PROTECTING DATA EXCHANGED BETWEEN A SERVICE USER AND A SERVICE PROVIDER

    公开(公告)号:EP3273380B1

    公开(公告)日:2018-12-12

    申请号:EP16180367.1

    申请日:2016-07-20

    发明人: Popescu, Stefan

    IPC分类号: G06F21/62 H04L29/06 G06F19/00

    摘要: The invention discloses a method of protecting data (TD, WD, RD) exchanged between a service user (10) and a service provider (11), which method comprises the steps of encoding data (TD, WD) by converting meaningful content (C) of the data (TD, WD) into meaningless content (X) to obtain encoded upload data (TD', WD') for sending to the service provider (SP); processing the encoded upload data (TD', WD') at the service provider (SP) to obtain encoded download data (RD') for sending to the service user (SU); and decoding the encoded download data (RD') by converting meaningless content (X) of the encoded download data (RD') into meaningful content (C) of download data (RD).

    MULTI-DISCIPLINARY DECISION SUPPORT
    4.
    发明公开

    公开(公告)号:EP3407227A1

    公开(公告)日:2018-11-28

    申请号:EP17172689.6

    申请日:2017-05-24

    IPC分类号: G06F19/00

    CPC分类号: G16H50/20 G16H50/30

    摘要: The invention relates to clinical decision support tool for supporting a decision based on a plurality of medical findings. The decision to be taken is by a multi-disciplinary team. The medical findings are based on different data sources and integrated to determine a complexity score, based on a consensus and/or conclusiveness of the medical findings. The medical findings and the complexity of the decision are displayed. A circular icon is used to display this information in an intuitive and simple manner. Multiple icons can be combined to arrive at a complexity score of a TNM staging decision.

    CELL ABNORMALITY DIAGNOSING SYSTEM USING DNN LEARNING, AND DIAGNOSIS MANAGING METHOD OF SAME

    公开(公告)号:EP3384856A1

    公开(公告)日:2018-10-10

    申请号:EP16870910.3

    申请日:2016-10-11

    申请人: Im, Wook-Bin

    发明人: Im, Wook-Bin

    IPC分类号: A61B10/02 G06N3/08 G06F19/00

    摘要: The present invention is a technology relating to cell abnormality diagnosis system using DNN learning, which comprises a cell diagnosis device being installed in a each hospital and determining normal cells or dangerous cells on the basis of neural network as to inspection-subject cell photos; and a neural network learning server being connected to the Internet and performing DNN learning on the neural network of the cell diagnosis device. In particular, the present invention relates to a technology in which inspection-subject cell photos and diagnostic result data are acquired in each hospital and then uploaded to the neural network learning server, and then on the basis of this information the learning server performs DNN learning on a neural network model which is installed in the cell diagnosis device of the hospital so as to generate an upgrade neural network model as well as to download the same to the cell diagnosis device, so that cell diagnosis device becomes to form a neural network model which is optimized to the diagnosis environment of the hospital.

    SYSTEM AND METHOD FOR FACILITATING HEALTH MONITORING BASED ON A PERSONALIZED PREDICTION MODEL

    公开(公告)号:EP3377997A1

    公开(公告)日:2018-09-26

    申请号:EP16804905.4

    申请日:2016-11-07

    IPC分类号: G06F19/00

    摘要: In certain implementations, health monitoring of an individual may be provided based on an individual-specific prediction model. In some implementations, a prediction model for health monitoring may be obtained. Health information associated with an individual may be obtained. The health information may indicate a co-occurrence of health conditions of the individual. An individual-specific prediction model associated with the individual may be generated based on the prediction model and the co-occurrence indication. Subsequent health information associated with the individual may be obtained. The subsequent health information may indicate one or more of: (i) subsequent measurements of the individual observed after the co-occurrence of the health conditions; or (ii) subsequent health conditions of the individual observed after the co-occurrence of the health conditions. A health status of the individual may be predicted based on the individual-specific prediction model and the subsequent health information.