# US 2021/0343140 A1 · System and method for monitoring an individual

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

- Number: US 2021/0343140 A1
- Document ID: US20210343140A1
- Status: Published application
- Kind: A1
- Application number: 17/378,302
- Filed: 2021-07-16
- Published: 2021-11-04
- Earliest claimed: 2019-09-30
- Assignees: Pink Nectarine Health AB
- Applicants: Pink Nectarine Health AB
- Inventors: Nils SVANGÅRD; Tor CARLSSON
- Web page: https://patentgrep.com/patent/US20210343140A1

## CPC

- G08B 29/185: {Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system}
- A61B 5/1113: {Local tracking of patients, e.g. in a hospital or private home}
- A61B 5/1115: {Monitoring leaving of a patient support, e.g. a bed or a wheelchair}
- A61B 5/1117: {Fall detection}
- G08B 21/0407: {based on behaviour analysis}
- G08B 21/043: {detecting an emergency event, e.g. a fall}
- G08B 21/0446: {worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait}
- G08B 21/0453: {worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing (detecting, measuring or recording for diagnostic purposes A61B5/00)}
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

A system for monitoring an individual within predetermined facilities in order to determine whether there is a need for setting an alert is provided. The system includes: a personal module to be worn by the monitored individual, the personal module including at least one motion sensor; at least one node module, with which the personal module is arranged to communicate; storage; and at least one processing device. The at least one processing device may be arranged to: receive sensor data from the at least one motion sensor in the personal module; determine whether the received sensor data indicates a specific alert state among a plurality of predetermined alert states, the alert states including at least a FALL alert state, to be used if a probable fall has been detected for the monitored individual, and an OUT OF BED alert state, to be used if it has been detected that the monitored individual is probably getting out of bed; determine the distance between the personal module and the at least one node module; determine the location of the personal module within the facilities based at least on the determined distance together with information retrieved from the storage regarding the layout of the facilities within which the monitoring of the individual takes place; and set an alert based at least on whether the received sensor data indicates an alert state and whether the determined location fulfils a predetermined location condition, indicating whether the individual is located in a certain room, such as e.g. the bedroom.

## Claims

### Claim 1

A system for monitoring an individual within predetermined facilities in order to determine whether there is a need for setting an alert, the system comprising:
a personal module to be worn by the monitored individual, the personal module comprising at least one motion sensor;
at least one node module, with which the personal module is arranged to communicate;
a storage means; and
at least one processing device, arranged to:
receive sensor data from the at least one motion sensor in the personal module;
determine whether the received sensor data indicates a specific alert state among a plurality of predetermined alert states, the alert states comprising at least a FALL alert state, to be used if a probable fall has been detected for the monitored individual, and an OUT OF BED alert state, to be used if it has been detected that the monitored individual is probably getting out of bed;
determine the location of the personal module within the facilities based at least on information retrieved from the storage means regarding the layout of the facilities within which the monitoring of the individual takes place;
determine and update an activity state for the monitored individual; and
set an alert based at least on:
whether the received sensor data indicates an alert state;
whether the determined location fulfils a predetermined location condition, indicating whether the individual is located in a certain room; and
whether at least one previously determined activity state for the monitored individual fulfils a predetermined state condition.

### Claim 2 (depends on 1)

The system according to claim 1, wherein the determination of whether the received sensor data indicates an alert state among a plurality of predetermined alert states is done by a trained machine learning algorithm.

### Claim 3 (depends on 1)

The system according to claim 1, wherein the at least one processing device is arranged to determine the location of the personal module based also on a determined distance between the personal module and at least one node module.

### Claim 4 (depends on 1)

The system according to claim 1, wherein the at least one processing device is arranged to determine the location of the personal module based also on an indication of the movement of the individual in relation to a previously determined location, based on sensor data from the at least one motion sensor.

### Claim 5 (depends on 1)

The system according to claim 1, wherein the at least one processing device is arranged to continuously determine and update the activity state for the monitored individual.

### Claim 6 (depends on 1)

The system according to claim 1, wherein the predetermined state condition comprises the following:
an OUT OF BED alert state can only be set if the previous activity state was some type of LYING IN BED activity state; and
a FALL alert state can only be set if the previous activity state was not any type of LYING activity state.

### Claim 7 (depends on 1)

The system according to claim 1, wherein the at least one processing device is arranged to set the alert based also on the time period for which the individual has had a specific activity state.

### Claim 8 (depends on 1)

The system according to claim 1, wherein the determination the activity state is done by a trained machine learning algorithm.

### Claim 9 (depends on 1)

The system according to claim 1, wherein the at least one processing device is further arranged to send an alarm signal if a predetermined alert is set.

### Claim 10 (depends on 1)

The system according to claim 1, wherein the at least one motion sensor is an accelerometer.

### Claim 11 (depends on 1)

The system according to claim 1, wherein the personal module is a wristworn device.

### Claim 12

A method for monitoring an individual within predetermined facilities in order to determine whether there is a need for setting an alert, the method comprising:
receiving sensor data from at least one motion sensor arranged in a personal module;
determining whether the received sensor data indicates a specific alert state among a plurality of predetermined alert states, the alert states comprising at least a FALL alert state, to be used if a probable fall has been detected for the monitored individual, and an OUT OF BED alert state, to be used if it has been detected that the monitored individual is probably getting out of bed;
determining the location of the personal module within the facilities based at least on information retrieved from a storage means regarding the layout of the facilities within which the monitoring of the individual takes place;
determining and updating an activity state for the monitored individual; and
setting an alert based at least on:
whether the received sensor data indicates an alert state;
whether the determined location fulfils a predetermined location condition, indicating whether the individual is located in a certain room; and
whether at least one previously determined activity state for the monitored individual fulfils a predetermined state condition.

### Claim 13 (depends on 12)

The method according to claim 12, wherein the determining of whether the received sensor data indicates a specific alert state among a plurality of predetermined alert states is done by a trained machine learning algorithm.

### Claim 14 (depends on 12)

The method according to claim 12, wherein the determining of the location of the personal module involves determining the distance between the personal module and at least one node module.

### Claim 15 (depends on 12)

The method according to claim 12, wherein the determining of the location of the personal module is based also on an indication of the movement of the individual in relation to a previously determined location, based on sensor data from the at least one motion sensor.

### Claim 16 (depends on 12)

The method according to claim 12, comprising continuously determining and updating the activity state for the monitored individual.

### Claim 17 (depends on 12)

The method according to claim 12, wherein the predetermined state condition comprises the following:
an OUT OF BED alert state can only be set if the previous activity state was some type of LYING IN BED activity state; and
a FALL alert state can only be set if the previous activity state was not any type of LYING activity state.

### Claim 18 (depends on 12)

The method according to claim 12, wherein the setting of the alert is based also on the time period for which the individual has had a specific activity state.

### Claim 19 (depends on 12)

The method according to claim 12, wherein determining of the activity state is done by a trained machine learning algorithm.

### Claim 20 (depends on 12)

The method according to claim 12, further comprising sending an alarm signal if a predetermined alert is set.
