Observational Study
Copyright ©The Author(s) 2021. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Oct 14, 2021; 27(38): 6476-6488
Published online Oct 14, 2021. doi: 10.3748/wjg.v27.i38.6476
Deep learning vs conventional learning algorithms for clinical prediction in Crohn's disease: A proof-of-concept study
Danny Con, Daniel R van Langenberg, Abhinav Vasudevan
Danny Con, Daniel R van Langenberg, Abhinav Vasudevan, Department of Gastroenterology and Hepatology, Eastern Health, Box Hill 3128, Victoria, Australia
Daniel R van Langenberg, Abhinav Vasudevan, Faculty of Medicine, Nursing and Health Sciences, Monash University, Box Hill 3128, Victoria, Australia
Author contributions: Con D contributed conceptualization, data collection, statistical analysis, data interpretation, manuscript drafting; van Langenberg DR contributed conceptualization, data interpretation, reviewing of manuscript critically for important intellectual content; Vasudevan A contributed conceptualization, data collection, data interpretation, reviewing of manuscript critically for important intellectual content; all authors approved the final version of the manuscript.
Institutional review board statement: This study was reviewed and approved by the Eastern Health Office of Research & Ethics (approval number: LR 61/2015).
Informed consent statement: Patients were not required to give informed consent to the study because the analysis used anonymous clinical data that were obtained retrospectively.
Conflict-of-interest statement: Con D has no relevant conflicts of interest to declare. AV has received financial support to attend educational meetings from Ferring. van Langenberg DR has served as a speaker and/or received travel support from Takeda, Ferring and Shire. He has consultancy agreements with Abbvie, Janssen and Pfizer. He received research funding grants for investigator-driven studies from Ferring, Shire and AbbVie.
Data sharing statement: No additional data are available.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Danny Con, MD, Doctor, Statistician, Department of Gastroenterology and Hepatology, Eastern Health, 8 Arnold Street, Box Hill 3128, Victoria, Australia. dannycon302@gmail.com
Received: March 5, 2021
Peer-review started: March 5, 2021
First decision: April 17, 2021
Revised: April 26, 2021
Accepted: September 6, 2021
Article in press: September 6, 2021
Published online: October 14, 2021
Processing time: 221 Days and 3.2 Hours
Abstract
BACKGROUND

Traditional methods of developing predictive models in inflammatory bowel diseases (IBD) rely on using statistical regression approaches to deriving clinical scores such as the Crohn's disease (CD) activity index. However, traditional approaches are unable to take advantage of more complex data structures such as repeated measurements. Deep learning methods have the potential ability to automatically find and learn complex, hidden relationships between predictive markers and outcomes, but their application to clinical prediction in CD and IBD has not been explored previously.

AIM

To determine and compare the utility of deep learning with conventional algorithms in predicting response to anti-tumor necrosis factor (anti-TNF) therapy in CD.

METHODS

This was a retrospective single-center cohort study of all CD patients who commenced anti-TNF therapy (either adalimumab or infliximab) from January 1, 2010 to December 31, 2015. Remission was defined as a C-reactive protein (CRP) < 5 mg/L at 12 mo after anti-TNF commencement. Three supervised learning algorithms were compared: (1) A conventional statistical learning algorithm using multivariable logistic regression on baseline data only; (2) A deep learning algorithm using a feed-forward artificial neural network on baseline data only; and (3) A deep learning algorithm using a recurrent neural network on repeated data. Predictive performance was assessed using area under the receiver operator characteristic curve (AUC) after 10× repeated 5-fold cross-validation.

RESULTS

A total of 146 patients were included (median age 36 years, 48% male). Concomitant therapy at anti-TNF commencement included thiopurines (68%), methotrexate (18%), corticosteroids (44%) and aminosalicylates (33%). After 12 mo, 64% had CRP < 5 mg/L. The conventional learning algorithm selected the following baseline variables for the predictive model: Complex disease behavior, albumin, monocytes, lymphocytes, mean corpuscular hemoglobin concentration and gamma-glutamyl transferase, and had a cross-validated AUC of 0.659, 95% confidence interval (CI): 0.562-0.756. A feed-forward artificial neural network using only baseline data demonstrated an AUC of 0.710 (95%CI: 0.622-0.799; P = 0.25 vs conventional). A recurrent neural network using repeated biomarker measurements demonstrated significantly higher AUC compared to the conventional algorithm (0.754, 95%CI: 0.674-0.834; P = 0.036).

CONCLUSION

Deep learning methods are feasible and have the potential for stronger predictive performance compared to conventional model building methods when applied to predicting remission after anti-TNF therapy in CD.

Keywords: Machine learning; Artificial intelligence; Precision medicine; Personalized medicine; Deep learning

Core Tip: Deep learning has vast potential, but its clinical utility in predicting outcomes in Crohn’s disease (CD) has not been explored. This study showed that deep learning algorithms (a recurrent neural network) using a more complex information structure including repeated biomarker measurements had a better predictive performance compared to a conventional statistical algorithm using only baseline data. This proof-of-concept study therefore paves the way for further research in the use of deep learning methods in clinical prediction in CD.