Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study

Objective To estimate the benefits, burden, and harms of implementing computer aided detection (CADe) of polyps in colonoscopy of population based screening programmes for colorectal cancer.Design Microsimulation modelling study.Setting Cost effectiveness working package in the OperA (optimising col...

Full description

Saved in:
Bibliographic Details
Main Authors: Cesare Hassan, Alessandro Repici, Farid Foroutan, Lise M Helsingen, Michael Bretthauer, Mette Kalager, Marco Spadaccini, Yuichi Mori, Magnus Løberg, Per Olav Vandvik, Loredana Correale, Natalie Halvorsen, Nastazja Pilonis, Shanaz Sultan
Format: Article
Language:English
Published: BMJ Publishing Group 2025-03-01
Series:BMJ Medicine
Online Access:https://bmjmedicine.bmj.com/content/4/1/e001446.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850046805530640384
author Cesare Hassan
Alessandro Repici
Farid Foroutan
Lise M Helsingen
Michael Bretthauer
Mette Kalager
Marco Spadaccini
Yuichi Mori
Magnus Løberg
Per Olav Vandvik
Loredana Correale
Natalie Halvorsen
Nastazja Pilonis
Shanaz Sultan
author_facet Cesare Hassan
Alessandro Repici
Farid Foroutan
Lise M Helsingen
Michael Bretthauer
Mette Kalager
Marco Spadaccini
Yuichi Mori
Magnus Løberg
Per Olav Vandvik
Loredana Correale
Natalie Halvorsen
Nastazja Pilonis
Shanaz Sultan
author_sort Cesare Hassan
collection DOAJ
description Objective To estimate the benefits, burden, and harms of implementing computer aided detection (CADe) of polyps in colonoscopy of population based screening programmes for colorectal cancer.Design Microsimulation modelling study.Setting Cost effectiveness working package in the OperA (optimising colorectal cancer prevention through personalised treatment with artificial intelligence) project. A parallel guideline committee panel (BMJ Rapid recommendation) was consulted in defining the screening interventions and selection of outcome measures.Population Four cohorts of 100 000 European individuals aged 60-69 years.Intervention The intervention was one screening of colonoscopy and a screening of colonoscopy after faecal immunochemical test every other year with CADe. The comparison group had the same screening every other year without CADe.Main outcome measures Benefits (colorectal cancer incidence and death), burden (surveillance colonoscopies), and harms (colonoscopy related adverse events) over 10 years were measured. The certainty in each outcome was assessed by use of the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) approach.Results For 100 000 individuals participating in colonoscopy screening, 824 (0.82%) were diagnosed with colorectal cancer within 10 years without CADe versus 713 (0.71%) with CADe (risk difference –0.11% (95% CI –0.43% to 0.21%)). For faecal immunochemical test screening colonoscopy, the risk was 5.82% (n=5820) without CADe versus 5.77% (n=5770) with CADe (difference –0.05% (–0.33% to 0.15%)). The risk of surveillance colonoscopy increased from 26.45% (n=26 453) to 32.82% (n=32 819) (difference 6.37% (5.8% to 6.9%)) for colonoscopy screening and from 52.26% (n=52 263) to 53.08% (n=53 082) (difference 0.82% (0.38% to 1.26%)) for faecal immunochemical test screening colonoscopy. No significant differences were noted in adverse events related to the colonoscopy between CADe and no CADe. The model estimates were sensitive to the assumed effects of screening on colorectal cancer risk and of CADe on adenoma detection rates. All outcomes were graded as low certainty.Conclusion With low certainty of evidence, adoption of CADe in population based screening provides small and uncertain clinical meaningful benefit, no incremental harms, and increased surveillance burden after screening.
format Article
id doaj-art-cd9b09235cda4e63b24a8d5ce6d5b7f5
institution DOAJ
issn 2754-0413
language English
publishDate 2025-03-01
publisher BMJ Publishing Group
record_format Article
series BMJ Medicine
spelling doaj-art-cd9b09235cda4e63b24a8d5ce6d5b7f52025-08-20T02:54:22ZengBMJ Publishing GroupBMJ Medicine2754-04132025-03-014110.1136/bmjmed-2025-001446Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling studyCesare Hassan0Alessandro Repici1Farid Foroutan2Lise M Helsingen3Michael Bretthauer4Mette Kalager5Marco Spadaccini6Yuichi Mori7Magnus Løberg8Per Olav Vandvik9Loredana Correale10Natalie Halvorsen11Nastazja Pilonis12Shanaz Sultan13Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, ItalyDepartment of Biomedical Sciences, Humanitas University, Pieve Emanuele, ItalymethodologistClinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway13 Clinical Effectiveness Research Group, University of Oslo, Oslo, NorwayClinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway24 Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, ItalyClinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo University Hospital, Oslo, NorwayClinical Effectiveness Research Group, Department of Transplantation Medicine, Oslo University Hospital, Oslo, NorwayDepartment of Medicine, Lovisenberg Diaconal Hospital, Oslo, NorwayEndoscopy Unit, Humanitas Clinical and Research Center IRCCS, Rozzano, ItalyClinical Effectiveness Research Group, Institute of Health and Society, University of Oslo, Oslo, NorwayClinical Effectiveness Research Group, Oslo University Hospital, Oslo, NorwayMinneapolis VA Healthcare System, University of Minnesota, Minneapolis, Minnesota, USAObjective To estimate the benefits, burden, and harms of implementing computer aided detection (CADe) of polyps in colonoscopy of population based screening programmes for colorectal cancer.Design Microsimulation modelling study.Setting Cost effectiveness working package in the OperA (optimising colorectal cancer prevention through personalised treatment with artificial intelligence) project. A parallel guideline committee panel (BMJ Rapid recommendation) was consulted in defining the screening interventions and selection of outcome measures.Population Four cohorts of 100 000 European individuals aged 60-69 years.Intervention The intervention was one screening of colonoscopy and a screening of colonoscopy after faecal immunochemical test every other year with CADe. The comparison group had the same screening every other year without CADe.Main outcome measures Benefits (colorectal cancer incidence and death), burden (surveillance colonoscopies), and harms (colonoscopy related adverse events) over 10 years were measured. The certainty in each outcome was assessed by use of the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) approach.Results For 100 000 individuals participating in colonoscopy screening, 824 (0.82%) were diagnosed with colorectal cancer within 10 years without CADe versus 713 (0.71%) with CADe (risk difference –0.11% (95% CI –0.43% to 0.21%)). For faecal immunochemical test screening colonoscopy, the risk was 5.82% (n=5820) without CADe versus 5.77% (n=5770) with CADe (difference –0.05% (–0.33% to 0.15%)). The risk of surveillance colonoscopy increased from 26.45% (n=26 453) to 32.82% (n=32 819) (difference 6.37% (5.8% to 6.9%)) for colonoscopy screening and from 52.26% (n=52 263) to 53.08% (n=53 082) (difference 0.82% (0.38% to 1.26%)) for faecal immunochemical test screening colonoscopy. No significant differences were noted in adverse events related to the colonoscopy between CADe and no CADe. The model estimates were sensitive to the assumed effects of screening on colorectal cancer risk and of CADe on adenoma detection rates. All outcomes were graded as low certainty.Conclusion With low certainty of evidence, adoption of CADe in population based screening provides small and uncertain clinical meaningful benefit, no incremental harms, and increased surveillance burden after screening.https://bmjmedicine.bmj.com/content/4/1/e001446.full
spellingShingle Cesare Hassan
Alessandro Repici
Farid Foroutan
Lise M Helsingen
Michael Bretthauer
Mette Kalager
Marco Spadaccini
Yuichi Mori
Magnus Løberg
Per Olav Vandvik
Loredana Correale
Natalie Halvorsen
Nastazja Pilonis
Shanaz Sultan
Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study
BMJ Medicine
title Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study
title_full Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study
title_fullStr Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study
title_full_unstemmed Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study
title_short Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study
title_sort benefits burden and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening microsimulation modelling study
url https://bmjmedicine.bmj.com/content/4/1/e001446.full
work_keys_str_mv AT cesarehassan benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT alessandrorepici benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT faridforoutan benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT lisemhelsingen benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT michaelbretthauer benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT mettekalager benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT marcospadaccini benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT yuichimori benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT magnusløberg benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT perolavvandvik benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT loredanacorreale benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT nataliehalvorsen benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT nastazjapilonis benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy
AT shanazsultan benefitsburdenandharmsofcomputeraidedpolypdetectionwithartificialintelligenceincolorectalcancerscreeningmicrosimulationmodellingstudy