Cited by 56Colorectal Cancer Screening and DetectionAI in cancer detectionColorectal Cancer Surgical Treatments

Computer-Aided Diagnosis for Leaving Colorectal Polyps In Situ: A Systematic Review and Meta-analysis

Open access
Hassan, Cesare, Misawa, Masashi, Rizkala, Tommy, Mori, Yuichi, Sultan, Shahnaz, Facciorusso, Antonio, Antonelli, Giulio, Spadaccini, Marco +18 more·2024·Annals of Internal Medicine

Abstract

BACKGROUND: Computer-aided diagnosis (CADx) allows prediction of polyp histology during colonoscopy, which may reduce unnecessary removal of nonneoplastic polyps. However, the potential benefits and harms of CADx are still unclear. PURPOSE: To quantify the benefit and harm of using CADx in colonoscopy for the optical diagnosis of small (≤5-mm) rectosigmoid polyps. DATA SOURCES: Medline, Embase, and Scopus were searched for articles published before 22 December 2023. STUDY SELECTION: Histologically verified diagnostic accuracy studies that evaluated the real-time performance of physicians in predicting neoplastic change of small rectosigmoid polyps without or with CADx assistance during colonoscopy. DATA EXTRACTION: The clinical benefit and harm were estimated on the basis of accuracy values of the endoscopist before and after CADx assistance. The certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. The outcome measure for benefit was the proportion of polyps predicted to be nonneoplastic that would avoid removal with the use of CADx. The outcome measure for harm was the proportion of neoplastic polyps that would be not resected and left in situ due to an incorrect diagnosis with the use of CADx. Histology served as the reference standard for both outcomes. DATA SYNTHESIS: Ten studies, including 3620 patients with 4103 small rectosigmoid polyps, were analyzed. The studies that assessed the performance of CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2% to 92.5%) and specificity of 88.9% (CI, 81.7% to 93.5%) in predicting neoplastic change. In the studies that compared histology prediction performance before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; risk ratio [RR], 1.06 [CI, 0.96 to 1.17]; moderate-certainty evidence) or in the proportion of neoplastic polyps that would be erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [CI, 0.69 to 1.33]; moderate-certainty evidence). LIMITATION: The application of optical diagnosis was only simulated, potentially altering the decision-making process of the operator. CONCLUSION: Computer-aided diagnosis provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy. PRIMARY FUNDING SOURCE: European Commission. (PROSPERO: CRD42023402197).

AI snapshot

Written from the paper’s full text.

TL;DR

This systematic review and meta-analysis found that computer-aided diagnosis (CADx) provided no incremental benefit or harm when used to support optical diagnosis of small (≤5-mm) rectosigmoid polyps during colonoscopy. Compared with endoscopists' unassisted predictions, CADx did not significantly change the proportion of nonneoplastic polyps left in situ or the proportion of neoplastic polyps erroneously left in situ.

Key findings

  • Across 10 studies (3620 patients, 4103 small rectosigmoid polyps), studies assessing CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2%–92.5%) and specificity of 88.9% (95% CI, 81.7%–93.5%) for predicting neoplastic change.
  • In the 4 studies comparing performance before versus after CADx assistance (2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; RR, 1.06 [95% CI, 0.96–1.17]; moderate-certainty evidence).
  • There was also no difference in the proportion of neoplastic polyps erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [95% CI, 0.69–1.33]; moderate-certainty evidence).
  • Conclusion: CADx provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy.

Methods

  • Design: Systematic review and meta-analysis of histologically verified diagnostic accuracy studies evaluating real-time physician performance in predicting neoplastic change of small rectosigmoid polyps without or with CADx assistance during colonoscopy.
  • Data sources: Medline, Embase, and Scopus searched for articles published before 22 December 2023.
  • Analysis: Clinical benefit (proportion of polyps predicted nonneoplastic that would avoid removal) and harm (proportion of neoplastic polyps erroneously left in situ) were estimated from endoscopist accuracy before and after CADx assistance, with histology as the reference standard; certainty of evidence assessed using GRADE.

Limitations

  • Stated: The application of optical diagnosis was only simulated, potentially altering the operator's decision-making process.
  • Evident from the text: The benefit/harm estimates derive from simulated rather than actual removal decisions, and the before-versus-after comparison rests on only 4 studies (2503 polyps), with confidence intervals for both outcomes crossing the null.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.7326/m23-2865

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

  • Findingown data
    § Abstract

    In studies assessing CADx alone (9 studies; 3237 polyps), the specificity in predicting neoplastic change was 88.9% (95% CI, 81.7% to 93.5%).

    “The studies that assessed the performance of CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2% to 92.5%) and specificity of 88.9% (CI, 81.7% to 93.5%) in predicting neoplastic change.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § Abstract

    In studies comparing histology prediction before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; RR, 1.06 [CI, 0.96 to 1.17]; moderate-certainty evidence).

    “In the studies that compared histology prediction performance before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; risk ratio [RR], 1.06 [CI, 0.96 to 1.17]; moderate-certainty evidence) or in the proportion of neoplastic polyps that would be erroneously left in situ”
    Quote in the paperSubstantial claim
  • Findingown data
    § Abstract

    Ten studies, including 3620 patients with 4103 small rectosigmoid polyps, were analyzed.

    “Ten studies, including 3620 patients with 4103 small rectosigmoid polyps, were analyzed.”
    Quote in the paperSubstantial claim
  • Findingown data
    § Abstract

    In studies assessing CADx alone (9 studies; 3237 polyps), the sensitivity in predicting neoplastic change was 87.3% (95% CI, 79.2% to 92.5%).

    “The studies that assessed the performance of CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2% to 92.5%) and specificity of 88.9% (CI, 81.7% to 93.5%) in predicting neoplastic change.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § Abstract

    In studies comparing histology prediction before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of neoplastic polyps that would be erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [CI, 0.69 to 1.33]; moderate-certainty evidence).

    “or in the proportion of neoplastic polyps that would be erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [CI, 0.69 to 1.33]; moderate-certainty evidence).”
    Quote in the paperSubstantial claim
  • Classified as probably not a substantial claim. 3
  • May combine two claims. 2
  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given
    § Abstract

    The certainty of evidence was assessed using the GRADE framework.

    “The certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework.”
    Quote in the paperNot a substantial claim
  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given
    § Abstract

    The application of optical diagnosis was only simulated, potentially altering the decision-making process of the operator.

    “The application of optical diagnosis was only simulated, potentially altering the decision-making process of the operator.”
    Quote in the paperNot a substantial claim
  • May combine two claims.

    Interpretationown data
    § Abstract

    Computer-aided diagnosis provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy.

    “Computer-aided diagnosis provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy.”
    Quote in the paperSubstantial claim
  • Classified as probably not a substantial claim.

    Study design and conductnone given
    § Abstract

    Histology served as the reference standard for both outcomes.

    “Histology served as the reference standard for both outcomes.”
    Quote in the paperSubstantial claim
4 of 4
  • The paper relies on this without support.

    Computer-aided diagnosis allows prediction of polyp histology during colonoscopy.

    “Computer-aided diagnosis (CADx) allows prediction of polyp histology during colonoscopy”
  • The paper relies on this without support.

    The potential benefits and harms of CADx are still unclear.

    “However, the potential benefits and harms of CADx are still unclear.”
2 of 2

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Hassan, C., Misawa, M., Rizkala, T., Mori, Y., Sultan, S., Facciorusso, A., Antonelli, G., Spadaccini, M., Houwen, B. B. S. L., Rondonotti, E., Patel, H., Khalaf, K., Li, J. W., Fernandez, G. M., Bhandari, P., Dekker, E., Gross, S., Berzin, T., Vandvik, P. O., Correale, L., Kudo, S.-E., Sharma, P., Rex, D. K., Repici, A., Foroutan, F., & CADx Analysis Study Group
Affiliations
  • Humanitas University (IT)
  • SHOWA Medical University Northern Yokohama Hospital (JP)
  • IRCCS Humanitas Research Hospital (IT)
  • Oslo University Hospital (NO)
  • University of Minnesota (US)
  • University of Foggia (IT)
  • Sapienza University of Rome (IT)
  • Amsterdam University Medical Centers (NL)
  • Ospedale Valduce (IT)
  • Kansas City VA Medical Center (US)
  • St. Michael's Hospital (CA)
  • SingHealth (SG)
  • Endoscopy Unit, Gastroenterology Department, Clinical Institute of Digestive and Metabolic Disease, Hospital Clínic de Barcelona, University of Barcelona, Barcelona, Spain (G.M.F.)
  • Queen Alexandra Hospital (GB)
  • NYU Langone Health (US)
  • Beth Israel Deaconess Medical Center (US)
  • Lovisenberg Diakonale Sykehus (NO)
  • Indiana University Hospital (US)
  • University Health Network (CA)
Corresponding author
  • Hassan, Cesare
  • Misawa, Masashi
  • Repici, Alessandro
  • Foroutan, Farid
Venue
Annals of Internal Medicine
Published
2024-07
Volume
177
Issue
7
Pages
919-928
ISSN
  • 0003-4819 (ISSN-L)
  • 1539-3704
OpenAlex
W4398131119
Cited by
56
References
30
Citations by year
2026: 19 · 2025: 27 · 2024: 10
FWCI
2.99
Type
journal article
Language
en
Open access
Locations
  • Annals of Internal Medicine (publishedVersion)
  • PubMed (publishedVersion)
  • Pure Amsterdam UMC (publishedVersion, other-oa)
  • Radboud Repository (Radboud University) (submittedVersion)
Funders
  • European Commission (101057099)
  • Associazione Italiana per la Ricerca sul Cancro (27843)
  • HORIZON EUROPE Framework Programme (101057099)
  • Japan Society for the Promotion of Science (23K02744)
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
computer-aided diagnosis, colorectal polyps, rectosigmoid polyps, polyp histology prediction, neoplastic polyps, polypectomy, colonoscopy, diagnostic accuracy, benefits and harms, small polyps, endoscopic diagnosis, colorectal cancer prevention, overdiagnosis
MeSH terms
Colonic Polyps, Colonoscopy, Diagnosis, Computer-Assisted, Humans, Colorectal Neoplasms

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.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-11-03.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-11-03.

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