Method, computer program, and system for automated real-time signal analysis for detection, quantification, and prediction of signal changes

• US 8,265,742 B2
• Filed: 03/16/2007
• Issued: 09/11/2012
• Est. Priority Date: 04/03/2000
• Status: Active Grant

• Current Assignee: Flint Hills Scientific, LLC
• Original Assignee: Flint Hills Scientific, LLC
• Inventors: Nikitin, Alexei V., Bhavaraju, Naresh C., Frei, Mark G., Osoria, Ivan, Davidchak, Ruslan
• Primary Examiner(s): Negin, Russell S
• Application Number:
  US11/724,738
• Publication Number:
  US 20070271066A1
• Time in Patent Office: 2,006 Days
• Field of Search: None
• US Class Current: 600/544
• CPC Class Codes: G06F 17/10 Complex mathematical operations function generation by table look-up G06F1/03; evaluation of elementary functions by calculation G06F7/544
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G16B 40/00 ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
• CPC Class Codes: G16B 40/10 Signal processing, e.g. from mass spectrometry [MS] or from PCR
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A method, computer program, and system for real-time signal analysis providing characterization of temporally-evolving densities and distributions of signal features of arbitrary-type signals in a moving time window by tracking output of order statistic filters (also known as percentile, quantile, or rank-order filters). Given a raw input signal of arbitrary type, origin, or scale, the present invention enables automated quantification and detection of changes in the distribution of any set of quantifiable features of that signal as they occur in time. Furthermore, the present invention'"'"'s ability to rapidly and accurately detect changes in certain features of an input signal can also enable prediction in cases where the detected changes associated with an increased likelihood of future signal changes.

Claims

1. A method of detecting or predicting a neurological event, the method comprising the steps of:

(a) receiving an input signal;

(b) determining a time-weighted function of the input signal;

(c) determining a percentile tracking filter estimate from the time-weighted function;

(d) comparing the percentile tracking filter estimate to a reference signal in order to detect or predict the neurological event; and

(e) communicating the detection or prediction of the neurological event, wherein each of the above steps is performed on a programmed computer.

2. The method as set forth in claim 1, wherein the percentile value of the input signal is estimated from the time-weighted function using a difference equation.

3. The method as set forth in claim 2, wherein the percentile tracking filter estimate is updated using a difference equation, wherein the difference equation updates the estimate by:

incrementing the estimate by a first non-negative value if the input signal is greater than the most recent percentile tracking filter estimate,

decrementing the estimate by a second non-negative value if the input signal is below the most recent percentile tracking filter estimate, or

leaving the estimate unchanged if the input signal value is equal to the most recent percentile tracking filter estimate.

4. The method as set forth in claim 3, wherein the first non-negative value and the second non-negative value are equal.

5. The method as set forth in claim 3, wherein the first non-negative value and the second non-negative value are unequal.

6. The method as set forth in claim 1, wherein the time-weighted function is determined by first determining at least one parameter upon which the time-weighted function depends and where the time-weighted function is selected from the group consisting of:

Gaussian distributions, Chi-square distributions, Uniform distributions, and Triangle distributions.

7. The method as set forth in claim 1, wherein the neurological event is an epileptic seizure.

8. The method as set forth in claim 1, wherein the neurological event is indicative of abnormal brain activity.

9. The method as set forth in claim 1, wherein the neurological event is indicative of normal brain activity.

10. The method as set forth in claim 1, wherein the reference signal is obtained by computing or estimating at least one percentile of a second time-weighted function of the input signal, with the second time-weighted function of the input signal corresponding to a longer time interval than the typical duration of the neurological event to be detected.