WO2011061606A2 - Methods and systems for atrial fibrillation detection - Google Patents

Abstract

Described are computer-based methods and apparatuses, including computer program products, for automated atrial fibrillation detection. Based on morphology analysis, atrial beats are recognized and used for R-R intervals analysis. The invented system creates R-R interval classes and estimates irregularity indicator value (deviation) for each class. The total average R-R intervals deviation for all analyzed atrial beats is calculated by weighted averaging of the irregularity indicator values of all classes, where the weight values are equal to the class sizes.

Description

Inventor: Marek Dziubinski

Attorney's Docket No.: MED-007PC

METHODS AND SYSTEMS FOR ATRIAL FIBRILLATION DETECTION BACKGROUND

Automated analysis of digitized electrocardiogram (ECG) signals has various applications. Algorithms operating in real-time with the ability to deal with lead- limited signals are mostly useful in monitoring systems, such as Home Tele Care (HTC) applications, outpatient monitoring systems, etc. In lead-limited ECG analysis, it is difficult to distinguish between parasite peaks and QRS complexes due to the limited number of additional leads, which are typically used for reference or comparison. The benefit of using the limited lead ECG is its simplicity, e.g., mounting only a few electrodes (2 or 3) is not complicated and provides more freedom in choosing areas of the body to attach the sensors. The limited number of leads is, especially useful in long- term monitoring applications, because decreased number of electrodes reduces skin irritation, and every few days patients can change the electrodes placement by themselves.

Automated interpretation of digital electrocardiographic signals has several important applications, among which the most popular are: automated arrhythmia diagnostics and QRS complexes classification, automated ST segment elevation and depression measurements and automated intervals measurements, including QT / QTc interval assessment. FIELD OF THE INVENTION

The present invention relates generally to computer-based methods and apparatuses, including computer program products, for automated ECG interpretation and/or assessment. SUMMARY

Analysis of a lead-limited ECG and detection of atrial fibrillation (Afib) episodes is difficult because the signals may contain a large number of ambiguities, i.e., signals from various patients may be substantially different. When disturbances occur in these signals it is easy to confuse parasite impulses or peaks with the impulses generated by the heart. Therefore, the lead-limited ECG analysis presents a great challenge from an automated analysis point of view.

The present system and method provide for ECG signal analysis having the ability to automatically identify atrial fibrillation episodes from an ECG signal gathered from a limited number of leads.

Increase of the ST elevation / depression accuracy allows for more effective ischemic problems detection. Normally ST measurement is performed at fixed interval, relative to R point. Heart rate changes, however affect the T wave position, where T wave moves towards R point with rate increase or moves away from the R point, when the rate decreases. QT interval monitoring allows for accurate evaluation of T wave position relative to R point, thus utilizing the T wave position information derived from QT interval measurements in determining J point position results in improved ST elevation / depression measurements accuracy.

BRIEF DESCRIPTION OF THE DRAWINGS

The foregoing and other objects, features and advantages will be apparent from the following more particular description of embodiments, as illustrated in the accompanying drawings in which like reference characters refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments.

FIG. 1 is a flow-chart of automatic atrial fibrillation detection algorithm;

FIG. 2 is a flow-chart illustration of a method for automated atrial fibrillation detection;

FIG. 3 is a flow-chart of automated ST deviation measurements;

FIG. 4 is a flow-chart illustration of a method for automated atrial fibrillation detection; and

FIGS. 5A-5B are illustrations of T wave position changes caused by heart rate changes.

DETAILED DESCRIPTION

FIG. 1 is a flow-chart illustration of the system 100 diagram for providing automated detection of atrial fibrillation episodes. The 'QRS detector' 101 detects QRS complexes in the ECG block. The 'QRS classifier' 102 based on beats' shape analysis, representing beats morphology, is responsible for distinguishing between atrial beats (e.g., narrow QRS complexes) and ventricular beats (e.g., wide QRS complexes) and artifacts (e.g., QRS complexes with disturbed shape, or surrounded by high-level noise). The 'QRS similarity estimator' 103 additionally verifies the morphology classification results for beats initially classified as atrial, by comparing these beats to each other. If the similarity indicator value exceeds a predefined threshold, the atrial beats are fed to the 'R-R intervals prematurity classifier' 104. The 'R-R intervals prematurity classifier' 104 utilizes the recognized atrial beats and is responsible for distinguishing between supraventricular premature beats (SV), normal beats (N) of regular heart rate, and missed beats (MB), with R-R intervals significantly lower than the leading heart rate average intervals. The 'R-R intervals irregularity estimator 105 creates five R-R interval subsets (A through E), containing:

A. intervals between SV and SV beat pairs 106; B. intervals between N and SV beat pairs 107;

C. intervals between SV and N beat pairs 108;

D. intervals between N and N beat pairs 109;

E. intervals between N and MB beat pairs 1 10.

The 'intervals deviation estimators' 111, 112, 113, 114, and 1 15 calculate intervals deviation for each subset. The average intervals deviation is calculated by the 'set-size-weighted averaged deviation estimator' 1 16, where the subset size is a weight parameter used in calculating the average deviation. If the average intervals deviation exceeds predefined threshold, the 'Afib detection module' 117 recognizes the atrial beats set as an atrial fibrillation episode.

FIG. 2 is a flowchart 200 illustration of a method for automated atrial fibrillation detection. The method includes, but is not limited to, the following steps:

1. providing digitized ECG signal block 201 ;

2. detecting QRS complexes for the provided block 202;

3. distinguishing between atrial beats and other beats, including artifacts 203;

4. generating intervals subsets between atrial beats, each subset for the same annotation pair intervals 204. The pair types include, but are not limited to:

• supraventricular + supraventricular,

• normal + supraventricular,

• supraventricular + normal,

• normal + normal,

• normal + missed beat.

5. calculating intervals deviation for each subset 205;

6. calculating subset-size-weighted average deviation for all atrial beats 206;

7. detecting atrial fibrillation episodes if the deviation exceeds a predefined threshold 207.

FIG. 3 is a flow-chart illustration of the system 300 diagram for providing automated ST deviation measurements. The 'QRS detector' 301 detects QRS complexes in the ECG block. The 'QRS classifier' 302 based on beats' shape analysis, representing beats morphology, is responsible for distinguishing between atrial beats (e.g., narrow QRS complexes) and ventricular beats (e.g., wide QRS complexes) and artifacts (QRS complexes with disturbed shape, or surrounded by high-level noise). The 'PQRST similarity estimator' 303 additionally verifies the QRS and T wave morphology classification results for beats initially classified as atrial, by comparing these beats to each other. If the similarity indicator value exceeds a predefined threshold, the atrial beats are fed to 'T wave shift estimator' module 304. The module 304 utilizes reference PQRST waveform for which the QT interval has been measured and J point has been established. The algorithm calculates QT interval variability with regard to the reference PQRST waveform. The time domain T wave shift is calculated with the use of modified AMDF (Average Magnitude Difference Function) technique, i.e., it is in fact inverted and normalized ASDF (Average Squared Difference Function). Both are popular methods used in speech processing.

The algorithm utilizes time domain shifted difference signal of T wave. Using the difference signal eliminates baseline level influence, because this influence may affect similarity calculations carried out by a matching function. The T wave matching function of the algorithm can be expressed in the following way:

where:

p - matching curve of the time domain shifted T wave difference signals,

- number of samples of the compared T waves

1,...,2 - N - 1

s_l , s₂ - compared T waves. The compared ECG periods are recursively averaged periods. Averaging allows for decreasing influence of parasite noise and disturbances.

Applying parabolic interpolation on the similarity curve, i.e. fitting parabola to the maximum sample and the surrounding samples allows for achieving T wave shift accuracy significantly exceeding the ECG signal sampling rate limitations: c = v max

^VR ~ ^VL

2^■ a

max max dv

where:

vmax - value of the maximum sample of the similarity curve,

VL > ^VR ~ value of the left and right sample surrounding the maximum,

I _dv - correction value of the maximum sample index,

*_max - index of the maximum sample of the similarity curve, ^zmax " approximated index with the use of parabolic interpolation.

The ST measurement point is corrected 305 and the ST deviation is calculated 306 based on the corrected measurement point.

FIG. 4 is a flowchart 400 illustration of a method for automated ST deviation measurement. The method includes, but is not limited to, the following steps:

1. providing digitized ECG signal block 401 ;

2. detecting QRS complexes for the provided block 402;

3. distinguishing between atrial beats and other beats, including artifacts 403 ; a. collecting the reference atrial PQRST complex waveform 403 a;

4. calculating T wave shift of the current PQRST complex relative to the reference waveform 404,

5. Adjusting the ST measurement point position 405,

6. Calculating ST deviation based on the corrected measurement point 406,

FIGS. 5A-5B are illustrations of T wave position change caused by heart rate increase. It can be observed that with the increase of heart rate (FIG. 5B), the RJ interval is shortened, while for slower rate, the RJ interval is extended. It can also be observed in the figure, that the heart rate changes influence QT interval as well, where the changes correspond with the RJ interval changes.

The above-described system and method can be implemented in digital electronic circuitry, in computer hardware, firmware, and/or software. The

implementation can be as a computer program product (i.e., a computer program tangibly embodied in an information carrier). The implementation can, for example, be in a machine-readable storage device and/or in a propagated signal, for execution by, or to control the operation of, data processing apparatus. The implementation can, for example, be a programmable processor, a computer, and/or multiple computers.

A computer program can be written in any form of programming language, including compiled and/or interpreted languages, and the computer program can be deployed in any form, including as a stand-alone program or as a subroutine, element, and/or other unit suitable for use in a computing environment. A computer program can be deployed to be executed on one computer or on multiple computers at one site.

Method steps can be performed by one or more programmable processors executing a computer program to perform functions of the invention by operating on input data and generating output. Method steps can also be performed by and an apparatus can be implemented as special purpose logic circuitry. The circuitry can, for example, be a FPGA (field programmable gate array) and/or an ASIC

(application-specific integrated circuit). Modules, subroutines, and software agents can refer to portions of the computer program, the processor, the special circuitry, software, and/or hardware that implements that functionality.

Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor receives instructions and data from a read-only memory or a random access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer can include, can be operatively coupled to receive data from and/or transfer data to one or more mass storage devices for storing data (e.g., magnetic, magneto-optical disks, or optical disks).

Data transmission and instructions can also occur over a communications network. Information carriers suitable for embodying computer program instructions and data include all forms of non- volatile memory, including by way of example semiconductor memory devices. The information carriers can, for example, be

EPROM, EEPROM, flash memory devices, magnetic disks, internal hard disks, removable disks, magneto-optical disks, CD-ROM, and/or DVD-ROM disks. The processor and the memory can be supplemented by, and/or incorporated in special purpose logic circuitry.

To provide for interaction with a user, the above described techniques can be implemented on a computer having a display device. The display device can, for example, be a cathode ray tube (CRT) and/or a liquid crystal display (LCD) monitor. The interaction with a user can, for example, be a display of information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer (e.g., interact with a user interface element). Other kinds of devices can be used to provide for interaction with a user. Other devices can, for example, be feedback provided to the user in any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback). Input from the user can, for example, be received in any form, including acoustic, speech, and/or tactile input.

The above described techniques can be implemented in a distributed computing system that includes a back-end component. The back-end component can, for example, be a data server, a middleware component, and/or an application server. The above described techniques can be implemented in a distributing computing system that includes a front-end component. The front-end component can, for example, be a client computer having a graphical user interface, a Web browser through which a user can interact with an example implementation, and/or other graphical user interfaces for a transmitting device. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), the Internet, wired networks, and/or wireless networks.

The system can include clients and servers. A client and a server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Packet-based networks can include, for example, the Internet, a carrier internet protocol (IP) network (e.g., local area network (LAN), wide area network (WAN), campus area network (CAN), metropolitan area network (MAN), home area network (HAN)), a private IP network, an IP private branch exchange (IPBX), a wireless network (e.g., radio access network (RAN), 802.11 network, 802.16 network, general packet radio service (GPRS) network, HiperLAN), and/or other packet-based networks. Circuit-based networks can include, for example, the public switched telephone network (PSTN), a private branch exchange (PBX), a wireless network (e.g., RAN, bluetooth, code-division multiple access (CDMA) network, time division multiple access (TDMA) network, global system for mobile communications (GSM) network), and/or other circuit-based networks. The transmitting device can include, for example, a computer, a computer with a browser device, a telephone, an IP phone, a mobile device (e.g., cellular phone, personal digital assistant (PDA) device, laptop computer, electronic mail device), and/or other communication devices. The browser device includes, for example, a computer (e.g., desktop computer, laptop computer) with a world wide web browser (e.g., Microsoft® Internet Explorer® available from Microsoft Corporation, Mozilla® Firefox available from Mozilla Corporation). The mobile computing device includes, for example, a Blackberry®.

Comprise, include, and/or plural forms of each are open ended and include the listed parts and can include additional parts that are not listed. And/or is open ended and includes one or more of the listed parts and combinations of the listed parts.

One skilled in the art will realize the invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The foregoing embodiments are therefore to be considered in all respects illustrative rather than limiting of the invention described herein. Scope of the invention is thus indicated by the appended claims, rather than by the foregoing description, and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

Claims

claimed is:

A system for atrial fibrillation detection based on lead-limited ECG signal analysis, the system comprising:

a QRS detection module for detection of QRS complexes;

a QRS classification module for distinguishing between atrial beats and other types of beats;

a R-R intervals prematurity classifier for generating atrial beat classes; an intervals irregularity estimator for calculating R-R intervals deviation for each class;

an averaged intervals deviation estimator for calculating total average deviation for all intervals classes; and

an atrial fibrillation detection decision module for detection of atrial fibrillation episodes.

The system of Claim 1, wherein the R-R intervals prematurity classifier recognizes supraventricular premature beat intervals, normal beat intervals of regular heart rate, and missed beat intervals, with R-R intervals significantly lower than the leading heart rate average intervals.

The system of Claim 1 , wherein the R-R intervals irregularity estimator calculates the intervals irregularity separately for intervals between

supraventricular and supravantricular beat-pairs, between normal and supraventricular beat-pairs, between supraventricular and normal beat-pairs, between normal and normal beat-pairs and between normal and missed beat- pairs. The system of Claim 3, wherein the averaged intervals deviation is calculated by weighted averaging of R-R intervals for all beat-pair classes.

The system of Claim 4, wherein the weighs values are equal to beat-pair classes sizes.

A method for automated atrial fibrillation detection based on a lead-limited ECG signal analysis, the method comprising the steps of:

providing lead-limited digitized ECG signal block;

detecting QRS complexes;

distinguishing between atrial beats and other beats;

generating intervals subsets for intervals between atrial beats pairs; calculating intervals deviation for each subset;

calculating a total subset-size-weighted average intervals deviation for all atrial beats; and

detecting atrial fibrillation episodes for the intervals deviation exceeding predefined threshold.

A method of Claim 6, wherein each subset is composed of defined annotation pairs.

A method of Claim 7, wherein the defined annotation pairs include:

- supraventricular + supraventricular pairs,

- normal + supraventricular pairs,

- supraventricular + normal pairs,

- normal + normal pairs, and/or

- normal + missed beat pairs. A system for ST segment deviation measurements utilizing QT changes information, the system comprising:

a QRS detection module for detection of QRS complexes; a QRS classification module for distinguishing between atrial beats and other types of beats;

a PQRST complex similarity estimation module for rejecting distorted beats;

T wave shift calculation module for calculating T wave position change relative to a reference PQRST complex; and

ST deviation calculation module utilizing T wave shift information in correcting J point position.

The system of Claim 9, wherein the T wave shift is calculated with the use of inverted Average Squared Difference Function algorithm, producing a similarity curve. 1. The system of Claim 10, wherein high accuracy of the T wave shift calculations is obtained by using parabolic interpolation of the similarity curve.

A method for ST segment deviation measurements utilizing QT changes information, the method comprising the steps of:

providing lead-limited digitized ECG signal block;

detecting QRS complexes;

distinguishing between atrial beats and other beats;

collecting reference PQRST complex and determining reference J point; 1 calculating T wave shift of all incoming beats relative to the reference PQRST complex; calculating modified J point positions for all incoming beats, based on the T wave shift intervals; and

calculating ST deviation values at modified J points position.