A Bayesian Model to Predict Survival After Left Ventricular Assist Device Implantation.
A Bayesian Model to Predict Survival After Left Ventricular Assist Device Implantation.
复制标题
DOI：
10.1016/j.jchf.2018.03.016
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Antaki J
中科院分区：
文献类型：
--
作者：
Kanwar MK;Lohmueller LC;Kormos RL;Teuteberg JJ;Rogers JG;Lindenfeld J;Bailey SH;McIlvennan CK;Benza R;Murali S;Antaki J
本研究探讨了使用贝叶斯统计模型来预测接受左心室辅助装置（LVAD）植入的患者在不同时间点的生存率。LVAD越来越多地用于终末期心力衰竭患者。适当的患者选择仍然是优化LVAD术后结局的关键。本研究使用的数据来自2012年1月至2015年12月期间植入了主要LVAD的机械辅助循环支持机构间登记研究（INTERMACS）的10，277例成人患者。使用多个植入前变量，回顾性计算LVAD后不同时间点（1、3和12个月）的死亡风险。对于这些终点中的每一个，使用最具预测性的变量构建单独的树增强朴素贝叶斯模型。发现分别有29、26和31个LVAD前变量在1、3和12个月时具有预测性。1个月死亡率的预测因素包括低INTERMACS特征、术前48小时急性事件数量、临时机械循环支持、肾功能和肝功能障碍。预测12个月死亡率的变量包括高龄、虚弱、器械策略、慢性肾脏疾病等。所有贝叶斯模型的准确性在76%至87%之间，受试者手术特征曲线下面积在0.70至0.71之间。基于INTERMACS综合登记研究的预测生存率的贝叶斯预后模型提供了基于术前变量的高度准确的死亡率预测。这些模型可能有助于临床决策，同时筛选LVAD治疗的候选人。
This study investigates the use of a Bayesian statistical models to predict survival at various time points in patients undergoing left ventricular assist device (LVAD) implantation. LVADs are being increasingly used in patients with end-stage heart failure. Appropriate patient selection continues to be key in optimizing post LVAD outcomes. Data used for this study were derived from 10,277 adult patients from the Inter-Agency Registry for Mechanically Assisted Circulatory Support (INTERMACS) who had a primary LVAD implanted between January 2012 and December 2015. Risk for mortality was calculated retrospectively for various time points (1, 3 and 12 months) post LVAD, using multiple pre implantation variables. For each of these endpoints, a separate tree-augmented naïve Bayes model was constructed using the most predictive variables. A set of 29, 26 and 31 pre LVAD variables were found to be predictive at 1, 3, and 12 month, respectively. Predictors of 1 month mortality included low INTERMACS profile, number of acute events 48 hours before surgery, temporary mechanical circulatory support, renal and hepatic dysfunction. Variables predicting 12 month mortality included advanced age, frailty, device strategy, chronic renal disease etc. The accuracy of all Bayesian models was between 76% and 87%, with an area under the receiver operative characteristics curve between 0.70 and 0.71. A Bayesian prognostic model for predicting survival based on the comprehensive INTERMACS registry provided highly accurate predictions of mortality based on pre-operative variables. These models may facilitate clinical decision making while screening candidates for LVAD therapy.
登录
查看更多内容
影响因子：
37.8
作者：
Yancy, Clyde W.;Jessup, Mariell;Westlake, Cheryl
通讯作者：
Westlake, Cheryl
影响因子：
7.5
作者：
Friedman, N;Geiger, D;Goldszmidt, M
通讯作者：
Goldszmidt, M
影响因子：
24
作者：
Cowger, Jennifer;Sundareswaran, Kartik;Slaughter, Mark S.
通讯作者：
Slaughter, Mark S.
DOI：
10.1097/mat.0000000000000035
发表时间：
2014-03
期刊：
ASAIO journal (American Society for Artificial Internal Organs : 1992)
影响因子：
--
作者：
Sabashnikov A;Mohite PN;Zych B;García D;Popov AF;Weymann A;Patil NP;Hards R;Capoccia M;Wahlers T;De Robertis F;Bahrami T;Amrani M;Banner NR;Simon AR
通讯作者：
Simon AR
影响因子：
8.9
作者：
Thomas, Sunu S.;Nahumi, Nadav;Jorde, Ulrich P.
通讯作者：
Jorde, Ulrich P.