A Framework for Patient State Tracking by Classifying Multiscalar Physiologic Waveform Features.
A Framework for Patient State Tracking by Classifying Multiscalar Physiologic Waveform Features.
复制标题
通过对多标量生理波形特征进行分类来跟踪患者状态的框架。
DOI：
10.1109/tbme.2017.2684244
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Jacono,FrankJ
中科院分区：
文献类型：
--
作者：
Vandendriessche,Benjamin;Abas,Mustafa;Dick,ThomasE;Loparo,KennethA;Jacono,FrankJ
量化生理波形中的非线性动力学的最新算法由于其深奥的性质而在临床上未得到充分利用。我们提出了一个可推广的框架，用于分类多标量波形特征，设计用于患者状态跟踪直接在beds.Methodsan人工神经网络分类器的设计，以评估多尺度波形特征对指纹数据库的多重分形合成时间序列。结果被映射到一个生理状态空间近实时patient-state tracking.Resultsthe框架进行了验证心脏跳动到跳动的动态处理与多尺度熵算法，并使用PhysioNet数据库进行评估。然后，我们应用我们的算法来预测败血症患者的28天死亡率，并发现它有更大的预后准确性比标准的临床严重程度scores.Conclusionwe开发了一种新的框架来分类多尺度特征的心跳到心跳的动态，并进行了初步的临床验证，以证明我们的方法产生了一个强大的量化病人的状态，重要性该框架生成有意义的和可操作的患者特异性信息，并且可以促进一类新的“始终在线”诊断工具的传播。
Objectivestate-of-the-art algorithms that quantify nonlinear dynamics in physiologic waveforms are underutilized clinically due to their esoteric nature. We present a generalizable framework for classifying multiscalar waveform features, designed for patient-state tracking directly at the bedside.Methodsan artificial neural network classifier was designed to evaluate multiscale waveform features against a fingerprint database of multifractal synthetic time series. The results are mapped into a physiologic state space for near real-time patient-state tracking.Resultsthe framework was validated on cardiac beat-to-beat dynamics processed with the multiscale entropy algorithm, and assessed using PhysioNet databases. We then applied our algorithm to predict 28-day mortality for sepsis patients, and found it had greater prognostic accuracy than standard clinical severity scores.Conclusionwe developed a novel framework to classify multiscale features of beat-to-beat dynamics, and performed an initial clinical validation to demonstrate that our approach generates a robust quantification of a patient's state, compatible with real-time bedside implementations.Significancethe framework generates meaningful and actionable patient-specific information, and could facilitate the dissemination of a new class of “always-on” diagnostic tools.