Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2025 Apr;32(4):2637-2650.
doi: 10.1245/s10434-024-16701-y. Epub 2024 Dec 30.

Machine Learning Prediction of Early Recurrence in Gastric Cancer: A Nationwide Real-World Study

Xing-Qi Zhang #  1   2   3 , Ze-Ning Huang #  1   2   3 , Ju Wu  1   4 , Xiao-Dong Liu  5 , Rong-Zhen Xie  1   6 , Ying-Xin Wu  1   7 , Chang-Yue Zheng  1   8 , Chao-Hui Zheng  1   2   3 , Ping Li  1   2   3 , Jian-Wei Xie  1   2   3 , Jia-Bin Wang  1   2   3 , Qi-Chen He  1   2   3 , Wen-Wu Qiu  1   2   3 , Yi-Hui Tang  1   2   3 , Hao-Xiang Zhang  1   2   3 , Yan-Bing Zhou  9 , Jian-Xian Lin  10   11   12 , Chang-Ming Huang  13   14   15
Affiliations
Multicenter Study

Machine Learning Prediction of Early Recurrence in Gastric Cancer: A Nationwide Real-World Study

Xing-Qi Zhang et al. Ann Surg Oncol. 2025 Apr.

Abstract

Background: Patients with gastric cancer (GC) who experience early recurrence (ER) within 2 years postoperatively have poor prognoses. This study aimed to analyze and predict ER after curative surgery for patients with GC using machine learning (ML) methods.

Patients and methods: This multicenter population-based cohort study included data from ten large tertiary regional medical centers in China. The clinical, pathological, and laboratory parameters were retrospectively collected from the records of 11,615 patients. The patients were randomly divided into training (70%) and test (30%) cohorts. A total of ten ML models were developed and validated to predict the ER. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), calibration plots, and Brier score (BS). SHapley Additive exPlanations (SHAP) was used to rank the input features and interpret predictions.

Results: ER was reported in 1794 patients (15%) during follow-up. The stacking ensemble model achieved AUCs of 1.0 and 0.8 in the training and testing cohorts, respectively, with a BS of 0.113. SHAP dependency plots revealed that tumor staging, elevated tumor marker levels, lymphovascular invasion, perineural invasion, and tumor size > 5 cm were associated with higher ER risk. The impact of age and the number of lymph nodes harvested on ER risk exhibited a "U-shaped distribution." Additionally, an online prediction tool based on the best model was developed to facilitate clinical applications.

Conclusions: We developed a robust clinical model for predicting the risk of ER after surgery for GC, which may aid in individualized clinical decision-making.

Keywords: Artificial intelligence; Gastric cancer; Machine learning; Prognosis; Recurrence.

PubMed Disclaimer

Conflict of interest statement

Disclosures: All authors have no conflict of interest and no potential benefits.

References

    1. Sung H, Ferlay J, Siegel R, et al. Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71(3):209–49. https://doi.org/10.3322/caac.21660 . - DOI - PubMed
    1. Akikazu Y, Shusuke H, Masaki U, et al. Adequate period of surveillance in each stage for curatively resected gastric cancer: analyzing the time and rates of recurrence. Gastric Cancer. 2021. https://doi.org/10.1007/s10120-020-01147-4 . - DOI
    1. Ryo T, Manabu O, Yosuke K, et al. Timing and site-specific trends of recurrence in patients with pathological stage II or III gastric cancer after curative gastrectomy followed by adjuvant S-1 monotherapy. Gastric Cancer. 2019. https://doi.org/10.1007/s10120-019-00953-9 . - DOI
    1. Huang C, Liu H, Hu Y, et al. Laparoscopic vs open distal gastrectomy for locally advanced gastric cancer: five-year outcomes from the CLASS-01 randomized clinical trial. JAMA Surg. 2022;157(1):9–17. https://doi.org/10.1001/jamasurg.2021.5104 . - DOI - PubMed
    1. Kakeji Y, Ishikawa T, Suzuki S, et al. A retrospective 5-year survival analysis of surgically resected gastric cancer cases from the Japanese Gastric Cancer Association nationwide registry (2001–2013). Off J Int Gastric Cancer Assoc Jpn Gastric Cancer Assoc. 2022;25(6):1082–93. https://doi.org/10.1007/s10120-022-01317-6 . - DOI

Publication types

MeSH terms

LinkOut - more resources