改善心力衰竭护理:基于深度学习的活动分类在左心室辅助设备患者
Laurenz Berger1,2, Max Haberbusch1,2,3, Christoph Gross4,5
1From the Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria.
概括
深度神经网络准确地使用心率,LVAD流量和加速度计数据对患者的活动进行分类. 这一进步对于左心室辅助器件 (LVAD) 的闭环控制至关重要.
科学领域:
- 生物医学工程 生物医学工程
- 医疗保健中的人工智能
- 心血管设备技术的技术
背景情况:
- 准确的患者活动分类对于左心室辅助器件 (LVAD) 的适应性控制至关重要.
- 目前的方法可能缺乏用于设备操作实时调整所需的精度.
- 闭环控制系统需要对患者状态进行可靠的反.
研究的目的:
- 开发和评估深度神经网络 (DNN) 以精确对LVAD患者的活动分类.
- 为了比较不同活动状态的二进制和多类DNN分类器的性能.
- 确定最佳的DNN架构和数据集成策略,以提高分类准确度.
主要方法:
- 分析了13名LVAD患者的生理数据 (心率,LVAD流量) 和加速度计数据.
- 训练二进制和多类DNN,包括循环和卷积层.
- 对各种模型架构进行超参数优化和测试,特别是双向长短期内存 (LSTM) 层.
主要成果:
- 整合了LVAD流量,心率和加速度计数据,获得了最高的分类准确度.
- 最佳的DNN架构实现了对二进制分类 (主动/非主动) 的准确率为91%,对多类分类的准确率为84%.
- 双向LSTM层被证明是有效的,用于二进制任务有两层,用于多类任务有三层.
结论:
- 深度神经网络提供了一种强大而准确的方法,用于在LVADs的背景下对患者活动进行分类.
- 这项技术对于实现有效的闭环控制和优化心脏护理设备性能至关重要.
- 这些发现支持将人工智能驱动的活动分类纳入未来的医疗器械控制系统.
相关概念视频
Heart Failure Drugs: Inotropic Agents
545
Positive inotropic agents are commonly used as the first line of treatment for heart failure. One such agent is digoxin, derived from the genus Digitalis, which has been known for centuries but effectively utilized since 1785. However, these cardiac glycosides can have potentially toxic effects due to their mechanism of action, which involves inhibiting Na+/K+-ATPase and increasing contractility. Digoxin is absorbed orally and distributed in various tissues, including the CNS. It has a long...
545
Pathophysiology of Heart Failure
1.5K
Heart failure (HF) is a progressive syndrome involving ventricles that leads to inadequate cardiac output. It can be classified based on location and output or ejection fraction. Ejection fraction (EF) is an essential measurement in the diagnosis and surveillance of HF. Reduced EF corresponds to systolic heart failure (HFrEF). However, HF with preserved ejection fraction (HFpEF) is becoming increasingly prevalent. Also known as diastolic HF, this form of HF is related to aging. The...
1.5K


