Rinehart Joseph, Tang Jia, Nam Jennifer, Sha Sophie, Mensah Paulette, Maxwell Hailey, Calderon Michael-David, Ma Michael, Joosten Alexandre
Department of Anesthesiology & Perioperative Care, University of California Irvine, 101 The City Drive South, Orange, CA, 92868, USA.
Department of Anesthesiology & Perioperative Care, UCI Medical Center, 101 the City Drive South, Orange, CA, 92868, USA.
J Clin Monit Comput. 2022 Feb;36(1):227-237. doi: 10.1007/s10877-020-00642-4. Epub 2021 Feb 1.
In critically ill and high-risk surgical room patients, an invasive arterial catheter is often inserted to continuously measure arterial pressure (AP). The arterial waveform pressure measurement, however, may be compromised by damping or inappropriate reference placement of the pressure transducer. Clinicians, decision support systems, or closed-loop applications that rely on such information would benefit from the ability to detect error from the waveform alone. In the present study we hypothesized that machine-learning trained algorithms could discriminate three types of transducer error from accurate monitoring with receiver operator characteristic (ROC) curve areas greater than 0.9. After obtaining written consent, patient arterial line waveform data was collected in the operating room in real-time during routine surgery requiring arterial pressure monitoring. Three deliberate error conditions were introduced during monitoring: Damping, Transducer High, and Transducer Low. The waveforms were split up into 10 s clips that were featurized. The data was also either calibrated against the patient's own baseline or left uncalibrated. The data was then split into training and validation sets, and machine-learning algorithms were run in a Monte-Carlo fashion on the training data with variable sized training sets and hyperparameters. The algorithms with the highest balanced accuracy were pruned, then the highest performing algorithm in the training set for each error state (High, Low, Damped) for both calibrated and uncalibrated data was finally tested against the validation set and the ROC and precision-recall curve area-under the curve (AUC) calculated. 38 patients were enrolled in the study with a mean age of 52 ± 15 years. A total of 40 h of monitoring time was recorded with approximately 120,000 heart beats featurized. For all error states, ROC AUCs for algorithm performance on classification of the state were greater than 0.9; when using patient-specific calibrated data AUCs were 0.94, 0.95, and 0.99 for the transducer low, transducer high, and damped conditions respectively. Machine-learning trained algorithms were able to discriminate arterial line transducer error states from the waveform alone with a high degree of accuracy.
在危重症和高风险手术室患者中，常插入有创动脉导管以持续测量动脉压（AP）。然而，动脉波形压力测量可能会因压力传感器的阻尼或不当的参考位置而受到影响。依赖此类信息的临床医生、决策支持系统或闭环应用程序将受益于仅从波形中检测误差的能力。在本研究中，我们假设经过机器学习训练的算法能够以大于0.9的受试者工作特征（ROC）曲线面积，从准确监测中区分三种类型的传感器误差。在获得书面同意后，在需要动脉压监测的常规手术期间，于手术室实时收集患者动脉管路波形数据。在监测过程中引入了三种故意设置的误差情况：阻尼、传感器偏高和传感器偏低。将波形分割成10秒的片段并提取特征。数据也可根据患者自身基线进行校准或保持未校准状态。然后将数据分为训练集和验证集，并以蒙特卡洛方式在具有可变大小训练集和超参数的训练数据上运行机器学习算法。对具有最高平衡准确率的算法进行修剪，然后针对校准和未校准数据，在每种误差状态（偏高、偏低、阻尼）的训练集中性能最佳的算法最终在验证集上进行测试，并计算ROC和精确召回曲线下面积（AUC）。38名患者参与了该研究，平均年龄为52±15岁。共记录了40小时的监测时间，约120,000次心跳被提取特征。对于所有误差状态，算法对状态分类的ROC AUC均大于0.9；使用患者特定校准数据时，传感器偏低、传感器偏高和阻尼情况下的AUC分别为0.94、0.95和0.99。经过机器学习训练的算法能够仅从波形中高度准确地区分动脉管路传感器误差状态。
