平均动脉压是所有你需要在机器学习模型的平均动脉压预测的预测
Thomas Tschoellitsch1, Sophie Kaltenleithner, Alexander Maletzky
1From the Department of Anesthesiology and Critical Care, Johannes Kepler University, Linz and Kepler University Hospital, Linz (TT, JM), Research Unit Medical Informatics, RISC Software GmbH, Hagenberg im Mühlkreis (SK, AM, PM, ST, MG), European Laboratory for Learning and Intelligent Systems Unit Linz, Austria and Linz Institute of Technology - Artificial Intelligence Lab and Institute for Machine Learning, Johannes Kepler University (PS, SH) and Institute of Signal Processing, Johannes Kepler University, Linz, Austria (CB).
机器学习使用过去的MAP值准确地预测了平均动脉压 (MAP) 的下降. 这种预测能力可以帮助临床医生更早地进行干预,以防止患者病情恶化.
科学领域:
- 关键护理医学 关键护理医学
- 生物医学工程 生物医学工程
- 机器学习在医疗保健中的应用
背景情况:
- 麻醉学和重症监护依赖于监测,以检测患者的病情恶化.
- 传统方法在预测不良事件方面提供了适度的可靠性.
- 降低平均动脉压 (MAP) 与并发症有关,需要预测模型.
研究的目的:
- 基于历史数据,评估机器学习在预测未来平均动脉压 (MAP) 值方面的有效性.
- 评估ML模型在预测MAP下一个关键值时的性能.
主要方法:
- 一个回顾性,使用MIMIC-III-WDB,VitalDB和内部数据集的观察性队列研究.
- 机器学习模型被训练成年患者侵入性测量血压 (IBP).
- 输入数据包括在预测视界 (5-20分钟) 之前的20分钟窗口内的MAP值.
主要成果:
- 模型实现了高预测准确度,内部数据集的ROC AUC高达0.963.
- 即使在专注于稳定患者的二次分析中,表现仍然很强.
- 在不同时间范围内,MAP低于65mmHg的预测是成功的.
结论:
- 机器学习模型可以在5到20分钟内可靠地预测65mmHg以下的平均动脉压 (MAP).
- 这些模型只需要历史的MAP数据作为输入.
- 早期预测MAP恶化的情况,可以及时进行临床干预.
相关概念视频
Measurement of Blood Pressure
Equipments Used To Measure Blood Pressure
This invasive approach involves cannulating a peripheral artery. During each cardiac contraction, pressure generates mechanical motion within the catheter, transmitted through rigid, fluid-filled tubing to a transducer. This transducer converts mechanical motion into electrical signals displayed as waveforms on a monitor. An automatic flushing system prevents blood backflow. Due to the potential risk of unexpected arterial blood loss, this method is primarily used in intensive...
Neural Regulation of Blood Pressure
Baroreceptor Reflex
Baroreceptors, located in the carotid sinuses and aortic arch, detect changes in blood pressure. When blood pressure rises, these stretch-sensitive receptors...
Pre-Procedural Guidelines for Assessing Blood Pressure
Mechanistic Models: Compartment Models in Individual and Population Analysis
Blood Pressure


