Claims:1. A system (10) to monitor Electrocardiography (ECG) signal of a user, wherein the system comprises:
one or more processors (20);
an input module (30) operable by the one or more processors (20), and configured to receive an input from one or more electrodes from one or more sources, wherein the input corresponds to Electrocardiography (ECG) signal;
a noise filtering module (40) operable by the one or more processors (20), and configured to eliminate at least one noise from the input retrieved by the input module (30);
a discrete wavelet transform module (60) operable by the one or more processors (20), and configured to generate at least one DWT coefficient of a pre-defined level;
a boundary detection module (55) operable by the one or more processors (20), and configured to segment the continues ECG signal into individual heart beats;
a fiducial points extraction module (50) operable by the one or more processors (20), and configured to extract one or more fiducial points from the Electrocardiography (ECG) signal, wherein the one or more fiducial points comprises at least one of P, Q, R, S, T, interval points comprising PR, QRS, QT, QTC, or a combination thereof,
wherein the at least one DWT coefficient is computed to generate a feedback to identify the corresponding one or more fiducial points from the input;
an ECG analysis module (70) operable by the one or more processors (20), and configured to:
classify the input into one or more categories upon analysing the Electrocardiography (ECG) signal using an analysis technique; and
analyse the interval points using a Phase space reconstruction (PSR) technique based on the one or more categories, to generate an analysis report; and
a suggestion module (80) operable by the one or more processors (20), and configured to generate a suggestion representative of at least one of a drug, a remedy, or a combination thereof based on the analysis report.
2. The system (10) as claimed in claim 1, wherein the at least one noise comprises one of powerline noise is removed by a notch filter, baseline noise is removed by a median filter, cutting-off the frequency of the ECG signal between 0.5 to 40 Hz by a Butterworth filter, or a combination thereof.
3. The system (10) as claimed in claim 1, wherein the one or more categories comprises at least one of a disease prone category comprising one of an atrial fibrillation, a bundle branch block, a myocardial infarction, a cardiomyopathy, hypertension or a combination thereof, or a healthy ECG category.
4. The system (10) as claimed in claim 1, comprising an alert generation module (90) operable by the one or more processors (20), and configured to generate an alert for at least one authorized entity at a pre-defined situation, wherein the pre-defined situation is identified based on the analysis report.
5. The system (10) as claimed in claim 1, comprising a representation module (100) operable by the one or more processors, and configured to represent the analysis report in a pre-defined format, wherein the pre-defined format comprises one of a graphical representation, a tabular representation, textual representation, or a combination thereof.
6. The system (10) as claimed in claim 1, comprising a storage medium (110) operatively coupled to the one or more processors (20), and configured to store data associated to the Electrocardiography (ECG) parameters of the user, wherein the storage medium comprises a cloud storage medium.
7. A method (500) for monitoring Electrocardiography (ECG) signal of a user comprising:
receiving, by an input module, an input from one or more electrodes from one or more sources, wherein the input corresponds to Electrocardiography (ECG) signal; (510)
eliminating, by a noise filtering module, at least one noise from the input retrieved; (520)
generating, by a discrete wavelet transform module, at least one DWT coefficient of a pre-defined level; (522)
segmenting, by a boundary detection module, the continues ECG signal into individual heart beats; (524)
extracting, by a fiducial extraction module, one or more fiducial points from the Electrocardiography (ECG) signal, wherein the one or more fiducial points comprises at least one of P, Q, R, S, T, interval points comprising PR, QRS, QT, QTC, or a combination thereof; (530)
wherein the at least one DWT coefficient is computed for generating feedback to identify the corresponding one or more fiducial points from the input; (540)
classifying, by an ECG analysis module, the input into one or more categories upon analysing the Electrocardiography (ECG) signal using an analysis technique; (550)
analysing, by the ECG analysis module, the interval points using a Phase space reconstruction (PSR) technique based on the one or more categories, for generating an analysis report; and (560)
generating, by a suggestion module, a suggestion representative of at least one of a drug, a remedy, or a combination thereof based on the analysis report. (570)
8. The method (500) as claimed in claim 7, wherein eliminating the at least one noise comprises eliminating one of powerline noise, baseline noise, cutting-off the frequency of the ECG signal between 0.5 to 40 Hz, or a combination thereof.
9. The method (500) as claimed in claim 7, wherein classifying the input into one or more categories comprises classifying the input into at least one of a disease prone category comprising one of an atrial fibrillation, a bundle branch block, a myocardial infarction, a cardiomyopathy, hypertension or a combination thereof, or a healthy ECG category.
10. The method (500) as claimed in claim 7, comprising:
generating, by an alert generation module, an alert for at least one authorized entity at a pre-defined situation, wherein the pre-defined situation is identified based on the analysis report; and
representing, by a representation module, the analysis report in a pre-defined format, wherein the pre-defined format comprises one of a graphical representation, a tabular representation, textual representation, or a combination thereof.
Dated this 04th day of October 2021

Signature

Harish Naidu
Patent Agent (IN/PA-2896)
Agent for the Applicant
, Description:FIELD OF INVENTION
[0001] Embodiments of the present disclosure relates to electrocardiography, and more particularly, to system and method to monitor electrocardiography (ECG) signal of a user.
BACKGROUND
[0002] Electrocardiography is the process of producing an electrocardiogram (ECG). ECG is a graph of voltage versus time of the electrical activity of the heart using electrodes placed on the skin. These electrodes detect the small electrical changes that are a consequence of cardiac muscle during each cardiac cycle (heartbeat). In a conventional approach, the ECG is performed at any required instances based on medical practitioner’s advice in order to analyse the functioning of cardiovascular system of a user. Also, the ECG is performed when there is any requirement based on medical condition of the user. However, in the conventional approach, the analysis of the ECG is performed manually upon observing characteristics of the wave in the ECG. Due to the human intervention during the analysis of the ECG, the analysed result is less accurate and less reliable. Also, the conventional system is slow as the time required to generate the ECG and analyse the same is quite lethargic. In addition, the user on whom the ECG is to be performed has to be present in a location where the apparatus is set up and also has to meet the expertise in person to obtain the analysis result, which makes the conventional approach more time consuming. Furthermore, the user is not regularly monitored and analysed for the cardiovascular problems.
[0003] Hence, there is a need for an improved system and method to monitor Electrocardiography (ECG) signal of a user to address the aforementioned issues.
BRIEF DESCRIPTION
[0004] In accordance with the present disclosure, a system to monitor Electrocardiography (ECG) signal of a user is provided. The system includes one or more processors. The system also includes an input module configured to receive an input from one or more electrodes from one or more sources, wherein the input corresponds to Electrocardiography (ECG) signal. The system also includes a noise filtering module configured to eliminate at least one noise from the input retrieved by the input module. The system also includes a discrete wavelet transform module configured to generate at least one DWT coefficient of a pre-defined level. The system also includes a boundary detection module configured to segment the continues ECG signal into individual heart beats. The system also includes a fiducial points extraction module configured to extract one or more fiducial points from the Electrocardiography (ECG) signal, wherein the one or more fiducial points comprises at least one of P, Q, R, S, T, interval points comprising PR, QRS, QT, QTC, or a combination thereof. The at least one DWT coefficient is computed to identify the corresponding one or more fiducial points from the input. The system also includes an ECG analysis module configured to classify the input into one or more categories upon analysing the Electrocardiography (ECG) signal using an analysis technique and to analyse the interval points using a Phase space reconstruction (PSR) technique based on the one or more categories, to generate an analysis report. The system also includes a suggestion module configured to generate a suggestion representative of at least one of a drug, a remedy, or a combination thereof based on the analysis report.
[0005] In accordance with the present disclosure, a method for monitoring Electrocardiography (ECG) signal of a user is provided. The method includes receiving an input from one or more electrodes from one or more sources, wherein the input corresponds to Electrocardiography (ECG) signal. The method also includes eliminating at least one noise from the input retrieved. The method also includes generating at least one DWT coefficient of a pre-defined level. The method also includes segmenting the continues ECG signal into individual heart beats. The method also includes extracting one or more fiducial points from the Electrocardiography (ECG) signal, wherein the one or more fiducial points comprises at least one of P, Q, R, S, T, interval points comprising PR, QRS, QT, QTC, or a combination thereof. The method also includes computing the at least one DWT coefficient of a pre-defined level for identifying the corresponding one or more fiducial points from the input. The method also includes classifying the input into one or more categories upon analysing the Electrocardiography (ECG) signal using an analysis technique. The method also includes analysing the interval points using a Phase space reconstruction (PSR) technique based on the one or more categories, for generating an analysis report. The method also includes generating a suggestion representative of at least one of a drug, a remedy, or a combination thereof based on the analysis report.
[0006] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.
BRIEF DESCRIPTION OF DRAWINGS
The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0007] FIG. 1 is a block diagram representation of a system to monitor Electrocardiography (ECG) signal of a user in accordance with an embodiment of the present disclosure;
[0008] FIG. 2 is a block diagram representation of an exemplary embodiment of the system coupled to an ECG device of FIG. 1 in accordance with an embodiment of the present disclosure;
[0009] FIG. 3 is a block diagram representation of a cloud processing module of FIG. 1 in accordance with an embodiment of the present disclosure;
[0010] FIG. 4 is a block diagram representation of a filtering process of FIG. 1 in accordance with an embodiment of the present disclosure;
[0011] FIG. 5 is a block diagram representation of a BDFE module of FIG. 1 in accordance with an embodiment of the present disclosure;
[0012] FIG. 6 is a block diagram representation of a PSR module of FIG. 1 in accordance with an embodiment of the present disclosure;
[0013] FIGs. 7a and 7b represent PSR plots for healthy and un-healthy ECG signals respectively of FIG. 1 in accordance with an embodiment of the present disclosure; and
[0014] FIG. 8 is a flow chart representing steps involved in a method for monitoring Electrocardiography (ECG) signal of a user in accordance with an embodiment of the present disclosure.
[0015] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0016] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as would normally occur to those skilled in the art are to be construed as being within the scope of the present invention.
[0017] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive thereof.
[0018] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0020] Embodiments of the present disclosure relates to system and method for monitoring Electrocardiography (ECG) signal of a user. As used herein, the term ‘Electrocardiography’ is defined as a process of producing an electrocardiogram (ECG). Also, the term ‘ECG’ is defined as a graph of voltage versus time of the electrical activity of the heart using electrodes placed on the skin.
[0021] FIG. 1 is a block diagram representation of a system to monitor Electrocardiography (ECG) signal of a user in accordance with an embodiment of the present disclosure. The system (10) includes one or more processors (20). The system (10) also includes an input module (30) configured to receive an input from one or more electrodes from one or more sources, wherein the input corresponds to Electrocardiography (ECG) signal. In one embodiment, the one or more sources may be at least one of an internal source, an external source, or a combination thereof. In another embodiment, the electrical signal from the one or more electrodes may be directly transmitted to the system. In yet another embodiment, the electrical signal from the one or more electrodes may be stored in a storage unit and may be further transmitted or retrieved as input from the input module (30). In such embodiment, the storage unit may be a remote storage unit such as a cloud storage unit.
[0022] The system (10) also includes a noise filtering module (40) configured to eliminate at least one noise from the input retrieved by the input module (30). In one embodiment, the at least one noise may include one of powerline noise removed by a notch filter, baseline noise removed by a median filter, cutting-off the frequency of the ECG signal between 0.5 to 40 Hz by a Butterworth filter, or a combination thereof. In one specific embodiment, the noise filtering module (40) may be operatively coupled to one or more filters to eliminate the at least one noise. In such embodiment, the noise filtering module (40) may generate a signal to enable an operation of at least one of the one or more filters for eliminating the at least one noise.
[0023] Furthermore, the system (10) includes a fiducial extraction module (50) configured to extract one or more fiducial points from the Electrocardiography (ECG) signal, wherein the one or more fiducial points comprises at least one of P, Q, R, S, T, interval points comprising PR, QRS, QT, QTC, or a combination thereof. In one specific embodiment, the system may include a boundary detection module (55) which may be configured to segment the continues ECG signal into individual heart beats. and the system may further include a feature extraction module (58) which may be configured to extract the fiducial points like P, Q, R, S and T information and intervals like PR, QRS, QT and QTC intervals.
[0024] The system (10) also includes a discrete wavelet transform module (60) configured to generate at least one DWT coefficient of a pre-defined level, wherein the at least one DWT coefficient is computed to generate a feedback to identify the corresponding one or more fiducial points from the input. In one exemplary embodiment, the DWT module may include a filter bank structure with cascaded high pass and low pass filters. In such embodiment, the DWT controller generates DWT coefficients up to 5th level. In one specific embodiment, 3rd level DWT coefficients are used in Boundary detection module.
[0025] In one exemplary embodiment, first R peaks are identified and then the boundaries are calculated using the detected R peaks. After the Boundary detection module segments the data, the main features of each beat are detected using Feature extraction module. The Feature extraction module uses 3rd level DWT coefficients to find QRS information and locations associated to the QRS. Further, the 5th level DWT coefficients may be used to find P, T wave locations.
[0026] The system (10) also includes an ECG analysis module (70) configured to classify the input into one or more categories upon analysing the Electrocardiography (ECG) signal using an analysis technique. In one embodiment, the one or more categories may include at least one of a disease prone category comprising one of an atrial fibrillation, a bundle branch block, a myocardial infarction, a cardiomyopathy, hypertension or a combination thereof, or a healthy ECG category.
[0027] The ECG analysis module (70) is also configured to analyse the interval points using a Phase space reconstruction (PSR) technique based on the one or more categories, to generate an analysis report.
[0028] Furthermore, the system (10) includes a suggestion module (80) configured to generate a suggestion representative of at least one of a drug, a remedy, or a combination thereof based on the analysis report. In one embodiment, the suggestion may be generated using one of an artificial intelligence technique, a machine learning technique, or a combination thereof. As used herein, the term ‘artificial intelligence technique’ may be defined as a kind of intelligence demonstrated by machines, as opposed to the natural intelligence displayed by humans or animals. Also, ‘machine learning technique’ is defined as study of computer algorithms that improve the system automatically through experience and by the use of data.
[0029] In operation, a bot may be created by the system (10) which may be configured to analyse the interval points using the said techniques, wherein the bot may train itself for a better analysis study post every analysis of one of the interval points, the input, or a combination thereof.
[0030] In one exemplary embodiment, the system (10) may further include an alert generation module (90) configured to generate an alert for at least one authorized entity at a pre-defined situation, wherein the pre-defined situation is identified based on the analysis report. In one embodiment, the alert may be in one of a text form, an audio form, a video form, a multimedia form, or a combination thereof. In one specific embodiment, the alert may be in a form of a notification.
[0031] In another exemplary embodiment, a representation module (100) configured to represent the analysis report in a pre-defined format, wherein the pre-defined format comprises one of a graphical representation, a tabular representation, textual representation, or a combination thereof.
[0032] In one specific embodiment, the system (10) may further include a storage medium (110) configured to store data associated to the Electrocardiography (ECG) parameters of the user. In such embodiment, the storage medium may be a cloud storage medium.
[0033] FIG. 2 is a block diagram representation of an exemplary embodiment of the system (120) coupled to an ECG device (130) of FIG. 1 in accordance with an embodiment of the present disclosure. The system (120) of FIG. 2 is substantially similar to a system (10) of FIG. 1. The ECG device (130) is configured from a mobile app using a Bluetooth medium via a user device (140). A plurality of electrodes from the ECG device (130) which is coupled to a user (150) will be connected to the system (120) and then the ECG device (130) starts recording the data associated to the ECG readings of the user (150). After recording the ECG device (130) transmits the data to a cloud server (160). In one specific embodiment, the cloud server may be developed based on Django (Python) web framework with MySQL as Database. Furthermore, the data from the cloud server (160) may be extracted by the user device (140) for further analysis of the data or may be analysed on the server using a BD and FE processing module (170) and an API (180). In one embodiment, the API may be based on Django (Python) web framework with MySQL as Database.
[0034] Upon analysis, the data may be viewed on the user device (140). The cloud server (160) may be operatively coupled to the user device (140) via a Wi-Fi medium. Also, the user device (140) may be operatively coupled to the ECG device (130) via one of a Bluetooth medium, a Wi-Fi medium, a BLE medium, or the like. In addition, the ECG device (130) is operatively coupled to the cloud server (160) via the Wi-Fi medium in order to transmit the data from the ECG device (130) to the cloud server (160)
[0035] In operation, the user (150) configures the ECG device (130) upon integrating the same using an application installed on the user device (140) to operate, monitor and manage the ECG of the user (150) remotely. All the analysed data is stored on the cloud server (160) which may provide access to one or more authorized users upon obtaining a permission to access the data.
[0036] Turning to FIGs. 3 and 4, FIG. 3 is a block diagram representation of a cloud processing module (190) of FIG. 1 in accordance with an embodiment of the present disclosure. FIG. 4 is a block diagram representation of a filtering process (290) of FIG. 1 in accordance with an embodiment of the present disclosure. The ECG device (130) (as shown in FIG. 2) saves and transmits the data associated to the ECG of the user in binary format (200) to the cloud server (160) (as shown in FIG. 2). The first step in the cloud processing module (190) which is housed on the cloud server (160) is to filter the data and de-noise to process the data further.
[0037] Initially, raw ECG signals from the ECG device (130) are first filtered (210) using Butterworth filter with cut-off frequencies as 0.5 Hz and 40 Hz as most of the ECG signal frequencies lies in this range in step 300 and 310. Next step is to remove the powerline noise with a notch filter around 50/60 Hz in step 320. These filtered signals are then processed through median filters to remove the Baseline noise with is generated because of body movements in step 330. These final de-noised signals are ready for further processing in step 340.
[0038] The filtering (210) is initially processed at a binary level (240) and using the BD FE module (250). Data from one or more filters and the BD FE module are obtained in .csv format in step 220 and 260. Furthermore, the post filtered data 230 and post_bdfe data 270 are stored in a database 280 for further reference of the data associated to the ECG of the user. The processing and analysis of the data is performed by the BDFE module which is disclosed as below.
[0039] FIG. 5 is a block diagram representation of a BDFE module (350) of FIG. 1 in accordance with an embodiment of the present disclosure. It should be noted that a BD FE processing module (170) of FIG. 2, BD FE module (250) of FIG. 3 are substantially similar to the BDFE module of FIG. 5. The de-noised signals (360), which is de-noised in step 340 of FIG. 2 are transmitted to the BD (Boundary detection) module (350). The BD module (350) segments the continuous ECG signal into beats and then these individual beats are transmitted to a feature extraction (FE) block (380). The FE block extracts the fiducial points like P, Q, R, S and T information and intervals like PR, QRS, QT and QTC intervals. Discrete wavelet transforms (DWT) are used in the BD module (350) and the FE module (380) upon receiving the DWT co-efficient from a DWT controller (390). DWT has filter bank structure with cascaded with cascaded high pass and low pass filters. In this module, the DWT controller (390) generates DWT coefficients up to 5th level. 3rd level DWT coefficients are used in a Boundary detection module (370). In this approach first R peaks are identified and then the boundaries are calculated using the detected R peaks. Further, as the BD module (370) segments the data, the main features of each beat are detected using the FE module (380). The FE module (380) uses 3rd level DWT coefficients to find QRS information and its locations and the 5th level DWT coefficients to find P, T wave locations. After getting all the standard features including HR, all these data and features are saved in database using API call.
[0040] Furthermore, any authorized entity such as a particular user, a doctor, a caretaker, or the like may view the user’s data using the mobile app. One or more set of instructions which are used in the system may be tested and verified using different largely publicly available and medically accepted databases such as, but not limited to, PTBDB, MIT-BIH, PPG-DaLiA datasets, or the like. All these datasets consist of ECG data recorded from patients having different diseases and doing different daily life activities.
[0041] FIG. 6 is a block diagram representation of a PSR module (410) of FIG. 1 in accordance with an embodiment of the present disclosure. The cloud processing may further include a classification module included after the feature extraction module (380). classification module may be configured to detect and classify the recorded ECG data into healthy or unhealthy categories upon detection of some disease. classification module is capable of detecting healthy, atrial fibrillation, bundle branch block, myocardial infarction, cardiomyopathy and hypertension. classification module uses the concept of Phase space reconstruction (PSR) on localized features (420) such as PR, QRS and QT interval.
[0042] In operation, the ECG data is extracted from an ECG database (430) which may be in a form of one or more arrays. The extracted data is first processed by BDFE module (370) to extract PR interval (440), QRS interval (450) and QT interval (460) which may be in the form of arrays. Each of these is considered as localized feature and 20 consecutive such features will be taken for PSR analysis in step 470. In PSR technique (420), all of the 20 localized features will be considered as single signal. This signal is then delayed and may be plotted original vs delayed version of the signal for reference and analysis purpose. These PSR plots will have closed contour for healthy signals and random plot for un-healthy signals which is disclosed as below.
[0043] FIGs. 7a and 7b represent PSR plots for healthy (480) and un-healthy (490) ECG signals respectively of FIG. 1 in accordance with an embodiment of the present disclosure. The PSR plots is considered as an image and coefficient of variation (CV) plot which may be obtained by counting the number pixels that has a value in the plot. This process is termed as black box counting. The chaotic nature of ECG (as shown in FIG. 7b) disease results in higher count of black boxes than that of healthy ECG signal (as shown in FIG. 7a) due to the spread of trajectories. Finally, thresholds have been extracted from CV plots for different disease categories. Using these thresholds, The ECG signals can be classified into healthy signals (480) and unhealthy signals (490). The particular disease also can be detected in this approach. In one specific embodiment, the PSR plots may be tested and verified using the PTBDB database and may further be deployed in the cloud server (160) (as shown in FIG. 2) for further review for the one or more entities.
[0044] In operation, the system (10) may work in four major step as disclosed below:
Step1: Lead Placement: where multiple patches are placed at corresponding parts of the user’s body, and a first end of each of the multiple electrodes are connected to the corresponding patches, and a second end of each of the multiple patched are connected to the ECG device (130);
Step 2: device configuration: a wireless medium such as the Bluetooth medium is turned ‘ON’ on the ECG device (130), further, the authorized entity can Login to the application on the computing device in order to connect the ECG device (130) to the application; Consequently, the ECG device is configured using one or more details such as the Wi-Fi details, the user details, or the like; In one embodiment, the authorized entity can login to the application upon providing one or more login credentials such as user name, password, or the like.
Step 3: Record and Upload Data: the ECG device (130) may include a record button which upon pressing can enable the recording of the ECG signal; consequently, the recorded ECG signal may be uploaded to the cloud server (160) upon pressing an upload button on the ECG device (130);
[0045] Step 4: View Data: the authorized entity can login to the application from any of the computing device and may select any of a plurality of user’s details whose data needs to be viewed; start time and end time may also be entered to search the exact required data of the corresponding user; consequently, the processed data can be viewed in the required format.
[0046] FIG. 8 is a flow chart representing steps involved in a method (500) for monitoring Electrocardiography (ECG) signal of a user in accordance with an embodiment of the present disclosure. The method (500) includes receiving an input from one or more electrodes from one or more sources, wherein the input corresponds to Electrocardiography (ECG) signal in step 510. In one embodiment, receiving the input may include receiving the input by an input module.
[0047] The method (500) also includes eliminating at least one noise from the input retrieved in step 520. In one embodiment, eliminating the at least one noise may include eliminating the at least one noise by a noise filtering module. In one exemplary embodiment, eliminating the at least one noise may include eliminating one of powerline noise, baseline noise, cutting-off the frequency of the ECG signal between 0.5 to 40 Hz, or a combination thereof.
[0048] Furthermore, the method (500) includes extracting one or more fiducial points from the Electrocardiography (ECG) signal in step 530. The one or more fiducial points includes at least one of P, Q, R, S, T, interval points comprising PR, QRS, QT, QTC, or a combination thereof. In one embodiment, extracting the one or more fiducial points may include extracting the one or more fiducial points by a fiducial extraction module.
[0049] The method (500) also includes generating at least one DWT coefficient of a pre-defined level, wherein the at least one DWT coefficient is computed for generating a feedback to identify the corresponding one or more fiducial points from the input in step 540. In one embodiment, generating the at least one DWT coefficient may include generating the at least one DWT coefficient by a discrete wavelet transform module.
[0050] The method (500) also includes classifying the input into one or more categories upon analysing the Electrocardiography (ECG) signal using an analysis technique in step 550. In one embodiment, classifying the input may include classifying the input by an ECG analysis module. In one exemplary embodiment, classifying the input into one or more categories may include classifying the input into at least one of a disease prone category comprising one of an atrial fibrillation, a bundle branch block, a myocardial infarction, a cardiomyopathy, hypertension or a combination thereof, or a healthy ECG category.
[0051] The method (500) further includes analysing the interval points using a Phase space reconstruction (PSR) technique based on the one or more categories, for generating an analysis report in step 560. In one embodiment, analysing the interval points may include analysing the interval points by the ECG analysis module.
[0052] Furthermore, the method (500) includes generating a suggestion representative of at least one of a drug, a remedy, or a combination thereof based on the analysis report in step 570. In one embodiment, generating the suggestion may include generating the suggestion by a suggestion module.
[0053] In one exemplary embodiment, the method (500) may further include generating an alert for at least one authorized entity at a pre-defined situation, wherein the pre-defined situation is identified based on the analysis report. In such embodiment, generating the alert may include generating the alert by an alert generation module.
[0054] In another exemplary embodiment, the method (500) may further include representing the analysis report in a pre-defined format, wherein the pre-defined format may include one of a graphical representation, a tabular representation, textual representation, or a combination thereof. In such embodiment, representing the analysis report may include representing the analysis report by a representation module.
[0055] It should be noted that all the elements, modules, devices, and the like disclosed in FIGs. 1-7 are substantially similar to those disclosed in FIG. 8; henceforth all the corresponding embodiments disclosed in FIGs. 1-7 holds good for FIG. 8.
[0056] Various embodiments of the present disclosure enable the system to analyse and monitor the ECG signal in either real time or at any required instant, either by retrieving from the cloud platform or performing the same on the cloud platform. In addition, any existing ECG device which may be IoT enabled can be integrated with the application and the retrieved signal may be used to analyse the ECG readings.
[0057] Furthermore, since the data is stored on the cloud, the same can be easily accessed at any point of time from any location and any computing device. Also, since the analysis and diagnosis of the ECG signal do not require bulky apparatus, the system becomes portable and easy to operate. Due to lesser number of components being used, the system is cost effective and more user friendly and more reliable.
[0058] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
[0059] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, the order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.