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
{"title":"基于机器学习的生存分析预测胃癌辅助化疗预后的发展和验证：一项多中心、纵向、队列研究。","authors":"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","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>The dySDT effectively stratifies mortality risk and provides valuable assistance in clinical decision-making after gastrectomy.</p>","PeriodicalId":9882,"journal":{"name":"Chinese Journal of Cancer Research","volume":"37 3","pages":"377-389"},"PeriodicalIF":7.0000,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12240237/pdf/","citationCount":"0","resultStr":"{\"title\":\"Development and validation of machine learning-based survival analysis to predict outcome in gastric cancer with adjuvant chemotherapy: A multicenter, longitudinal, cohort study.\",\"authors\":\"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\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>The dySDT effectively stratifies mortality risk and provides valuable assistance in clinical decision-making after gastrectomy.</p>\",\"PeriodicalId\":9882,\"journal\":{\"name\":\"Chinese Journal of Cancer Research\",\"volume\":\"37 3\",\"pages\":\"377-389\"},\"PeriodicalIF\":7.0000,\"publicationDate\":\"2025-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12240237/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Chinese Journal of Cancer Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.21147/j.issn.1000-9604.2025.03.07\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chinese Journal of Cancer Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.21147/j.issn.1000-9604.2025.03.07","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
Development and validation of machine learning-based survival analysis to predict outcome in gastric cancer with adjuvant chemotherapy: A multicenter, longitudinal, cohort study.
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.
期刊介绍：
Chinese Journal of Cancer Research (CJCR; Print ISSN: 1000-9604; Online ISSN:1993-0631) is published by AME Publishing Company in association with Chinese Anti-Cancer Association.It was launched in March 1995 as a quarterly publication and is now published bi-monthly since February 2013.
CJCR is published bi-monthly in English, and is an international journal devoted to the life sciences and medical sciences. It publishes peer-reviewed original articles of basic investigations and clinical observations, reviews and brief communications providing a forum for the recent experimental and clinical advances in cancer research. This journal is indexed in Science Citation Index Expanded (SCIE), PubMed/PubMed Central (PMC), Scopus, SciSearch, Chemistry Abstracts (CA), the Excerpta Medica/EMBASE, Chinainfo, CNKI, CSCI, etc.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
