Dataset Information

Artificial Intelligence-Aid Colonoscopy Vs. Conventional Colonoscopy for Polyp and Adenoma Detection: A Systematic Review of 7 Discordant Meta-Analyses.

ABSTRACT: Objectives: Multiple meta-analyses which investigated the comparative efficacy and safety of artificial intelligence (AI)-aid colonoscopy (AIC) vs. conventional colonoscopy (CC) in the detection of polyp and adenoma have been published. However, a definitive conclusion has not yet been generated. This systematic review selected from discordant meta-analyses to draw a definitive conclusion about whether AIC is better than CC for the detection of polyp and adenoma. Methods: We comprehensively searched potentially eligible literature in PubMed, Embase, Cochrane library, and China National Knowledgement Infrastructure (CNKI) databases from their inceptions until to April 2021. Assessment of Multiple Systematic Reviews (AMSTAR) instrument was used to assess the methodological quality. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist was used to assess the reporting quality. Two investigators independently used the Jadad decision algorithm to select high-quality meta-analyses which summarized the best available evidence. Results: Seven meta-analyses met our selection criteria finally. AMSTAR score ranged from 8 to 10, and PRISMA score ranged from 23 to 26. According to the Jadad decision algorithm, two high-quality meta-analyses were selected. These two meta-analyses suggested that AIC was superior to CC for colonoscopy outcomes, especially for polyp detection rate (PDR) and adenoma detection rate (ADR). Conclusion: Based on the best available evidence, we conclude that AIC should be preferentially selected for the route screening of colorectal lesions because it has potential value of increasing the polyp and adenoma detection. However, the continued improvement of AIC in differentiating the shape and pathology of colorectal lesions is needed.

SUBMITTER: Pan H

PROVIDER: S-EPMC8792899 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:To compare magnetic imaging-assisted colonoscopy (MIC) with conventional colonoscopy (CC).Magnetic imaging technology provides a computer-generated image of the shape and position of the colonoscope onto a monitor to give visual guidance to the endoscopist. It is designed to improve colonoscopy performance and tolerability for patients by enabling visualization of loop formation and endoscope position. Recently, a new version of MIC technology was developed for which there are limited data.To evaluate this latest generation of MIC among experienced rather than inexperienced or trainee endoscopists, a prospective randomized trial was performed using only gastroenterologists with therapeutic endoscopy training. Consecutive patients undergoing elective outpatient colonoscopy were randomized to MIC or CC, with patients blinded to their group assignment. Endoscopic procedural metrics and quantities of conscious sedation medications were recorded during the procedures. The procedure was classified as "usual" or "difficult" by the endoscopist at the conclusion of each case based on the need for adjunctive maneuvers to facilitate endoscope advancement. After more than one hour post-procedure, patients completed a 10 cm visual analogue pain scale to reflect the degree of discomfort experienced during their colonoscopy. The primary outcome was patient comfort expressed by the visual analogue pain score. Secondary outcomes consisted of endoscopic procedural metrics as well as a sedation score derived from standardized dose increments of the conscious sedation medications.Two hundred fifty-three patients were randomized and underwent MIC or CC between September 2011 and October 2012. The groups were similar in terms of the indications for colonoscopy and patient characteristics. There were no differences in cecal intubation rates (100% vs 99%), insertion distance-to-cecum (82 cm vs 83 cm), time-to-cecum (6.5 min vs 7.2 min), or polyp detection rate (47% vs 52%) between the MIC and CC groups. The primary outcome of mean pain score (1.0 vs 0.9 out of 10, P = 0.41) did not differ between MIC and CC groups, nor did the mean sedation score (8.2 vs 8.5, P = 0.34). Within the subgroup of cases considered more challenging or difficult, time-to-cecum was significantly faster with MIC compared to CC, 10.1 min vs 13.4 min respectively (P = 0.01). Sensitivity analyses confirmed a similar pattern of overall findings when each endoscopist was considered separately, demonstrating that the mean results for the entire group were not unduly influenced by outlier results from any one endoscopist.Although the latest version of MIC resulted in faster times-to-cecum within a subgroup of more challenging cases, overall it was no better than CC in terms of patient comfort, sedation requirements and endoscopic procedural metrics, when performed in experienced hands.

Dataset Information

Artificial Intelligence-Aid Colonoscopy Vs. Conventional Colonoscopy for Polyp and Adenoma Detection: A Systematic Review of 7 Discordant Meta-Analyses.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets