changzhou, China
| | - Suhong Xia
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jialun Guan
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Chenyu Yan
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China
| | - Qiaoyun Tong
- Department of Gastroenterology, Yichang Central People’s Hospital, China Three Gorges University, Yichang, China
| | - Hui Long
- Department of Gastroenterology, Tianyou Hospital, Wuhan University of Science and Technology, Wuhan, China
| | - Juanli Zhang
- Department of Gastroenterology, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan, China
- Department of Gastroenterology, Affiliated Hospital of Hubei University of Chinese Medicine, Wuhan, China
| | - Ruihong Chen
- Department of Gastroenterology, Xiantao First People’s Hospital Affiliated to Yangtze University, Wuhan, China
| | - Dean Tian
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaoping Luo
- Department of Pediatrics, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Fang Xiao
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jiazhi Liao
- Department of Gastroenterology, Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|
|
2
|
Galati JS, Duve RJ, O'Mara M, Gross SA. Artificial intelligence in gastroenterology: A narrative review. Artif Intell Gastroenterol 2022; 3:117-141. [DOI: 10.35712/aig.v3.i5.117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/09/2022] [Revised: 11/21/2022] [Accepted: 12/21/2022] [Indexed: 12/28/2022] Open
Abstract
Artificial intelligence (AI) is a complex concept, broadly defined in medicine as the development of computer systems to perform tasks that require human intelligence. It has the capacity to revolutionize medicine by increasing efficiency, expediting data and image analysis and identifying patterns, trends and associations in large datasets. Within gastroenterology, recent research efforts have focused on using AI in esophagogastroduodenoscopy, wireless capsule endoscopy (WCE) and colonoscopy to assist in diagnosis, disease monitoring, lesion detection and therapeutic intervention. The main objective of this narrative review is to provide a comprehensive overview of the research being performed within gastroenterology on AI in esophagogastroduodenoscopy, WCE and colonoscopy.
Collapse
Affiliation(s)
- Jonathan S Galati
- Department of Medicine, NYU Langone Health, New York, NY 10016, United States
| | - Robert J Duve
- Department of Internal Medicine, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, Buffalo, NY 14203, United States
| | - Matthew O'Mara
- Division of Gastroenterology, NYU Langone Health, New York, NY 10016, United States
| | - Seth A Gross
- Division of Gastroenterology, NYU Langone Health, New York, NY 10016, United States
| |
Collapse
|
|
3
|
Walsh CM, Lightdale JR, Fishman DS, Furlano RI, Mamula P, Gillett PM, Narula P, Hojsak I, Oliva S, Homan M, Riley MR, Huynh HQ, Rosh JR, Jacobson K, Tavares M, Leibowitz IH, Utterson EC, Croft NM, Mack DR, Brill H, Liu QY, Bontems P, Lerner DG, Amil-Dias J, Kramer RE, Otley AR, Ambartsumyan L, Connan V, McCreath GA, Thomson MA. Pediatric Endoscopy Quality Improvement Network Pediatric Endoscopy Reporting Elements: A Joint NASPGHAN/ESPGHAN Guideline. J Pediatr Gastroenterol Nutr 2022; 74:S53-S62. [PMID: 34402488 DOI: 10.1097/mpg.0000000000003266] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
INTRODUCTION High-quality procedure reports are a cornerstone of high-quality pediatric endoscopy as they ensure the clear communication of procedural events and outcomes, guide patient care and facilitate continuous quality improvement. The aim of this document is to outline standardized reporting elements that achieved international consensus as requirements for high-quality pediatric endoscopy procedure reports. METHODS With support from the North American and European Societies of Pediatric Gastroenterology, Hepatology and Nutrition (NASPGHAN and ESPGHAN), an international working group of the Pediatric Endoscopy Quality Improvement Network (PEnQuIN) used Delphi methodology to identify key elements that should be found in all pediatric endoscopy reports. Item reduction was attained through iterative rounds of anonymized online voting using a 6-point scale. Responses were analyzed after each round and items were excluded from subsequent rounds if ≤50% of panelists rated them as 5 ("agree moderately") or 6 ("agree strongly"). Reporting elements that ≥70% of panelists rated as "agree moderately" or "agree strongly" were considered to have achieved consensus. RESULTS Twenty-six PEnQuIN group members from 25 centers internationally rated 63 potential reporting elements that were generated from a systematic literature review and the Delphi panelists. The response rates were 100% for all three survey rounds. Thirty reporting elements reached consensus as essential for inclusion within a pediatric endoscopy report. DISCUSSION It is recommended that the PEnQuIN Reporting Elements for pediatric endoscopy be universally employed across all endoscopists, procedures and facilities as a foundational means of ensuring high-quality endoscopy services, while facilitating quality improvement activities in pediatric endoscopy.
Collapse
Affiliation(s)
- Catharine M Walsh
- Division of Gastroenterology, Hepatology and Nutrition and the Research and Learning Institutes, The Hospital for Sick Children, Department of Paediatrics and the Wilson Centre, University of Toronto, Toronto, Ontario, Canada
| | - Jenifer R Lightdale
- Division of Gastroenterology and Nutrition, UMass Memorial Children's Medical Center, Department of Pediatrics, University of Massachusetts Medical School, Worcester, MA, United States
| | - Douglas S Fishman
- Section of Pediatric Gastroenterology, Hepatology and Nutrition, Texas Children's Hospital, Baylor College of Medicine, Houston, TX, United States
| | - Raoul I Furlano
- Pediatric Gastroenterology & Nutrition, Department of Pediatrics, University Children's Hospital Basel, University of Basel, Basel, Switzerland
| | - Petar Mamula
- Division of Gastroenterology, Hepatology and Nutrition, Children's Hospital of Philadelphia, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, United States
| | - Peter M Gillett
- Paediatric Gastroenterology, Hepatology and Nutrition Department, Royal Hospital for Sick Children, Edinburgh, Scotland, United Kingdom
| | - Priya Narula
- Department of Paediatric Gastroenterology, Sheffield Children's NHS Foundation Trust, Sheffield, South Yorkshire, United Kingdom
| | - Iva Hojsak
- Referral Center for Pediatric Gastroenterology and Nutrition, Children's Hospital Zagreb, University of Zagreb Medical School, Zagreb, University J.J. Strossmayer Medical School, Osijek, Croatia
| | - Salvatore Oliva
- Pediatric Gastroenterology and Liver Unit, Maternal and Child Health Department, Umberto I - University Hospital, Sapienza - University of Rome, Rome, Italy
| | - Matjaž Homan
- Department of Gastroenterology, Hepatology and Nutrition, University Children's Hospital, Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia
| | - Matthew R Riley
- Department of Pediatric Gastroenterology, Providence St. Vincent's Medical Center, Portland, OR, United States
| | - Hien Q Huynh
- Pediatric Gastroenterology and Nutrition, Department of Pediatrics, Stollery Children's Hospital, University of Alberta, Edmonton, Alberta, Canada
| | - Joel R Rosh
- Division of Pediatric Gastroenterology, Department of Pediatrics, Goryeb Children's Hospital, Icahn School of Medicine at Mount Sinai, Morristown, NJ, United States
| | - Kevan Jacobson
- Division of Gastroenterology, Hepatology and Nutrition, British Columbia's Children's Hospital and British Columbia Children's Hospital Research Institute, University of British Columbia, Vancouver, British Columbia, Canada
| | - Marta Tavares
- Division of Pediatrics, Pediatric Gastroenterology Department, Centro Materno Infantil do Norte, Centro Hospitalar Universitário do Porto, ICBAS - Instituto de Ciências Biomédicas Abel Salazar, Porto, Portugal
| | - Ian H Leibowitz
- Division of Gastroenterology, Hepatology and Nutrition, Children's National Medical Center, Department of Pediatrics, George Washington University, Washington, DC, United States
| | - Elizabeth C Utterson
- Pediatric Gastroenterology, Hepatology and Nutrition, Department of Pediatrics, Washington University School of Medicine/St. Louis Children's Hospital, St. Louis, MO, United States
| | - Nicholas M Croft
- Blizard Institute, Barts and the London School of Medicine, Queen Mary University of London, London, United Kingdom
| | - David R Mack
- Division of Gastroenterology, Hepatology and Nutrition, Children's Hospital of Eastern Ontario, Department of Pediatrics, University of Ottawa, Ottawa, Ontario, Canada
| | - Herbert Brill
- Division of Gastroenterology & Nutrition, Department of Pediatrics, McMaster Children's Hospital, McMaster University, Department of Paediatrics, William Osler Health System, Department of Pediatrics, University of Toronto, Toronto, Ontario, Canada
| | - Quin Y Liu
- Division of Gastroenterology and Hepatology, Medicine and Pediatrics, Cedars-Sinai Medical Center, David Geffen School of Medicine at UCLA, Los Angeles, CA, United States
| | - Patrick Bontems
- Division of Pediatrics, Department of Pediatric Gastroenterology, Queen Fabiola Children's University Hospital, ICBAS - Université Libre de Bruxelles, Brussels, Belgium
| | - Diana G Lerner
- Division of Pediatrics, Pediatric Gastroenterology, Hepatology and Nutrition, Children's of Wisconsin, Medical College of Wisconsin, Milwaukee, WI, United States
| | - Jorge Amil-Dias
- Pediatric Gastroenterology, Department of Pediatrics, Centro Hospitalar Universitário S. João, Porto, Portugal
| | - Robert E Kramer
- Pediatric Gastroenterology, Hepatology and Nutrition, Department of Pediatrics, Children's Hospital of Colorado, University of Colorado, Aurora, CO, United States
| | - Anthony R Otley
- Gastroenterology & Nutrition, Department of Pediatrics, IWK Health, Dalhousie University, Halifax, Nova Scotia, Canada
| | - Lusine Ambartsumyan
- Division of Gastroenterology and Hepatology, Seattle Children's Hospital, Department of Pediatrics, University of Washington, Seattle, WA, United States
| | - Veronik Connan
- Child Health Evaluative Sciences, SickKids Research Institute, The Hospital for Sick Children, Toronto, Ontario, Canada
| | - Graham A McCreath
- Child Health Evaluative Sciences, SickKids Research Institute, The Hospital for Sick Children, Toronto, Ontario, Canada
| | - Mike A Thomson
- Department of Paediatric Gastroenterology, Sheffield Children's NHS Foundation Trust, Sheffield, South Yorkshire, United Kingdom
| |
Collapse
|
|
4
|
Li JW, Wang LM, Ang TL. Artificial intelligence-assisted colonoscopy: a narrative review of current data and clinical applications. Singapore Med J 2022; 63:118-124. [PMID: 35509251 PMCID: PMC9251247 DOI: 10.11622/smedj.2022044] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/22/2023]
Abstract
Colonoscopy is the reference standard procedure for the prevention and diagnosis of colorectal cancer, which is a leading cause of cancer-related deaths in Singapore. Artificial intelligence systems are automated, objective and reproducible. Artificial intelligence-assisted colonoscopy has recently been introduced into clinical practice as a clinical decision support tool. This review article provides a summary of the current published data and discusses ongoing research and current clinical applications of artificial intelligence-assisted colonoscopy.
Collapse
Affiliation(s)
- James Weiquan Li
- Department of Gastroenterology and Hepatology, Changi General Hospital, Singapore
- Yong Loo Lin School of Medicine, National University of Singapore, Singapore
- SingHealth Duke-NUS Medicine Academic Clinical Programme, Singapore
| | - Lai Mun Wang
- Pathology Section, Department of Laboratory Medicine, Changi General Hospital, Singapore
- SingHealth Duke-NUS Pathology Academic Clinical Programme, Singapore
| | - Tiing Leong Ang
- Department of Gastroenterology and Hepatology, Changi General Hospital, Singapore
- Yong Loo Lin School of Medicine, National University of Singapore, Singapore
- SingHealth Duke-NUS Medicine Academic Clinical Programme, Singapore
| |
Collapse
|
|
5
|
Li JW, Ang TL. Colonoscopy and artificial intelligence: Bridging the gap or a gap needing to be bridged? Artif Intell Gastrointest Endosc 2021; 2:36-49. [DOI: 10.37126/aige.v2.i2.36] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/19/2021] [Revised: 03/27/2021] [Accepted: 04/20/2021] [Indexed: 02/06/2023] Open
Abstract
Research in artificial intelligence (AI) in gastroenterology has increased over the last decade. Colonoscopy represents the most widely published field with regards to its use in gastroenterology. Most studies to date center on polyp detection and characterization, as well as real-time evaluation of adequacy of mucosal exposure for inspection. This review article discusses how advances in AI has bridged certain gaps in colonoscopy. In addition, the gaps formed with the development of AI that currently prevent its routine use in colonoscopy will be explored.
Collapse
Affiliation(s)
- James Weiquan Li
- Department of Gastroenterology and Hepatology, Changi General Hospital, Singapore 529889, Singapore
| | - Tiing Leong Ang
- Department of Gastroenterology and Hepatology, Changi General Hospital, Singapore 529889, Singapore
| |
Collapse
|
|
6
|
Li S, Monachese M, Salim M, Arya N, Sahai AV, Forbes N, Teshima C, Yaghoobi M, Chen YI, Lam E, James P. Standard reporting elements for the performance of EUS: Recommendations from the FOCUS working group. Endosc Ultrasound 2021; 10:84-92. [PMID: 33666183 PMCID: PMC8098847 DOI: 10.4103/eus-d-20-00234] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/07/2023] Open
Abstract
Background and Objectives Quality indicators for the performance of EUS have been developed to monitor and improve service value and patient outcomes. To support the incorporation of these indicators and standardize EUS documentation, we propose standard EUS reporting elements for endosonographers and endoscopy units. Methods A comprehensive literature search and review was performed to identify EUS quality indicators and key components of high-quality standardized EUS reporting. Guidance statements regarding standard EUS reporting elements were developed and reviewed at the Forum for Canadian Endoscopic Ultrasound (FOCUS) 2019 Annual Meeting. Results EUS reporting elements can be divided into preprocedural, intraprocedural, and postprocedural items. Preprocedural components include the type, indication, and urgency of the procedure and patient clinical information and consent. Intraprocedural components include the adequacy and extent of examination, relevant landmarks, lesion characteristics, sampling method, specimen quality, and intraprocedural adverse events. Postprocedural components include a summary and synthesis of relevant findings as well as recommended management and follow-up. Conclusions Standardizing reporting elements may help improve the care of patients undergoing EUS procedures. Our review provides a practical guide and compilation of recommended reporting elements to ensure ongoing best practices and quality improvement in EUS.
Collapse
Affiliation(s)
- Suqing Li
- Division of Gastroenterology and Hepatology, University Health Network, University of Toronto, Toronto, Canada
| | - Marc Monachese
- Division of Gastroenterology and Hepatology, University Health Network, University of Toronto, Toronto, Canada
| | - Misbah Salim
- Division of Gastroenterology and Hepatology, University Health Network, University of Toronto, Toronto, Canada
| | - Naveen Arya
- Division of Gastroenterology, Oakville Trafalgar Memorial Hospital, Oakville, Ontario, Canada
| | - Anand V Sahai
- Division of Gastroenterology, University of Montreal, Montreal, Quebec, Canada
| | - Nauzer Forbes
- Department of Medicine, Division of Gastroenterology and Hepatology, University of Calgary, Calgary, AB, Canada
| | - Christopher Teshima
- Department of Medicine, Division of Gastroenterology, St. Michael's Hospital, University of Calgary, Toronto, Canada
| | - Mohammad Yaghoobi
- Division of Gastroenterology, McMaster University Medical Center, McMaster University, Hamilton, Canada
| | - Yen-I Chen
- Division of Gastroenterology and Hepatology, McGill University Health Centre, Montreal, Canada
| | - Eric Lam
- Department of Medicine, Division of Gastroenterology, University of British Columbia, Vancouver, BC, Canada
| | - Paul James
- Division of Gastroenterology and Hepatology, University Health Network, University of Toronto, Toronto, Canada
| |
Collapse
|
|
7
|
Vilmann AS, Lachenmeier C, Svendsen MBS, Søndergaard B, Park YS, Svendsen LB, Konge L. Using computerized assessment in simulated colonoscopy: a validation study. Endosc Int Open 2020; 8:E783-E791. [PMID: 32490164 PMCID: PMC7247901 DOI: 10.1055/a-1132-5259] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/29/2019] [Accepted: 01/27/2020] [Indexed: 01/06/2023] Open
Abstract
Background and study aims Patient safety during a colonoscopy highly depends on endoscopist competence. Endoscopic societies have been calling for an objective and regular assessment of the endoscopists, but existing assessment tools are time-consuming and prone to bias. We aimed to develop and gather evidence of validity for a computerized assessment tool delivering automatic and unbiased assessment of colonoscopy based on 3 dimensional coordinates from the colonoscope. Methods Twenty-four participants were recruited and divided into two groups based on experience: 12 experienced and 12 novices. Participants performed twice on a physical phantom model with a standardized alpha loop in the sigmoid colon. Data was gathered directly from the Olympus ScopeGuide system providing XYZ-coordinates along the length of the colonoscope. Five different motor skill measures were developed based on the data, named: Travel Length, Tip Progression, Chase Efficiency, Shaft movement without tip progression, and Looping. Results The experinced had a lower travel length ( P < 0.001), tip progression ( P < 0.001), chase efficiency ( P = 0.001) and looping ( P = 0.006), and a higher shaft movement without tip progression ( P < 0.001) reaching the cecum compared with the novices. A composite score was developed based on the five measurements to create a combined score of progression, the 3D-Colonoscopy-Progression-Score (3D-CoPS). The 3D-CoPS revealed a significant difference between groups (experienced: 0.495 (SD 0.303) and novices -0.454 (SD 0.707), P < 0.001). Conclusion This study presents a novel, real-time computerized assessment tool for colonoscopy, and strong evidence of validity was gathered in a simulation-based setting. The system shows promising opportunities for automatic, unbiased and continuous assessment of colonoscopy performance.
Collapse
Affiliation(s)
| | | | | | - Bo Søndergaard
- University Hospital Hvidovre, Department of Gastroenterology and Gastrointestinal Surgery, Copenhagen, Denmark
| | - Yoon Soo Park
- University of Illinois at Chicago, Department of Medical Education, Chicago, Illinois, United States
| | | | - Lars Konge
- Rigshospitalet – CAMES, Copenhagen, Denmark
| |
Collapse
|
|
8
|
Zimmermann-Fraedrich K, Sehner S, Rex DK, Kaltenbach T, Soetikno R, Wallace M, Leung WK, Guo C, Gralnek IM, Brand EC, Groth S, Schachschal G, Ikematsu H, Siersema PD, Rösch T. Right-Sided Location Not Associated With Missed Colorectal Adenomas in an Individual-Level Reanalysis of Tandem Colonoscopy Studies. Gastroenterology 2019; 157:660-671.e2. [PMID: 31103625 DOI: 10.1053/j.gastro.2019.05.011] [Citation(s) in RCA: 20] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/06/2018] [Revised: 05/07/2019] [Accepted: 05/10/2019] [Indexed: 12/14/2022]
Abstract
BACKGROUND & AIMS Interval cancers occur more frequently in the right colon. One reason could be that right-sided adenomas are frequently missed in colonoscopy examinations. We reanalyzed data from tandem colonoscopies to assess adenoma miss rates in relation to location and other factors. METHODS We pooled data from 8 randomized tandem trials comprising 2218 patients who had diagnostic or screening colonoscopies (adenomas detected in 49.8% of patients). We performed a mixed-effects logistic regression with patients as cluster effects with different independent parameters. Factors analyzed included location (left vs right, splenic flexure as cutoff), adenoma size, form, and histologic features. Analyses were controlled for potential confounding factors such as patient sex and age, colonoscopy indication, and bowel cleanliness. RESULTS Right-side location was not an independent risk factor for missed adenomas (odds ratio [OR] compared with the left side, 0.94; 95% CI, 0.75-1.17). However, compared with adenomas ≤5 mm, the OR for missing adenomas of 6-9 mm was 0.62 (95% CI, 0.44-0.87), and the OR for missing adenomas of ≥10 mm was 0.51 (95% CI, 0.33-0.77). Compared with pedunculated adenomas, sessile (OR, 1.82; 95% CI, 1.16-2.85) and flat adenomas (OR, 2.47; 95% CI, 1.49-4.10) were more likely to be missed. Histologic features were not significant risk factors for missed adenomas (OR for adenomas with high-grade intraepithelial neoplasia, 0.68; 95% CI, 0.34-1.37 and OR for sessile serrated adenomas, 0.87; 95% CI, 0.47-1.64 compared with low-grade adenomas). Men had a higher number of adenomas per colonoscopy (1.27; 95% CI, 1.21-1.33) than women (0.86; 95% CI, 0.80-0.93). Men were less likely to have missed adenomas than women (OR for missed adenomas in men, 0.73; 95% CI, 0.57-0.94). CONCLUSIONS In an analysis of data from 8 randomized trials, we found that right-side location of an adenoma does not increase its odds for being missed during colonoscopy but that adenoma size and histologic features do increase risk. Further studies are needed to determine why adenomas are more frequently missed during colonoscopies in women than men.
Collapse
Affiliation(s)
| | - Susanne Sehner
- Department of Medical Biometry and Epidemiology, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Douglas K Rex
- Division of Gastroenterology and Hepatology, Indiana University School of Medicine, Indianapolis, Indiana
| | - Tonya Kaltenbach
- Veterans Administration San Francisco and University of California San Francisco, San Francisco, California
| | - Roy Soetikno
- Veterans Administration San Francisco and University of California San Francisco, San Francisco, California
| | - Michael Wallace
- Division of and Hepatology, Mayo Clinic Jacksonville, Jacksonville, Florida
| | - Wai K Leung
- Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
| | - Chuanguo Guo
- Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
| | - Ian M Gralnek
- Institute of Gastroenterology and Hepatology, Emek Medical Center, Afula, Israel
| | - Eelco C Brand
- Department of Gastroenterology and Hepatology, University Medical Center, Utrecht, The Netherlands
| | - Stefan Groth
- Department of Interdisciplinary Endoscopy, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Guido Schachschal
- Department of Interdisciplinary Endoscopy, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Hiroaki Ikematsu
- Department of Gastroenterology and Gastrointestinal Oncology, National Cancer Center Hospital East, Kashiwa, Chiba, Japan
| | - Peter D Siersema
- Department of Gastroenterology and Hepatology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Thomas Rösch
- Department of Interdisciplinary Endoscopy, University Hospital Hamburg-Eppendorf, Hamburg, Germany.
| |
Collapse
|
|
9
|
Dilly CK, Kahi CJ. Does Increased Adenoma Detection Reduce the Risk of Colorectal Cancer, and How Good Do We Need to Be? Curr Gastroenterol Rep 2019; 21:9. [PMID: 30815756 DOI: 10.1007/s11894-019-0678-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Abstract
PURPOSE OF REVIEW Colorectal cancer (CRC) is largely preventable with colonoscopy and other screening modalities. However, the effectiveness of screening and surveillance depends on the quality of the colonoscopy exam. Adenoma detection rate (ADR) is the best-validated metric by which we measure individual physicians' performance. RECENT FINDINGS Recent evidence suggests that ADR benchmarks may be inappropriately low. There is proof that improving ADR leads to significant reductions in post-colonoscopy CRC (PCCRC). Two studies have demonstrated that when a colonoscopy is performed by physicians with higher ADRs, patients are less likely to have advanced adenomas on surveillance and less likely to develop or die from PCCRC. Finally, there is at least some evidence that higher ADRs do not lead to more cumulative surveillance exams. The ADR is a useful outcome measure that can provide individual endoscopists and their patients with information about the likelihood of developing PCCRC. To achieve the lowest possible PCCRC rate, we should be striving for higher ADRs. While strategies and innovations may help a bit in improving ADRs, our efforts should focus on ensuring a complete mucosal exam for each patient. Behavioral psychology theories may provide useful frameworks for studying motivating factors that drive a careful exam.
Collapse
Affiliation(s)
- Christen K Dilly
- Richard L. Roudebush VA Medical Center, 1481 Street, Indianapolis, IN, 46202, USA. .,Division of Gastroenterology, Hepatology and Nutrition, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
| | - Charles J Kahi
- Richard L. Roudebush VA Medical Center, 1481 Street, Indianapolis, IN, 46202, USA.,Division of Gastroenterology, Hepatology and Nutrition, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| |
Collapse
|
|
10
|
van de Meeberg MM, Ouwendijk RJT, ter Borg PCJ, van den Hazel SJ, van de Meeberg PC. The Polyp Manager: a new tool for optimal polyp documentation during colonoscopy. A pilot study. Endosc Int Open 2016; 4:E572-6. [PMID: 27227117 PMCID: PMC4874792 DOI: 10.1055/s-0042-103414] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/18/2015] [Accepted: 02/08/2016] [Indexed: 11/03/2022] Open
Abstract
BACKGROUND AND STUDY AIMS Conventional reporting of polyps is often incomplete. We tested the Polyp Manager (PM), a new software application permitting the endoscopist to document polyps in real time during colonoscopy. We studied completeness of polyp descriptions, user-friendliness and the potential time benefit. PATIENTS AND METHODS In two Dutch hospitals colonoscopies were performed with PM (as a touchscreen endoscopist-operated device or nurse-operated desktop application). Completeness of polyp descriptions was compared to a historical group with conventional reporting (CRH). Prospectively, we compared user-friendliness (VAS-scores) and time benefit of the endoscopist-operated PM to conventional reporting (CR) in one hospital. Duration of colonoscopy and time needed to report polyps and provide a pathology request were measured. Provided that using PM does not prolong colonoscopy, the sum of the latter two was considered as a potential time-benefit if the PM were fully integrated into a digital reporting system. RESULTS A total of 144 regular colonoscopies were included in the study. Both groups were comparable with regard to patient characteristics, duration of colonoscopy and number of polyps. Using the PM did reduce incomplete documentation of the following items in CRH-reports: location (96 % vs 82 %, P = 0.01), size (95 % vs 89 %, P = 0.03), aspect (71 % vs 36 %, P < 0.001) and completeness of removal (61 % vs 37 %, P < 0.001). In the prospective study 23 PM-colonoscopies where compared to 28 CR-colonoscopies. VAS-scores were significantly higher in the endoscopist-operated PM group. Time to report was 01:27 ± 01:43 minutes (median + interquartile range) in the entire group (PM as CR), reflecting potential time benefit per colonoscopy. CONCLUSIONS The PM is a user-friendly tool that seems to improve completeness of polyp reporting. Once integrated with digital reporting systems, it is probably time saving as well.
Collapse
Affiliation(s)
- Maartje M. van de Meeberg
- Department of Gastroenterology and Hepatology, Slingeland Hospital, Doetinchem, The Netherlands.,Corresponding author Maartje Miep van de Meeberg P.O. Box 169Doetinchem7000 ADThe Netherlands+003-1617345688
| | - Rob J. Th. Ouwendijk
- Departement of Gastroenterology and Hepatology, Ikazia Hospital, Rotterdam, The Netherlands.
| | - Pieter C. J. ter Borg
- Departement of Gastroenterology and Hepatology, Ikazia Hospital, Rotterdam, The Netherlands.
| | - Sven J. van den Hazel
- Department of Gastroenterology and Hepatology, Slingeland Hospital, Doetinchem, The Netherlands.
| | - Paul C. van de Meeberg
- Department of Gastroenterology and Hepatology, Slingeland Hospital, Doetinchem, The Netherlands.
| |
Collapse
|
|
11
|
The Quality of Colonoscopy Reporting in Usual Practice: Are Endoscopists Reporting Key Data Elements? Can J Gastroenterol Hepatol 2016; 2016:1929361. [PMID: 27579299 PMCID: PMC4992524 DOI: 10.1155/2016/1929361] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/19/2015] [Accepted: 07/03/2016] [Indexed: 12/17/2022] Open
Abstract
Background. High quality reporting of endoscopic procedures is critical to the implementation of colonoscopy quality assurance programs. Objective. The aim of our research was to (1) determine the quality of colonoscopy (CS) reporting in "usual practice," (2) identify factors associated with good quality reporting, and (3) compare CS reporting in open-access and non-open-access procedures. Methods. 557 CS reports were randomly selected and assigned a score based on the number of mandatory data elements included in the report. Reports documenting greater than 70% of the mandatory data elements were considered to be of good quality. Physician and procedure factors associated with good quality CS reporting were identified. Results. Variables that were consistently well documented included date of the procedure (99.6%), procedure indication (88.9%), a description of the most proximal anatomical segment reached (98.6%), and documentation of polyp location (97.8%). Approximately 79.4% of the reports were considered to be of good quality. Gastroenterology specialty, lower annual CS volume, and fewer years in practice were associated with good quality reporting. Discussion. CS reporting in usual practice in Ontario lacks quality in several areas. Almost 1 in 5 reports was of poor quality in our study. Conclusions. Targeted interventions and/or use of mandatory fields in synoptic reports should be considered to improve CS reporting.
Collapse
|
|
12
|
A Review on the Quality of Colonoscopy Reporting. Can J Gastroenterol Hepatol 2016; 2016:9423142. [PMID: 27446877 PMCID: PMC4904656 DOI: 10.1155/2016/9423142] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/04/2015] [Accepted: 08/22/2015] [Indexed: 12/21/2022] Open
Abstract
Colonoscopy reports are important communication tools for providers and patients with potential to serve as information sources for research, quality, performance, and resource management. Despite decades of work, studies continue to indicate that colonoscopy reports are often incomplete. Although electronic medical records (EMRs) and databases can address this problem, costs, workflow, and interoperability (difficulty exchanging information between systems) continue to limit adoption and implementation of endoscopy EMRs in Canada and elsewhere. Quality and reporting guidelines alone have proven to be insufficient. In this review we have derived and applied five key themes to challenges in the current state of colonoscopy reporting and propose strategies to address them.
Collapse
|
|
13
|
Finlayson A, Chandra R, Hastie IA, Jones IT, Shedda S, Hong MKY, Yen A, Hayes IP. Triradiate caecal fold: Is it a useful landmark for caecal intubation in colonoscopy? World J Gastrointest Endosc 2015; 7:1103-1106. [PMID: 26421107 PMCID: PMC4580952 DOI: 10.4253/wjge.v7.i13.1103] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/02/2015] [Revised: 08/21/2015] [Accepted: 09/02/2015] [Indexed: 02/05/2023] Open
Abstract
AIM: To determine the frequency of identification of the triradiate fold during colonoscopy and evaluate its reliability as a marker of caecal intubation.
METHODS: One hundred consecutive patients undergoing colonoscopy in a tertiary hospital colorectal unit from May to September 2013 were studied. Video documentation of the caecum was recorded and shown to consultant colorectal surgeons on the unit. Each reviewer was asked through a series of questions to independently identify the triradiate fold. The main outcome was the frequency of visualisation of the triradiate fold in the caecum.
RESULTS: The triradiate fold was seen on average in 18% of cases, but inter-observer agreement was poor. There were only four patients (4%) in which all reviewers agreed on the presence of a triradiate fold. In patients who had undergone previous appendicectomy, the appendiceal orifice was less frequently seen compared with patients who had not undergone appendicectomy.
CONCLUSION: The triradiate fold is infrequently seen during colonoscopy and is therefore an unreliable landmark of caecal intubation.
Collapse
|
|
14
|
Lu JJ, Decker CH, Connolly SE. Improving Endoscopic Adherence to Quality Metrics in Colonoscopy. Ochsner J 2015; 15:413-417. [PMID: 26730225 PMCID: PMC4679302] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/05/2023] Open
Abstract
BACKGROUND Appropriate documentation of quality metrics in the endoscopy reports provides evidence that a thorough and complete examination was performed. The aim of our study was to assess compliance with 3 current quality metrics for colonoscopy defined by the American Society for Gastrointestinal Endoscopy. METHODS We retrospectively examined colonoscopy reports from 6 gastroenterologists at Ochsner Medical Center for appropriate documentation of the quality of the bowel preparation and photodocumentation of the appendiceal orifice and the ileocecal valve. A performance review and educational session then took place with each physician. Subsequent colonoscopy reports were evaluated to monitor for improvement. RESULTS Bowel preparation documentation was high before and after the educational sessions (97.5% and 97.2%). Preeducation, the mean photodocumentation rate of the appendiceal orifice was 55% (range, 23%-84%). For the ileocecal valve, the documentation rate was 32.5% (range, 3%-73%). Posteducation, the mean appendiceal orifice labeling increased to an average of 91%, with a median change of 28.5% (P=0.0313). Documentation of the ileocecal valve improved to an average of 73%, a median change of 37.5% (P=0.0625). CONCLUSION Although reassessment of subsequent reports will be necessary to evaluate the permanence of this intervention, our evidence suggests that educational sessions can improve the quality and accuracy of documentation of quality metrics during colonoscopies.
Collapse
Affiliation(s)
- Jonathan J. Lu
- Department of Internal Medicine, Ochsner Clinic Foundation, New Orleans, LA
| | | | - Sean E. Connolly
- Department of Gastroenterology, Ochsner Clinic Foundation, New Orleans, LA
| |
Collapse
|
|
15
|
Abstract
Colonoscopy is an excellent area for quality improvement because it is high volume, has significant associated risk and expense, and there is evidence that variability in its performance affects outcomes. The best end point for validation of quality metrics in colonoscopy is colorectal cancer incidence and mortality, but a more readily accessible metric is the adenoma detection rate. Fourteen quality metrics were proposed in 2006, and these are described in this article. Implementation of quality improvement initiatives involves rapid assessments and changes on an iterative basis, and can be done at the individual, group, or facility level.
Collapse
|
|
16
|
Quintero E, Alarcón-Fernández O, Jover R. [Colonoscopy quality control as a requirement of colorectal cancer screening]. GASTROENTEROLOGIA Y HEPATOLOGIA 2013; 36:597-605. [PMID: 23769425 DOI: 10.1016/j.gastrohep.2013.02.005] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/12/2013] [Accepted: 02/13/2013] [Indexed: 12/11/2022]
Abstract
The strategies used in population-based colorectal screening strategies culminate in colonoscopy and consequently the success of these programs largely depends on the quality of this diagnostic test. The main factors to consider when evaluating quality are scientific-technical quality, safety, patient satisfaction, and accessibility. Quality indicators allow variability among hospitals, endoscopy units and endoscopists to be determined and can identify those not achieving recommended standards. In Spain, the working group for colonoscopy quality of the Spanish Society of Gastroenterology and the Spanish Society of Gastrointestinal Endoscopy have recently drawn up a Clinical Practice Guideline that contains the available evidence on the quality of screening colonoscopy, as well as the basic requirements that must be met by endoscopy units and endoscopists carrying out this procedure. The implementation of training programs and screening colonoscopy quality controls are strongly recommended to guarantee the success of population-based colorectal cancer screening.
Collapse
Affiliation(s)
- Enrique Quintero
- Servicio de Aparato Digestivo, Hospital Universitario de Canarias, La Laguna, Santa Cruz de Tenerife, España; Servicio de Aparato Digestivo, Universidad de La Laguna, La Laguna, Santa Cruz de Tenerife, España.
| | | | | |
Collapse
|