应用集成学习建立异基因造血干细胞移植后无GVHD无复发生存预测模型
本研究为回顾性数据挖掘研究,纳入日本17家移植中心共2207例首次接受异基因造血干细胞移植的成年患者,采用Cox比例风险回归与7种机器学习算法堆叠集成建立无移植物抗宿主病无复发生存(GRFS)预测模型。集成模型C指数为0.670,优于Cox-PH的0.668、随机生存森林的0.660和Dynamic DeepHit的0.646。高危组2年GRFS概率为30.54%,低危组为40.69%(高危较低危风险比2.127,95%CI 1.19-3.80)。
要点
- 堆叠集成模型预测GRFS的C指数为0.670,高于Cox-PH的0.668、随机生存森林的0.660和Dynamic DeepHit的0.646。
- 高危组2年GRFS概率为30.54%,低危组为40.69%。
- 高危组较低危组风险比为2.127(95%CI 1.19-3.80)。
核心结论
- 应用多种机器学习算法堆叠集成开发了新的生存分析预测模型,对GRFS的风险分层优于现有方法。
研究设计与样本
- 回顾性数据挖掘研究,队列为在日本17家移植中心组成的京都干细胞移植组内首次接受异基因造血干细胞移植的2207例成年患者。
- 主要终点为无移植物抗宿主病无复发生存(GRFS)。
- 采用Cox比例风险回归与7种机器学习算法堆叠集成建立预测模型。
主要发现
- 患者中位年龄为48岁。
- 集成模型预测GRFS的C指数为0.670,Cox-PH为0.668,随机生存森林为0.660,Dynamic DeepHit为0.646。
- 高危组2年GRFS概率为30.54%,低危组为40.69%。
- 高危组较低危组的风险比为2.127(95%CI,1.19-3.80)。
临床怎么用
- 原文未据此给出临床推荐。
局限性
- 原文未报告局限性。
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
Graft-versus-host disease-free, relapse-free survival (GRFS) is a useful composite end point that measures survival without relapse or significant morbidity after allogeneic hematopoietic stem cell transplantation (allo-HSCT). We aimed to develop a novel analytical method that appropriately handles right-censored data and competing risks to understand the risk for GRFS and each component of GRFS. This study was a retrospective data-mining study on a cohort of 2207 adult patients who underwent their first allo-HSCT within the Kyoto Stem Cell Transplantation Group, a multi-institutional joint research group of 17 transplantation centers in Japan. The primary end point was GRFS. A stacked ensemble of Cox Proportional Hazard (Cox-PH) regression and 7 machine-learning algorithms was applied to develop a prediction model. The median age for the patients was 48 years. For GRFS, the stacked ensemble model achieved better predictive accuracy evaluated by C-index than other state-of-the-art competing risk models (ensemble model: 0.670; Cox-PH: 0.668; Random Survival Forest: 0.660; Dynamic DeepHit: 0.646). The probability of GRFS after 2 years was 30.54% for the high-risk group and 40.69% for the low-risk group (hazard ratio compared with the low-risk group: 2.127; 95% CI, 1.19-3.80). We developed a novel predictive model for survival analysis that showed superior risk stratification to existing methods using a stacked ensemble of multiple machine-learning algorithms.
引用
- Iwasaki M, Kanda J, Arai Y, et al. Establishment of a predictive model for GVHD-free, relapse-free survival after allogeneic HSCT using ensemble learning. Blood Adv. 2022. PMID: 34933327. doi:10.1182/bloodadvances.2021005800
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。