Development and validation of machine learning-based survival analysis to predict outcome in gastric cancer with adjuvant chemotherapy: A multicenter, longitudinal, cohort study

Yan Pan; Linbin Lu; Xianchun Gao; Jun Yu; Sitian Dai; Ruirong Yao; Ning Han; Xinlin Wang; Abudurousuli Reyila; Shibo Wang; Junya Yan; Zhen Xu; Yuanyuan Lu; Mengbin Li; Jipeng Li; Jiayun Liu; Qingchuan Zhao; Kaichun Wu; Yongzhan Nie

doi:10.21147/j.issn.1000-9604.2025.03.07

Development and validation of machine learning-based survival analysis to predict outcome in gastric cancer with adjuvant chemotherapy: A multicenter, longitudinal, cohort study

Chin J Cancer Res. 2025 Jun 30;37(3):377-389. doi: 10.21147/j.issn.1000-9604.2025.03.07.

Authors

Yan Pan^#¹, Linbin Lu^#^{1

2}, Xianchun Gao¹, Jun Yu¹, Sitian Dai¹, Ruirong Yao¹, Ning Han¹, Xinlin Wang¹, Abudurousuli Reyila¹, Shibo Wang¹, Junya Yan¹, Zhen Xu¹, Yuanyuan Lu¹, Mengbin Li¹, Jipeng Li¹, Jiayun Liu³, Qingchuan Zhao¹, Kaichun Wu¹, Yongzhan Nie¹

Affiliations

¹ State Key Laboratory of Cancer Biology and National Clinical Research Center for Digestive Diseases, Xijing Hospital of Digestive Diseases, Fourth Military Medical University, Xi'an 710032, China.
² Department of Oncology, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou 350028, China.
³ State Key Laboratory of Cancer Biology, Department of Clinical Laboratory, Xijing Hospital and School of Basic Medicine, Fourth Military Medical University, Xi'an 710032, China.

^# Contributed equally.

PMID: 40642491
PMCID: PMC12240237
DOI: 10.21147/j.issn.1000-9604.2025.03.07

Abstract

Objective: The previously integrated tumor-inflammation-nutrition (HI-GC) score has demonstrated dynamic monitoring value for recurrence and clinical decision-making in patients with postsurgical gastric cancer (GC). However, its failure to incorporate clinical-pathological factors limits its capacity for baseline risk assessment. This study aimed to develop a model that accurately identifies patients for adjuvant chemotherapy and dynamically evaluates recurrence risk.

Methods: This retrospective, multicenter, longitudinal cohort study, spanning nine hospitals, included 7,085 patients with GC post-radical gastrectomy. A baseline prognostic model was constructed using 117 machine-learning algorithms. The dynamic survival decision tree model (dySDT) was employed to combine the baseline model with the HI-GC score.

Results: A Cox regression model incorporating six factors was used to create a nomogram [Harrell's C-index: training cohort: 0.765; 95% confidence interval (95% CI): 0.747, 0.783; validation set: 0.810; 95% CI: 0.747, 0.783], including pT stage, positive lymph node ratio, pN stage, tumor size, age, and adjuvant chemotherapy. The best-performing machine learning model exhibited similar predictive accuracy to the nomogram (C-index: 0.770). For the short-term dySDT at 1 month, the mortality hazard ratios (HRs) for groups IIa, IIb, and III were 2.61 (95% CI: 2.24, 3.04), 5.02 (95% CI: 4.15, 6.06), and 8.88 (95% CI: 7.57, 10.42), respectively, compared to group I. Stratified analysis revealed a significant interaction between adjuvant chemotherapy and overall survival in each subgroup (P<0.001). The long-term dySDT at 1 year showed HRs of 3.25 (95% CI: 2.12, 4.97) for group II, 6.73 (95% CI: 4.29, 10.56) for group IIIa, and 17.88 (95% CI: 10.71, 29.84) for group IIIb.

Conclusions: The dySDT effectively stratifies mortality risk and provides valuable assistance in clinical decision-making after gastrectomy.

Keywords: Gastric cancer; HI-GC score; machine learning; predictive model.