Determining health change of a user with neuro and neuro-mechanical fingerprints

• US 10,357,210 B2
• Filed: 02/02/2016
• Issued: 07/23/2019
• Est. Priority Date: 02/04/2015
• Status: Active Grant

• Current Assignee: Proprious Technologies
• Original Assignee: Proprius Technologies SARL
• Inventors: Zizi, Martin, Sharkey, Hugh
• Primary Examiner(s): Wu, Eugene T
• Application Number:
  US15/013,764
• Publication Number:
  US 20160220151A1
• Time in Patent Office: 1,267 Days
• CPC Class Codes: A61B 5/1101 Detecting tremor
• CPC Class Codes: A61B 5/117 Identification of persons methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/4064 Evaluating the brain A61B5/031, A61B5/369, A61B5/14553 take precedence
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: A61B 5/4842 Monitoring progression or stage of a disease
• CPC Class Codes: A61B 5/6897 Computer input devices, e.g. mice or keyboards
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: A61B 5/7235 Details of waveform analysis A61B5/349 takes precedence
• CPC Class Codes: A61B 5/7253 characterised by using transforms
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick

Abstract

In accordance with one embodiment, a method for determining changes in health of a user is disclosed. The method includes sensing multi-dimensional motion of a body part of a user to generate a first multi-dimensional motion signal at a first time and date; in response to the first multi-dimensional motion signal, generating a first neuro-mechanical fingerprint; generating a first health measure in response to the first NFP and user calibration parameters; sensing multi-dimensional motion of the body part of the user to generate another multi-dimensional motion signal at another time and date; in response to the another multi-dimensional motion signal, generating another neuro-mechanical fingerprint; generating another health measure in response to the another NFP and the user calibration parameters; and comparing the first health measure with the another health measure to determine a difference representing the health degradation of the user.

Claims

1. A method of monitoring a user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability, the method comprising:

sensing, with a handheld size device with a sensor capable of sensing neuro-muscular micro-motions, a first motion of a body part of a user on a first time period;

based on the sensed first motion, generating a first sensor data with a predetermined sampling frequency over a predetermined sample period by the sensor on the first time period, the first sensor data including a gravitational component and one or more indicators relating to the user'"'"'s status;

generating first micro-motions data by suppressing signal components associated with a voluntary movement of the user from the first sensor data, the first micro-motions data comprising a non-transitory representation of the first sensor data and status information for the user on the first time period;

timestamping the first micro-motions data thereby generating first micro-motions data having a first timestamp associated with the first time period;

extracting a first neuro-mechanical value from the first micro-motions data for the user by processing at least one predetermined measurable feature associated with a neuro-muscular function of a user, wherein the at least one predetermined measurable feature has a mathematical property that distinctly represents the user, and wherein the mathematical property includes only one of;

values of a peak amplitude and a peak quefrency from a CEPSTRUM waveform of the micro-motions data, an orbit information from Poincare plots of the micro-motions data, or a center of gravity of strange attractors and a series of Lyapunov exponent from Chaos analytics of the micro-motions data;

sensing a second motion of the body part of the user on a second time period differing from the first time period;

based on the sensed second motion, generating a second sensor data at the predetermined sampling frequency over the predetermined sampled period with the sensor on the second time period;

generating second micro-motions data by suppressing signal components associated with a voluntary movement of the user from the second sensor data, the second micro-motions data comprising a non-transitory representation of the second sensor data and status information for the user on the second time period;

timestamping the second micro-motions data thereby generating second micro-motions data having a second timestamp associated with the second time period;

extracting a second neuro-mechanical value from the second micro-motions data for the user by processing the at least one predetermined measurable feature associated with the neuro-muscular function of the user;

comparing, with an electronic circuit, the first neuro-mechanical value and the second neuro-mechanical value to monitor the user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability; and

generating a report including a difference between the first neuro-mechanical value and the second neuro-mechanical value based on the comparing performed with the electronic circuit.

2. The method of claim 1, wherein the extracting of the first neuro-mechanical value from the first micro-motions data includes using a signal processing algorithm;

and wherein

the signal processing algorithm comprises exclusively one of;

CEPSTRUM analysis, Poincare plots, Markov model analysis, Chaos analytics, or dynamical systems signal analysis based on reconstructed phase spaces (RPS),

the first micro-motions data of interest has a frequency less than about 30 Hertz (Hz).

3. The method of claim 1, wherein the comparing determines a difference between the first neuro-mechanical value and the second neuro-mechanical value between the first timestamp and the second timestamp and the method further comprises:

repeatedly generating additional neuro-mechanical values and performing comparisons in support of determining a difference between the additional neuro-mechanical values over time.

4. The method of claim 1, wherein

the comparing indicates a difference between the first neuro-mechanical value on the first time period and the second neuro-mechanical value on the second time period is above a match level for the user.

5. The method of claim 1, wherein

the comparing indicates a difference between the first neuro-mechanical value at the first time period and the second neuro-mechanical value at the second time period is below a match level for the user.

6. The method of claim 1, wherein the report further indicates if the difference between neuro-mechanical values is outside a match level.

7. The method of claim 1, wherein

the first motion of the body part of the user comprising using muscles to support the body part against the force of gravity.

8. The method of claim 1, wherein

the first motion of the body part of the user is sensed in three dimensions with a three-dimensional accelerometer to generate three-dimensional sensor data on the first time period.

9. The method of claim 1, wherein the first motion of the body part of the user is sensed locally to generate a first motion signal and the method further comprises:

transmitting the first sensor data remotely over a communication system to a server;

storing remotely the first sensor data; and

generating remotely the first neuro-mechanical value.

10. The method of claim 1, wherein

the difference is associated with drinking alcohol;

and

the difference restricts the user'"'"'s capability of operating machinery or a vehicle.

11. The method of claim 1, wherein

the body part is located near the user'"'"'s heart to monitor heart rhythm variability.

12. The method of claim 1, further comprising:

determining if a tremor is a resting tremor in order to monitor for a condition of neurodegenerative disease, wherein the resting tremor is determined by identifying a body part that is not active but is supported against gravity.

13. The method of claim 12, wherein the first motion is a multi-dimensional motion comprising a tremor having a frequency, the tremor selected from a set including one or more tremor types.

14. A method of monitoring a user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability, the method comprising:

sensing, with a handheld size device having a multi-dimensional sensor capable of sensing neuro-muscular micro-motions, multi-dimensional motion of a body part on a first plurality of time periods;

generating a plurality of multi-dimensional sensor data with a predetermined sampling frequency over a predetermined sample period by the sensor on the first plurality of time periods in response to the sensing, wherein each sensor data of the plurality of multi-dimensional sensor data includes a gravitational component;

generating micro-motions data by suppressing signal components associated with a voluntary movement of the user from the plurality of multi-dimensional sensor data, the micro-motions data including a non-transitory representation of each sensor data and user status information on each of the plurality of time periods;

timestamping each micro-motions data with a timestamp associated with one of the plurality of time periods;

extracting, from the micro-motions data, a plurality of neuro-mechanical values associated with the user for the respective plurality of time periods by processing at least one predetermined measurable feature associated with a neuro-muscular function of a user, wherein the at least one predetermined measurable feature has a mathematical property that distinctly represents the user, and wherein the mathematical property includes one of;

values of a peak amplitude and a peak quefrency from a CEPSTRUM waveform of the micro-motions data, an orbit information from Poincare plots of the micro-motions data, or a center of gravity of strange attractors and a series of Lyapunov exponent from Chaos analytics of the micro-motions data; and

comparing, with an electronic circuit, at least two of the plurality of neuro-mechanical values between two time periods to monitor the user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability; and

generating a report including a difference between the at least two of the plurality of neuro-mechanical values.

15. The method of claim 14, the extracting the plurality of neuro-mechanical values further comprises exclusively one of:

CEPSTRUM analysis, Poincare plots, Markov model analysis, Chaos analytics, or dynamical systems signal analysis based on reconstructed phase spaces (RPS),

wherein a difference between two neuro-mechanical values is outside a match level is an indicator of a condition for the user.

16. The method of claim 14, further comprises:

searching for one or more calibration parameters of the plurality of neuro-mechanical values, wherein one or more calibration parameters relate to an effect of a known pathology upon the user, the known pathology comprising;

dystonia, a neuromuscular disease, and a neurodegenerative disease.

17. The method of claim 14, wherein

the first sensor data has a frequency less than about 30 Hertz (Hz), and

wherein each motion is a multi-dimensional motion comprising a tremor having a frequency, the tremor selected from a set including one or more tremor types, the comparing analyzes the plurality of neuro-mechanical values over time, and the method further comprises

analyzing frequency components in each of the plurality of multi-dimensional motion signals to determine if the frequency components are associated with a pathological condition.

18. The method of claim 14, further comprises:

storing the plurality of multi-dimensional sensor data into a storage device for subsequent processing.

19. The method of claim 18, further comprises:

searching for one or more calibration parameters of the plurality of multi-dimensional sensor data to determine a pathological condition.

20. A system for monitoring a user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability, the system comprising:

a handheld size device having a multi-dimensional sensor configured to sample multi-dimensional neuro-muscular micro-motions of a body part of a user and generate a first sensor data with a predetermined sampling frequency over a predetermined sample period in response thereto, the generated first sensor data comprising a gravitational component;

a signal processor configured to process the first sensor data by suppressing signal components associated with voluntary movement of the user from the sensor data and to output first micro-motions data;

a timestamper configured to provide a timestamp for the first micro-motions data;

a storage device configured to store the first micro-motions data and provide access to stored data, the storage device further configured to store multi-dimensional sensor data and respective neuro-mechanical values for the multi-dimensional sensor data at different dates for processing by a processor;

one or more processors coupled to the storage device, the one or more processors configured to execute instructions for processing micro-motions data, including micro-motions data stored in the storage device,

wherein, based on the micro-motions data, at least one processor is configured to generate a plurality of neuro-mechanical values for the respective plurality of dates by processing at least one predetermined measurable feature associated with a neuro-muscular function of a user, wherein the at least one predetermined measurable feature has a mathematical property that distinctly represents the user,

wherein the mathematical property includes one of;

values of a peak amplitude and a peak quefrency from a CEPSTRUM waveform of the micro-motions data, an orbit information from Poincare plots of the micro-motions data, or a center of gravity of strange attractors and a series of Lyapunov exponent from Chaos analytics of the micro-motions data, and

wherein at least one processor is configured to compare at least two of the plurality of neuro-mechanical values to monitor the user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability.

21. The system of claim 20, wherein the at least one processor is further configured for exclusively one of:

CEPSTRUM analysis, Poincare plots, Markov model analysis, Chaos analytics, or dynamical systems signal analysis based on reconstructed phase spaces (RPS), and

wherein a difference between two neuro-mechanical values is outside a match level is an indicator of a condition for the user.

22. The system of claim 20, wherein

at least one processor is configured to search for one or more calibration parameters of the plurality of neuro-mechanical values, wherein one or more calibration parameters relate to an effect of a known pathology upon the user, the known pathologies comprising:

dystonia, a neuromuscular disease, and a neurodegenerative disease.

23. The system of claim 20, wherein

the first sensor data has a frequency less than about 30 Hertz (Hz), and

at least one processor is configured to analyze frequency components in each of the multi-dimensional sensor data to determine if the frequency components are associated with a pathological condition, wherein the first motion data is a multi-dimensional sensor data including a tremor having a frequency, the tremor selected from a set including one or more tremor types.

24. An electronic device to monitor a user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability, the electronic device comprising,

a processor;

a display coupled to the processor;

one or more motion sensors coupled to the processor, the one or more motion sensors capable of sensing neuro-muscular micro-motions;

a power circuit coupled to the processor;

a wireless transceiver coupled to the processor;

a memory coupled to the processor; and

a non-transitory computer program product including instructions stored in the memory, wherein the instructions configure the processor to perform the functions of;

collecting a first sensor data with a predetermined sampling frequency over a predetermined sample period by sensing a first motion of a body part of a user from the motion sensor on a first time period;

generating a first micro-motions data by suppressing signal components associated with a voluntary movement of the user from the first sensor data, the first micro-motions data comprising a non-transitory representation of the first motion signal and status information for the user on the first time period;

timestamping the first micro-motions data thereby generating first micro-motions data having a first timestamp associated with the first time period;

extracting a first neuro-mechanical value from the first micro-motions data for the user by processing the at least one predetermined measurable feature associated with the neuro-muscular function of the user, wherein the at least one predetermined measurable feature has a mathematical property that distinctly represents the user, and wherein the mathematical property includes one of;

values of a peak amplitude and a peak quefrency from a CEPSTRUM waveform of the micro-motions data, an orbit information from Poincare plots of the micro-motions data, or a center of gravity of strange attractors and a series of Lyapunov exponent from Chaos analytics of the micro-motions data;

collecting a second sensor data with a predetermined sampling frequency over a predetermined sample period by sensing a second motion of a body part of a user from the motion sensor on a second time period differing from the first time period;

generating a second micro-motions data by suppressing signal components associated with a voluntary movement of the user from the second sensor data, the second micro-motions data comprising a non-transitory representation of the second motion signal and status information for the user on the second time period;

timestamping the second micro-motions data thereby generating second micro-motions data having a second timestamp associated with the second time period;

extracting a second neuro-mechanical value from the second micro-motions data for the user by processing the at least one predetermined measurable feature associated with the neuro-muscular function of the user;

comparing the first neuro-mechanical value and the second neuro-mechanical value to monitor the user for neurodegenerative diseases, drinking alcohol, and heart rhythm variability.

25. The electronic device of claim 24, wherein the processor is configured for performing the extracting by performing exclusively one of:

CEPSTRUM analysis, Poincare plots, Markov model analysis, Chaos analytics, or dynamical systems signal analysis based on reconstructed phase spaces (RPS), and

wherein a difference between the first neuro-mechanical value and the second neuro-mechanical value is outside a match level providing an indicator of a condition for the user.

26. The electronic device of claim 24, wherein

the processor is configured to search for one or more calibration parameters of the first and second neuro-mechanical values,

wherein one or more calibration parameters relate to an effect of a known pathology upon the user, the known pathologies comprising dystonia, a neuromuscular disease, and a neurodegenerative disease.

27. The electronic device of claim 24, wherein

the processor is further configured to analyze frequency components in the first and second sensor data to determine if the frequency components are associated with a pathological condition, wherein the first micro-motions data is a multi-dimensional sensor data including a tremor having a low frequency, the tremor selected from a set including one or more tremor types;

wherein the first sensor data has a frequency less than about 30 Hertz (Hz).