Evaluation of an Artificial Intelligence-Augmented Digital System for Histologic Classification of Colorectal Polyps

Colorectal polyps are common, and their histopathologic classification is used in the planning of follow-up surveillance. Substantial variation has been observed in pathologists' classification of colorectal polyps, and improved assessment by pathologists may be associated with reduced subseque...

Full description

Saved in:
Bibliographic Details
Published in:JAMA network open 2021-11, Vol.4 (11), p.e2135271-e2135271
Main Authors: Nasir-Moin, Mustafa, Suriawinata, Arief A, Ren, Bing, Liu, Xiaoying, Robertson, Douglas J, Bagchi, Srishti, Tomita, Naofumi, Wei, Jason W, MacKenzie, Todd A, Rees, Judy R, Hassanpour, Saeed
Format: Article
Language:English
Subjects:
Accuracy
Artificial Intelligence
Classification
Colonic Polyps - classification
Colonic Polyps - diagnosis
Colonic Polyps - diagnostic imaging
Colonic Polyps - pathology
Colonoscopy
Colorectal Neoplasms - classification
Colorectal Neoplasms - diagnosis
Data Accuracy
Diagnostic Tests, Routine - methods
Health Informatics
Humans
Image Interpretation, Computer-Assisted - methods
Microscopy
New Hampshire
Online Only
Original Investigation
Polyps
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Colorectal polyps are common, and their histopathologic classification is used in the planning of follow-up surveillance. Substantial variation has been observed in pathologists' classification of colorectal polyps, and improved assessment by pathologists may be associated with reduced subsequent underuse and overuse of colonoscopy. To compare standard microscopic assessment with an artificial intelligence (AI)-augmented digital system that annotates regions of interest within digitized polyp tissue and predicts polyp type using a deep learning model to assist pathologists in colorectal polyp classification. In this diagnostic study conducted at a tertiary academic medical center and a community hospital in New Hampshire, 100 slides with colorectal polyp samples were read by 15 pathologists using a microscope and an AI-augmented digital system, with a washout period of at least 12 weeks between use of each modality. The study was conducted from February 10 to July 10, 2020. Accuracy and time of evaluation were used to compare pathologists' performance when a microscope was used with their performance when the AI-augmented digital system was used. Outcomes were compared using paired t tests and mixed-effects models. In assessments of 100 slides with colorectal polyp specimens, use of the AI-augmented digital system significantly improved pathologists' classification accuracy compared with microscopic assessment from 73.9% (95% CI, 71.7%-76.2%) to 80.8% (95% CI, 78.8%-82.8%) (P 
ISSN:2574-3805
2574-3805
DOI:10.1001/jamanetworkopen.2021.35271