"As we strive for more accurate risk stratification and implement treat-to target therapies, virtual chromoendoscopy, which is now part of all the endoscopes currently in use in daily clinical practice, should be adopted widely," Dr. Marietta Iacucci of the University of Birmingham, UK, told Reuters Health by email.
"These technologies may significantly enhance our decision-making ability in real time and accurately predict outcomes," she said. "Now is the time to train the eyes so that endoscopic scoring and histologic scoring can become very close."
As reported in Gastroenterology, the multicenter study assessed inflammatory activity with high definition and virtual chromoendoscopy in the rectum and sigmoid using the Mayo Endoscopic Score (MES), UC Endoscopic Index of Severity (UCEIS), and PICaSSO. Targeted biopsies were assessed using using the Robarts Histological Index (RHI), Nancy Histological index (NHI) and other scores.
The final analysis included 302 UC patients (mean age, 48; 59% men; mean disease duration, 15 years). Follow-up data were obtained six and 12 months after colonoscopy.
PICaSSO had a significantly superior correlation with histology scores than MES and UCEIS.
A PICaSSO score of 3 or less detected histologic remission by RHI (3 or less plus absence of neutrophils) with an area under the receiver operating characteristic curve of 0.90, and an NHI (1 or less) AUROC of 0.82.
Interobserver agreement for PICaSSO was 0.88 - significantly better than MES or UCEIS, with a less meaningful misclassification rate.
Notably, at 6- and 12-months follow-up, a PICaSSO score of 3 or less predicted better outcomes than PICaSSO >3 (hazard ratio, 0.19), as well as PICaSSO 4-8 (HR 0.25); this was similar to histologic remission.
The authors note, "We have previously shown that the PICaSSO score could be reproduced in less experienced and trainee endoscopists after a short training module. (https://bit.ly/2O5F0ui).
Dr. Iacucci said, "We recognize that daily adoption of optical diagnosis in non-experts' hands is still a challenge. To overcome these challenges and variability we are working in a multidisciplinary team to develop PICaSSO artificial intelligence, a deep learning-based image analysis that can perform better and without conventional naked eye interpretation for assessing disease activity and remission and to predict response to therapy."
Dr. Sonia Friedman, Director of Women's Health in the Center for Crohn's and Colitis at Brigham and Women's Hospital in Boston, commented in an email to Reuters Health. "PICaSSO is promising as a highly accurate scoring system to assess UC severity and clinical course."
"Since it uses the newest colonoscopic technology, it is likely superior to current endoscopic scoring systems," she said. "One caveat is that the gastroenterologists involved in the current study were all experienced in IBD endoscopy and further real-life study is needed to reproduce the results in less experienced gastroenterologists."
SOURCE: https://bit.ly/3b06FWR Gastroenterology, online February 6, 2021.
By Marilynn Larkin
Posted on
site created by:
© 2024 Medicom Medical Publishers. All rights reserved. Terms and Conditions | Privacy Policy
HEAD OFFICE
Laarderhoogtweg 25
1101 EB Amsterdam
The Netherlands
T: +31 85 4012 560
E: publishers@medicom-publishers.com