Artificial intelligence image-based prediction models in IBD exhibit high risk of bias: A systematic review.

Artificial intelligence Computer vision Deep learning Imaging Inflammatory bowel disease Machine learning

Journal

Computers in biology and medicine
ISSN: 1879-0534
Titre abrégé: Comput Biol Med
Pays: United States
ID NLM: 1250250

Informations de publication

Date de publication:
Mar 2024
Historique:
received: 04 09 2023
revised: 04 01 2024
accepted: 30 01 2024
pubmed: 15 2 2024
medline: 15 2 2024
entrez: 14 2 2024
Statut: ppublish

Résumé

There has been an increase in the development of both machine learning (ML) and deep learning (DL) prediction models in Inflammatory Bowel Disease. We aim in this systematic review to assess the methodological quality and risk of bias of ML and DL IBD image-based prediction studies. We searched three databases, PubMed, Scopus and Embase, to identify ML and DL diagnostic or prognostic predictive models using imaging data in IBD, to Dec 31, 2022. We restricted our search to include studies that primarily used conventional imaging data, were undertaken in human participants, and published in English. Two reviewers independently reviewed the abstracts. The methodological quality of the studies was determined, and risk of bias evaluated using the prediction risk of bias assessment tool (PROBAST). Forty studies were included, thirty-nine developed diagnostic models. Seven studies utilized ML approaches, six were retrospective and none used multicenter data for model development. Thirty-three studies utilized DL approaches, ten were prospective, and twelve multicenter studies. Overall, all studies demonstrated high risk of bias. ML studies were evaluated in 4 domains all rated as high risk of bias: participants (6/7), predictors (1/7), outcome (3/7), and analysis (7/7), and DL studies evaluated in 3 domains: participants (24/33), outcome (10/33), and analysis (18/33). The majority of image-based studies used colonoscopy images. The risk of bias was high in AI IBD image-based prediction models, owing to insufficient sample size, unreported missingness and lack of an external validation cohort. Models with a high risk of bias are unlikely to be generalizable and suitable for clinical implementation.

Sections du résumé

BACKGROUND BACKGROUND
There has been an increase in the development of both machine learning (ML) and deep learning (DL) prediction models in Inflammatory Bowel Disease. We aim in this systematic review to assess the methodological quality and risk of bias of ML and DL IBD image-based prediction studies.
METHODS METHODS
We searched three databases, PubMed, Scopus and Embase, to identify ML and DL diagnostic or prognostic predictive models using imaging data in IBD, to Dec 31, 2022. We restricted our search to include studies that primarily used conventional imaging data, were undertaken in human participants, and published in English. Two reviewers independently reviewed the abstracts. The methodological quality of the studies was determined, and risk of bias evaluated using the prediction risk of bias assessment tool (PROBAST).
RESULTS RESULTS
Forty studies were included, thirty-nine developed diagnostic models. Seven studies utilized ML approaches, six were retrospective and none used multicenter data for model development. Thirty-three studies utilized DL approaches, ten were prospective, and twelve multicenter studies. Overall, all studies demonstrated high risk of bias. ML studies were evaluated in 4 domains all rated as high risk of bias: participants (6/7), predictors (1/7), outcome (3/7), and analysis (7/7), and DL studies evaluated in 3 domains: participants (24/33), outcome (10/33), and analysis (18/33). The majority of image-based studies used colonoscopy images.
CONCLUSION CONCLUSIONS
The risk of bias was high in AI IBD image-based prediction models, owing to insufficient sample size, unreported missingness and lack of an external validation cohort. Models with a high risk of bias are unlikely to be generalizable and suitable for clinical implementation.

Identifiants

DOI: 10.1016/j.compbiomed.2024.108093 PMID: 38354499
pubmed: 38354499
pii: S0010-4825(24)00177-X
doi: 10.1016/j.compbiomed.2024.108093
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

108093

Informations de copyright

Copyright © 2024. Published by Elsevier Ltd.

Déclaration de conflit d'intérêts

Declaration of competing interest Xiaoxuan Liu MS, James Reigle, Surya Prasath PhD and Jasbir Dhaliwal have no declaration of interests.

Auteurs

Xiaoxuan Liu (X)

Department of Biomedical Informatics, College of Medicine, University of Cincinnati, OH, USA; Department of Pediatrics, University of Cincinnati, College of Medicine, Cincinnati, OH, USA.

James Reigle (J)

Department of Pediatrics, University of Cincinnati, College of Medicine, Cincinnati, OH, USA; Cincinnati Children's Hospital Medical Center, Division of Gastroenterology, Hepatology and Nutrition, USA.

V B Surya Prasath (VBS)

Department of Biomedical Informatics, College of Medicine, University of Cincinnati, OH, USA; Department of Pediatrics, University of Cincinnati, College of Medicine, Cincinnati, OH, USA; Cincinnati Children's Hospital Medical Center, Division of Gastroenterology, Hepatology and Nutrition, USA.

Jasbir Dhaliwal (J)

Department of Biomedical Informatics, College of Medicine, University of Cincinnati, OH, USA; Department of Pediatrics, University of Cincinnati, College of Medicine, Cincinnati, OH, USA; Cincinnati Children's Hospital Medical Center, Division of Gastroenterology, Hepatology and Nutrition, USA. Electronic address: Jasbir.dhaliwal@cchmc.org.

Classifications MeSH