METHOD AND SYSTEM FOR MONITORING A SUBJECT

Abstract

A method for monitoring a subject, includes: capturing high-bandwidth data pertaining to the subject; cyclically storing a recent portion of the high-bandwidth data in a first memory; monitoring one or more physiological signals of the subject; analyzing the monitored physiological signals to allow detection of one or more target events; upon detection of a target event: copying a then recent portion of the high-bandwidth data from the first memory to a second memory; and storing high-bandwidth captured in a predetermined period subsequent to the detection in the second memory. The one or more physiological signals include EEG. The one or more target events include epileptic seizures. A computer program product and a system may use the method.

Claims

1.-15. (canceled)

16. A method for monitoring a subject, the method comprising: capturing high-bandwidth data pertaining to said subject; cyclically storing a recent portion of said high-bandwidth data in a first memory; monitoring one or more physiological signals of said subject; analyzing said monitored physiological signals to allow detection of one or more target events; upon detection of a target event: copying a then recent portion of said high-bandwidth data from said first memory to a second memory; and storing high-bandwidth captured in a predetermined period subsequent to said detection in said second memory, wherein said one or more physiological signals include EEG; and wherein said one or more target events include epileptic seizures.

17. The method according to claim 16, wherein said high-bandwidth data comprises video images of said subject.

18. The method according to claim 16, wherein said high-bandwidth data comprises high-resolution EEG signals.

19. The method according to claim 16, wherein said storing of said high-bandwidth data captured in said predetermined period subsequent to said detection comprises copying a further portion of said high-bandwidth data from said first memory to said second memory.

20. The method according to claim 16, wherein said first memory is comprised in a mobile device and said capturing of said high-bandwidth data is performed using a sensor associated with said mobile device.

21. The method according to claim 16, wherein said second memory is comprised in said mobile device.

22. The method according to claim 21, wherein said second memory is comprised in an apparatus separate from said mobile device, said mobile device being configured to transmit data to said apparatus via a data communication network.

23. The method according to claim 20, wherein said high-bandwidth data comprises video images and said sensor associated with said mobile device is a camera integrated in said mobile device.

24. The method according to claim 16, wherein said one or more physiological signals further include one or more of the groups of ECG, body temperature, movement, skin conductivity, heart rate, oxygen saturation.

25. The method according to claim 16, wherein said analyzing comprises applying a deep-learning algorithm.

26. A computer program product comprising code means configured to cause a processor, when executed, to perform the steps of the method according to claim 16.

27. A system for monitoring a subject, the system comprising: a first sensor arranged for capturing high-bandwidth data pertaining to said subject; a first memory adapted to cyclically store a recent portion of said captured high-bandwidth data; a second memory adapted for long-term storage of high-bandwidth data; second sensors adapted to monitor one or more physiological signals of said subject; and processing means configured to: analyze said monitored physiological signals to allow detection of one or more target events; and upon detection of a target event: copy a then recent portion of said high-bandwidth data from said first memory to said second memory; and store high-bandwidth data captured in a predetermined period subsequent to said detection in said second memory, wherein said one or more physiological signals include EEG; and wherein said one or more target events include epileptic seizures.

28. The system according to claim 27, wherein said high-bandwidth data comprises video images and wherein said first sensor arranged for capturing high-bandwidth data pertaining to said subject comprises a camera arranged for capturing video images of said subject.

29. The system according to claim 28, wherein at least said camera, said first memory, and said processing means are comprised in a mobile device.

30. The system according to claim 27, wherein said high-bandwidth data comprises high-resolution EEG signals.

Description

BRIEF DESCRIPTION OF THE FIGURES

[0042] These and other features and advantages of embodiments of the present invention will now be described with reference to the accompanying drawings, in which:

[0043] FIG. 1 provides a flow chart of an embodiment of the method according to the present invention;

[0044] FIG. 2 schematically illustrates an embodiment of the system according to the present invention;

[0045] FIG. 3 is a schematic timing diagram further illustrating the operation of the present invention.

DESCRIPTION OF EMBODIMENTS

[0046] FIG. 1 provides a flow chart of an embodiment of the method according to the present invention.

[0047] Throughout the application of the method according to the present invention, high-bandwidth data pertaining to the subject are captured. Without loss of generality, the figures and the present description will use the example of capturing video images of the subject 1010 for illustration purposes.

[0048] A recent portion of these video images is cyclically stored 1020 in a first memory, such as a circular buffer, in such a way that the most recent bit of video data is present in the first memory at any given time. The capturing 1010 and cyclic storage 1020 are preferably performed by a mobile device, such as a PDA, smart phone, or tablet. The mobile device may be installed in a cradle that ensures a continuous power supply and/or network connectivity.

[0049] The recent portion of the video images that is stored 1020 in the first memory preferably spans at least 10 seconds, more preferably at least 30 seconds, and most preferably at least 60 seconds.

[0050] In parallel, one or more physiological signals of the subject are being monitored 1030. Without limitation, these physiological signals may include EEG, ECG, body temperature, movement, skin conductivity, heart rate, and oxygen saturation.

[0051] The physiological signals are provided by sensor devices, which are preferably non-invasive, or minimally invasive. For example, absence seizures are advantageously detected by analyzing EEG signals, which may be captured by a non-invasive headset worn by the subject, which may be shaped, without limitation, as a hat, cap, head-strap, visor, or the like. Heart rate, oxygen saturation, and body temperature can be sensed by means of optical sensors, which may be placed in contact with the subject's body in the form of wristbands, finger pinching apparatus, chest straps, and the like. The sensor devices may relay their signals to the above mentioned mobile device via a wireless personal area network interface (e.g. Bluetooth or Bluetooth LE) or a wireless local area network interface (e.g. IEEE Std 802.11 “Wi-Fi”).

[0052] The physiological signals are analyzed 1040 to allow detection of one or more target events, for example by applying a deep-learning algorithm. The analyzing 1040 may take place on a continuous basis, in parallel with the monitoring 1030, or intermittently, but must be in either case happen within a sufficient short delay of the capturing of the signals to ensure that the pre-event video data of interest is still present in the first memory when the occurrence of a target event is established. The analyzing 1040 may take place locally, on the same device that collects the signals, or by a remote apparatus, connected to the former device by a network (“in the cloud”).

[0053] When a target event is detected, the pre-event data of interest and the data pertaining to the actual event are transferred 1050 to a more permanent storage, referred to as the second memory, by copying 1051 a then recent portion of the video images from the first memory to the second memory; and storing 1052 video images captured in a predetermined period subsequent to the detection in the second memory. This transfer may happen in a single copying operation, at or shortly after the end of the event, when both the pre-event data of interest and the data pertaining to the actual event are present in the first memory.

[0054] Optionally, the equipment may be configured so as to allow a manual triggering of the transfer 1050 to the second memory, independently of the detection of a target event.

[0055] Preferably, an audio signal is captured in conjunction with the video images, and the resulting audio data is stored along with the stored video data. Preferably, the monitored physiological signals are also stored along with the stored video data. Throughout this application, any references to storage of “video data” may be read as optionally including the corresponding audio data and the corresponding physiological signal data.

[0056] Where a mobile device is used for video capturing 1010 and initial storage 1020, the second memory may also be comprised in the mobile device. The mobile device may be equipped with a separate memory component (e.g. a flash memory) for this purpose, or it may use a different segment of the same memory component that provides the first memory.

[0057] Alternatively or additionally, the second memory may be comprised in an apparatus separate from said mobile device, the mobile device being configured to transmit data to the apparatus via a data communication network.

[0058] In an alternative setup, the device that captures the video and that receives the physiological signals continuously transmits that data to an external apparatus (e.g., a server to which the former device is connected via a data communication network such as the internet), and the external apparatus performs the cyclic storage 1020, the analysis 1040, and the selective transfer 1050 to permanent storage. Other functional divisions of the steps of the method according to the present invention between different devices are possible without deviating from the scope of the invention.

[0059] In a further variant of the invention, a low-quality video stream is stored in its entirety, and the selective event-centric storage described above is applied to a high-quality video stream.

[0060] The present invention also pertains to a computer program product comprising code means configured to cause a processor in a system with appropriate network interfaces, when executed, to perform the steps of the method described above. The computer program product may comprise computer code stored on a computer-readable medium such as, but not limited to, a magnetic carrier, an optical carrier, or semiconductor memory.

[0061] FIG. 2 schematically illustrates an embodiment of the system according to the present invention.

[0062] The system 2000 comprises a camera 2010 arranged for capturing video images of the subject; a first memory 2020 adapted to cyclically store a recent portion of the captured video images; and sensors 2030 adapted to monitor one or more physiological signals of the subject.

[0063] The system 2000 further comprises a second memory 2050 adapted for long-term storage of video images.

[0064] The system 2000 comprises a processing means 2040 configured to: [0065] analyze said monitored physiological signals to allow detection of one or more target events; and [0066] upon detection of a target event: [0067] copy a then recent portion of said video images from said first memory 2020 to said second memory 2050; and [0068] store video images captured in a predetermined period subsequent to said detection in said second memory 2050.

[0069] The processing means may be implemented in dedicated hardware (e.g., ASIC), configurable hardware (e.g., FPGA), programmable components (e.g., a DSP or general purpose processor with appropriate software), or any combination thereof. The same component may also include other functions.

[0070] As explained above with reference to FIG. 1, at least the camera 2010, the first memory 2020, and the processing means 2040 may be comprised in a mobile device.

[0071] Optional features described hereinabove with reference to embodiments of the method according to the present invention may be applied with the same technical effects and advantages to embodiments of the computer program product or the system of the present invention.

[0072] FIG. 3 illustrates certain aspects of embodiments of the present invention by means of a schematic timing diagram. The four illustrated time axes, labeled A, B, C, and D, share a common time origin (illustrated by the vertical line joining the axes).

[0073] Axis A, which represents the monitored physiological parameters, illustrates the occurrence in time of a target event, between periods of normal readings.

[0074] Axis B, which illustrates the analysis of the monitored parameters, shows that the detection of the occurrence of the target event takes place shortly after the onset of the target event, and likewise, the detection of the end of the target event takes place shortly after the actual ending of the target event.

[0075] Axis C illustrates the content of the first memory (cyclic memory or short-term memory), and indicates the amount of “history”, in terms of high-bandwidth data (in particular video data), available in the first memory at the time of detection of the target event (double arrow).

[0076] Axis D represents the second memory (long-term memory). In the illustrated case, a recent portion of the high-bandwidth data is transferred 1051 to the second memory, whereby “recent” is defined relative to the detected start time of the target event. In addition, a certain amount of high-bandwidth data captured after the event detection is copied to the second memory 1052 (or recorded directly thereto). In this scenario, the amount of time spanned by the post-detection data to be transferred 1052 must take into account the duration of the target event; it may in particular be useful to include some data pertaining to a certain amount of time after the end of the target event in the transfer 1052 to the second memory. As can be seen from this diagram, the dimensioning of the first memory must take into account the time offset between actual start of a target event and the detection of the target event.

[0077] While the invention has been described hereinabove with reference to specific embodiments, this was done to clarify and not to limit the invention, the scope of which is to be determined by reference to the accompanying claims.