Machine learning for multidimensional response and survival after cardiac resynchronization therapy using features from cardiac magnetic resonance.
Machine learning for multidimensional response and survival after cardiac resynchronization therapy using features from cardiac magnetic resonance.
复制标题
DOI：
10.1016/j.hroo.2022.06.005
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Bilchick, Kenneth C.
中科院分区：
文献类型：
--
作者：
Bivona, Derek J.;Tallavajhala, Srikar;Abdi, Mohamad;Oomen, Pim J. A.;Gao, Xu;Malhotra, Rohit;Darby, Andrew E.;Monfredi, Oliver J.;Mangrum, J. Michael;Mason, Pamela K.;Mazimba, Sula;Salerno, Michael;Kramer, Christopher M.;Epstein, Frederick H.;Holmes, Jeffrey W.;Bilchick, Kenneth C.
关键词：
心脏再同步化治疗（CRT）的反应是复杂的，需要更好的方法来预测生存情况以及对进阶治疗的需求。
目的是利用机器学习来描述多维CRT反应及其与长期生存的关系。
评估了39项基线特征（包括心脏磁共振[CMR]结果以及肾小球滤过率[GFR]等临床参数）与一个多维CRT反应向量（由CRT后左心室收缩末期容积指数[LVESVI]分数变化、CRT后B型利钠肽以及峰值摄氧量变化组成）之间的关联。机器学习生成了反应集群，交叉验证评估了集群与4年生存率之间的关联。
在200名接受CRT和CMR的患者（中位年龄67.4岁，女性占27.0%）中，CMR CURE - SVD不同步参数（与CRT后脑利钠肽[BNP]和LVESVI分数变化相关）以及GFR（与峰值摄氧量和CRT后BNP相关）与不止1个反应参数存在关联。机器学习定义了3个反应集群：集群1（n = 123，生存率90.2%[最佳]），集群2（n = 45，生存率60.0%[中等]），集群3（n = 32，生存率34.4%[最差]）。将6个月的反应集群添加到基线特征中，使4年生存率的受试者工作特征曲线下面积从0.78提高到0.86（P = 0.02）。开发了一个基于网络的应用程序，用于未来患者的集群判定。
机器学习描述了受CMR特征、肾功能和其他因素影响的不同CRT反应集群。相对于基线特征，这些集群对长期生存具有强大的累加影响。
Cardiac resynchronization therapy (CRT) response is complex, and better approaches are required to predict survival and need for advanced therapies. The objective was to use machine learning to characterize multidimensional CRT response and its relationship with long-term survival. Associations of 39 baseline features (including cardiac magnetic resonance [CMR] findings and clinical parameters such as glomerular filtration rate [GFR]) with a multidimensional CRT response vector (consisting of post-CRT left ventricular end-systolic volume index [LVESVI] fractional change, post-CRT B-type natriuretic peptide, and change in peak VO2) were evaluated. Machine learning generated response clusters, and cross-validation assessed associations of clusters with 4-year survival. Among 200 patients (median age 67.4 years, 27.0% women) with CRT and CMR, associations with more than 1 response parameter were noted for the CMR CURE-SVD dyssynchrony parameter (associated with post-CRT brain natriuretic peptide [BNP] and LVESVI fractional change) and GFR (associated with peak VO2 and post-CRT BNP). Machine learning defined 3 response clusters: cluster 1 (n = 123, 90.2% survival [best]), cluster 2 (n = 45, 60.0% survival [intermediate]), and cluster 3 (n = 32, 34.4% survival [worst]). Adding the 6-month response cluster to baseline features improved the area under the receiver operating characteristic curve for 4-year survival from 0.78 to 0.86 (P = .02). A web-based application was developed for cluster determination in future patients. Machine learning characterizes distinct CRT response clusters influenced by CMR features, kidney function, and other factors. These clusters have a strong and additive influence on long-term survival relative to baseline features.
登录
查看更多内容
影响因子：
1.4
作者：
Wiley, Carmen L.;Switzer, Sean P.;Dart, Richard A.
通讯作者：
Dart, Richard A.
影响因子：
--
作者：
Ebong, Imo;Mazimba, Sula;Breathett, Khadijah
通讯作者：
Breathett, Khadijah
影响因子：
5.5
作者：
Takase, Hiroyuki;Dohi, Yasuaki
通讯作者：
Dohi, Yasuaki
影响因子：
158.5
作者：
Abraham, WT;Fisher, WG;McAtee, P
通讯作者：
McAtee, P
影响因子：
37.8
作者：
Chung, Eugene S.;Leon, Angel R.;Murillo, Jaime
通讯作者：
Murillo, Jaime