EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Serum Bile Acid Metabolomics‐Based Machine Learning Model for Non‐Invasive Diagnosis of Gastric Cancer

Nuo Yao, Xiaodong Qu, Ya Zheng, Songbo Li, Xidong Fang, Kexin Lin, Xingyu Zhao, Danyang Zhao, Yongning Zhou iD, Junye Liu iD, Yongquan Shi iD

Cancer Medicine · 2026

DOI: 10.1002/cam4.72346 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancer Medicine, 2026. Verfasst von Nuo Yao und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology & Hepatology, State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers, National Clinical R…. Hauptthemen laut MEDLINE: Stomach Neoplasms, Metabolomics, Machine Learning, Biomarkers, Tumor. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China, National Science and Technology Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Gastric cancer (GC) has posed a severe threat to human health. Metabolomics analysis has been applied in the context of multiple diseases, offering new perspectives for the development of non‐invasive detections.

Objective

We aimed to develop a diagnostic model for GC based on a serum bile acid (BA) panel.

Methods

A total of 632 participants were recruited for serum samples collection, and their clinical characteristics were recorded. Targeted BA profiling was conducted using ultra‐performance liquid chromatography–mass spectrometry (UPLC–MS). Participants from Xi'an were randomly allocated into a training cohort and an internal tuning cohort at a 7:3 ratio. The key BAs were identified through the two‐step selection method, and nine machine learning (ML) models were constructed and optimized. The optimal model was further evaluated externally using an independent validation cohort from Lanzhou.

Results

A panel of 10 serum BAs was confirmed for the construction of a diagnostic model. The XGBoost model exhibited the best performance on the tuning cohort, with an area under the receiver operating characteristic curve (AUROC) of 0.858. It also exhibited robust performance on the external validation cohort (AUROC = 0.816), significantly outperforming tumor markers (with the highest AUROC of CA72‐4 = 0.68). The developed model also demonstrated satisfactory predictive performance for patients with resectable stage GC (Stage I–II) (average precision [AP] = 0.75).

Conclusion

GC patients exhibit BA metabolic disorders. The XGBoost model based on a 10‐BA panel exhibited superior efficacy in GC detection, indicating its promising potential for clinical application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Stomach NeoplasmsMetabolomicsMachine LearningBiomarkers, TumorBile Acids and SaltsHumansFemaleMaleMiddle AgedAgedROC CurveBoosting Machine Learning Algorithms

Stichwörter der Autor:innen

bile acidsbiomarkersdiagnostic modelgastric cancermachine learning

Substanzen

Biomarkers, TumorBile Acids and Salts

Autor:innen und Institutionen

  • Department of Gastroenterology & Hepatology, State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers, National Clinical Research Center for Digestive Diseases, Xijing Hospital, The Fourth Mil…
  • Department of Gastroenterology, The First Hospital of Lanzhou University, Lanzhou, China.
  • Department of Radiation Protective Medicine, Air Force Medical University, Xi'an, Shaanxi, China.

ORCID-Profile: Yongning Zhou, Junye Liu, Yongquan Shi

Förderung

  • National Natural Science Foundation of China
  • National Science and Technology Major Project

Zitieren

APA

Yao, N., Qu, X., Zheng, Y., Li, S., Fang, X., Lin, K., Zhao, X., Zhao, D., Zhou, Y., Liu, J., & Shi, Y. (2026). Serum Bile Acid Metabolomics‐Based Machine Learning Model for Non‐Invasive Diagnosis of Gastric Cancer. Cancer Medicine. https://doi.org/10.1002/cam4.72346

Vancouver

Yao N, Qu X, Zheng Y, Li S, Fang X, Lin K, et al. Serum Bile Acid Metabolomics‐Based Machine Learning Model for Non‐Invasive Diagnosis of Gastric Cancer. Cancer Medicine. 2026. doi:10.1002/cam4.72346

BibTeX
@article{Yao2026,
  author = {Yao, Nuo and Qu, Xiaodong and Zheng, Ya and Li, Songbo and Fang, Xidong and Lin, Kexin and Zhao, Xingyu and Zhao, Danyang and Zhou, Yongning and Liu, Junye and Shi, Yongquan},
  title = {Serum Bile Acid Metabolomics‐Based Machine Learning Model for Non‐Invasive Diagnosis of Gastric Cancer},
  journal = {Cancer Medicine},
  year = {2026},
  doi = {10.1002/cam4.72346}
}
Kostenlos starten →