Method and apparatus for diagnosing joints

• US 5,413,116 A
• Filed: 06/24/1993
• Issued: 05/09/1995
• Est. Priority Date: 06/24/1993
• Status: Expired due to Term

• Current Assignee: Biomet Sports Medicine LLC (Zimmer Biomet Holdings, Inc.)
• Original Assignee: Bioresearch Incorporated
• Inventors: Radke, John C., Ryan, Gregory J., Hershberger, Troy W.
• Primary Examiner(s): HINDENBURG, MAX F
• Application Number:
  US08/083,219
• Time in Patent Office: 684 Days
• Field of Search: 128/630, 128/715, 128/773, 128/782
• US Class Current: 600/590
• CPC Class Codes: A61B 5/1114 Tracking parts of the body
• CPC Class Codes: A61B 5/1121 Determining geometric values, e.g. centre of rotation or angular range of movement
• CPC Class Codes: A61B 5/1127 using markers
• CPC Class Codes: A61B 5/4514 Cartilage
• CPC Class Codes: A61B 5/4528 Joints A61B5/4533, A61B5/4538 take precedence
• CPC Class Codes: A61B 5/682 Mouth, e.g., oral cavity; tongue; Lips; Teeth
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 7/006 Detecting skeletal, cartilage or muscle noise A61B7/003 and A61B7/008 take precedence
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: Y10S 128/925 Neural network

Abstract

A method and apparatus for diagnosing joints based on sensed joint vibrations. Accelerometers disposed on the skin adjacent to the joint detect vibrational patterns during movement of the joint. These patterns are then processed by one processor to generate a predetermined set of data parameters descriptive of the vibration pattern. Also, the position and velocity of the joint during the vibration is recorded. This information from numerous patients with known joint conditions is used to train a adaptive interpreter, such as a neural network, to produce an output in response to these inputs which is indicative of the known joint condition. Once trained, the adaptive interpreter can then interpret this set of parameters for an unknown joint to generate a fast and reliable diagnosis. The result is a non-subjective joint disorder classification system that can be utilized by persons without particular expertise in analyzing joint vibrational patterns.

Claims

1. A system for classifying degenerative joint disease conditions, the system comprising:

a) sensor means for detecting a vibration pattern from the joint;

b) preprocessor means for providing a predetermined set of data parameters descriptive of the vibration pattern; and

c) trainable adaptive interpreter means for receiving said data parameters as input and producing an output which indicates at least one classification of the degenerative disease condition of said joint.

2. The system of claim 1, wherein said preprocessor means includes means for determining the frequency spectrum of said vibration pattern.

3. The system of claim 2, wherein said preprocessing means includes means for determining an integral of the frequency spectrum of said vibration pattern.

4. The system of claim 2, wherein said preprocessing means includes means for determining the median frequency of said vibration pattern.

5. The system of claim 1, further comprising means for measuring the instantaneous position of the joint during movement of the joint.

6. The system of claim 1, further comprising means for measuring the velocity of the joint during movement of the joint.

7. The system of claim 1, further comprising means for determining the range of motion of said joint, said range of motion being received by said interpreter as input.

8. The system of claim 1, wherein said interpreter comprises a neural network.

9. The system of claim 8, wherein said neural network is a multi-layer perceptron.

10. The system of claim 8, wherein said neural network contains adjustable weights which are generated during a training session using vibration patterns from joints with known conditions.

11. The system of claim 8, wherein said neural network contains fixed weights generated from a training session using vibration patterns from joints with known conditions.

12. A method for classifying degenerative joint disease conditions, said method comprising the steps of:

a) detecting a first set of vibration patterns from one or more joints, the joints having a known condition;

b) using said first set of vibration patterns and said known joint conditions to train an adaptive interpreter to produce an output indicating particular known degenerative joint disease conditions in response to particular vibration patterns;

c) detecting a second set of vibration patterns from a subject joint; and

d) transmitting said second set of vibration patterns to said adaptive interpreter wherein said adaptive interpreter generates an output indicating the presence of one or more of said known degenerative joint disease conditions in said subject joint.

13. The method of claim 12, wherein the step of using said first set of vibration patterns and said known joint conditions to train an adaptive interpreter further comprises the steps of interactively processing said first set of vibration patterns in a neural network until the output indicates the known joint condition.

14. The method of claim 13, wherein said step of interactively processing comprises a backpropagation training procedure.

15. The method of claim 12, wherein the joint comprises two portions on opposite sides of the joint and said step of detecting further comprises the step of placing one sensor adjacent to each joint portion.

16. The method of claim 12, further comprising the step of detecting the frequency spectrum of the vibration pattern.

17. The method of claim 16, further comprising the step of an integral of the frequency spectrum of the vibration pattern.

18. The method of claim 17, further comprising the step of the sampling only a portion of said detected vibration pattern, said portion beginning a period before and ending a period after said peak amplitude wherein only said sampled portion of first and second set of vibration patterns is transmitted to said interpreter.

19. The method of claim 18, further comprising the step of repeating the step of sampling a plurality of times and averaging said sampled vibration pattern before transmitting to the interpreter.

20. The method of claim 12, further comprising the step of measuring the instantaneous position of the joint during movement thereof.

21. The method of claim 12, further comprising the step of measuring the velocity of the joint during movement thereof.

22. The method of claim 12, wherein said adaptive interpreter is a neural network and wherein the step of using said first set of vibration patterns and said known joint conditions to train an adaptive interpreter includes the step of employing backpropagation to train the adaptive interpreter.

23. A system for classifying a trauma induced joint condition said system comprising:

a) sensor means for detecting a vibration pattern from the joint;

b) preprocessor means for providing a predetermined set of data parameters descriptive of the vibration pattern; and

c) trainable adaptive interpreter means for receiving said data parameters as input and producing an output which indicates at least one classification of the trauma induced condition of said joint.

24. A system for classifying joint conditions in a load bearing joint, the system comprising:

a) sensor means for detecting a vibration pattern from the joint;

b) preprocessor means for providing a predetermined set of data parameters descriptive of the vibration pattern; and

c) trainable adaptive interpreter means for receiving said data parameters as input and producing an output which indicates at least one classification of the condition of said joint.

25. The system of claim 24 wherein said joint condition is congenital.

26. The system of claim 24 wherein said joint is a knee.

27. The system of claim 24 wherein said joint is a hip.

28. A system for classifying degenerative joint disease conditions, the system comprising:

a) sensor means of detecting a vibration pattern from the joint;

b) means for receiving non-vibrational diagnostic information relating to said joint;

c) preprocessor means for providing a predetermined set of data parameters descriptive of the vibration pattern and said diagnostic information; and

d) trainable adaptive interpreter means for receiving said data parameters as input and producing an output which indicates at least one classification of the degenerative disease condition of said joint.