EUVIMEDEUVIMED entdecken
Crossref

Optical Diagnosis in Colonoscopy: We can’t all be (GI) Geniuses

M. hanly, R. Varley, L. Kumar, E. Gibbons, M. Mccrossan, D. Aimee, S. Thomas, B. Hall, O. B. Kelly, G. Horgan, G. Doherty

Endoscopy · 01.04.2024 · 56 (S 02 S 02) · S220-S221

DOI: 10.1055/s-0044-1783196 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Endoscopy, erschienen am 01.04.2024. Verfasst von M. hanly und 10 weiteren Autor:innen. Die Arbeit nennt 2 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

To compare the performance of expert endoscopists, trainee endoscopists and CADx in characterising colonic polyps.

Methods

In this multi-centre prospective comparison study, independent endoscopists performed high-definition colonoscopies with GI Genius (Medtronic, Dublin, Ireland) between August and November 2022. All detected polyps were documented (white light imaging, narrow band imaging and near focus), resected and retrieved. CADx diagnosis was recorded (adenoma/non-adenoma/no prediction). Histologic diagnosis was recorded. Blinded to histologic diagnosis, expert and trainee endoscopists independently predicted polyp type based on photo documentation. Comparison of diagnosis was made between Consultants, Specialist Registrars (SpR’s), First year trainees and CADx (GI Genius) and compared against final histologic diagnosis.

Results

139 polyps across two centres were detected. GI Genius correctly characterised 97 (69.8%), incorrectly characterised 25 (18%) and made no prediction for 17 polyps (12.2%). Consultants correctly characterised 91 (65.5%), incorrectly characterised 32 (23%) and made no prediction for 16 polyps (11.5%). SpR's correctly characterised 93 (66.9%), incorrectly characterised 25 (18%) and made no prediction for 21 polyps (15.1%). GI Genius and Consultants agreed for 72 (51.8%), disagreed for 40 (28.8%) and at least one made no prediction for 27 polyps (19.4%). GI Genius and SpR's agreed for 78 (56.1%), disagreed for 27 (19.4%) and at least one made no prediction for 34 polyps (24.5%). First year Trainees in site one and one in site two correctly characterised 93 / 191(48.9%) and incorrectly 60/191 (31.6%)

Conclusions

Our data corresponds with previously published studies. Interestingly, trainee characterisation was similar to both consultant and CADx predictions in our study. Both SpR's endoscopists are experienced endoscopists nearing the end of training scheme. There was a significant drop in the percentage of correctly diagnosed polyps in the first year trainees. [ 1 ] [ 2 ] This suggests that CADx polyp characterisation may be useful in an early training phase, as it appears to be a reliable and consistent tool for diagnosis. A resect and discard strategy with CADx does not at present appear feasible. Publication History Article published online: 15 April 2024 © 2024. European Society of Gastrointestinal Endoscopy. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany

Zitieren

APA

hanly, M., Varley, R., Kumar, L., Gibbons, E., Mccrossan, M., Aimee, D., Thomas, S., Hall, B., Kelly, O. B., Horgan, G., & Doherty, G. (2024). Optical Diagnosis in Colonoscopy: We can’t all be (GI) Geniuses. Endoscopy, 56(S 02 S 02), S220-S221. https://doi.org/10.1055/s-0044-1783196

Vancouver

hanly M, Varley R, Kumar L, Gibbons E, Mccrossan M, Aimee D, et al. Optical Diagnosis in Colonoscopy: We can’t all be (GI) Geniuses. Endoscopy. 2024;56(S 02 S 02):S220-S221. doi:10.1055/s-0044-1783196

BibTeX
@article{hanly2024,
  author = {hanly, M. and Varley, R. and Kumar, L. and Gibbons, E. and Mccrossan, M. and Aimee, D. and Thomas, S. and Hall, B. and Kelly, O. B. and Horgan, G. and Doherty, G.},
  title = {Optical Diagnosis in Colonoscopy: We can’t all be (GI) Geniuses},
  journal = {Endoscopy},
  year = {2024},
  volume = {56},
  number = {S 02 S 02},
  pages = {S220--S221},
  doi = {10.1055/s-0044-1783196}
}
Kostenlos starten →