首页> 外文会议>Second ICSC Symposium on Engineering of Intelligent Systems, Jun 27-30, 2000, Scotland, U.K. >An Evaluation of the Effects of Blood Flow Velocity Waveforms from Umbilical and Cerebral Artery for Antenatal Fetal Risk Assessment Decision
【24h】

An Evaluation of the Effects of Blood Flow Velocity Waveforms from Umbilical and Cerebral Artery for Antenatal Fetal Risk Assessment Decision

机译:脐血和脑动脉血流速度波形对产前胎儿风险评估决策的影响评估

获取原文
获取原文并翻译 | 示例

摘要

Our purpose is to study a system for antepartum fetal evaluation. The task is to investigate the doppler ultrasound measurements of umbilical artery (UA) and cerebral artery (CA) to relate the health conditions of fetuses using discriminant functions of pattern recognition. We use the following UA blood flow velocity waveforms: pulsality index (PI), resistance index (RI) and systolic/diastolic ratio (S/D) in terms of weeks (week index: WI as a normalized value) and derive linear (LDA), quadratic (QDA), and a nonlinear discriminant (artificial Neural Network: ANN) functions to decide if there is hypoxia suspicion. With these indices, a specificity and sensitivity are 100% and 88%. Furthermore, the RIs of UA and CA and the ratios of cerebral-umbilical resistance indices (CRI/URI) are also used and a specificity of 100% and sensitivity of 93 % are obtained.. We then analyze the individual effects of these indices using Principal Component Analysis (PCA) method. It is verified that S/D ratio in UA measurements has the biggest effect on the indication of adverse conditions. It has also been demonstrated that discriminant functions can be employed as a reasonable medical aid to phycisians during intensive surveilance of fetuses.
机译:我们的目的是研究一种产前胎儿评估系统。任务是研究使用模式识别的判别函数,对脐动脉(UA)和脑动脉(CA)进行多普勒超声测量,以关联胎儿的健康状况。我们使用以下UA血流速度波形:脉搏指数(PI),阻力指数(RI)和收缩/舒张比(S / D)(以周为单位)(周指数:WI为归一化值)并得出线性(LDA) ,二次(QDA)和非线性判别式(人工神经网络:ANN)的功能来确定是否存在缺氧可疑之处。使用这些指标,特异性和敏感性分别为100%和88%。此外,还使用了UA和CA的RIs和脑脐电阻指数(CRI / URI)的比率,特异性为100%,敏感性为93%。主成分分析(PCA)方法。验证了UA测量中的S / D比对不良状况的指示影响最大。还已经证明,在胎儿的强化监护过程中,判别功能可以用作对水手的合理医疗帮助。

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