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

• US 9,659,216 B2
• Filed: 09/10/2012
• Issued: 05/23/2017
• Est. Priority Date: 04/03/2000
• Status: Expired due to Term

• Current Assignee: Flint Hills Scientific, LLC
• Original Assignee: Flint Hills Scientific, LLC
• Inventors: Nikitin, Alexei V., Bhavaraju, Naresh C., Osorio, Ivan, Davidchack, Ruslan L., Frei, Mark G.
• Primary Examiner(s): Negin, Russell S
• Application Number:
  US13/608,551
• Publication Number:
  US 20130012825A1
• Time in Patent Office: 1,716 Days
• Field of Search: None
• 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 medical device including a power source for detecting an epileptic seizure, the medical device configured to implement a method including:

(a) receiving via one or more processors a heart signal from a patient;

(b) determining via the one or more processors a heart signal feature from the heart signal;

(c) determining via the one or more processors a first percentile tracking filter estimate from the heart signal feature in a foreground time window;

(d) determining via the one or more processors a second percentile tracking filter estimate from the heart signal feature in a background time window;

(e) comparing via the one or more processors a foreground data to a background data;

(f) detecting via the one or more processors the epileptic seizure based on the comparison of the foreground data to the background data; and

(g) in response to the detecting of the epileptic seizure, providing via the one or more processors an output indicative of the detection of the epileptic seizure;

wherein at least one of the first percentile tracking filter estimate and the second percentile tracking filter estimate is updated using a difference equation, wherein the difference equation updates the at least one of the first percentile tracking filter estimate and the second percentile tracking filter estimate based on a comparison of a heart signal feature status versus a most recent percentile tracking filter estimate status where the comparison determines a first state, a second state, and a third state, wherein the difference equation updates the at least one of the first percentile tracking filter estimate and the second percentile tracking filter by incrementing the at least one of the first percentile tracking filter estimate and the second percentile tracking filter estimate by a first non-negative value based on the first state where the first state is that the heart signal feature is greater than a most recent percentile tracking filter estimate, wherein the difference equation updates the at least one of the first percentile tracking filter estimate and the second percentile tracking filter estimate by decrementing the at least one of the first percentile tracking filter estimate and the second percentile tracking filter estimate by a second non-negative value based on the second state where the second state is that the heart signal feature is below the most recent percentile tracking filter estimate; and

wherein the difference equation updates the at least one of the first percentile tracking filter estimate and the second percentile tracking filter estimate by leaving the at least one of the first percentile tracking filter estimate and the second percentile tracking filter estimate unchanged based on the third state where the third state is that the heart signal feature value is equal to the most recent percentile tracking filter estimate;

wherein the utilization of the first percentile tracking filter estimate and the second percentile tracking filter estimate extends a power source life of the power source based on a power consumption associated with a computational process relating to the first percentile tracking filter estimate and the second percentile tracking filter estimate.

2. The medical device of claim 1, wherein the method further comprising:

(i) receiving a percentile value from a programmer.

3. The medical device of claim 1, wherein determining the first percentile tracking filter estimate and the second percentile tracking filter estimate each comprise determining a time-weighted function of the heart signal feature, and estimating one or more of the percentile tracking filter estimates from the time-weighted function.

4. The medical device of claim 3, 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 at least one of:

a Gaussian distribution function;

a Chi-square distribution function;

an Uniform distribution function; and

a Triangle distribution function.

5. The medical device of claim 1, wherein the first non-negative value and the second non-negative value are equal.

6. The medical device of claim 1, wherein the heart signal feature is the heart signal.