Intelligent wearable monitor systems and methods

• US 20050240086A1
• Filed: 03/14/2005
• Published: 10/27/2005
• Est. Priority Date: 03/12/2004
• Status: Active Grant

• Current Assignee: The Trustees of Dartmounth College (Dartmouth College)
• Original Assignee: The Trustees of Dartmounth College (Dartmouth College)
• Inventors: Akay, Metin
• Granted Patent: US 7,981,058 B2
• Time in Patent Office: Days
• US Class Current: 600/300
• CPC Class Codes: A61B 2560/045 with a separable interface unit, e.g. for communication
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/0024 for multiple sensor units attached to the patient, e.g. using a body or personal area network
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/1124 Determining motor skills
• CPC Class Codes: A61B 5/4082 Diagnosing or monitoring movement diseases, e.g. Parkinson, Huntington or Tourette
• CPC Class Codes: A61B 5/6824 Arm or wrist
• CPC Class Codes: A61B 5/6825 Hand
• 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

Abstract

An intelligent wearable monitoring system includes a wireless personal area network for extended monitoring of a patient'"'"'s motor functions. The wireless personal area network includes an intelligent accelerometer unit, a personal server and a remote access unit. The intelligent accelerometer unit measures acceleration data of the patient, in real-time. The personal server processes the acceleration data, applying linear and non-linear analysis, such as fractal analysis, to generate motor function information from the acceleration data. Motor function information is transmitted to a remote access unit for statistical analysis and formatting into visual representations. A data management unit receives the formatted motor function information and displays the information, for example, for viewing by the patient'"'"'s physician.

Claims

1. An intelligent wearable monitor system, comprising:

one or more intelligent accelerometer units operable for capturing acceleration data while worn by a patient;

a personal server operable for processing acceleration data from the intelligent accelerometer units to generate motor function information;

a remote access unit operable for receiving motor function information from the personal server, and

a data management unit operable for storing motor function information from the remote access unit.

2. The intelligent wearable monitor system of claim 1, wherein the intelligent accelerometer units, the personal server and the remote access unit form a wireless personal area network.

3. The intelligent wearable monitor system of claim 1, wherein the intelligent accelerometer units comprise:

one or more accelerometers for sensing acceleration;

a microprocessor configured for recording and preprocessing the acceleration data from the accelerometers, and

a wireless transceiver for transmitting the acceleration data to the personal server and receiving data from the personal server.

4. The intelligent wearable monitor of claim 1, the intelligent accelerometer units and the personal server being removably attachable to a wearer'"'"'s body.

5. The intelligent wearable monitor system of claim 1, the remote access unit comprising:

a user interface;

a transceiver;

a processor, and

a non-volatile memory.

6. The intelligent wearable monitor system of claim 5, the remote access unit further comprising software including data mining and analysis tools for processing motion information.

7. A method of monitoring the motor function of a patient, comprising:

capturing acceleration data from the patient with one or more accelerometers positioned on the patient;

wirelessly communicating the acceleration data to a personal server positioned on the patient at a location spaced from the accelerometers; and

processing the acceleration data to generate motor function information.

8. The method of claim 7, the step of processing comprising processing at the personal server.

9. The method of claim 7, the step of processing comprising dividing the acceleration data into epochs.

10. The method of claim 9, the step of processing the acceleration data comprising electronically marking the epochs.

11. The method of claim 7, the step of processing the acceleration data comprising attaching the time and date to the acceleration data.

12. The method of claim 7, the step of processing the acceleration data comprising processing, identifying and measuring physical activity.

13. The method of claim 7, the step of processing acceleration data comprising computing linear parameters for the acceleration data.

14. The method of claim 13, computing linear parameters for acceleration data comprising calculating one or more of a jerk metric, a root mean square value;

a range of autocorrelation function;

a correlation coefficients for pairs of acceleration channels;

a smoothness metric, and an RMS value of the jerk metric.

15. The method of claim 7, the step of processing acceleration data comprising computing nonlinear parameters for the acceleration data.

16. The method of claim 15, computing nonlinear parameters comprising calculating one or more nonlinear parameters for the motor function information, the nonlinear parameters chosen from the group of a maximum likelihood estimator fractal, an approximate entropy method, an approximate cross entropy method and an average amount of mutual information measure.

17. The method of claim 7, further comprising formatting the motor function information by performing at least one of statistical analysis and data mining.

18. A method for assessing motor function of a patient, comprising:

capturing first acceleration data from one or more accelerometers at one or more locations on the patient;

dividing the first acceleration data into training epochs;

training an artificial neural network with the training epochs;

storing the training epochs as baseline acceleration data;

capturing second acceleration data from the one or more accelerometers at the one or more locations on the patient; and

processing the second acceleration data with the artificial neural network to determine the motor function.

19. The method of claim 18, further comprising processing the first and second acceleration data to generate first and second movement information.

20. The method of claim 19, further comprising training the artificial neural network with the first movement information.

21. The method of claim 19, further comprising processing the second movement information with the artificial neural network to determine motor function.

22. The method of claim 19, further comprising comparing one or more of the first and second movement-related data and the first and second movement information with software including an ADL index.

23. A method for assessing the motor function of a patient, comprising the steps of:

capturing first acceleration data of the patient, utilizing one or more accelerometers;

processing the acceleration data into movement information, utilizing a personal server;

wirelessly transmitting the motor function information to a remote access unit;

formatting the motor function information into formatted information at the remote access unit;

wirelessly transmitting the formatted information to a data management unit;

displaying the formatted information at the data management unit, and

determining a level of functional impairment of the patient.

24. The method of claim 23, wherein determining a level of functional impairment of the patient comprises diagnosing a neurological disorder.

25. The method of claim 24, wherein determining a level of functional impairment of the patient comprises determining the severity of a neurological disorder.