文献速递妇科

机器学习生存模型预测上皮性卵巢癌复发时间

Machine-learning survival models for predicting time to recurrence in epithelial ovarian cancer.
PubMed 文献 · Gynecol Oncol · 2025-12-05

本研究利用一线化疗结束时病历信息,训练5种机器学习生存模型预测上皮性卵巢癌复发时间,并在全部患者及III/IV期患者中验证。梯度提升生存分析(GBSA)预测全时段复发性能最佳,2年和3年累积/动态AUC(CD-AUC)均高于0.8;DeepSurv和随机生存森林(RSF)在15个月短时程预测中表现最好。模型预测准确性可具临床实用性,但需验证性研究确认。

要点

  • GBSA预测全时段复发CD-AUC在2年和3年高于0.8,性能最佳。
  • DeepSurv和RSF对15个月短时程复发预测表现最好。
  • I期、HRD阴性、NACT及一线化疗期间CA125升高为显著复发预测因素。

核心结论

  • 机器学习生存模型预测复发时间的准确性足以具有临床实用性,但需验证性研究确认这些发现。

研究设计与样本

  • 研究使用患者病历中一线化疗结束时已知信息训练5种生存模型:惩罚Cox比例风险模型(PenCoxPH)、随机生存森林(RSF)、梯度提升生存分析(GBSA)、DeepSurv和FastCPH,预测复发时间。
  • 模型在全部患者及仅III和IV期患者中训练,并分别使用全长(总复发时间)数据和短时程(限制于15个月)复发数据训练,以提高一线化疗完成后第一年的预测准确性。
  • 评估PenCoxPH模型的特征风险比。

主要发现

  • GBSA预测全时段复发时间获得最高性能评分,DeepSurv和RSF在短时程复发预测中表现最佳。
  • GBSA在2年和3年的累积/动态AUC(CD-AUC)高于0.8。
  • I期、HRD阴性、NACT及一线化疗期间CA125升高为复发的显著预测因素。
  • PenCoxPH和FastCPH在高分期高级别浆液性队列全时程复发中6个月CD-AUC为0.74。

临床怎么用

  • 作者认为,提供者可能利用这些信息调整维持治疗策略并选择患者参加临床试验。

局限性

  • 原文指出需验证性研究确认这些发现。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To evaluate the effectiveness of machine learning survival models to predict time to recurrence using information from patient medical records known at the completion of frontline chemotherapy. METHODS: Five survival models - Penalized Cox Proportional Hazards (PenCoxPH), Random Survival Forest (RSF), Gradient Boosted Survival Analysis (GBSA), DeepSurv, and FastCPH - were trained on medical record data and used to predict time to recurrence. The models were trained on both the full set of patients and high-stage (III and IV) patients only. They were trained on the full-length (total time to recurrence) data as well as short-horizon (restricted to 15 months) recurrence data to increase prediction accuracy for the first year following completion of frontline chemotherapy. Feature hazard ratios for the PenCoxPH model were evaluated. RESULTS: GBSA received the highest performance scores when predicting full-length time to recurrence, while the DeepSurv and RSF models did best on predictions for short-horizon recurrence. GBSA achieved CD-AUC (cumulative/dynamic AUC) measures above 0.8 at 2 and 3 years. Stage I, HRD Negative, NACT and a rise in CA125 over the course of frontline chemotherapy were significant predictors of recurrence. PenCoxPH and FastCPH achieved a 6-month CD-AUC of 0.74 the high-stage, high-grade serous cohort for full-horizon recurrence. CONCLUSION: Machine learning survival models can predict time to recurrence with sufficient accuracy to be clinically useful. While confirmatory studies are needed to validate these findings, providers could potentially use this information to tailor treatment strategies in maintenance therapy and select patients for clinical trial enrollment.

来源:Gynecol Oncol,查看原文。版权归原作者所有。

引用

  1. Nakayama J, McGaughey M, Pindzola G, et al. Machine-learning survival models for predicting time to recurrence in epithelial ovarian cancer. Gynecol Oncol. 2025. PMID: 41351944. doi:10.1016/j.ygyno.2025.11.021

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。