METHOD FOR CONFIDENCE LEVEL DETERMINATION OF AMBULATORY HR ALGORITHM BASED ON A THREE-WAY RHYTHM CLASSIFIER

• US 20150327781A1
• Filed: 05/13/2015
• Published: 11/19/2015
• Est. Priority Date: 05/13/2014
• Status: Active Grant

• Current Assignee: Sensium Healthcare Limited
• Original Assignee: Sensium Healthcare Limited
• Inventors: HERNANDEZ-SILVEIRA, Miguel, ANG, Su-Shin
• Granted Patent: US 10,357,167 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method of determining a confidence level in a heart rate obtained from an ECG signal of a patent comprises determining a heart rate from a segment of an ECG signal, the segment having a pre-determined length, and determining a first confidence level in the determined heart rate. If the first confidence level exceeds a predetermined value, the heart rate is output. Otherwise, the method further comprises determining a set of features from the segment of the ECG signal; and classifying the segment of the ECG signal, based on one or more features selected from the determined set of features and the heart rate, into one of at least three classes: noise, an abnormal sinus rhythm and a normal sinus rhythm.

Claims

1. A method comprising:

determining a heart rate from a segment of an ECG signal, the segment having a pre-determined length, and determining a first confidence level in the determined heart rate;

if the first confidence level exceeds a predetermined value, outputting the heart rate;

otherwise;

determining a set of features from the segment of the ECG signal; and

classifying the segment of the ECG signal based on one or more features selected from the determined set of features and the heart rate;

wherein classifying the segment of ECG signal comprises classifying the segment of ECG signal into any one of at least three classes;

noise, an abnormal sinus rhythm, and a normal sinus rhythm.

2. A method as claimed in claim 1 and comprising, if classifying the segment of the ECG signal comprises classifying the segment of the ECG signal as an abnormal sinus rhythm or a normal sinus rhythm, outputting the determined heart rate after classifying the segment of the ECG signal.

3. A method as claimed in claim 1 and, if classifying the segment of the ECG signal comprises classifying the segment of the ECG signal as indicative of noise, further comprising outputting an error indication.

4. A method as claimed in claim 1 wherein determining the first confidence level comprises determining a noise level in the segment of the ECG signal.

5. A method as claimed in claim 1 wherein determining the set of features comprises processing the segment and determining the set of features from the processed segment.

6. A method as claimed in claim 1 wherein classifying the segment of the ECG signal comprises classifying the segment of the ECG signal based on two features selected from the determined set of features and the heart rate.

7. A method as claimed in claim 1 wherein the ECG signal is a single lead ECG signal.

14. A non-transitory computer-readable medium containing instructions that, when executed on a processor, cause the processor to carry out a method as defined in claim 1.

8. An apparatus comprising:

a module configured to determine a heart rate from a segment of an ECG signal, the segment having a pre-determined length, and to determine a first confidence level in the determined heart rate;

a module configured to, if the first confidence level exceeds a predetermined value, output the heart rate;

a module configured to, if the first confidence level does not exceed the predetermined value, determine a set of features from the segment of the ECG signal; and

a classifying module configured to classify the segment of the ECG signal based on features selected from the determined set of features and the heart rate;

wherein the classifying module is configured to classify the heart rate determined from the segment of ECG signal into any one of at least three classes;

noise, an abnormal sinus rhythm and a normal sinus rhythm.

9. An apparatus as claimed in claim 8 and configured to, if the classifying module classifies the segment of the ECG signal as an abnormal sinus rhythm or a normal sinus rhythm, output the determined heart rate.

10. An apparatus as claimed in claim 8 and configured to classify the segment of the ECG signal based on two features selected from the determined set of features and the heart rate.

11. An apparatus as claimed in claim 8 and further comprising an input for receiving an ECG signal.

12. An apparatus as claimed in claim 11 and comprising a segmenter module configured to segment an ECG signal received at the input.

13. A system comprising an apparatus as defined in claim 11 and a single lead ECG system connectable to the input of the apparatus.