Predicting delayed cerebral ischemia after subarachnoid hemorrhage using physiological time series data.
Predicting delayed cerebral ischemia after subarachnoid hemorrhage using physiological time series data.
复制标题
DOI：
10.1007/s10877-018-0132-5
复制
发表时间：
2019-03
影响因子：
2.2
通讯作者：
Elhadad N
中科院分区：
文献类型：
--
作者：
Park S;Megjhani M;Frey HP;Grave E;Wiggins C;Terilli KL;Roh DJ;Velazquez A;Agarwal S;Connolly ES Jr;Schmidt JM;Claassen J;Elhadad N
利用时间无监督特征工程方法开发和验证蛛网膜下腔出血(SAH)后迟发性脑缺血(DCI)的预测模型，显示出比标准特征更高的精度。纳入了2006-2014年间连续488名SAH患者进入三级护理医院。80%的模型接受了培训，而20%的模型被留出来进行验证测试。评估基线资料和标准分级标准：年龄、性别、Hunt Hess分级、改良Fisher评分(MFS)和格拉斯哥昏迷评分(GCS)。使用一种应用随机核的无监督方法来从生理时间序列(收缩和舒张压、心率、呼吸频率和血氧饱和度)中提取特征。在派生数据集的特征子集上训练分类器(偏最小二乘、线性和核支持向量机)。模型被应用于验证数据集。最佳分类器在验证数据集上的性能按特征子集报告。标准评分(MFS)：AUC 0.58。综合人口统计和评分标准：AUC 0.60。随机核导出的生理特征：AUC 0.74。结合基线和生理特征并进行冗余特征约简：AUC 0.77。目前的DCI预测工具依赖于入院成像，并且有利地简单易用。然而，对于高频生理时间序列数据，我们使用了一种不可知的、计算成本低的学习方法，我们证明了我们的模型实现了更高的分类精度。
To develop and validate a prediction model for delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH) using a temporal unsupervised feature engineering approach, demonstrating improved precision over standard features. 488 consecutive SAH admissions from 2006–2014 to a tertiary care hospital were included. Models were trained on 80%, while 20% were set aside for validation testing. Baseline information and standard grading scales were evaluated: age, sex, Hunt Hess grade, modified Fisher Scale (mFS), and Glasgow Coma Scale (GCS). An unsupervised approach applying random kernels was used to extract features from physiological time series (systolic and diastolic blood pressure, heart rate, respiratory rate, and oxygen saturation). Classifiers (Partial Least Squares, linear and kernel Support Vector Machines) were trained on feature subsets of the derivation dataset. Models were applied to the validation dataset. The performances of the best classifiers on the validation dataset are reported by feature subset. Standard grading scale (mFS): AUC 0.58. Combined demographics and grading scales: AUC 0.60. Random kernel derived physiologic features: AUC 0.74. Combined baseline and physiologic features with redundant feature reduction: AUC 0.77. Current DCI prediction tools rely on admission imaging and are advantageously simple to employ. However, using an agnostic and computationally inexpensive learning approach for high frequency physiologic time series data, we demonstrated that our models achieve higher classification accuracy.
登录
查看更多内容
影响因子：
--
作者：
Dua, Sumeet;Saini, Sheetal;Singh, Harpreet
通讯作者：
Singh, Harpreet
DOI：
10.1109/jproc.2015.2501978
发表时间：
2016-02
期刊：
Proceedings of the IEEE. Institute of Electrical and Electronics Engineers
影响因子：
--
作者：
Johnson AE;Ghassemi MM;Nemati S;Niehaus KE;Clifton DA;Clifford GD
通讯作者：
Clifford GD
影响因子：
8.8
作者：
Gaieski, David F.;Mikkelsen, Mark E.;Goyal, Munish
通讯作者：
Goyal, Munish
影响因子：
3.5
作者：
Calviere, Lionel;Nasr, Nathalie;Larrue, Vincent
通讯作者：
Larrue, Vincent
影响因子：
8.3
作者：
Frontera, Jennifer A.;Fernandez, Andres;Mayer, Stephan A.
通讯作者：
Mayer, Stephan A.