Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical Diagnosis

Background and Aims: The pathophysiology of inflammatory bowel disease (IBD) including ulcerative colitis (UC) and Crohn’s disease (CD) remains unclear. While IBD is heterogeneous, most molecular-targeted drugs (MTDs) are effective for both UC and CD. The immunological pathoetiology can be considere...

Full description

Saved in:
Bibliographic Details
Main Authors: Jun Miyoshi, Satoshi Tamura, Noriaki Oguri, Daisuke Saito, Yuu Nishinarita, Haruka Wada, Nobuki Nemoto, Minoru Matsuura, Tadakazu Hisamatsu
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Gastro Hep Advances
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772572325000548
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850136889094307840
author Jun Miyoshi
Satoshi Tamura
Noriaki Oguri
Daisuke Saito
Yuu Nishinarita
Haruka Wada
Nobuki Nemoto
Minoru Matsuura
Tadakazu Hisamatsu
author_facet Jun Miyoshi
Satoshi Tamura
Noriaki Oguri
Daisuke Saito
Yuu Nishinarita
Haruka Wada
Nobuki Nemoto
Minoru Matsuura
Tadakazu Hisamatsu
author_sort Jun Miyoshi
collection DOAJ
description Background and Aims: The pathophysiology of inflammatory bowel disease (IBD) including ulcerative colitis (UC) and Crohn’s disease (CD) remains unclear. While IBD is heterogeneous, most molecular-targeted drugs (MTDs) are effective for both UC and CD. The immunological pathoetiology can be considered to overlap regardless of clinical manifestations. Classifying IBD based on its immune profile could contribute to understanding its pathophysiology and predict the efficacy of therapy in individual cases. Machine learning has the advantage of being able to analyze complex data and could provide insights into the subcategorization of IBD using its immune profile. Methods: The study used 20 cytokines and chemokines in serum samples from 69 patients with active UC (n = 51) or CD (n = 18) who were MTD-naïve before starting induction therapy. Multidimensional immune profiles considering the balance of items were used for machine learning to classify samples. The clinical outcome was the steroid-free clinical remission rate at 6 months in the patients treated with an MTD (n = 59). Results: Levels of 13 cytokines and chemokines were analyzed. The balance of these 13 cytokines and chemokines was categorized into 5 groups. Cytokines and chemokines appeared to be more balanced in CD than in UC. Machine learning classified 69 patients with IBD into 5 clusters regardless of diagnosis. Among the 59 patients who started an MTD, the steroid-free clinical remission rate at 6 months was 68.4%, 52.6%, 50.0%, 37.5%, and 28.6% in each cluster. A significant association trend was observed between clustering and clinical outcome (P = .043). Conclusion: This proof-of-concept study indicates that machine learning using the serum immune profile can classify active IBD regardless of the clinical diagnosis.
format Article
id doaj-art-3de47a22a8bd41ccb832b2154ea2154d
institution OA Journals
issn 2772-5723
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Gastro Hep Advances
spelling doaj-art-3de47a22a8bd41ccb832b2154ea2154d2025-08-20T02:31:00ZengElsevierGastro Hep Advances2772-57232025-01-014710066710.1016/j.gastha.2025.100667Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical DiagnosisJun Miyoshi0Satoshi Tamura1Noriaki Oguri2Daisuke Saito3Yuu Nishinarita4Haruka Wada5Nobuki Nemoto6Minoru Matsuura7Tadakazu Hisamatsu8Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, Japan; Correspondence: Address correspondence to: Jun Miyoshi, MD, PhD, Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, Shinkawa 6-20-2, Mitaka-shi, Tokyo 181-8611, Japan.Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu University, Gifu, Japan; Satoshi Tamura, PhD, Department of Electrical, Electronic & Computer Engineering, Faculty of Engineering, Gifu University, 1-1 Yanagito, Gifu-shi, Gifu 501-1193, Japan.Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, JapanDepartment of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, Japan; Department of Gastroenterology and Hepatology, Kyorin University Suginami Hospital, Tokyo, JapanDepartment of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, JapanDepartment of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, JapanDepartment of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, JapanDepartment of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, JapanDepartment of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, Japan; Tadakazu Hisamatsu, MD, PhD, AGAF, FACG, Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, Shinkawa 6-20-2, Mitaka-shi, Tokyo 181-8611, Japan.Background and Aims: The pathophysiology of inflammatory bowel disease (IBD) including ulcerative colitis (UC) and Crohn’s disease (CD) remains unclear. While IBD is heterogeneous, most molecular-targeted drugs (MTDs) are effective for both UC and CD. The immunological pathoetiology can be considered to overlap regardless of clinical manifestations. Classifying IBD based on its immune profile could contribute to understanding its pathophysiology and predict the efficacy of therapy in individual cases. Machine learning has the advantage of being able to analyze complex data and could provide insights into the subcategorization of IBD using its immune profile. Methods: The study used 20 cytokines and chemokines in serum samples from 69 patients with active UC (n = 51) or CD (n = 18) who were MTD-naïve before starting induction therapy. Multidimensional immune profiles considering the balance of items were used for machine learning to classify samples. The clinical outcome was the steroid-free clinical remission rate at 6 months in the patients treated with an MTD (n = 59). Results: Levels of 13 cytokines and chemokines were analyzed. The balance of these 13 cytokines and chemokines was categorized into 5 groups. Cytokines and chemokines appeared to be more balanced in CD than in UC. Machine learning classified 69 patients with IBD into 5 clusters regardless of diagnosis. Among the 59 patients who started an MTD, the steroid-free clinical remission rate at 6 months was 68.4%, 52.6%, 50.0%, 37.5%, and 28.6% in each cluster. A significant association trend was observed between clustering and clinical outcome (P = .043). Conclusion: This proof-of-concept study indicates that machine learning using the serum immune profile can classify active IBD regardless of the clinical diagnosis.http://www.sciencedirect.com/science/article/pii/S2772572325000548Inflammatory Bowel DiseaseUlcerative ColitisCrohn’s DiseaseImmune ProfileMachine Learning
spellingShingle Jun Miyoshi
Satoshi Tamura
Noriaki Oguri
Daisuke Saito
Yuu Nishinarita
Haruka Wada
Nobuki Nemoto
Minoru Matsuura
Tadakazu Hisamatsu
Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical Diagnosis
Gastro Hep Advances
Inflammatory Bowel Disease
Ulcerative Colitis
Crohn’s Disease
Immune Profile
Machine Learning
title Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical Diagnosis
title_full Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical Diagnosis
title_fullStr Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical Diagnosis
title_full_unstemmed Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical Diagnosis
title_short Machine Learning of Serum Cytokine and Chemokine Profiles Can Classify Inflammatory Bowel Disease Beyond Clinical Diagnosis
title_sort machine learning of serum cytokine and chemokine profiles can classify inflammatory bowel disease beyond clinical diagnosis
topic Inflammatory Bowel Disease
Ulcerative Colitis
Crohn’s Disease
Immune Profile
Machine Learning
url http://www.sciencedirect.com/science/article/pii/S2772572325000548
work_keys_str_mv AT junmiyoshi machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT satoshitamura machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT noriakioguri machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT daisukesaito machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT yuunishinarita machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT harukawada machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT nobukinemoto machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT minorumatsuura machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis
AT tadakazuhisamatsu machinelearningofserumcytokineandchemokineprofilescanclassifyinflammatoryboweldiseasebeyondclinicaldiagnosis