In Intensive Care Units (ICU), the abundance of multivariate time series presents an opportunity for machine learning (ML) to enhance patient phenotyping. In contrast to previous research focused on electronic health records (EHR), here we propose an ML approach for phenotyping using routinely collected physiological time series data. Our new algorithm integrates Long Short-Term Memory (LSTM) networks with collaborative filtering concepts to identify common physiological states across patients. Tested on real-world ICU clinical data for intracranial hypertension (IH) detection in patients with brain injury, our method achieved an area under the curve (AUC) of 0.889 and average precision (AP) of 0.725. Moreover, our algorithm outperforms autoencoders in learning more structured latent representations of the physiological signals. These findings highlight the promise of our methodology for patient phenotyping, leveraging routinely collected multivariate time series to improve clinical care practices.

翻译：在重症监护病房（ICU）中，丰富的多变量时间序列数据为机器学习（ML）提升患者表型分析提供了机遇。与以往专注于电子健康记录（EHR）的研究不同，本文提出一种利用常规采集的生理时间序列数据进行表型分析的ML方法。我们提出的新算法将长短期记忆（LSTM）网络与协同过滤概念相结合，以识别跨患者的共同生理状态。在针对脑损伤患者颅内高压（IH）检测的真实世界ICU临床数据测试中，本方法取得了曲线下面积（AUC）0.889和平均精度（AP）0.725的性能。此外，我们的算法在学习生理信号更具结构化的潜在表征方面优于自编码器。这些发现凸显了本方法在患者表型分析中的应用潜力，能够利用常规采集的多变量时间序列数据改进临床诊疗实践。