1
|
Liu W, Wu Y, Yuan X, Zhang J, Zhou Y, Zhang W, Zhu P, Tao Z, He L, Hu B, Yi Z. Artificial intelligence-based assessments of colonoscopic withdrawal technique: a new method for measuring and enhancing the quality of fold examination. Endoscopy 2022; 54:972-979. [PMID: 35391493 PMCID: PMC9500011 DOI: 10.1055/a-1799-8297] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
BACKGROUND This study aimed to develop an artificial intelligence (AI)-based system for measuring fold examination quality (FEQ) of colonoscopic withdrawal technique. We also examined the relationship between the system's evaluation of FEQ and FEQ scores from experts, and adenoma detection rate (ADR) and withdrawal time of colonoscopists, and evaluated the system's ability to improve FEQ during colonoscopy. METHODS First, we developed an AI-based system for measuring FEQ. Next, 103 consecutive colonoscopies performed by 11 colonoscopists were collected for evaluation. Three experts graded FEQ of each colonoscopy, after which the recorded colonoscopies were evaluated by the system. We further assessed the system by correlating its evaluation of FEQ against expert scoring, historical ADR, and withdrawal time of each colonoscopist. We also conducted a prospective observational study to evaluate the system's performance in enhancing fold examination. RESULTS The system's evaluations of FEQ of each endoscopist were significantly correlated with experts' scores (r = 0.871, P < 0.001), historical ADR (r = 0.852, P = 0.001), and withdrawal time (r = 0.727, P = 0.01). For colonoscopies performed by colonoscopists with previously low ADRs (< 25 %), AI assistance significantly improved the FEQ, evaluated by both the AI system (0.29 [interquartile range (IQR) 0.27-0.30] vs. 0.23 [0.17-0.26]) and experts (14.00 [14.00-15.00] vs. 11.67 [10.00-13.33]) (both P < 0.001). CONCLUSION The system's evaluation of FEQ was strongly correlated with FEQ scores from experts, historical ADR, and withdrawal time of each colonoscopist. The system has the potential to enhance FEQ.
Collapse
Affiliation(s)
- Wei Liu
- Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Yu Wu
- Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu, Sichuan, China
| | - Xianglei Yuan
- Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Jingyu Zhang
- State Key Laboratory of Ultrasound in Medicine and Engineering, College of Biomedical Engineering, Chongqing Medical University, Chongqing, Sichuan, China
| | - Yao Zhou
- Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu, Sichuan, China
| | - Wanhong Zhang
- Department of Gastroenterology, Cangxi Peopleʼs Hospital, Guangyuan, Sichuan, China
| | - Peipei Zhu
- Department of Gastroenterology, Dazhou Integrated Traditional Chinese and Western Medicine Hosptial, Dazhou, Sichuan, China
| | - Zhang Tao
- Department of Gastroenterology, Nanchong Central Hospital, Nanchong, Sichuan, China
| | - Long He
- Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Bing Hu
- Department of Gastroenterology, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Zhang Yi
- Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu, Sichuan, China
| |
Collapse
|
2
|
Castaneda D, Popov VB, Verheyen E, Wander P, Gross SA. New technologies improve adenoma detection rate, adenoma miss rate, and polyp detection rate: a systematic review and meta-analysis. Gastrointest Endosc 2018; 88:209-222.e11. [PMID: 29614263 DOI: 10.1016/j.gie.2018.03.022] [Citation(s) in RCA: 43] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/27/2017] [Accepted: 03/25/2018] [Indexed: 12/11/2022]
Abstract
BACKGROUND AND AIMS The need to increase the adenoma detection rate (ADR) for colorectal cancer screening has ushered in devices that mechanically or optically improve conventional colonoscopy. Recently, new technology devices (NTDs) have become available. We aimed to compare the ADR, polyp detection rate (PDR), and adenoma miss rate (AMR) between NTDs and conventional colonoscopy and between mechanical and optical NTDs. METHODS MEDLINE and Embase databases were searched from inception through September 2017 for articles or abstracts reporting ADR, PDR, and AMR with NTDs. Randomized controlled trials and case-control studies with >10 subjects were included. Primary outcomes included ADR, PDR, and AMR odds ratio (OR) between conventional colonoscopy and NTDs. Secondary outcomes included cecal intubation rates, adverse events, cecal intubation time, and total colonoscopy time. RESULTS From 141 citations, 45 studies with 20,887 subjects were eligible for ≥1 analyses. Overall, the ORs for ADR (1.35; 95% confidence interval [CI] 1.24-1.47; P < .01) and PDR (1.51; 95% CI, 1.37-1.67; P < .01) were higher with NTDs. Higher ADR (OR, 1.52 vs 1.25; P = .035) and PDR (OR, 1.63 vs 1.10; P ≤ .01) were observed with mechanical NTDs. The overall AMR with NTDs was lower compared with conventional colonoscopy (OR, .19; 95% CI, .14-.26; P < .01). Mechanical NTDs had lower AMRs compared with optical NTDs (OR, .10 vs .33; P < .01). No differences in cecal intubation rates, cecal intubation time, or total colonoscopy time were found. CONCLUSIONS Newer endoscopic technologies are an effective option to improve ADR and PDR and decrease AMR, particularly with mechanical NTDs. No differences in operability and safety were found.
Collapse
Affiliation(s)
- Daniel Castaneda
- Department of Medicine, Mount Sinai St. Luke's-West Hospitals, Icahn School of Medicine, New York, New York, USA
| | - Violeta B Popov
- Division of Gastroenterology, New York VA Harbor Healthcare, NYU School of Medicine, New York, New York, USA
| | - Elijah Verheyen
- Department of Medicine, Mount Sinai St. Luke's-West Hospitals, Icahn School of Medicine, New York, New York, USA
| | - Praneet Wander
- Department of Gastroenterology, Northshore Long Island Jewish Hospital, New York, New York, USA
| | - Seth A Gross
- Clinical Care and Quality, Division of Gastroenterology, NYU Langone Health, NYU School of Medicine, New York, New York, USA
| |
Collapse
|
3
|
Abstract
The correlation between a low adenoma detection rate (ADR) and interval cancers (ICs) has made ADR one of the most important quality indicators for colonoscopy. Data from nation-wide colorectal cancer (CRC) screening programs showed that there is room for improvement in ADR in order to reduce ICs in Taiwan. Measures with and without adjunct tools have been shown to have the potential to increase ADR, with the latter being more convenient to apply without additional cost. Optimal withdrawal techniques coupled with sufficient withdrawal time, training endoscopists with emphasis on recognition of subtle characteristics of flat lesions, dynamic position changes during the withdrawal phase, removing small polyps found during insertion, and retroflexion in the right colon have all been associated with increased ADR. In particular, water exchange (WE), which is characterized using water in lieu of air and suction removal of infused water during insertion, appears to meet the needs of colonoscopy patients in Taiwan. Analyses of both primary and secondary outcome variables of recently published studies have consistently shown that WE yields higher ADR than traditional air insufflation, even in propofol-sedated patients. Colonoscopists participating in the nationwide CRC screening program in Taiwan should consider applying one or more of the above measures to improve ADR and hopefully reduce ICs.
Collapse
Affiliation(s)
- Yu-Hsi Hsieh
- Division of Gastroenterology, Department of Medicine, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan.,School of Medicine, Tzu Chi University, Hualien, Taiwan
| | - Felix W Leung
- Sepulveda Ambulatory Care Center, Veterans Affairs Greater Los Angeles Healthcare System, North Hill, CA, USA.,Division of Gastroenterology, Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA
| |
Collapse
|
4
|
Mir FA, Boumitri C, Ashraf I, Matteson-Kome ML, Nguyen DL, Puli SR, Bechtold ML. Cap-assisted colonoscopy versus standard colonoscopy: is the cap beneficial? A meta-analysis of randomized controlled trials. Ann Gastroenterol 2017; 30:640-648. [PMID: 29118558 PMCID: PMC5670283 DOI: 10.20524/aog.2017.0180] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/28/2017] [Accepted: 06/21/2017] [Indexed: 12/14/2022] Open
Abstract
Background: In an effort to improve visualization during colonoscopy, a transparent plastic cap or hood may be placed on the end of the colonoscope. Cap-assisted colonoscopy (CAC) has been studied and is thought to improve polyp detection. Numerous studies have been conducted comparing pertinent clinical outcomes between CAC and standard colonoscopy (SC) with inconsistent results. Methods: Numerous databases were searched in November 2016. Only randomized controlled trials (RCTs) involving adult subjects that compared CAC to SC were included. Outcomes of total colonoscopy time, time to cecum, cecal intubation rate, terminal ileum intubation rate, polyp detection rate (PDR), and adenoma detection rate (ADR) were analyzed in terms of odds ratio (OR) or mean difference (MD) with fixed effect and random effects models. Results: Five hundred eighty-nine articles and abstracts were discovered. Of these, 23 RCTs (n=12,947) were included in the analysis. CAC showed statistically significant superiority in total colonoscopy time (MD -1.51 min; 95% confidence interval [CI] -2.67 to -0.34; P<0.01) and time to cecum (MD -0.82 min; 95%CI -1.20 to -0.44; P<0.01) compared to SC. CAC also showed better PDR (OR 1.17; 95%CI 1.06-1.29; P<0.01) but not ADR (OR 1.11; 95%CI 0.95-1.30; P=0.20). In contrast, on sensitivity analysis, ADR was better with CAC. Terminal ileum intubation and cecal intubation rates demonstrated no significant difference between the two groups (P=0.11 and P=0.73, respectively). Conclusions: The use of a transparent cap during colonoscopy improves PDR while reducing procedure times. ADR may improve in cap-assisted colonoscopy but further studies are required to confirm this.
Collapse
Affiliation(s)
- Fazia A Mir
- Department of Medicine, University of Missouri, Columbia (Fazia A. Mir, Christine Boumitri, Imran Ashraf, Michelle L. Matteson-Kome, Matthew L. Bechtold), USA
| | - Christine Boumitri
- Department of Medicine, University of Missouri, Columbia (Fazia A. Mir, Christine Boumitri, Imran Ashraf, Michelle L. Matteson-Kome, Matthew L. Bechtold), USA
| | - Imran Ashraf
- Department of Medicine, University of Missouri, Columbia (Fazia A. Mir, Christine Boumitri, Imran Ashraf, Michelle L. Matteson-Kome, Matthew L. Bechtold), USA
| | - Michelle L Matteson-Kome
- Department of Medicine, University of Missouri, Columbia (Fazia A. Mir, Christine Boumitri, Imran Ashraf, Michelle L. Matteson-Kome, Matthew L. Bechtold), USA
| | - Douglas L Nguyen
- Department of Medicine, University of California, Irvine (Douglas L. Nguyen), USA
| | - Srinivas R Puli
- Department of Medicine, University of Illinois, Peoria (Srinivas R. Puli), USA
| | - Matthew L Bechtold
- Department of Medicine, University of Missouri, Columbia (Fazia A. Mir, Christine Boumitri, Imran Ashraf, Michelle L. Matteson-Kome, Matthew L. Bechtold), USA
| |
Collapse
|