Method and system for screening of atrial fibrillation

• US 9,913,588 B2
• Filed: 08/21/2015
• Issued: 03/13/2018
• Est. Priority Date: 11/01/2013
• Status: Active Grant

• Current Assignee: Verily Life Sciences LLC (Alphabet Inc.)
• Original Assignee: Cardiio, Inc.
• Inventors: Poh, Ming-Zher
• Primary Examiner(s): Peng, Bo J
• Application Number:
  US14/833,010
• Publication Number:
  US 20150359443A1
• Time in Patent Office: 935 Days
• CPC Class Codes: A61B 2576/023 for the heart
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/0261 using optical means, e.g. infrared light
• CPC Class Codes: A61B 5/0295 using plethysmography, i.e. measuring the variations in the volume of a body part as modified by the circulation of blood therethrough, e.g. impedance plethysmography
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• 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: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The present disclosure provides a description of various methods and systems associated with determining possible presence of Atrial Fibrillation (AF). In one example, a camera of a client device, such as a mobile phone, may acquire a series of images of a body part of a user. A plethysmographic waveform may be generated from the series of images. An autocorrelation function may be calculated from the waveform, and a number of features may be computed from the autocorrelation function. Based on an analysis of the features, a determination may be made about whether the user is experiencing AF. Such determined may be output to a display of the mobile phone for user review.

Claims

1. A method for detecting presence of atrial fibrillation,

the method comprising:

acquiring, using one or more sensors, a series of images from a body part;

extracting a time-varying signal representing a plethysmographic waveform from one or more channels of the series of images;

calculating an autocorrelation function of the plethysmographic waveform;

measuring one or more peak amplitudes each corresponding to a height of a peak in the autocorrelation function;

measuring one or more peak times each corresponding to a location of the peak in the autocorrelation function;

analyzing, using a processor, the one or more peak amplitudes and the one or more peak times to produce an indication of atrial fibrillation; and

generating an alert based on the indication of an atrial fibrillation condition.

2. The method according to claim 1, wherein the sensor comprises a camera.

3. The method according to claim 1, wherein the one or more sensors are an element of a at least one of a mobile device or a watch.

4. The method according to claim 1, wherein extracting the time-varying signal representing the plethysmographic waveform further comprises:

a) identifying a region of interest; and

b) averaging pixels within the region of interest.

5. The method according to claim 1, wherein the sensor comprises at least one light sensor configured to receive light from a light source.

6. The method according to claim 1, further comprising computing at least one feature from at least one of:

area-under-curve, a variation between autocorrelation coefficients, or a complexity of the autocorrelation function.

7. The method according to claim 1, wherein measuring one or more peak amplitudes comprises extracting a sequence of peak-amplitudes from the autocorrelation function using a peak detection algorithm.

8. The method according to claim 7, wherein analyzing the one or more peak amplitudes further comprises computing a strength of a monotone association between peak-amplitudes and corresponding lag times.

9. The method according to claim 1, wherein analyzing the one or more peak amplitudes and the one or more peak times utilizes a machine learning algorithm.

10. The method according to claim 1, wherein generating an alert to the user comprises displaying a result of the AF determination.

11. The method according to claim 10, further comprising displaying an AF probability.

12. The method according to claim 1, wherein measuring one or more peak amplitudes comprises measuring the amplitude of the first non-zero-lag peak in the autocorrelation function.

13. The method according to claim 1, wherein analyzing the one or more peak amplitudes further comprises one or more of:

computing variation between the one or more peak amplitudes, and computing complexity between the one or more peak amplitudes.

14. The method according to claim 1, wherein analyzing the one or more peak amplitudes and one or more peak times comprises comparing the one or more peak amplitudes and one or more peak times to respective threshold values.

15. The method according to claim 1, wherein analyzing the one or more peak times further comprises one or more of:

computing time intervals between the one or more peak times;

computing variation of time intervals between the one or more peak times;

or computing complexity of time intervals between the one or more peak times.

16. A system for detecting presence of atrial fibrillation, the system comprising:

at least one sensor for acquiring a series of images from a body part; and

a processor configured for extracting a time-varying signal representing a plethysmographic waveform from one or more channels of the series of images, for calculating an autocorrelation function of the plethysmographic waveform, measuring one or more peak amplitudes each corresponding to a height of a peak in the autocorrelation function, measuring one or more peak times each corresponding to a location of a peak in the autocorrelation function, analyzing the one or more peak amplitudes and the one or more peak times to produce an indication of atrial fibrillation, and generating an alert based on the indication of an atrial fibrillation condition.

17. A non-transitory computer-readable storage medium storing a set of instructions capable of being executed by a processor, that when executed by the processor causes the processor to:

acquire, using one or more sensors, a series of images from a body part;

extract a time-varying signal representing a plethysmographic waveform from one or more channels of the series of images;

calculate an autocorrelation function of the plethysmographic waveform;

measure one or more peak amplitudes each corresponding to a height of a peak in the autocorrelation function;

measure one or more peak times each corresponding to a location of a peak in the autocorrelation function;

analyze the one or more peak amplitudes and the one or more peak times to produce an indication of an atrial fibrillation condition;

and wherein the set of instructions, when executed by the processor, further causes the processor to generate an alert to a user based on the indication of an atrial fibrillation condition.