Scholarlink

Background <p>Machine learning (ML) is increasingly being used to predict prognosis. This study aimed to establish and compare various ML models for predicting five-year all-cause mortality in patients with mixed gastric cancer, focusing on identifying significant prognostic features.</p> Methods <p>We developed five ML models using a follow-up database of mixed gastric cancer patients. The model with the highest performance, the Light Gradient Boosting Machine (LGBM), was selected to predict five-year all-cause mortality. The log-rank test was employed to evaluate the divergence of Kaplan–Meier curves.</p> Results <p>The LGBM model excelled in predicting and stratifying patient risk, achieving an average AUC of 0.887 (SD: 0.079), an F1-score of 0.790 (SD: 0.060), and a Brier score of 0.152 (SD: 0.036) in the training set. In the test set, it achieved a maximum AUC of 0.835 (95% CI: 0.823–0.848) and a minimum Brier score of 0.172 (95% CI: 0.166–0.177). Higher machine learning scores correlated with increased mortality risk. Key prognostic factors included pN stage, pTNM stage, tumor diameter, surgical radicality, Fbg levels, and biomarkers CA199, CA724, and CA125.</p> Conclusion <p>This study successfully applied ML techniques to predict five-year all-cause mortality in patients with mixed gastric cancer. The LGBM model proved effective in both prediction and risk stratification, highlighting critical prognostic factors that clinicians should consider in patient management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning-based prediction of five-year all-cause mortality in patients with mixed gastric cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月4日

查看全文
  • Cong Wang,
  • Hongwei Li,
  • Hongye Yang,
  • Yingwei Xue

摘要

Background

Machine learning (ML) is increasingly being used to predict prognosis. This study aimed to establish and compare various ML models for predicting five-year all-cause mortality in patients with mixed gastric cancer, focusing on identifying significant prognostic features.

Methods

We developed five ML models using a follow-up database of mixed gastric cancer patients. The model with the highest performance, the Light Gradient Boosting Machine (LGBM), was selected to predict five-year all-cause mortality. The log-rank test was employed to evaluate the divergence of Kaplan–Meier curves.

Results

The LGBM model excelled in predicting and stratifying patient risk, achieving an average AUC of 0.887 (SD: 0.079), an F1-score of 0.790 (SD: 0.060), and a Brier score of 0.152 (SD: 0.036) in the training set. In the test set, it achieved a maximum AUC of 0.835 (95% CI: 0.823–0.848) and a minimum Brier score of 0.172 (95% CI: 0.166–0.177). Higher machine learning scores correlated with increased mortality risk. Key prognostic factors included pN stage, pTNM stage, tumor diameter, surgical radicality, Fbg levels, and biomarkers CA199, CA724, and CA125.

Conclusion

This study successfully applied ML techniques to predict five-year all-cause mortality in patients with mixed gastric cancer. The LGBM model proved effective in both prediction and risk stratification, highlighting critical prognostic factors that clinicians should consider in patient management.