Comparison of Artificial Intelligence With Other Interventions to Improve Adenoma Detection Rate for Colonoscopy

Abstract

Introduction: Recent randomized controlled trials (RCTs) and metaanalysis have demonstrated improved adenoma detection rate (ADR) for colonoscopy with artificial intelligence (AI) compared with highdefinition (HD) colonoscopy without AI. We aimed to perform a systematic review and network meta-analysis of all RCTs to assess the impact of AI compared with other endoscopic interventions aimed at increasing ADR such as distal attachment devices, dye-based/virtual chromoendoscopy, water-based techniques, and balloon-assisted devices.Methods: A comprehensive literature search of PubMed/Medline, Embase, and Cochrane was performed through May 6, 2022, to include RCTs comparing ADR for any endoscopic intervention mentioned above. Network meta-analysis was conducted using a frequentist approach and random effects model. Relative risk (RR) and 95% CI were calculated for proportional outcome. Results: A total of 94 RCTs with 61,172 patients (mean age 59.1 ± 5.2 y, females 45.8%) and 20 discrete study interventions were included. Network meta-analysis demonstrated significantly improved ADR for AI compared with autofluorescence imaging (

9-Minute Withdrawal Time Improves Adenoma Detection Rate Compared With 6-Minute Withdrawal Time During Colonoscopy

“…We speculate that the benefits will be higher in low detectors as Zhao et al 13 suggested a more pronounced effect. Fifth, with the advent of artificial intelligence (AI), assisted colonoscopy procedures and its effects on ADR, the effects of a longer WT in AI-assisted colonoscopy need to be evaluated 23,24 . Sixth, long-term follow-up is required to delineate the effects of 9WT on interval cancer rate incidence.…”

Artificial intelligence and the push for small adenomas: all we need?

“…They all show a more or less significant increase in detection of small adenomas. The same results are summarized over and over again in no less than 16 meta-analyses 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 , plus a protocol for a further one 36 , as well as a meta-analysis of some of these meta-analyses 37 !…”

“…They all show a more or less significant increase in detection of small adenomas. The same results are summarized over and over again in no less than 16 meta-analyses [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35], plus a protocol for a further one [36], as well as a meta-analysis of some of these meta-analyses [37]! "The question relates to the ultimate clinical relevance of increasing ADR from high to even higher levels …, we still do not know whether we have a cutoff ADR level, above which there is no further improvement in cancer prevention.…”

Harnessing the potential of artificial intelligence‐assisted colonoscopy to reduce the risk of post‐colonoscopy interval colorectal cancer

“…7 A network MA had reported that AI-assisted colonoscopy achieved higher ADR than the use of distal attachments. 8 There are currently no published data on the combined use of AI-assisted colonoscopy and distal attachments, which logically would be synergistic and should further increase ADR. However, there is an ongoing RCT (NCT05133544) on the use Endocuff with or without AI-assisted colonoscopy in the detection of colorectal adenoma.…”

“…A recent RCT with 1813 subjects reported that Endocuff Vision significantly increased ADR (47.8% vs 40.8%; RR 1.17, 95% CI: 1.06–1.30) in a CRC screening program where patients underwent colonoscopy following a positive fecal immunochemical test 7 . A network MA had reported that AI‐assisted colonoscopy achieved higher ADR than the use of distal attachments 8 . There are currently no published data on the combined use of AI‐assisted colonoscopy and distal attachments, which logically would be synergistic and should further increase ADR.…”