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 Aug;39(8):5152-5170.
doi: 10.1007/s00464-025-11946-4. Epub 2025 Jul 9.

Predicting the prognosis of radical gastrectomy for patients with locally advanced gastric cancer after neoadjuvant chemotherapy using machine learning technology: a multicenter study in China

Ze-Ning Huang #  1   2   3   4 , Qi-Chen He #  1   2   3   4 , Yu-Qin Sun #  5 , Yu-Bin Ma  6 , Wen-Wu Qiu  1   2   3   4 , Ji-Xun He  1   2   3   4 , Chao-Hui Zheng  1   2   3   4 , Ping Li  1   2   3   4 , Jia-Bin Wang  1   2   3   4 , Qi-Yue Chen  1   2   3   4 , Long-Long Cao  1   2   3   4 , Mi Lin  1   2   3   4 , Ru-Hong Tu  1   2   3   4 , Chang-Ming Huang  1   2   3   4 , Jian-Xian Lin  1   2   3   4 , Jian-Wei Xie  7   8   9   10
Affiliations
Multicenter Study

Predicting the prognosis of radical gastrectomy for patients with locally advanced gastric cancer after neoadjuvant chemotherapy using machine learning technology: a multicenter study in China

Ze-Ning Huang et al. Surg Endosc. 2025 Aug.

Abstract

Background: Neoadjuvant chemotherapy (NAC) can improve the prognosis of patients with locally advanced gastric cancer (LAGC). However, precise models for accurate prognostic predictions are lacking. We aimed to utilize Cox regression and integrate various machine learning (ML) algorithms to identify and prioritize key factors influencing LAGC overall survival to establish an efficient prognostic prediction model.

Methods: Data from 385 patients with LAGC who underwent NAC followed by radical gastrectomy at two centers between January 2016 and December 2020 were analyzed (internal training set, n = 167; internal validation set, n = 112; external validation set, n = 106). The internal cohort was randomly divided into training and validation sets in a 6:4 ratio.

Results: The support vector machine (SVM) model was identified as the best predictive model (AUC values: internal training set, 0.93; internal validation set, 0.74; external validation set, 0.74), outperforming the ypTNM staging system (AUC values: internal training set, 0.9330 vs. 0.7170; internal validation set, 0.7440 vs. 0.6700; external validation set, 0.7403 vs. 0.6960, respectively). In the internal cohort, patients in the HRG (High Risk Group) had significantly lower mean overall survival compared with patients in the LRG (Low Risk Group) (47.33 vs. 64.97 months, respectively; log-rank P = 0.006) and a higher recurrence rate (48.0% vs. 35.6%, respectively; P = 0.041).

Conclusions: The SVM model predicted postoperative survival and recurrence patterns in patients with LAGC post-NAC, and can address the limitations of the ypTNM staging system through providing more targeted decision-making for individualized treatment.

Keywords: Gastrectomy; Gastric cancer; Machine learning; Neoadjuvant chemotherapy.

PubMed Disclaimer

Conflict of interest statement

Declarations. Conflict of interest: Ze-Ning Huang, Qi-Chen He, Yu-Qin Sun, Yu-Bin Ma, Wen-Wu Qiu, Ji-Xun He, Chao-Hui Zheng, Ping Li, Jia-Bin Wang, Qi-Yue Chen, Long-Long Cao, Mi Lin, Ru-Hong Tu, Chang-Ming Huang, Jian-Xian Lin and Jian-Wei Xie have no conflicts of interest or financial ties to disclose. Ethical approval: This study was approved by the Institutional Review Board of the Affiliated Union Hospital of Fujian Medical University and the Affiliated Zhangzhou Hospital of Fujian Medical University, and the Affiliated Hospital of Qinghai University. Written informed consent was obtained from all patients. Consent to publish: Not applicable. Research involving human and animal participants: All procedures of the study were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the principles of the Helsinki Declaration of 1964 and later versions. Informed consent or a substitute for it was obtained from all patients for inclusion in the study.

Similar articles

See all similar articles

References

    1. Sung H, Ferlay J, Siegel RL et al (2021) Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71(3):209–249. https://doi.org/10.3322/caac.21660 - DOI - PubMed
    1. Xu BB, Lu J, Zheng ZF et al (2019) The predictive value of the preoperative C-reactive protein-albumin ratio for early recurrence and chemotherapy benefit in patients with gastric cancer after radical gastrectomy: using randomized phase III trial data. Gastric Cancer 22(5):1016–1028. https://doi.org/10.1007/s10120-019-00936-w - DOI - PubMed
    1. Chang JS, Kim KH, Yoon HI et al (2017) Locoregional relapse after gastrectomy with D2 lymphadenectomy for gastric cancer. Br J Surg 104(7):877–884. https://doi.org/10.1002/bjs.10502 - DOI - PubMed
    1. Cunningham D, Allum WH, Stenning SP et al (2006) Perioperative chemotherapy versus surgery alone for resectable gastroesophageal cancer. N Engl J Med 355(1):11–20. https://doi.org/10.1056/NEJMoa055531 - DOI - PubMed
    1. Ychou M, Boige V, Pignon JP et al (2011) Perioperative chemotherapy compared with surgery alone for resectable gastroesophageal adenocarcinoma: an FNCLCC and FFCD multicenter phase III trial. J Clin Oncol 29(13):1715–1721. https://doi.org/10.1200/JCO.2010.33.0597 - DOI - PubMed

Publication types

LinkOut - more resources