Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice

Idan Levy; Liora Bruckmayer; Eyal Klang; Shomron Ben-Horin; Uri Kopylov

doi:10.14309/ajg.0000000000001970

Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice

Idan Levy, Liora Bruckmayer, Eyal Klang, Shomron Ben-Horin, Uri Kopylov^*

^*Corresponding author for this work

Sheba Medical Center at Tel Hashomer

Research output: Contribution to journal › Article › peer-review

49 Scopus citations

Abstract

The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.

Original language	English
Pages (from-to)	1871-1873
Number of pages	3
Journal	American Journal of Gastroenterology
Volume	117
Issue number	11
DOIs	https://doi.org/10.14309/ajg.0000000000001970
State	Published - 1 Nov 2022
Externally published	Yes

Funding

Funders	Funder number
Medtronic

Access to Document

10.14309/ajg.0000000000001970

Cite this

@article{53c3db2e620a4d6687131fb4ea9ff49c,

title = "Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice",

abstract = "The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.",

author = "Idan Levy and Liora Bruckmayer and Eyal Klang and Shomron Ben-Horin and Uri Kopylov",

note = "Publisher Copyright: {\textcopyright} 2021 American Heart Association, Inc.",

year = "2022",

month = nov,

day = "1",

doi = "10.14309/ajg.0000000000001970",

language = "אנגלית",

volume = "117",

pages = "1871--1873",

journal = "American Journal of Gastroenterology",

issn = "0002-9270",

publisher = "Springer Nature",

number = "11",

}

TY - JOUR

T1 - Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice

AU - Levy, Idan

AU - Bruckmayer, Liora

AU - Klang, Eyal

AU - Ben-Horin, Shomron

AU - Kopylov, Uri

PY - 2022/11/1

Y1 - 2022/11/1

N2 - The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.

AB - The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.

UR - http://www.scopus.com/inward/record.url?scp=85141890375&partnerID=8YFLogxK

U2 - 10.14309/ajg.0000000000001970

DO - 10.14309/ajg.0000000000001970

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 36001408

AN - SCOPUS:85141890375

SN - 0002-9270

VL - 117

SP - 1871

EP - 1873

JO - American Journal of Gastroenterology

JF - American Journal of Gastroenterology

IS - 11

ER -

Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this