背景:预测异基因造血细胞移植(HCT)后的结果仍然是一个主要挑战。机器学习(ML)是可以促进HCT预测模型的生成的计算过程。当应用于大型单中心同种异体HCT数据库时,我们试图研究多种ML算法的预后潜力。
方法:我们的注册包括1976年1月至2017年12月接受同种异体HCT的2697例患者,每个ML算法的总体生存率(OS)的预测性评估中包括45个移植前基线变量,通过曲线下面积(AUC)确定。EBMT机器学习研究中使用的移植前变量(Shouval等人,2015)被用作比较基准。
结果:在整个数据集上,与第二好的模型相比,随机森林(RF)算法表现最好(AUC0.71±0.04),逻辑回归(LR)(AUC=0.69±0.04)(p<0.001)。与通过EBMT研究检查的有限变量相比,使用所有45个变量,两种算法都显示出改善的AUC得分。在完整数据集上使用RF在HCT后100天的存活率将患者区分为具有不同2年OS的不同预后组(p<0.0001)。然后,我们检查了允许显著的个体变量识别的ML方法,包括LR和RF,并确定了匹配的相关捐赠者(HR=0.49,p<0.0001),增加TBI剂量(HR=1.60,p=0.006),受体年龄增加(HR=1.92,p<0.0001),较高的基线Hb(HR=0.59,p=0.0002)和增加的基线FEV1(HR=0.73,p=0.02),在其他人中。
结论:在单中心同种异体HCT数据库中应用多种ML技术值得进一步研究,并可能为识别具有预后潜力的变量提供有用的工具。
BACKGROUND: Prediction of outcomes following allogeneic hematopoietic cell transplantation (HCT) remains a major challenge. Machine learning (ML) is a computational procedure that may facilitate the generation of HCT prediction models. We sought to investigate the prognostic potential of multiple ML algorithms when applied to a large single-center allogeneic HCT database.
METHODS: Our registry included 2,697 patients that underwent allogeneic HCT from January 1976 to December 2017. 45 pretransplant baseline variables were included in the predictive assessment of each ML algorithm on overall survival (OS) as determined by area under the curve (AUC). Pretransplant variables used in the EBMT ML study (Shouval et al., 2015) were used as a benchmark for comparison.
RESULTS: On the entire dataset, the random forest (RF) algorithm performed best (AUC 0.71 ± 0.04) compared to the second-best model, logistic regression (LR) (AUC = 0.69 ± 0.04) (p < 0.001). Both algorithms demonstrated improved AUC scores using all 45 variables compared to the limited variables examined by the EBMT study. Survival at 100 days post-HCT using RF on the full dataset discriminated patients into different prognostic groups with different 2-year OS (p < 0.0001). We then examined the ML methods that allow for significant individual variable identification, including LR and RF, and identified matched related donors (HR = 0.49, p < 0.0001), increasing TBI dose (HR = 1.60, p = 0.006), increasing recipient age (HR = 1.92, p < 0.0001), higher baseline Hb (HR = 0.59, p = 0.0002), and increased baseline FEV1 (HR = 0.73, p = 0.02), among others.
CONCLUSIONS: The application of multiple ML techniques on single-center allogeneic HCT databases warrants further investigation and may provide a useful tool to identify variables with prognostic potential.