Method and device for multimodal neurological evaluation

1. A method of building a classifier for multimodal assessment of a subject's neurological condition, comprising the steps of:

providing a signal processing device operatively connected to a memory device storing results of two or more different assessments performed on a plurality of individuals in the presence or absence of brain abnormalities, the signal processing device comprising a processor configured to perform the steps of:

extracting quantitative features from the results of the two or more different assessments;

storing the extracted features in a pool of selectable features;

selecting a subset of features from the pool of selectable features to construct the classifier; and

determining classification accuracy of the classifier by using it to classify data records having a priori classification information.

2. The method of claim 1 , further comprising the step of applying one or more data reduction criteria to the pool of selectable features to create a reduced pool of features from which the subset of features for constructing the classifier are selected.

3. The method of claim 1 , wherein the two or more different assessments comprise neurophysiological and neurocognitive assessments.

4. The method of claim 3 , wherein the neurophysiological assessments comprise recording of brain electrical signals.

5. The method of claim 3 , wherein the two or more different assessments comprise one or more types of reaction time measurements.

6. The method of claim 3 , wherein the neurocognitive assessment is performed using a dynamic questionnaire designed to change questions based on answers provided to prior questions.

7. The method of claim 1 , wherein the two or more different assessments comprise measurement of various physiological parameters.

8. The method of claim 7 , wherein the two or more assessments comprise recording of electrocardiographic signals.

9. The method of claim 1 , wherein the subset of features are selected using an evolutionary algorithm.

10. The method of claim 9 , wherein the evolutionary algorithm applied is a genetic algorithm.

11. The method of claim 10 , wherein the selected subset of features is optimized using at least one of a Random Mutation Hill Climbing algorithm and a Modified Random Mutation Hill Climbing algorithm.

12. The method of claim 1 , wherein the subset of features is selected using a Simple Feature Picker algorithm.

13. The method of claim 12 , wherein the selected subset of features is optimized using at least one of a Random Mutation Hill Climbing algorithm and a Modified Random Mutation Hill Climbing algorithm.

14. The method of claim 1 , wherein the classifier is a Linear Discriminant Function.

15. The method of claim 1 , wherein the classifier is a Quadratic Discriminant Function.

16. The method of claim 1 , wherein an objective function is used to evaluate the performance of the classifier.

17. The method of claim 16 , wherein the objective function used is Area Under the Receiver Operating Curve of the classifier.

18. A method of building a classifier for classification of individual data into one of two or more categories of a neurological condition, the method comprising the steps of:

providing a processor configured to build a classifier;

providing a memory device operatively coupled to the processor, the memory device storing a population reference database comprising a pool of quantitative features extracted from the results of physiological and neurocognitive assessments performed on a plurality of individuals in the presence or absence of brain abnormalities;

selecting a plurality of brain electrical signal features from the pool of quantitative features in the population reference database;

selecting another plurality of quantitative features derived from one or more additional assessments performed on the plurality of individuals in the population reference database;

constructing a classifier using the selected quantitative features; and

evaluating performance of the classifier using pre-labeled data records stored in the memory device, wherein the pre-labeled data records are assigned a priori to one of the two or more categories.

19. The method of claim 18 , wherein the one or more additional assessments comprise assessment of reaction time.

20. The method of claim 18 , wherein the one or more additional assessments comprise recording of electrocardiographic signals.

21. The method of claim 18 , further comprising the step of applying one or more data reduction criteria to the selected features to create a reduced subset of features from which the classifier is constructed.

22. The method of claim 18 , wherein the quantitative features are selected using an evolutionary algorithm.

23. The method of claim 22 , wherein the evolutionary algorithm applied is a genetic algorithm.

24. The method of claim 23 , wherein the selection of features is optimized using at least one of a Random Mutation Hill Climbing algorithm and a Modified Random Mutation Hill Climbing algorithm.

25. The method of claim 18 , wherein the quantitative features are selected using a Simple Feature Picker algorithm.

26. The method of claim 25 , wherein the selection of features is optimized using at least one of a Random Mutation Hill Climbing algorithm and a Modified Random Mutation Hill Climbing algorithm.

27. The method of claim 18 , wherein the classifier is a Discriminant Function.

28. The method of claim 27 , wherein the classifier is a Quadratic Discriminant Function.

29. The method of claim 27 , wherein the classifier is a Linear Discriminant Function.

30. The method of claim 18 , wherein an objective function is used to evaluate the performance of the classifier.

31. The method of claim 18 , wherein the objective function used is Area Under the Receiver Operating Curve of the binary classifier.

32. The method of claim 18 , wherein the classifier is a binary classifier.

33. The method of claim 18 , wherein the classifier is a multiclass classifier.