Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA.
Heinz College of Information Systems and Public Policy, Carnegie Mellon University, Pittsburgh, PA.
AMIA Annu Symp Proc. 2021 Jan 25;2020:619-628. eCollection 2020.
The efficacy of early fluid treatment in patients with sepsis is unclear and may contribute to serious adverse events due to fluid non-responsiveness. The current method of deciding if patients are responsive to fluid administration is often subjective and requires manual intervention. This study utilizes MIMIC III and associated matched waveform datasets across the entire ICU stay duration of each patient to develop prediction models for assessing fluid responsiveness in sepsis patients. We developed a pipeline to extract high frequency continuous waveform data and included waveform features in the prediction models. Comparing across five machine learning models, random forest performed the best when no waveform information is added (AUC = 0.84), with mean arterial blood pressure and age identified as key factors. After incorporation of features from physiologic waveforms, logistic regression with L1 penalty provided consistent performance and high interpretability, achieving an accuracy of 0.89 and F1 score of 0.90.
在脓毒症患者中，早期液体治疗的疗效尚不清楚，并且可能由于液体无反应性而导致严重不良事件。目前，决定患者对液体治疗是否有反应的方法通常是主观的，需要人工干预。本研究利用 MIMIC III 和相关匹配的波形数据集，在每个患者的整个 ICU 住院期间，开发了用于评估脓毒症患者液体反应性的预测模型。我们开发了一个提取高频连续波形数据的管道，并在预测模型中包含了波形特征。在比较了五个机器学习模型后，当不添加波形信息时，随机森林表现最好（AUC = 0.84），平均动脉压和年龄被确定为关键因素。在纳入生理波形特征后，具有 L1 惩罚的逻辑回归提供了一致的性能和高度的可解释性，达到了 0.89 的准确性和 0.90 的 F1 分数。
