# US 2024/0422295 A1 · Client-side Patient Room Real-Time Monitoring and Alerting System

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0422295 A1
- Document ID: US20240422295A1
- Status: Published application
- Kind: A1
- Application number: 18/818,033
- Filed: 2024-08-28
- Published: 2024-12-19
- Earliest claimed: 2020-12-03
- Assignees: Vitalchat, Inc.
- Applicants: Vitalchat, Inc.
- Inventors: Ghafran Abbas
- Web page: https://patentgrep.com/patent/US20240422295A1

## CPC

- A61B 5/002: {Monitoring the patient using a local or closed circuit, e.g. in a room or building (A61B5/0017 takes precedence)}
- H04N 7/183: {for receiving images from a single remote source}
- A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet}
- A61B 5/1115: {Monitoring leaving of a patient support, e.g. a bed or a wheelchair}
- A61B 5/1128: {using image analysis (A61B5/1127 takes precedence)}
- A61B 5/7267: {involving training the classification device}
- A61B 5/746: {Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms}
- A61B 5/747: {in case of emergency, i.e. alerting emergency services}
- G06F 18/2431: Multiple classes
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06V 40/23: {Recognition of whole body movements, e.g. for sport training}
- G08B 5/22: using electric transmission; using electromagnetic transmission
- G08B 21/0476: {Cameras to detect unsafe condition, e.g. video cameras}
- G16H 30/40: for processing medical images, e.g. editing
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 80/00: ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
- A61G 12/005: {mounted on the wall}
- A61G 2203/30: characterised by sensor means
- A61G 2203/36: for motion
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61G: TRANSPORT, PERSONAL CONVEYANCES OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS (appliances for aiding patients or disabled persons to walk A61H3/00); OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES (embalming corpses A01N1/00)

## 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.

## Claims

### Claim 1

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; and
presenting, at the user device, a notification based on the active state.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
storing, at the user device, the first state and a corresponding timestamp.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
transmitting a request to the monitoring device to modify a quality or a compression rate of the video stream based on the active state.

### Claim 4 (depends on 1)

The method of claim 1, wherein the machine learning model is a multi-label image classification model configured to detect multiple states simultaneously.

### Claim 5 (depends on 1)

The method of claim 1, wherein the notification includes a description of the active state.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
transmitting another notification directly to a device associated with a healthcare provider.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
displaying a real-time view of the patient room based on the video stream when the active state is detected.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
displaying individual images of the video stream while no active state is detected.

### Claim 9 (depends on 8)

The method of claim 8, wherein the individual images constitute key frames.

### Claim 10

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; and
present a notification based on the active state.

### Claim 11 (depends on 10)

The system of claim 10, wherein the user device is further configured to:
transmit a request to the monitoring device to modify a quality or a compression rate of the video stream based on the active state.

### Claim 12 (depends on 10)

The system of claim 10, wherein the machine learning model is a multi-label image classification model configured to detect multiple states simultaneously.

### Claim 13 (depends on 10)

The system of claim 10, wherein the notification includes a description of the active state.

### Claim 14 (depends on 10)

The system of claim 10, wherein the user device is further configured to:
display a real-time view of the patient room based on the video stream when the active state is detected.

### Claim 15 (depends on 10)

The system of claim 10, wherein the user device is further configured to:
display individual images of the video stream while no active state is detected.

### Claim 16 (depends on 15)

The system of claim 15, wherein the individual images constitute key frames of the video stream.

### Claim 17

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; and
presenting, at the user device, a notification based on the active state.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, the operations further comprising:
storing, at the user device, the first state and a corresponding timestamp.

### Claim 19 (depends on 17)

The non-transitory computer-readable medium of claim 17, further comprising:
transmitting a request to the monitoring device to modify a quality or a compression rate of the video stream based on the active state.

### Claim 20 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the machine learning model is a multi-label image classification model configured to detect multiple states simultaneously.
