Abaach M, Morilla I. Learning models for colorectal cancer signature reconstruction and classification in patients with chronic inflammatory bowel disease. Artif Intell Cancer 2022; 3(2): 27-41 [DOI: 10.35713/aic.v3.i2.27]
Corresponding Author of This Article
Ian Morilla, PhD, Assistant Professor, Research Associate, Laboratoire Analyse, Géométrie et Applications, Centre National de la Recherche Scientifique (Unité mixte de Recherche), Université Sorbonne Paris Nord, 99 avenue Jean Baptiste clément, Villetaneuse, Paris 93430, France. morilla@math.univ-paris13.fr
Research Domain of This Article
Mathematical & Computational Biology
Article-Type of This Article
Basic Study
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (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/
Apr 28, 2022 (publication date) through Mar 1, 2026
Times Cited of This Article
Times Cited (0)
Journal Information of This Article
Publication Name
Artificial Intelligence in Cancer
ISSN
2644-3228
Publisher of This Article
Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA
Share the Article
Abaach M, Morilla I. Learning models for colorectal cancer signature reconstruction and classification in patients with chronic inflammatory bowel disease. Artif Intell Cancer 2022; 3(2): 27-41 [DOI: 10.35713/aic.v3.i2.27]
Learning models for colorectal cancer signature reconstruction and classification in patients with chronic inflammatory bowel disease
Ian Morilla, Mariem Abaach
Mariem Abaach, Mathématiques Appliquées à Paris 5, Unité mixte de Recherche, Centre National de la Recherche Scientifique, Université de Paris, Paris 75006, France
Ian Morilla, Laboratoire Analyse, Géométrie et Applications, Centre National de la Recherche Scientifique (Unité mixte de Recherche), Université Sorbonne Paris Nord, Villetaneuse, Paris 93430, France
Author contributions: Morilla I conceived and designed the computational experiments; Abaach M and Morilla I performed computational experiments, analyzed the miRNomic data, performed formal analysis; Morilla I wrote the original manuscript Abaach M and Morilla I reviewed and edited the manuscript.
Institutional review board statement: The protocols involving human participants conformed to the local Ethics Committee (CPP-Île de France IV No. 2009/17) and to the principles set out in the WMA Declaration of Helsinki, and the Belmont Report from the Department of Health and Human Services. Human ileal biopsies were obtained from the IBD Gastroenterology Unit, Beaujon Hospital and a written informed consent was obtained from all the patients before inclusion in the study.
Institutional animal care and use committee statement: The protocols involving human participants conformed to the local Ethics Committee (CPP-Île de France IV No. 2009/17) and to the principles set out in the WMA Declaration of Helsinki, and the Belmont Report from the Department of Health and Human Services. Human ileal biopsies were obtained from the IBD Gastroenterology Unit, Beaujon Hospital and a written informed consent was obtained from all the patients before inclusion in the study.
Conflict-of-interest statement: All authors declare no conflicts of interest in this paper.
ARRIVE guidelines statement: The authors have read the ARRIVE guidelines, and the manuscript was prepared and revised according to the ARRIVE guidelines.
Corresponding author: Ian Morilla, PhD, Assistant Professor, Research Associate, Laboratoire Analyse, Géométrie et Applications, Centre National de la Recherche Scientifique (Unité mixte de Recherche), Université Sorbonne Paris Nord, 99 avenue Jean Baptiste clément, Villetaneuse, Paris 93430, France. morilla@math.univ-paris13.fr
Received: December 9, 2021 Peer-review started: December 9, 2021 First decision: January 26, 2022 Revised: February 16, 2022 Accepted: April 28, 2022 Article in press: April 28, 2022 Published online: April 28, 2022 Processing time: 139 Days and 21.8 Hours
ARTICLE HIGHLIGHTS
Research background
Face the overabundance of information, it is not easy to clinicians discriminating amid biological indicators that potentially could be helpful during an inflammatory bowel disease (IBD) disease therapy.
Research motivation
There exist intra patient differences in miRNA expression between the inflammatory and healthy tissue, between the healthy tissue of an inflammatory and non-inflammatory patient and between the healthy tissue of a cancer and non- cancer colic patient. We want to identify a minimal miRNA profile of developing or not cancer in patients with a chronic inflammatory bowel disease. In other words, a miRNA profile of healthy tissue from patients with chronic IBD with (case) vs without cancer (control). In that way, provided a specific miRNA profile is of interest, this one could be prospectively validated, and its predictive marker maybe also developed. Ultimately, this would allow clinicians to in- crease the diagnosis colonoscopy pace in IBD patients where a miRNA profile of risk is detected and conversely decreasing that pace in patients tagged as at lower risk.
Research objectives
In this scenario, the identification of an optimal signa- ture, for example composed by microRNA (miRNA), associated with colorectal cancer (CRC) in patients with one chronic IBD is of vital importance.
Research methods
We provide a framework of well-established statistical learning methods (i.e., RF, SVM, PLS-DA, ...) wisely adapted to reconstructing a CRC network leveraged to stratify these patients.
Research results
Our strategy provides an adjusted signature of 5 miRNAs with a percentage of success in patient classification of 82% in Crohn’s disease (resp. 81% in Ulcerative Colitis).
Research conclusions
The application of the proposed method to a multi-class classification further points out the robustness and efficiency of our strategy particularly in the CD and UC group of patients. Additionally, the use of parse PLS Discriminant Analysis spots a minimal signature with accurate enough performances.
Research perspectives
In the next future, the combination of this method with deep learning models will enable more intricate relationships between the elements of the signature and possibly another robust clinical data. Finally, we are convinced our methodology will be also instrumental for other diseases broadening the general framework herein provided.
