Title: A Machine Learning-Based Diagnostic Model for Crohn's Disease and Ulcerative Colitis Utilizing Fecal Microbiome Analysis

Journal: Microorganisms

Authors: Hyeonwoo Kim^1,†, Ji Eun Na^2,†, Sangsoo Kim¹, Tae-Oh Kim², Soo-Kyung Park ^3,4, Chil-Woo Lee⁴, Kyeong Ok Kim⁵, Geom-Seog Seo⁶, Min Suk Kim⁷, Jae Myung Cha⁸, Ja Seol Koo⁹ and Dong-Il Park^3,4,*

Affiliations

 ¹ Department of Bioinformatics, Soongsil University, Seoul 06978, Republic of Korea

 ² Department of Internal Medicine, College of Medicine, Inje University Haeundae Paik Hospital, Busan 48108, Republic of Korea

 ³ Division of Gastroenterology, Department of Internal Medicine and Inflammatory Bowel Disease Center, Kangbuk Samsung Hospital, School of Medicine, Sungkyunkwan University, Seoul 03181, Republic of Korea

 ⁴ Medical Research Institute, Kangbuk Samsung Hospital, School of Medicine, Sungkyunkwan University, Seoul 03181, Republic of Korea

 ⁵ Department of Internal Medicine, College of Medicine, Yeungnam University, Daegu 42415, Republic of Korea

 ⁶ Department of Internal Medicine, School of Medicine, Wonkwang University, Iksan 54538, Republic of Korea

 ⁷ Department of Human Intelligence and Robot Engineering, Sangmyung University, Cheonan-si 31066, Republic of Korea

 ⁸ Department of Internal Medicine, Kyung Hee University Hospital at Gangdong, Kyung Hee University College of Medicine, Seoul 05278, Republic of Korea

 ⁹ Division of Gastroenterology and Hepatology, Department of Internal Medicine, Ansan Hospital, Korea University College of Medicine, Ansan 15355, Republic of Korea

 ^* Correspondence

 ^† These authors contributed equally to this work.

Abstract:

Recent research has demonstrated the potential of fecal microbiome analysis using machine learning (ML) in the diagnosis of inflammatory bowel disease (IBD), mainly Crohn’s disease (CD) and ulcerative colitis (UC). This study employed the sparse partial least squares discriminant analysis (sPLS-DA) ML technique to develop a robust prediction model for distinguishing among CD, UC, and healthy controls (HCs) based on fecal microbiome data. Using data from multicenter cohorts, we conducted 16S rRNA gene sequencing of fecal samples from patients with CD (n = 671) and UC (n = 114) while forming an HC cohort of 1462 individuals from the Kangbuk Samsung Hospital Healthcare Screening Center. A streamlined pipeline based on HmmUFOTU was used. After a series of filtering steps, 1517 phylotypes and 1846 samples were retained for subsequent analysis. After 100 rounds of downsampling with age, sex, and sample size matching, and division into training and test sets, we constructed two binary prediction models to distinguish between IBD and HC and CD and UC using the training set. The binary prediction models exhibited high accuracy and area under the curve (for differentiating IBD from HC (mean accuracy, 0.950; AUC, 0.992) and CD from UC (mean accuracy, 0.945; AUC, 0.988)), respectively, in the test set. This study underscores the diagnostic potential of an ML model based on sPLS-DA, utilizing fecal microbiome analysis, highlighting its ability to differentiate between IBD and HC and distinguish CD from UC.

Keywords: inflammatory bowel disease; Crohn’s disease; ulcerative colitis; fecal microbiome; sparse partial least squares discriminant analysis; machine learning

DOI: https://doi.org/10.3390/microorganisms12010036

Published: 24 December 2023

붙임: A Machine Learning-Based Diagnostic Model for Crohn’s Disease and Ulcerative Colitis Utilizing Fecal Microbiome Analysis.pdf