Establishment of a predictive model for GVHD-free, relapse-free survival after allogeneic HSCT using ensemble learning.
Establishment of a predictive model for GVHD-free, relapse-free survival after allogeneic HSCT using ensemble learning.
复制标题
DOI：
10.1182/bloodadvances.2021005800
复制
发表时间：
2022-04-26
期刊：
影响因子：
7.5
通讯作者：
Takaori-Kondo, Akifumi
中科院分区：
文献类型：
--
作者：
Iwasaki, Makoto;Kanda, Junya;Arai, Yasuyuki;Kondo, Tadakazu;Ishikawa, Takayuki;Ueda, Yasunori;Imada, Kazunori;Akasaka, Takashi;Yonezawa, Akihito;Yago, Kazuhiro;Nohgawa, Masaharu;Anzai, Naoyuki;Moriguchi, Toshinori;Kitano, Toshiyuki;Itoh, Mitsuru;Arima, Nobuyoshi;Takeoka, Tomoharu;Watanabe, Mitsumasa;Hirata, Hirokazu;Asagoe, Kosuke;Miyatsuka, Isao;An, Le My;Miyanishi, Masanori;Takaori-Kondo, Akifumi
机器学习算法的堆叠集成可以建立比现有方法更准确的生存分析预测模型。堆叠集成模型可以应用于移植前特征的HSCT结果的个性化预测。无移植物抗宿主病、无复发生存期（GRFS）是一个有用的复合终点，用于衡量异基因造血干细胞移植（allo-HSCT）后无复发或显著发病的生存率。我们的目的是开发一种新的分析方法，适当地处理右删失数据和竞争风险，以了解GRFS和GRFS的每个组成部分的风险。本研究是一项回顾性数据挖掘研究，对2207例在京都干细胞移植组（一个由日本17个移植中心组成的多机构联合研究组）接受首次allo-HSCT的成人患者进行了队列研究。主要终点为GRFS。应用考克斯比例风险（Cox-PH）回归和7种机器学习算法的堆叠集成来开发预测模型。患者的中位年龄为48岁。对于GRFS，堆叠集成模型通过C指数评估的预测准确性优于其他最先进的竞争风险模型（集成模型：0.670; Cox-PH：0.668;随机生存森林：0.660;动态DeepHit：0.646）。高风险组和低风险组2年后GRFS的概率分别为30.54%和40.69%（与低风险组相比的风险比：2.127; 95% CI，1.19-3.80）。我们开发了一种用于生存分析的新型预测模型，该模型显示出比使用多种机器学习算法的堆叠集成的现有方法更优越的上级风险分层。
Stacked ensemble of machine-learning algorithms could establish more accurate prediction model for survival analysis than existing methods. Stacked ensemble model can be applied to personalized prediction of HSCT outcomes from pretransplant characteristics. 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.
登录
查看更多内容
DOI：
10.1016/j.bbmt.2008.12.497
发表时间：
2009-03
期刊：
Biology of blood and marrow transplantation : journal of the American Society for Blood and Marrow Transplantation
影响因子：
--
作者：
Giralt S;Ballen K;Rizzo D;Bacigalupo A;Horowitz M;Pasquini M;Sandmaier B
通讯作者：
Sandmaier B
影响因子：
20.3
作者：
Armand, Philippe;Kim, Haesook T.;Saber, Wael
通讯作者：
Saber, Wael
影响因子：
51.1
作者：
Bornhaeuser, Martin;Kienast, Joachim;Stelljes, Matthias
通讯作者：
Stelljes, Matthias
影响因子：
7.2
作者：
Collins, Gary S.;Reitsma, Johannes B.;Moons, Karel G. M.
通讯作者：
Moons, Karel G. M.
影响因子：
2
作者：
Austin, Peter C.;Harrell, Frank E., Jr.;van Klaveren, David
通讯作者：
van Klaveren, David