Risk-Stratified Biologic Efficacy in Ulcerative Colitis: A Multicenter Machine Learning Study
Inflammatory Bowel Diseases · 2025
DOI: 10.1093/ibd/izaf272 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Inflammatory Bowel Diseases, 2025. Verfasst von Pingxin Zhang und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China. Hauptthemen laut MEDLINE: Colitis, Ulcerative, Machine Learning, Biological Products. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Key R&D Program of China, Key-Area Research and Development Program of Guangdong Province.
Abstract (Originalsprache)
Background
Ulcerative colitis (UC) exhibits a heterogeneous clinical course, complicating prognostication and therapeutic decision making. Current tools inadequately predict progression or identify patients most likely to benefit from biologic therapies. We aimed to develop a machine learning model for risk stratification and evaluate its utility in optimizing biologic therapy outcomes.
Methods
In this multicenter retrospective study, we analyzed 481 UC patients as the training cohort and 131 external validation patients. Disease progression—defined as treatment escalation, UC-related hospitalization, or surgery—served as the primary endpoint. Four models (Cox regression, logistic regression, random forest, XGBoost) were developed to predict progression risk. Biologic-treated patients (n = 235) were stratified into risk groups using the optimal model, with outcomes including mucosal healing, relapse, and acute severe UC assessed.
Results
The random forest model demonstrated superior performance, achieving an area under the curve of 0.959 in training set and 0.759 in validation set. High-risk biologic-treated patients (n = 172) exhibited lower mucosal healing rates (33.7% vs 55.2%; P = .049) and higher hazards of clinical relapse (hazard ratio [HR], 3.35; P = .003), hospitalization (HR, 2.03; P = .014), and acute severe UC (HR, 2.70; P = .030) compared with low-risk patients (n = 63). No differences in serological remission, surgery, or biologic switching were observed.
Conclusions
Our random forest model enables precise risk stratification in UC, distinguishing patients with divergent responses to biologics. Low-risk patients derive significant benefit from timely biologics, while high-risk subgroups may require intensified strategies. This framework advances personalized UC management, though prospective validation is warranted.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Gastroenterology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
- Department of Gastroenterology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China.
- Institute of Precision Medicine, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, Guangdong, China.
- Department of Gastroenterology, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
- Department of Gastroenterology, Shenzhen Qianhai Taikang Hospital, Shenzhen, Guangdong, China.
ORCID-Profile: Pingxin Zhang, Shixian Hu, Rui Feng, Yun Qiu, Minhu Chen
Förderung
- National Key R&D Program of China
- Key-Area Research and Development Program of Guangdong Province
Zitieren
APA
Zhang, P., Zhang, C., Liu, Z., Chen, L., Wang, Y., Su, F., Liu, X., Huang, Z., Hu, S., Feng, R., Mao, R., Chao, K., Qiu, Y., & Chen, M. (2025). Risk-Stratified Biologic Efficacy in Ulcerative Colitis: A Multicenter Machine Learning Study. Inflammatory Bowel Diseases. https://doi.org/10.1093/ibd/izaf272
Vancouver
Zhang P, Zhang C, Liu Z, Chen L, Wang Y, Su F, et al. Risk-Stratified Biologic Efficacy in Ulcerative Colitis: A Multicenter Machine Learning Study. Inflammatory Bowel Diseases. 2025. doi:10.1093/ibd/izaf272
BibTeX
@article{Zhang2025,
author = {Zhang, Pingxin and Zhang, Chuhan and Liu, Zishan and Chen, Liru and Wang, Yu and Su, Fengyuan and Liu, Xinyu and Huang, Zicheng and Hu, Shixian and Feng, Rui and Mao, Ren and Chao, Kang and Qiu, Yun and Chen, Minhu},
title = {Risk-Stratified Biologic Efficacy in Ulcerative Colitis: A Multicenter Machine Learning Study},
journal = {Inflammatory Bowel Diseases},
year = {2025},
doi = {10.1093/ibd/izaf272}
}
EUVIMED