首页> 外文会议>Annual International Conference of the IEEE Engineering in Medicine and Biology Society >A dynamic Bayesian network approach for time-specific survival probability prediction in patients after ventricular assist device implantation
【24h】

A dynamic Bayesian network approach for time-specific survival probability prediction in patients after ventricular assist device implantation

机译:动态贝叶斯网络方法用于心室辅助装置植入后患者的特定时间生存概率预测

获取原文

摘要

In this work we present a decision support tool for the calculation of time-dependent survival probability for patients after ventricular assist device implantation. Two different models have been developed, a short term one which predicts survival for the first three months and a long term one that predicts survival for one year after implantation. In order to model the time dependencies between the different time slices of the problem, a dynamic Bayesian network (DBN) approach has been employed. DBNs order to capture the temporal events of the patient disease and the temporal data availability. High accuracy results have been reported for both models. The short and long term DBNs reached an accuracy of 96.97% and 93.55% respectively.
机译:在这项工作中,我们提出了一个决策支持工具,用于计算室心辅助装置植入后患者的时间依赖存存概率。已经开发了两种不同的模型,这是一个短期,这是前三个月的生存,并且长期预测植入后一年的生存。为了模拟问题的不同时间片之间的时间依赖性,已经采用了一种动态贝叶斯网络(DBN)方法。 DBNS命令捕获患者疾病的时间事件和时间数据可用性。两种型号都报告了高精度结果。短期和长期DBN分别达到96.97%和93.55%的准确性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号