TRAINING SIMULATOR FOR DIRECT LARYNGOSCOPY
    4.
    发明申请

    公开(公告)号:WO2023034433A1

    公开(公告)日:2023-03-09

    申请号:PCT/US2022/042233

    申请日:2022-08-31

    IPC分类号: G09B23/32 G09B23/30 G09B9/00

    摘要: Described are examples of a training simulator for direct laryngoscopy, which reproduce the dynamics of the human airway and hyoid bone movement observed in the human anatomy during movement of the somatic skeleton and direct laryngoscopy procedures. Training simulators can include a skeleton structure having a styloid process analogue, a mandible analogue, and a longitudinally extending column configured to move between an extended state and a flexed state. A suspension chain can extend parallel to the column and be configured to move with the column. The suspension chain can include a hyoid analogue coupled to the styloid process analogue, the mandible analogue, and an anchor point situated along the column of the skeleton structure. Training simulators can also include a glottis analogue, the visibility of which can be greater when the column is in a flexed state, than when the column is in an extended state.

    EFFICIENTLY TRAINING AND EVALUATING PATIENT TREATMENT PREDICTION MODELS

    公开(公告)号:WO2022217051A1

    公开(公告)日:2022-10-13

    申请号:PCT/US2022/024021

    申请日:2022-04-08

    IPC分类号: G16H20/00 G06N20/00 G16H50/20

    摘要: Systems and methods are described for training a treatment prediction model using patient profiles. The training can include applying a machine-learning technique that causes the treatment prediction model to learn to predict a likelihood that a given patient will respond to a particular medical treatment according to a one or more criteria. A first subset of predictive features are identified from an expanded set of predictive features that are most predictive of whether a given patient will respond to the particular medical treatment according to the one or more criteria. The treatment prediction model is configured to generate predictions from values for the first subset of predictive features that are most predictive, without requiring values for a second subset of predictive features that are less predictive than features from the first subset. The treatment prediction model can be applied to generate a treatment response prediction for a new patient.