域名知识 包括单调神经网络指南 患者特异性 诱导全身麻醉剂量
Kathryn Sarullo1, Muntaha Samad2, Samir Kendale3
1From the Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, Missouri.
机器学习模型,包括一种新的单调神经网络 (MNN),可以预测诱导后低血压. 该MNN整合了领域知识,以改善芬太尼和普罗波福的患者特异性麻醉剂量.
科学领域:
- 麻醉学 麻醉学
- 机器学习 机器学习
- 预测分析是一种预测分析.
背景情况:
- 诱导后低血压是不良手术结果的重要危险因素.
- 麻醉剂量取决于患者的数据和麻醉师的专业知识.
- 机器学习为预测低血压提供了先进的方法,神经网络显示出有希望的结果.
研究的目的:
- 开发机器学习模型来预测诱导后低血压.
- 建议芬太尼和普罗波福的通用和患者特定的麻醉剂量.
- 将临床领域的知识纳入预测模型.
主要方法:
- 诱导后低血压定义为诱导后10分钟内的平均动脉压<65 mm Hg.
- 利用了201,000个患者记录的数据集,其中包括临床数据和药物历史.
- 实施并比较各种分类算法,包括一个新的单调神经网络 (MNN).
主要成果:
- 渐变增强和神经网络显示出高性能,但缺乏域知识集成.
- MNN成功地结合了麻醉剂量与低血压风险之间的单调关系.
- 热图可视化了平均和特定患者的低血压概率,MNN提供了更顺的预测.
结论:
- 该MNN准确地预测了诱导后低血压,与现有方法相比.
- 该模型编码了临床相关的单调关系,以提高可解释性.
- 这种工具有助于麻醉师优化患者特定的芬太尼和普罗波剂量.
更多相关视频
14:52Recording Brain Electromagnetic Activity During the Administration of the Gaseous Anesthetic Agents Xenon and Nitrous Oxide in Healthy Volunteers
Published on: January 13, 2018
10:19Induction of an Isoelectric Brain State to Investigate the Impact of Endogenous Synaptic Activity on Neuronal Excitability In Vivo
Published on: March 31, 2016
相关概念视频
Stages of General Anesthesia
General Anesthesia: Overview
General anesthesia induces unconsciousness in the whole body, while the others target specific areas or sensations. It is administered to minimize adverse effects, maintain...
Parenteral Anesthetics: Overview
Local Anesthetics: Clinical Application as Spinal Anesthesia
Inhalational Anesthetics: Overview
Local Anesthetics: Adverse Effects
Once absorbed into the systemic circulation, local anesthetics can affect the organs that depend on the functioning of sodium...
