Method and apparatus for the detection of neuromuscular disease using disease specific evoked neuromuscular response analysis

• US 7,452,335 B2
• Filed: 11/06/2002
• Issued: 11/18/2008
• Est. Priority Date: 11/06/2001
• Status: Expired due to Fees

• Current Assignee: Neurometrix, Inc.
• Original Assignee: Neurometrix, Inc.
• Inventors: Gozani, Shai N., Wells, Martin D.
• Primary Examiner(s): Hindenburg; Max
• Assistant Examiner(s): Apanius; Michael
• Application Number:
  US10/288,852
• Publication Number:
  US 20030093006A1
• Time in Patent Office: 2,204 Days
• Field of Search: 600/546, 600/547, 600/554, 607/48
• US Class Current: 600/554
• CPC Class Codes: A61B 5/24 Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
• CPC Class Codes: A61B 5/388 Nerve conduction study, e.g. detecting action potential of peripheral nerves
• CPC Class Codes: A61B 5/4041 Evaluating nerves condition

Abstract

A method and apparatus for assessing neuromuscular pathology in an individual, by (a) applying a plurality of stimuli to a peripheral nerve; (b) recording from the peripheral nerve, or from a muscle innervated by the peripheral nerve, at least one response to each stimulus; (c) processing each response into at least one response characteristic; (d) compiling the response characteristics from all of the responses into a plurality of descriptive parameters of the response characteristics; and (e) analyzing the plurality of descriptive parameters according to a function specific to the neuromuscular pathology so as to yield an indicator of the pathology.

Claims

1. A method for the determination of a composite pathology function whose output indicates a neuromuscular pathology in an individual, the method comprising the steps of:

(a) selecting a first group of individuals that have the neuromuscular pathology;

(b) applying a plurality of stimuli to a peripheral nerve of each individual in said first group of individuals so as to evoke a plurality of responses to said stimuli from said peripheral nerve or from a muscle innervated by said peripheral nerve;

(c) recording said responses;

(d) processing each of said responses into at least one selected response characteristic;

(e) compiling said at least one response characteristic from all of said responses into a first set of selected descriptive parameters characterizing said first group of individuals;

(f) selecting a second group of individuals that do not have the neuromuscular pathology;

(g) repeating steps (b), (c), (d) and (e) on each individual of said second group of individuals that do not have the neuromuscular pathology to generate a second set of said descriptive parameters characterizing said second group of individuals; and

(h) processing said first and second sets of descriptive parameters so as to determine a composite pathology function of said descriptive parameters that is indicative of the neuromuscular pathology, said composite pathology function being characterized in that the composite pathology function integrates the descriptive parameters into a single index represented by the following equation;

${\mathrm{NC}}_{\mathrm{composite}}={\mathrm{e<br><br>}}^{\frac{\underset{i=1}{\overset{N}{\sum <br><br>}}<br><br>{\mathrm{\alpha <br><br>}}_i<br><br>p_i}{1+\underset{i=1}{\overset{N}{\sum <br><br>}}<br><br>{\mathrm{\alpha <br><br>}}_i<br><br>p_i}}$

where N represents a total number of predictive nerve conduction parameters, p_i is the i-th nerve conduction parameter value and α

_i is a corresponding weighting coefficient.

2. The method of claim 1 wherein said processing of said first and second sets of descriptive parameters is performed using logistic regression analysis.

3. The method of claim 1 wherein said processing of said first and second sets of descriptive parameters is performed using an artificial neural network.

4. The method of claim 1 wherein said processing of said first and second sets of descriptive parameters is performed using linear discriminate analysis.

5. The method of claim 1 wherein said processing of said first and second sets of descriptive parameters is performed using linear multivariate regression.

6. The method of claim 1 wherein said processing of said first and second sets of descriptive parameters is performed using clustering.