公开(公告)号：US09750463B2

公开(公告)日：2017-09-05

申请号：US14101663

申请日：2013-12-10

Applicant: General Electric Company

Inventor： Gokul Swamy ,  Sahika Genc ,  Hariharan Ravishankar ,  Aditya Saha

IPC: A61B5/00 ,  A61B5/08 ,  A61B5/0205 ,  A61B5/145 ,  A61B5/20 ,  A61B5/083 ,  A61B5/021 ,  A61B5/024 ,  A61B5/01

CPC classification number: A61B5/7275 ,  A61B5/002 ,  A61B5/0022 ,  A61B5/01 ,  A61B5/02055 ,  A61B5/021 ,  A61B5/024 ,  A61B5/0816 ,  A61B5/0836 ,  A61B5/14532 ,  A61B5/14542 ,  A61B5/201 ,  A61B5/202 ,  A61B5/7203 ,  A61B5/7246 ,  A61B5/7264 ,  A61B5/746 ,  G06F19/00

Abstract: Embodiments of the disclosure are directed to a system for analysis of respiratory distress in hospitalized patients. The system performs multi-parametric simultaneous analysis of respiration rate (RR) and pulse oximetry (SpO2) data trends in order to gauge patterns of patient instability pertaining to respiratory distress. Three patterns in SpO2 and RR are used along with LOWESS algorithm and Chauvenets criteria for outlier rejection to obtain robust short term and long term trends in RR and SpO2. Pattern analysis detects the presence of any one of three pattern types proposed. Further, a learning paradigm is introduced to find unknown instances of respiratory distress. This algorithm in conjunction with the learning model allows early detection of respiratory distress in hospital ward and ICU patients.

公开(公告)号：US20150157275A1

公开(公告)日：2015-06-11

申请号：US14101663

申请日：2013-12-10

Applicant: General Electric Company

Inventor： Gokul Swamy ,  Sahika Genc ,  Hariharan Ravishankar ,  Aditya Saha

IPC: A61B5/00 ,  A61B5/20 ,  A61B5/145 ,  A61B5/0205 ,  A61B5/1455

CPC classification number: A61B5/7275 ,  A61B5/002 ,  A61B5/0022 ,  A61B5/01 ,  A61B5/02055 ,  A61B5/021 ,  A61B5/024 ,  A61B5/0816 ,  A61B5/0836 ,  A61B5/14532 ,  A61B5/14542 ,  A61B5/201 ,  A61B5/202 ,  A61B5/7203 ,  A61B5/7246 ,  A61B5/7264 ,  A61B5/746 ,  G06F19/00

Abstract: Embodiments of the disclosure are directed to a system for analysis of respiratory distress in hospitalized patients. The system performs multi-parametric simultaneous analysis of respiration rate (RR) and pulse oximetry (SpO2) data trends in order to gauge patterns of patient instability pertaining to respiratory distress. Three patterns in SpO2 and RR are used along with LOWESS algorithm and Chauvenets criteria for outlier rejection to obtain robust short term and long term trends in RR and SpO2. Pattern analysis detects the presence of any one of three pattern types proposed. Further, a learning paradigm is introduced to find unknown instances of respiratory distress. This algorithm in conjunction with the learning model allows early detection of respiratory distress in hospital ward and ICU patients.

Abstract translation: 本公开的实施例涉及用于分析住院患者呼吸窘迫的系统。 系统进行呼吸速率（RR）和脉搏血氧饱和度（SpO2）数据趋势的多参数同时分析，以衡量与呼吸窘迫有关的患者不稳定状态。 使用SpO2和RR中的三种模式以及LOWESS算法和Chauvenets等离子体排斥标准，以获得RR和SpO2的强大的短期和长期趋势。 模式分析检测提出的三种模式类型中的任一种的存在。 此外，引入了一种学习范例来发现呼吸窘迫的未知事例。 该算法结合学习模型，可以及早发现医院病房和ICU患者的呼吸窘迫。