SYSTEM AND METHOD FOR PROCESSING SIGNALS FOR THE REAL-TIME DETECTION OF A FUNCTIONAL CYCLIC ACTIVITY

• US 20120095742A1
• Filed: 04/06/2010
• Published: 04/19/2012
• Est. Priority Date: 04/07/2009
• Status: Active Grant

• Current Assignee: Assistance Publique - Hopitaux De Paris, Université Grenoble Alpes
• Original Assignee: Assistance Publique - Hopitaux De Paris
• Inventors: Heyer, Laurent, Gumery, Pierre-Yves
• Granted Patent: US 8,897,867 B2
• Time in Patent Office: Days
• US Class Current: 703/11
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• CPC Class Codes: A61B 5/4818 Sleep apnoea

Abstract

A system and method for processing signals for the real-time detection of a functional cyclic activity, include: elements for simultaneously receiving signals acquired by a sensor array having at least two sensors; elements for recording and preprocessing the acquired signals during a plurality of consecutive cycles; elements for identifying event combinations from the recordings of the acquired signals, enabling a calibration to be carried out, including: elements for identifying a plurality of events in the acquired signals, each signal including an identified event; elements for defining a model of the functional activity, consisting of a time order of the events and the mean delays between the events, and elements for defining a detection time window from the functional activity model.

Claims

1. A system for processing signals for the real-time detection of a cyclic functional activity, the processing system being characterized in that it comprises:

means for simultaneously receiving signals acquired by a sensor array including at least two sensors;

means for recording and preprocessing the acquired signals during a plurality of consecutive processing cycles;

means for identifying event combinations from the recordings of the acquired signals, enabling a calibration to be carried out, including;

means for identifying a plurality of events in the acquired signals, each acquired signal of an acquisition means including an identified event,

means for defining a model of the functional activity, the model being a timing chart consisting of a time order of the plurality of identified events and the mean delays between the identified events,

means for defining a detection time window from the model of the functional activity.

2. The processing system according to claim 1, characterized in that the plurality of consecutive processing cycles includes ten to twenty cycles.

3. The processing system according to claim 1, characterized in that it also comprises means for validating the sensor array, including:

means for calculating match scores for each pair of acquired signals, and

means for comparing each calculated match score of each pair of acquired signals to a threshold value.

4. The processing system according to claim 1, characterized in that it also comprises means for monitoring the functional activity for a last full cycle, including:

means for calculating a sliding mean of the delays between the signals acquired during a plurality of consecutive monitoring cycles, the plurality of consecutive monitoring cycles comprising the last full cycle; and

means for displaying (10) the sliding mean of the delays.

5. The processing system according to claim 4, characterized in that the plurality of consecutive monitoring cycles is smaller than the plurality of consecutive processing cycles.

6. The processing system according to claim 4, characterized in that the monitoring means also comprise:

means for comparing the sliding mean of the delays to the mean of the delays calculated during the calibration step in order to detect an anomaly; and

means for generating and transmitting an alert signal in case of anomaly.

7. The processing system according to claim 1, characterized in that it comprises signal acquisition means incorporating the sensor array

8. The processing system according to claim 7, characterized in that the signal acquisition means are cardiac muscular signal acquisition means.

9. The processing system according to claim 7, characterized in that the signal acquisition means are cardiac skeletal signal acquisition means.

10. The processing system according to claim 7, characterized in that the signal acquisition means are respiratory muscular signal acquisition means.

11. The processing system according to claim 7, characterized in that the signal acquisition means are noninvasive acquisition means.

12. The processing system according to claim 10, characterized in that it also includes complementary processing means including:

means for receiving a signal of ventilatory activity of a patient comprising a ventilatory event;

means for the real-time detection of a ventilatory demand, the ventilatory demand being defined by an ordered succession of the ventilatory event and respiratory events identified using the respiratory activity model and detected in the acquired muscular signals, and

means for generating and transmitting a control signal to a respiratory aid device (44) connected to a patient.

13. The processing system according to claim 10, characterized in that it also includes complementary processing means including means for acquiring information relative to the status of the respiratory aid device and means for comparing that information relative to the respiratory aid device and the detection of the patient'"'"'s respiratory activity.

14. A method for processing signals for the real-time detection of a cyclic functional activity, intended to be used by a processing system according to claim 1, the processing method comprising the following steps:

simultaneously receiving (14) signals acquired by a sensor array including at least two sensors, and recording the signals acquired during a plurality of consecutive processing cycles;

calibrating (24), from recordings of the acquired signals, the calibration comprising the following steps;

identifying a plurality of events in the acquired signals, each acquired signal of an acquisition means including an identified event,

defining (26) a model of the functional activity, the model being a time order of the plurality of identified events and the mean delays between the identified events,

defining (28) a detection time window from the model of the functional activity.

15. The processing method according to claim 14, characterized in that it comprises, after the calibration step (24), a step for monitoring (30) the functional activity for a last full cycle, including the following steps:

a step for calculating (32) a sliding mean of the delays between the signals acquired during a plurality of consecutive monitoring cycles, the plurality of consecutive monitoring cycles comprising the last full cycle; and

a step for displaying (34) the sliding mean of the delays.

16. The processing method according to claim 14, characterized in that the acquired signals are respiratory muscular signals and in that the functional activity model is a respiratory activity model.

17. The processing method according to claim 16, characterized in that it comprises, after the calibration step (24), the following steps:

a step for receiving (50) a signal of ventilatory activity of a patient comprising a ventilatory event;

a step for real-time detection (52) of a ventilatory demand, the ventilatory demand being defined by an ordered succession of the ventilatory event and respiratory events identified using the respiratory activity model and detected in the acquired muscular signals, then

a step (54) for generating and transmitting a control signal to a respiratory aid device (44) connected to a patient.

18. The processing system according to claim 2, characterized in that it also comprises means for validating the sensor array, including:

means for calculating match scores for each pair of acquired signals, and

means for comparing each calculated match score of each pair of acquired signals to a threshold value.

19. The processing system according to claim 5, characterized in that the monitoring means also comprise:

means for comparing the sliding mean of the delays to the mean of the delays calculated during the calibration step in order to detect an anomaly; and

means for generating and transmitting an alert signal in case of anomaly.

20. The processing method according to claim 15, characterized in that the acquired signals are respiratory muscular signals and in that the functional activity model is a respiratory activity model.