Client-side patient room real-time monitoring and alerting system
AssigneeVitalchat, Inc.
InventorGhafran Abbas
Life of this patent
Estimating the term…
Abstract
A video stream is received from a monitoring device located in a patient room. Images from the video stream are analyzed using a machine learning model to detect a first state associated with the patient room. A second is detected state from subsequent images of the video stream using the machine learning model. The first state and the second state are compared to identify a change indicating an active state. A notification is presented at the user device based on the active state.
Claims20
A method implemented by a user device, comprising:
- receiving a video stream from a monitoring device located in a patient room;
- analyzing images from the video stream using a machine learning model to detect a first state associated with the patient room;
- detecting a second state from subsequent images of the video stream using the machine learning model;
- comparing the first state and the second state to identify a change indicating an active state;
- presenting, at the user device, a notification based on the active state;
- and
- displaying individual images of the video stream while no active state is detected.
A system for monitoring patient environments, comprising:
- a monitoring device configured to:
- obtain a video stream of at least a part of a patient room;
- and
- transmit the video stream to a user device;
- and
- the user device configured to:
- receive the video stream from the monitoring device;
- analyze images from the video stream using a machine learning model to detect a first state associated with the patient room;
- detect a second state from subsequent images of the video stream using the machine learning model;
- compare the first state and the second state to identify a change indicating an active state;
- present a notification based on the active state;
- and
- display individual images of the video stream while no active state is detected.
A non-transitory computer-readable medium having stored thereon instructions that, when executed by one or more processors of a user device, cause the one or more processors to perform operations comprising:
- receiving a video stream from a monitoring device located in a patient room;
- analyzing images from the video stream using a machine learning model to detect a first state associated with the patient room;
- detecting a second state from subsequent images of the video stream using the machine learning model;
- comparing the first state and the second state to identify a change indicating an active state;
- presenting, at the user device, a notification based on the active state;
- and
- displaying individual images of the video stream while no active state is detected.
Dependencies are inferred from the claim text.