Graph-based analysis for bio-signal event sensing

• US 10,282,875 B2
• Filed: 12/11/2015
• Issued: 05/07/2019
• Est. Priority Date: 12/11/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chen, Chia-Yu, Hsueh, Pei-Yun S., Lai, Jui-Hsin, Xia, Yinglong
• Primary Examiner(s): Tryder, Gregory J
• Assistant Examiner(s): Le, Michael
• Application Number:
  US14/966,693
• Publication Number:
  US 20170169591A1
• Time in Patent Office: 1,243 Days
• CPC Class Codes: A61B 2503/12 Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
• CPC Class Codes: A61B 2505/07 Home care
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs

Abstract

One or more biological signals are obtained. The one or more biological signals are converted to one or more graph structures. Correlation between two or more of the biological signals are determined using the one or more graph structures. One or more changes in the one or more graph structures within a time window are recorded. A signal graph model is generated based on the recorded changes.

Claims

1. A method, comprising the steps of:

obtaining one or more biological signals from one or more sensors attached to one or more subjects, wherein the one or more biological signals are associated with one or more signal channels;

converting the one or more biological signals into one or more graph structures, wherein each graph structure comprises one or more nodes representing respective ones of the one or more signal channels at a time index;

determining one or more correlations associated with the one or more signal channels using at least one of the one or more graph structures, wherein the one or more correlations comprise a correlation type selected from the group consisting of a temporal concurrent correlation, a temporal sequential correlation, and a spatial correlation;

recording one or more changes in the one or more correlations within at least one time window, wherein the at least one time window is defined based on at least one of the one or more time indices;

generating a signal graph model based on the one or more recorded changes;

determining one or more correlation confidence levels for the one or more correlations; and

one of;

storing one or more of the one or more biological signals associated with a correlation confidence level exceeding a specified correlation confidence threshold; and

discarding one or more of the one or more biological signals associated with a correlation confidence level below a specified correlation confidence threshold; and

wherein the steps are performed by at least one processor device coupled to a memory.

2. The method of claim 1, further comprising comparing the one or more recorded changes to one or more patterns stored in a database.

3. The method of claim 2, further comprising generating at least one of a message and an alert in response to a match between the one or more recorded changes and a pattern for a medical condition stored in the database.

4. The method of claim 3, further comprising transmitting the at least one of the message and the alert to one or more devices.

5. The method of claim 1, wherein the one or more biological signals are obtained in real-time or near real-time from the one or more sensors.

6. The method of claim 5, wherein the one or more sensors are comprised within one or more wearable devices.

7. The method of claim 5, wherein the one or more biological signals are converted into the one or more graph structures in real-time or near real-time.

8. The method of claim 1, wherein determining the one or more correlations comprises determining one or more appearance correlations between two or more signal channels at a given time index.

9. The method of claim 1, wherein determining the one or more correlations comprises determining one or more temporal correlations, and wherein determining the one or more temporal correlations comprises determining a temporal correlation between a given signal channel at a first time index and the given signal channel at a second time index.

10. The method of claim 1, wherein the signal graph model comprises one or more dependency graphs.

11. The method of claim 1 further comprising displaying the signal graph model on one or more devices.

12. The method of claim 1, wherein the one or more graph structures are more compressed than the one or more biological signals.

13. An apparatus comprising:

a memory and a processor operatively coupled to the memory and configured to implement the steps of;

obtaining one or more biological signals from one or more sensors attached to one or more subjects, wherein the one or more biological signals are associated with one or more signal channels;

converting the one or more biological signals into one or more graph structures, wherein each graph structure comprises one or more nodes representing respective ones of the one or more signal channels at a time index;

determining one or more correlations associated with the one or more signal channels using at least one of the one or more graph structures, wherein the one or more correlations comprise a correlation type selected from the group consisting of a temporal concurrent correlation, a temporal sequential correlation, and a spatial correlation;

recording one or more changes in the one or more correlations within at least one time window, wherein the at least one time window is defined based on at least one of the one or more time indices;

generating a signal graph model based on the one or more recorded changes;

determining one or more correlation confidence levels for the one or more correlations; and

one of;

storing one or more of the one or more biological signals associated with a correlation confidence level exceeding a specified correlation confidence threshold; and

discarding one or more of the one or more biological signals associated with a correlation confidence level below a specified correlation confidence threshold.

14. The apparatus of claim 13, wherein the processor is further configured to implement the steps of:

comparing the one or more recorded changes to one or more patterns stored in a database;

generating at least one of a message and an alert in response to match between the one or more recorded changes and a pattern for a medical condition stored in the database; and

transmitting the at least one of the message and the alert to one or more devices.

15. The apparatus of claim 13, wherein the one or more biological signals are obtained in real-time or near real-time from the one or more sensors.

16. The apparatus of claim 15, wherein the one or more sensors are comprised within one or more wearable devices.

17. A computer program product comprising a non-transitory computer readable storage medium for storing computer readable program code which, when executed, causes a computer to:

obtain one or more biological signals from one or more sensors attached to one or more subjects, wherein the one or more biological signals are associated with one or more signal channels;

convert the one or more biological signals to one or more graph structures, wherein each graph structure comprises one or more nodes representing respective ones of the one or more signal channels at a time index;

determine one or more correlations associated with the one or more signal channels using at least one of the one or more graph structures, wherein the one or more correlations comprise a correlation type selected from the group consisting of a temporal concurrent correlation, a temporal sequential correlation, and a spatial correlation;

record one or more changes in the one or more correlations within at least one time window, wherein the at least one time window is defined based on at least one of the one or more time indices;

generate a signal graph model based on the one or more recorded changes;

determine one or more correlation confidence levels for the one or more correlations; and

one of;

storing one or more of the one or more biological signals associated with a correlation confidence level exceeding a specified correlation confidence threshold; and

discarding one or more of the one or more biological signals associated with a correlation confidence level below a specified correlation confidence threshold.