Usefulness of Machine Learning-Based Gut Microbiome Analysis for Identifying Patients with Irritable Bowels Syndrome

Hirokazu Fukui; Akifumi Nishida; Satoshi Matsuda; Fumitaka Kira; Satoshi Watanabe; Minoru Kuriyama; Kazuhiko Kawakami; Yoshiko Aikawa; Noritaka Oda; Kenichiro Arai; Atsushi Matsunaga; Masahiko Nonaka; Katsuhiko Nakai; Wahei Shinmura; Masao Matsumoto; Shinji Morishita; Aya K Takeda; Hiroto Miwa

doi:10.3390/jcm9082403

Usefulness of Machine Learning-Based Gut Microbiome Analysis for Identifying Patients with Irritable Bowels Syndrome

J Clin Med. 2020 Jul 27;9(8):2403. doi: 10.3390/jcm9082403.

Authors

Hirokazu Fukui¹, Akifumi Nishida^{2

3

4}, Satoshi Matsuda⁵, Fumitaka Kira^{2

6}, Satoshi Watanabe², Minoru Kuriyama², Kazuhiko Kawakami⁵, Yoshiko Aikawa⁵, Noritaka Oda⁵, Kenichiro Arai⁵, Atsushi Matsunaga⁵, Masahiko Nonaka⁵, Katsuhiko Nakai⁵, Wahei Shinmura⁶, Masao Matsumoto⁶, Shinji Morishita⁶, Aya K Takeda², Hiroto Miwa¹

Affiliations

¹ Division of Gastroenterology and Hepatology, Department of Internal Medicine, Hyogo College of Medicine, 1-1, Mukogawa, Nishinomiya 663-8501, Japan.
² Cykinso Inc., 1-36-1, Yoyogi, Shinjuku, Tokyo 151-0053 Japan.
³ Department of Electrical Engineering and Bioscience, Waseda University, 1-104, Totsuka, Shinjuku, Tokyo 169-8050, Japan.
⁴ School of Computing, Tokyo Institute of Technology, 2-12-1, Okayama, Meguro, Tokyo 152-8550, Japan.
⁵ Colo-proctological Institute, Matsuda Hospital, 753, Irino-cho, Nishi-ku, Hamamatsu, Shizuoka 432-8061, Japan.
⁶ Department of Gastroenterology, JCHO Tokyo Shinjuku Medical Center, 5-1, Tsukudo, Shinjuku, Tokyo 162-8543, Japan.

Abstract

Irritable bowel syndrome (IBS) is diagnosed by subjective clinical symptoms. We aimed to establish an objective IBS prediction model based on gut microbiome analyses employing machine learning. We collected fecal samples and clinical data from 85 adult patients who met the Rome III criteria for IBS, as well as from 26 healthy controls. The fecal gut microbiome profiles were analyzed by 16S ribosomal RNA sequencing, and the determination of short-chain fatty acids was performed by gas chromatography-mass spectrometry. The IBS prediction model based on gut microbiome data after machine learning was validated for its consistency for clinical diagnosis. The fecal microbiome alpha-diversity indices were significantly smaller in the IBS group than in the healthy controls. The amount of propionic acid and the difference between butyric acid and valerate were significantly higher in the IBS group than in the healthy controls (p < 0.05). Using LASSO logistic regression, we extracted a featured group of bacteria to distinguish IBS patients from healthy controls. Using the data for these featured bacteria, we established a prediction model for identifying IBS patients by machine learning (sensitivity >80%; specificity >90%). Gut microbiome analysis using machine learning is useful for identifying patients with IBS.

Keywords: IBS; gut microbiome; machine learning; short-chain fatty acids.