CoChat
Sign Up
Cited by 16Colorectal Cancer Screening and DetectionAI in cancer detectionColorectal Cancer Surgical Treatments

Assessment of the role of artificial intelligence in the association between time of day and colonoscopy quality

Open access
Lu, Zihua, Zhang, Lihui, Yao, Liwen, Gong, Dexin, Wu, Lianlian, Xia, Meiqing, Zhang, Jun, Zhou, Wei +6 more·2023·JAMA Network Open
DOI 10.1001/jamanetworkopen.2022.53840PMC PMC9890283
Open this paper in CoChat — free accountOpen PDF

Abstract

Importance: Time of day was associated with a decline in adenoma detection during colonoscopy. Artificial intelligence (AI) systems are effective in improving the adenoma detection rate (ADR), but the performance of AI during different times of the day remains unknown. Objective: To validate whether the assistance of an AI system could overcome the time-related decline in ADR during colonoscopy. Design, Setting, and Participants: This cohort study is a secondary analysis of 2 prospective randomized controlled trials (RCT) from Renmin Hospital of Wuhan University. Consecutive patients undergoing colonoscopy were randomly assigned to either the AI-assisted group or unassisted group from June 18, 2019, to September 6, 2019, and July 1, 2020, to October 15, 2020. The ADR of early and late colonoscopy sessions per half day were compared before and after the intervention of the AI system. Data were analyzed from March to June 2022. Exposure: Conventional colonoscopy or AI-assisted colonoscopy. Main Outcomes and Measures: Adenoma detection rate. Results: A total of 1780 patients (mean [SD] age, 48.61 [13.35] years, 837 [47.02%] women) were enrolled. A total of 1041 procedures (58.48%) were performed in early sessions, with 357 randomized into the unassisted group (34.29%) and 684 into the AI group (65.71%). A total of 739 procedures (41.52%) were performed in late sessions, with 263 randomized into the unassisted group (35.59%) and 476 into the AI group (64.41%). In the unassisted group, the ADR in early sessions was significantly higher compared with that of late sessions (13.73% vs 5.70%; P = .005; OR, 2.42; 95% CI, 1.31-4.47). After the intervention of the AI system, as expected, no statistically significant difference was found (22.95% vs 22.06%, P = .78; OR, 0.96; 95% CI; 0.71-1.29). Furthermore, the AI systems showed better assistance ability on ADR in late sessions compared with early sessions (odds ratio, 3.81; 95% CI, 2.10-6.91 vs 1.60; 95% CI, 1.10-2.34). Conclusions and Relevance: In this cohort study, AI systems showed higher assistance ability in late sessions per half day, which suggests the potential to maintain high quality and homogeneity of colonoscopies and further improve endoscopist performance in large screening programs and centers with high workloads.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1001/jamanetworkopen.2022.53840

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Use of CADe eliminates the adverse effect of number of endoscopies per day on performance.

    “It was found that the number of endoscopies performed in a day by an endoscopist negatively impacted performance [86][87][88] , but the use of CADe eliminates this adverse effect [85] .”

    From Enhancing human-AI collaboration: The case of colonoscopy (2024) · cites this paper as [85]

    The Results (Association of Time of Day and ADR/PDR; page not provided) found no statistically significant early–late difference in adenoma detection rate in the CADe group, which supports a reduced time-of-day effect. But the rate was still numerically lower in late sessions (14.71% versus 25.30%), and the study compared session timing rather than the number of endoscopies performed per day. It therefore does not establish that CADe eliminates the adverse effect claimed. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 31

  1. [1]Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018; 68(6): 394- 424. doi: 10.3322/caac.21492 30207593 · DOI · Paper page
  2. [2]Atkin WS, Edwards R, Kralj-Hans I,; UK Flexible Sigmoidoscopy Trial Investigators. Once-only flexible sigmoidoscopy screening in prevention of colorectal cancer: a multicentre randomised controlled trial. Lancet. 2010; 375(9726): 1624- 1633. doi: 10.1016/S0140-6736(10)60551-X 20430429 · DOI
  3. [3]Doubeni CA, Corley DA, Quinn VP,. Effectiveness of screening colonoscopy in reducing the risk of death from right and left colon cancer: a large community-based study. Gut. 2018; 67(2): 291- 298. doi: 10.1136/gutjnl-2016-312712 27733426 PMC5868294 · DOI
  4. [5]Sanaka MR, Shah N, Mullen KD, Ferguson DR, Thomas C, McCullough AJ. Afternoon colonoscopies have higher failure rates than morning colonoscopies. Am J Gastroenterol. 2006; 101(12): 2726- 2730. doi: 10.1111/j.1572-0241.2006.00887.x 17227519 · DOI
  5. [6]Sanaka MR, Deepinder F, Thota PN, Lopez R, Burke CA. Adenomas are detected more often in morning than in afternoon colonoscopy. Am J Gastroenterol. 2009; 104(7): 1659- 1664. doi: 10.1038/ajg.2009.249 19491841 · DOI
  6. [7]Gurudu SR, Ratuapli SK, Leighton JA, Heigh RI, Crowell MD. Adenoma detection rate is not influenced by the timing of colonoscopy when performed in half-day blocks. Am J Gastroenterol. 2011; 106(8): 1466- 1471. doi: 10.1038/ajg.2011.125 21502998 · DOI · Paper page
  7. [8]Teng TY, Khor SN, Kailasam M, Cheah WK, Lau CCL. Morning colonoscopies are associated with improved adenoma detection rates. Surg Endosc. 2016; 30(5): 1796- 1803. doi: 10.1007/s00464-015-4448-7 26198158 · DOI
  8. [9]Lee TJ, Rees CJ, Blanks RG,. Colonoscopic factors associated with adenoma detection in a national colorectal cancer screening program. Endoscopy. 2014; 46(3): 203- 211. doi: 10.1055/s-0033-1358831 24473907 · DOI · Paper page
  9. [10]Lee A, Iskander JM, Gupta N,. Queue position in the endoscopic schedule impacts effectiveness of colonoscopy. Am J Gastroenterol. 2011; 106(8): 1457- 1465. doi: 10.1038/ajg.2011.87 21448145 PMC4098876 · DOI · Paper page
  10. [11]Spadaccini M, Iannone A, Maselli R,. Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: a systematic review and network meta-analysis. Lancet Gastroenterol Hepatol. 2021; 6(10): 793- 802. doi: 10.1016/S2468-1253(21)00215-6 34363763 · DOI
  11. [12]Marcondes FO, Gourevitch RA, Schoen RE, Crockett SD, Morris M, Mehrotra A. Adenoma detection rate falls at the end of the day in a large multi-site sample. Dig Dis Sci. 2018; 63(4): 856- 859. doi: 10.1007/s10620-018-4947-1 29397494 PMC6715419 · DOI
  12. [13]Wang P, Xiao X, Glissen Brown JR,. Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nat Biomed Eng. 2018; 2(10): 741- 748. doi: 10.1038/s41551-018-0301-3 31015647 · DOI
  13. [14]Gong D, Wu L, Zhang J,. Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study. Lancet Gastroenterol Hepatol. 2020; 5(4): 352- 361. doi: 10.1016/S2468-1253(19)30413-3 31981518 · DOI · Paper page
  14. [15]Yao L, Zhang L, Liu J,. Effect of an artificial intelligence-based quality improvement system on efficacy of a computer-aided detection system in colonoscopy: a four-group parallel study. Endoscopy. 2022; 54(8): 757- 768. doi: 10.1055/a-1706-6174 34823258 · DOI · Paper page
  15. [16]Lee A, Jensen CD, Marks AR, Endoscopist fatigue estimates and colonoscopic adenoma detection in a large community-based setting. Gastrointest Endosc. 2017; 85(3): 601- 610.e2. doi: 10.1016/j.gie.2016.09.033 27702568 PMC5318254 · DOI
  16. [17]Ndounga Diakou LA, Trinquart L, Hróbjartsson A,. Comparison of central adjudication of outcomes and onsite outcome assessment on treatment effect estimates. Cochrane Database Syst Rev. 2016; 3(3): MR000043. doi: 10.1002/14651858.MR000043.pub2 26961577 PMC7187204 · DOI
  17. [18]Elsheikh TM, Kirkpatrick JL, Fischer D, Herbert KD, Renshaw AA. Does the time of day or weekday affect screening accuracy? A pilot correlation study with cytotechnologist workload and abnormal rate detection using the ThinPrep Imaging System. Cancer Cytopathol. 2010; 118(1): 41- 46. doi: 10.1002/cncy.20060 20099317 · DOI
  18. [19]Stec N, Arje D, Moody AR, Krupinski EA, Tyrrell PN. A systematic review of fatigue in radiology: is it a problem? AJR Am J Roentgenol. 2018; 210(4): 799- 806. doi: 10.2214/AJR.17.18613 29446673 · DOI
  19. [20]Korenblit J, Tholey DM, Tolin J,. Effect of the time of day and queue position in the endoscopic schedule on the performance characteristics of endoscopic ultrasound-guided fine-needle aspiration for diagnosing pancreatic malignancies. Endosc Ultrasound. 2016; 5(2): 78- 84. doi: 10.4103/2303-9027.180470 27080605 PMC4850799 · DOI
  20. [21]Joseph DA, Meester RG, Zauber AG,. Colorectal cancer screening: estimated future colonoscopy need and current volume and capacity. Cancer. 2016; 122(16): 2479- 2486. doi: 10.1002/cncr.30070 27200481 PMC5559728 · DOI
  21. [22]Chan MY, Cohen H, Spiegel BM. Fewer polyps detected by colonoscopy as the day progresses at a Veteran’s Administration teaching hospital. Clin Gastroenterol Hepatol. 2009; 7(11): 1217- 1223. doi: 10.1016/j.cgh.2009.07.013 19631284 · DOI
  22. [23]Jover R, Zapater P, Bujanda L,; COLONPREV Study Investigators. Endoscopist characteristics that influence the quality of colonoscopy. Endoscopy. 2016; 48(3): 241- 247. doi: 10.1055/s-0042-100185 26845473 · DOI
  23. [24]Park JH, Kim SJ, Hyun JH,. Correlation between bowel preparation and the adenoma detection rate in screening colonoscopy. Ann Coloproctol. 2017; 33(3): 93- 98. doi: 10.3393/ac.2017.33.3.93 28761869 PMC5534501 · DOI
  24. [25]Shaukat A, Rector TS, Church TR,. Longer withdrawal time is associated with a reduced incidence of interval cancer after screening colonoscopy. Gastroenterology. 2015; 149(4): 952- 957. doi: 10.1053/j.gastro.2015.06.044 26164494 · DOI
  25. [26]Munson GW, Harewood GC, Francis DL. Time of day variation in polyp detection rate for colonoscopies performed on a 3-hour shift schedule. Gastrointest Endosc. 2011; 73(3): 467- 475. doi: 10.1016/j.gie.2010.07.025 20933230 · DOI
  26. [27]Freedman JS, Harari DY, Bamji ND,. The detection of premalignant colon polyps during colonoscopy is stable throughout the workday. Gastrointest Endosc. 2011; 73(6): 1197- 1206. doi: 10.1016/j.gie.2011.01.019 21396640 · DOI
  27. [28]Mahmud N, Cohen J, Tsourides K, Berzin TM. Computer vision and augmented reality in gastrointestinal endoscopy. Gastroenterol Rep (Oxf). 2015; 3(3): 179- 184. doi: 10.1093/gastro/gov027 26133175 PMC4527270 · DOI
  28. [29]Tawfik DS, Profit J, Morgenthaler TI,. Physician burnout, well-being, and work unit safety grades in relationship to reported medical errors. Mayo Clin Proc. 2018; 93(11): 1571- 1580. doi: 10.1016/j.mayocp.2018.05.014 30001832 PMC6258067 · DOI
  29. [30]Pickhardt PJ, Nugent PA, Mysliwiec PA, Choi JR, Schindler WR. Location of adenomas missed by optical colonoscopy. Ann Intern Med. 2004; 141(5): 352- 359. doi: 10.7326/0003-4819-141-5-200409070-00009 15353426 · DOI
  30. [31]Alshabibi AS, Suleiman ME, Tapia KA, Brennan PC. Effects of time of day on radiological interpretation. Clin Radiol. 2020; 75(2): 148- 155. doi: 10.1016/j.crad.2019.10.006 31699432 · DOI
  31. [32]Gu M, Thapa S. Colorectal cancer in the United States and a review of its heterogeneity among Asian American subgroups. Asia Pac J Clin Oncol. 2020; 16(4): 193- 200. doi: 10.1111/ajco.13324 32129941 · DOI

Cited by

Sorted by citations

Authors
Lu, Z., Zhang, L., Yao, L., Gong, D., Wu, L., Xia, M., Zhang, J., Zhou, W., Huang, X., He, C., Wu, H., Zhang, C., Li, X., & Yu, H.
Affiliations
  • Renmin Hospital of Wuhan University (CN)
  • Wuhan City Chinese Medicine Hospital (CN)
Corresponding author
Yu, Honggang
ORCID
Venue
JAMA Network Open
Publisher
American Medical Association (AMA)
Published
2023-01-31
Volume
6
Issue
1
Pages
e2253840
ISSN
2574-3805 (ISSN-L)
DOI
10.1001/jamanetworkopen.2022.53840
PMC
PMC9890283
OpenAlex
W4318667565
Cited by
16
References
1
Citations by year
2026: 4 · 2025: 4 · 2024: 4 · 2023: 4
FWCI
1.88
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JAMA Network Open (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
Health Commission of Hubei Province (WJ202C003)
Topics
  • Health Sciences › Medicine › Oncology › Colorectal Cancer Screening and Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Oncology › Colorectal Cancer Surgical Treatments
Keywords
artificial intelligence-assisted colonoscopy, adenoma detection rate, time of day, colonoscopy quality, colorectal cancer screening, colorectal adenoma, polyp detection rate, colorectal cancer prevention
MeSH terms
Adenoma, Adult, Artificial Intelligence, Colonoscopy, Female, Humans, Male, Middle Aged, Time Factors, Cohort Studies, Randomized Controlled Trials as Topic

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review