SYSTEM FOR ESTIMATING A POSE OF A SUBJECT

    公开(公告)号:US20230096850A1

    公开(公告)日:2023-03-30

    申请号:US17957245

    申请日:2022-09-30

    Abstract: A method and a system of estimating a pose of a subject is disclosed. The method includes receiving a video stream from an imaging device in real-time; applying a trained computational model to extract feature maps from images received from the video stream; determining initial estimates of heatmaps and part affinity fields (pafs) from the extracted feature maps; refining the initial estimates of the heatmaps and pafs to output refined heatmaps and pafs; refining the heatmaps and pafs upon completing the refining of the initial estimates using a self-attention module; detecting keypoints on the heatmaps; and performing graph matching on the pafs to group the keypoints to different subjects.

    Prediction of ventilator-associated pneumonia (VAP)

    公开(公告)号:US12249427B2

    公开(公告)日:2025-03-11

    申请号:US17879240

    申请日:2022-08-02

    Abstract: Described herein are methods, devices and systems for predicting ventilator associated pneumonia (VAP). In an example, data of a patient including one or more features useful in predicting VAPs are accessed and the features are extracted. A model is activated based on a time parameter associated with mechanical ventilation or length of stay in ICU. The extracted features are evaluated automatically by the activated model to determine a probability that a VAP will occur. If it is determined, based on the evaluating, that a VAP has a probability of occurring that exceeds a threshold, an indication that the VAP is predicted to occur may be provided. Other examples are disclosed and claimed.

    PREDICTION OF VENTILATOR-ASSOCIATED PNEUMONIA (VAP)

    公开(公告)号:US20230110196A1

    公开(公告)日:2023-04-13

    申请号:US17879240

    申请日:2022-08-02

    Abstract: Described herein are methods, devices and systems for predicting ventilator associated pneumonia (VAP). In an example, data of a patient including one or more features useful in predicting VAPs are accessed and the features are extracted. A model is activated based on a time parameter associated with mechanical ventilation or length of stay in ICU. The extracted features are evaluated automatically by the activated model to determine a probability that a VAP will occur. If it is determined, based on the evaluating, that a VAP has a probability of occurring that exceeds a threshold, an indication that the VAP is predicted to occur may be provided. Other examples are disclosed and claimed.

Patent Agency Ranking