1
|
Cold KM, Vamadevan A, Vilmann AS, Svendsen MBS, Konge L, Bjerrum F. Computer-aided quality assessment of endoscopist competence during colonoscopy: a systematic review. Gastrointest Endosc 2024; 100:167-176.e1. [PMID: 38580134 DOI: 10.1016/j.gie.2024.04.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/16/2024] [Revised: 03/28/2024] [Accepted: 03/28/2024] [Indexed: 04/07/2024]
Abstract
BACKGROUND AND AIMS Endoscopists' competence can vary widely, as shown in the variation in the adenoma detection rate (ADR). Computer-aided quality assessment (CAQ) can automatically assess performance during individual procedures. In this review we identified and described different CAQ systems for colonoscopy. METHODS A systematic review of the literature was done using MEDLINE, EMBASE, and Scopus based on 3 blocks of terms according to the inclusion criteria: colonoscopy, competence assessment, and automatic evaluation. Articles were systematically reviewed by 2 reviewers, first by abstract and then in full text. The methodological quality was assessed using the Medical Education Research Study Quality Instrument (MERSQI). RESULTS Of 12,575 identified studies, 6831 remained after removal of duplicates and 6806 did not pass the eligibility criteria and were excluded, leaving 25 studies, of which 13 studies were included in the final analysis. Five categories of CAQ systems were identified: withdrawal speedometer (7 studies), endoscope movement analysis (3 studies), effective withdrawal time (1 study), fold examination quality (1 study), and visual gaze pattern (1 study). The withdrawal speedometer was the only CAQ system that tested its feedback by examining changes in ADR. Three studies observed an improvement in ADR, and 2 studies did not. The methodological quality of the studies was high (mean MERSQI, 15.2 points; maximum, 18 points). CONCLUSIONS Thirteen studies developed or tested CAQ systems, most frequently by correlating it to the ADR. Only 5 studies tested feedback by implementing the CAQ system. A meta-analysis was impossible because of the heterogeneous study designs, and more studies are warranted.
Collapse
Affiliation(s)
- Kristoffer Mazanti Cold
- Copenhagen Academy for Medical Education and Simulation (CAMES), Center for HR & Education, the Capital Region of Denmark, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Anishan Vamadevan
- Copenhagen Academy for Medical Education and Simulation (CAMES), Center for HR & Education, the Capital Region of Denmark, Copenhagen, Denmark
| | - Andreas Slot Vilmann
- Copenhagen Academy for Medical Education and Simulation (CAMES), Center for HR & Education, the Capital Region of Denmark, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark; Gastrounit, Surgical Section, Copenhagen University Hospital-Herlev and Gentofte, Herlev, Denmark
| | - Morten Bo Søndergaard Svendsen
- Copenhagen Academy for Medical Education and Simulation (CAMES), Center for HR & Education, the Capital Region of Denmark, Copenhagen, Denmark; Department of Computer Science, Faculty of Science, University of Copenhagen, Copenhagen, Denmark
| | - Lars Konge
- Copenhagen Academy for Medical Education and Simulation (CAMES), Center for HR & Education, the Capital Region of Denmark, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Flemming Bjerrum
- Copenhagen Academy for Medical Education and Simulation (CAMES), Center for HR & Education, the Capital Region of Denmark, Copenhagen, Denmark; Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark; Gastrounit, Surgical Section, Copenhagen University Hospital-Amager and Hvidovre, Hvidovre, Denmark
| |
Collapse
|
2
|
Wittbrodt M, Klug M, Etemadi M, Yang A, Pandolfino JE, Keswani RN. Assessment of colonoscopy skill using machine learning to measure quality: Proof-of-concept and initial validation. Endosc Int Open 2024; 12:E849-E853. [PMID: 38966321 PMCID: PMC11221895 DOI: 10.1055/a-2333-8138] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/22/2024] [Accepted: 05/14/2024] [Indexed: 07/06/2024] Open
Abstract
Background and study aims Low-quality colonoscopy increases cancer risk but measuring quality remains challenging. We developed an automated, interactive assessment of colonoscopy quality (AI-CQ) using machine learning (ML). Methods Based on quality guidelines, metrics selected for AI development included insertion time (IT), withdrawal time (WT), polyp detection rate (PDR), and polyps per colonoscopy (PPC). Two novel metrics were also developed: HQ-WT (time during withdrawal with clear image) and WT-PT (withdrawal time subtracting polypectomy time). The model was pre-trained using a self-supervised vision transformer on unlabeled colonoscopy images and then finetuned for multi-label classification on another mutually exclusive colonoscopy image dataset. A timeline of video predictions and metric calculations were presented to clinicians in addition to the raw video using a web-based application. The model was externally validated using 50 colonoscopies at a second hospital. Results The AI-CQ accuracy to identify cecal intubation was 88%. IT ( P = 0.99) and WT ( P = 0.99) were highly correlated between manual and AI-CQ measurements with a median difference of 1.5 seconds and 4.5 seconds, respectively. AI-CQ PDR did not significantly differ from manual PDR (47.6% versus 45.5%, P = 0.66). Retroflexion was correctly identified in 95.2% and number of right colon evaluations in 100% of colonoscopies. HQ-WT was 45.9% of, and significantly correlated with ( P = 0.85) WT time. Conclusions An interactive AI assessment of colonoscopy skill can automatically assess quality. We propose that this tool can be utilized to rapidly identify and train providers in need of remediation.
Collapse
Affiliation(s)
| | - Matthew Klug
- Information Services, Northwestern Medicine, Chicago, United States
| | - Mozziyar Etemadi
- Information Services, Northwestern Medicine, Chicago, United States
- Anesthesiology, Northwestern University Feinberg School of Medicine, Chicago, United States
| | - Anthony Yang
- Surgery, Indiana University School of Medicine, Indianapolis, United States
| | - John E. Pandolfino
- Medicine, Northwestern University Feinberg School of Medicine, Chicago, United States
| | - Rajesh N. Keswani
- Medicine, Northwestern University Feinberg School of Medicine, Chicago, United States
| |
Collapse
|
3
|
Jong MR, de Groof AJ. Advancement of artificial intelligence systems for surveillance endoscopy of Barrett's esophagus. Dig Liver Dis 2024; 56:1126-1130. [PMID: 38071181 DOI: 10.1016/j.dld.2023.11.038] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 11/27/2023] [Accepted: 11/28/2023] [Indexed: 06/29/2024]
Abstract
Barrett's esophagus (BE) is a precursor disease for esophageal adenocarcinoma. Timely detection and treatment has significant influence on patient outcomes. Over the last years, several artificial intelligence (AI) systems have emerged to assist the endoscopist. The primary focus of research has been computer aided detection (CADe). Several groups have succeeded in developing competitive models for neoplasia detection. Additionally, computer aided diagnosis (CADx) models have been developed for subsequent lesion characterization and assistance in clinical decision making. Future studies should focus on bridging the domain gap between academic development and integration in daily practice.
Collapse
Affiliation(s)
- M R Jong
- Department of Gastroenterology and Hepatology, Amsterdam Gastroenterology Endocrinology Metabolism, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands
| | - A J de Groof
- Department of Gastroenterology and Hepatology, Amsterdam Gastroenterology Endocrinology Metabolism, Amsterdam UMC, University of Amsterdam, Amsterdam, the Netherlands.
| |
Collapse
|
4
|
Lui TKL, Ko MKL, Liu JJ, Xiao X, Leung WK. Artificial intelligence-assisted real-time monitoring of effective withdrawal time during colonoscopy: a novel quality marker of colonoscopy. Gastrointest Endosc 2024; 99:419-427.e6. [PMID: 37858761 DOI: 10.1016/j.gie.2023.10.035] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Revised: 10/06/2023] [Accepted: 10/11/2023] [Indexed: 10/21/2023]
Abstract
BACKGROUND AND AIMS The importance of withdrawal time during colonoscopy cannot be overstated in mitigating the risk of missed lesions and postcolonoscopy colorectal cancer. We evaluated a novel colonoscopy quality metric called the effective withdrawal time (EWT), which is an artificial intelligence (AI)-derived quantitative measure of quality withdrawal time, and its association with various colonic lesion detection rates as compared with standard withdrawal time (SWT). METHODS Three hundred fifty video recordings of colonoscopy withdrawal (from the cecum to the anus) were assessed by the new AI model. The primary outcome was adenoma detection rate (ADR) according to different quintiles of EWT. Multivariate logistic regression, adjusting for baseline covariates, was used to determine the adjusted odd ratios (ORs) for EWT on lesion detection rates, with the lowest quintile as reference. The area under the receiver-operating characteristic curve of EWT was compared with SWT. RESULTS The crude ADR in different quintiles of EWT, from lowest to highest, was 10.0%, 31.4%, 33.3%, 53.5%, and 85.7%. The ORs of detecting adenomas and polyps were significantly higher in all top 4 quintiles when compared with the lowest quintile. Each minute increase in EWT was associated with a 49% increase in ADR (aOR, 1.49; 95% confidence interval [CI], 1.36-1.65). The area under the receiver-operating characteristic curve of EWT was also significantly higher than SWT on adenoma detection (.80 [95% CI, .75-.84] vs .70 [95% CI, .64-.74], P < .01). CONCLUSIONS AI-derived monitoring of EWT is a promising novel quality indicator for colonoscopy, which is more associated with ADR than SWT.
Collapse
Affiliation(s)
- Thomas K L Lui
- Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
| | - Michael K L Ko
- Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
| | | | | | - Wai K Leung
- Department of Medicine, Queen Mary Hospital, University of Hong Kong, Hong Kong, China
| |
Collapse
|
5
|
Mansour NM. Artificial Intelligence in Colonoscopy. Curr Gastroenterol Rep 2023; 25:122-129. [PMID: 37129831 DOI: 10.1007/s11894-023-00872-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/03/2023] [Indexed: 05/03/2023]
Abstract
PURPOSE OF REVIEW Artificial intelligence (AI) is a rapidly growing field in gastrointestinal endoscopy, and its potential applications are virtually endless, with studies demonstrating use of AI for early gastric cancer, inflammatory bowel disease, Barrett's esophagus, capsule endoscopy, as well as other areas in gastroenterology. Much of the early studies and applications of AI in gastroenterology have revolved around colonoscopy, particularly with regards to real-time polyp detection and characterization. This review will cover much of the existing data on computer-aided detection (CADe), computer-aided diagnosis (CADx), and briefly discuss some other interesting applications of AI for colonoscopy, while also considering some of the challenges and limitations that exist around the use of AI for colonoscopy. RECENT FINDINGS Multiple randomized controlled trials have now been published which show a statistically significant improvement when using AI to improve adenoma detection and reduce adenoma miss rates during colonoscopy. There is also a growing pool of literature showing that AI can be helpful for characterizing/diagnosing colorectal polyps in real time. AI has also shown promise in other areas of colonoscopy, including polyp sizing and automated measurement and monitoring of quality metrics during colonoscopy. AI is a promising tool that has the ability to shape the future of gastrointestinal endoscopy, with much of the early data showing significant benefits to use of AI during colonoscopy. However, there remain several challenges that may delay or hamper the widespread use of AI in the field.
Collapse
Affiliation(s)
- Nabil M Mansour
- Section of Gastroenterology and Hepatology, Baylor College of Medicine, 7200 Cambridge St., Suite 8B, Houston, TX, 77030, USA.
| |
Collapse
|