利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

49 条记录 (耗时 0.034 秒)

    PATIENT STATE DETECTION BASED ON SUPPORT VECTOR MACHINE BASED ALGORITHM
    1.
    发明申请
    PATIENT STATE DETECTION BASED ON SUPPORT VECTOR MACHINE BASED ALGORITHM 审中-公开
    基于支持向量机的患者状态检测算法

    公开(公告)号：US20100280574A1

    公开(公告)日：2010-11-04

    申请号：US12694042

    申请日：2010-01-26

    申请人： David L. Carlson ,  Timothy J. Denison ,  Ali H. Shoeb

    发明人： David L. Carlson ,  Timothy J. Denison ,  Ali H. Shoeb

    IPC分类号： A61N1/08

    CPC分类号： A61N1/36082 ,  G06F2221/2101 ,  G06F2221/2105 ,  G06K9/6268 ,  G06N20/00 ,  G16H50/50

    摘要： A patient state is detected with at least one classification boundary generated by a supervised machine learning technique, such as a support vector machine. In some examples, the patient state detection is used to at least one of control the delivery of therapy to a patient, to generate a patient notification, to initiate data recording, or to evaluate a patient condition. In addition, an evaluation metric can be determined based on a feature vector, which is determined based on characteristics of a patient parameter signal, and the classification boundary. Example evaluation metrics can be based on a distance between at least one feature vector and the classification boundary and/or a trajectory of a plurality of feature vectors relative to the classification boundary over time.

    摘要翻译： 用监督机器学习技术（例如支持向量机）生成的至少一个分类边界来检测病人状态。 在一些示例中，患者状态检测用于控制对患者的治疗递送，产生患者通知，开始数据记录或评估患者状况中的至少一个。 此外，可以基于基于患者参数信号的特性确定的特征向量和分类边界来确定评估度量。 示例评估度量可以基于至少一个特征向量与分类边界之间的距离和/或相对于分类边界随时间的多个特征向量的轨迹。

    PATIENT STATE DETECTION BASED ON SUPERVISED MACHINE LEARNING BASED ALGORITHM
    2.
    发明申请
    PATIENT STATE DETECTION BASED ON SUPERVISED MACHINE LEARNING BASED ALGORITHM 审中-公开
    基于监督机器学习算法的患者状态检测

    公开(公告)号：US20100280335A1

    公开(公告)日：2010-11-04

    申请号：US12694044

    申请日：2010-01-26

    申请人： David L. Carlson ,  Timothy J. Denison ,  Ali H. Shoeb ,  David E. Linde

    发明人： David L. Carlson ,  Timothy J. Denison ,  Ali H. Shoeb ,  David E. Linde

    IPC分类号： A61B5/00 ,  A61B5/11

    CPC分类号： A61N1/36082 ,  G06F2221/2101 ,  G06F2221/2105 ,  G06K9/6268 ,  G06N20/00 ,  G16H50/50

    摘要： A patient state is detected with at least one classification boundary generated by a supervised machine learning technique, such as a support vector machine. In some examples, the patient state detection is used to at least one of control the delivery of therapy to a patient, to generate a patient notification, to initiate data recording, or to evaluate a patient condition. In addition, an evaluation metric can be determined based on a feature vector, which is determined based on characteristics of a patient parameter signal, and the classification boundary. Example evaluation metrics can be based on a distance between at least one feature vector and the classification boundary and/or a trajectory of a plurality of feature vectors relative to the classification boundary over time.

    摘要翻译： 用监督机器学习技术（例如支持向量机）生成的至少一个分类边界来检测病人状态。 在一些示例中，患者状态检测用于控制对患者的治疗递送，产生患者通知，开始数据记录或评估患者状况中的至少一个。 此外，可以基于基于患者参数信号的特性确定的特征向量和分类边界来确定评估度量。 示例评估度量可以基于至少一个特征向量与分类边界之间的距离和/或相对于分类边界随时间的多个特征向量的轨迹。

    POSTURE STATE DETECTION
    3.
    发明申请
    POSTURE STATE DETECTION 审中-公开
    姿态检测

    公开(公告)号：US20100280579A1

    公开(公告)日：2010-11-04

    申请号：US12694053

    申请日：2010-01-26

    申请人： Timothy J. Denison ,  David L. Carlson ,  Ali H. Shoeb ,  David E. Linde

    发明人： Timothy J. Denison ,  David L. Carlson ,  Ali H. Shoeb ,  David E. Linde

    IPC分类号： A61N1/36

    CPC分类号： A61N1/36082 ,  G06F2221/2101 ,  G06F2221/2105 ,  G06K9/6268 ,  G06N20/00 ,  G16H50/50

    摘要： A patient state is detected with at least one classification boundary generated by a supervised machine learning technique, such as a support vector machine. The patient state can be, for example, a patient posture state. In some examples, the patient state detection is used to at least one of control the delivery of therapy to a patient, to generate a patient notification, to initiate data recording, or to evaluate a patient condition. In addition, an evaluation metric can be determined based on a feature vector, which is determined based on characteristics of a patient parameter signal, and the classification boundary. Example evaluation metrics can be based on a distance between at least one feature vector and the classification boundary and/or a trajectory of a plurality of feature vectors relative to the classification boundary over time.

    摘要翻译： 用监督机器学习技术（例如支持向量机）生成的至少一个分类边界来检测病人状态。 患者状态可以是例如患者姿势状态。 在一些示例中，患者状态检测用于控制对患者的治疗递送，产生患者通知，开始数据记录或评估患者状况中的至少一个。 此外，可以基于基于患者参数信号的特性确定的特征向量和分类边界来确定评估度量。 示例评估度量可以基于至少一个特征向量与分类边界之间的距离和/或相对于分类边界随时间的多个特征向量的轨迹。