Critical care clinicians are trained to analyze simultaneously multiple physiological parameters to predict critical conditions such as hemodynamic instability. We developed the Multi-task Learning Physiological Deep Learner (MTL-PDL), a deep learning algorithm that predicts simultaneously the mean arterial pressure (MAP) and the heart rate (HR).

In an external validation dataset, our model exhibited very good calibration: R² of 0.747 (95% confidence interval, 0.692 to 0.794) and 0.850 (0.815 to 0.879) for respectively, MAP and HR prediction 60-minutes ahead of time. For acute hypotensive episodes defined as a MAP below 65 mmHg for 5 min, our MTL-PDL reached a predictive value of 90% for patients at very high risk (predicted MAP ≤ 60 mmHg) and 2‰ for patients at low risk (predicted MAP >70 mmHg).

Based on its excellent prediction performance, the Physiological Deep Learner has the potential to help the clinician proactively adjust the treatment in order to avoid hypotensive episodes and end-organ hypoperfusion.

重症监护临床医生经过培训，可以同时分析多个生理参数，以预测诸如血流动力学不稳定等危急情况。我们开发了多任务学习生理深度学习器 (MTL-PDL)，这是一种深度学习算法，可同时预测平均动脉压 (MAP) 和心率 (HR)。

在外部验证数据集中，我们的模型表现出非常好的校准：对于提前 60 分钟的 MAP 和 HR 预测，R ^{2 分别}为 0.747（95% 置信区间，0.692 至 0.794）和 0.850（0.815 至 0.879）。对于定义为 MAP 低于 65 mmHg 持续 5 分钟的急性低血压发作，我们的 MTL-PDL 对极高风险（预测 MAP ≤ 60 mmHg）患者的预测值达到 90%，对低风险患者（预测 MAP）达到 2‰ >70 毫米汞柱）。

基于其出色的预测性能，生理深度学习器有可能帮助临床医生主动调整治疗，以避免低血压发作和终末器官灌注不足。