Thayer School of Engineering, Dartmouth College, 14 Engineering Dr, Hanover, NH 03755, USA.
Insight Research, 412 Lakeview Way, Emerald Hills, CA 94062, USA.
Mil Med. 2021 Jan 25;186(Suppl 1):445-451. doi: 10.1093/milmed/usaa418.
Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances.
Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes.
Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence.
We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.
在危重病患者中，早期预测急性低血压事件（AHE）有可能改善预后。在这项研究中，我们将不同的机器学习算法应用于包含超过 60000 个真实重症监护病房记录的 MIMIC III Physionet 数据集，以测试常用的机器学习技术并比较它们的性能。
应用包括 K-最近邻、逻辑回归、支持向量机、随机森林和称为长短期记忆的深度学习方法在内的五种分类方法，提前 30 分钟预测 AHE。分析了在包含和不包含有创特征的情况下模型性能的差异。为了进一步研究潜在平均动脉压（MAP）的模式，我们应用回归方法，通过在下一个 60 分钟内进行线性回归来预测连续的 MAP 值。
支持向量机在召回率（84%）方面表现最佳。在分类中包含有创特征可显著提高性能，召回率和精度均提高了 20 多个百分点。我们能够以 10mmHg 的均方根误差（一种常用的预测值与观测值之间差异的度量）预测未来 60 分钟的 MAP。将连续 MAP 预测转换为 AHE 二进制预测后，我们实现了 91%的召回率和 68%的精度。除了预测 AHE 之外，MAP 预测还提供了有关 AHE 发生的时间和严重程度的有用信息。
我们能够使用大型真实数据集提前 30 分钟以 80%以上的精度和召回率预测 AHE。回归模型的预测可以为从业者提供更精细、可解释的信号。与仅基于可用的、受限的无创技术预测 AHE 相比，在预测 AHE 时包含有创特征可提高模型性能。这表明探索更多无创技术对于 AHE 预测的重要性。
