Rapid Learning Community for Predictive Models of Medical Knowledge
    1.
    发明申请
    Rapid Learning Community for Predictive Models of Medical Knowledge 审中-公开
    医学知识预测模型快速学习社区

    公开(公告)号:US20140088989A1

    公开(公告)日:2014-03-27

    申请号:US14027494

    申请日:2013-09-16

    IPC分类号: G06F19/00

    CPC分类号: G16H50/70 G16H50/50

    摘要: A predictive model of medical knowledge is trained from patient data of multiple different medical centers. The predictive model is machine learnt from routine patient data from multiple medical centers. Distributed learning avoids transfer of the patient data from any of the medical centers. Each medical center trains the predictive model from the local patient data. The learned statistics, and not patient data, are transmitted to a central server. The central server reconciles the statistics and proposes new statistics to each of the local medical centers. In an iterative approach, the predictive model is developed without transfer of patient data but with statistics responsive to patient data available from multiple medical centers. To assure comfort with the process, the transmitted statistics may be in a human readable format.

    摘要翻译: 医学知识的预测模型是从多个不同医疗中心的患者数据进行培训。 预测模型是从多个医疗中心的常规患者数据获得的机器。 分布式学习避免了从任何医疗中心转移患者数据。 每个医疗中心从当地患者数据中训练预测模型。 学习的统计信息而不是患者数据被传送到中央服务器。 中央服务器统计统计数据,并向每个当地医疗中心提出新的统计数据。 在迭代方法中,预测模型是在没有转移患者数据的情况下开发的,但是对于可从多个医疗中心获得的患者数据进行统计。 为了确保该过程的舒适度,所发送的统计数据可以是人类可读的格式。

    System for Adaptively Querying a Data Storage Repository
    2.
    发明申请
    System for Adaptively Querying a Data Storage Repository 审中-公开
    用于自适应查询数据存储库的系统

    公开(公告)号:US20080222121A1

    公开(公告)日:2008-09-11

    申请号:US11756886

    申请日:2007-06-01

    IPC分类号: G06F17/30 G06F7/10

    CPC分类号: G06F16/8358 G06F16/258

    摘要: An input processor receives a plurality of different first query messages in a corresponding plurality of different formats. A repository includes stored data elements in a first storage data structure. An intermediary processor automatically: parses the plurality of first query messages to identify requested data elements; maps the identified requested data elements to stored data elements in the first storage data structure of the repository; generates a plurality of second query messages in a format compatible with the repository for acquiring the stored data elements; acquires the stored data elements from the repository using the generated plurality of second query messages; and processes the acquired stored data elements in the plurality of second query messages for output in a format compatible with the corresponding plurality of different formats of the first query messages.

    摘要翻译: 输入处理器以相应的多种不同格式接收多个不同的第一查询消息。 存储库包括存储在第一存储数据结构中的数据元素。 中间处理器自动地:解析多个第一查询消息以识别所请求的数据元素; 将识别的请求的数据元素映射到存储库的第一存储数据结构中的存储的数据元素; 以与所述存储库兼容的格式生成多个第二查询消息,以获取所存储的数据元素; 使用所生成的多个第二查询消息从存储库获取存储的数据元素; 并且处理在多个第二查询消息中获取的存储的数据元素,以便以与第一查询消息的对应的多种不同格式兼容的格式输出。