A method for determining electrolyte imbalance of a user and an electronic device thereof

Abstract

The present disclosure relates to a method and an electronic device for determining electrolyte imbalance of a user. The method comprises receiving a Photoplethysmogram (PPG) data comprising a plurality of PPG features. The method further comprises identifying one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical electrocardiogram (ECG) features with the plurality of PPG features. Thereafter, the method comprises determining an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.

Description

A METHOD FOR DETERMINING ELECTROLYTE IMBALANCE OF A USER AND AN ELECTRONIC DEVICE THEREOF

[0001] The present disclosure relates generally to the field of electronic devices. In particular the present disclosure relates to determining wellness of a user using a wearable device. More particularly, the present disclosure relates to method and electronic device for determining electrolyte imbalance of a user.

[0002] The following description of the related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section is used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of the prior art.

[0003] Electrolyte imbalance is a prevalent health issue that can arise from various factors, affecting approximately one in five individuals without their awareness. Electrolytes are crucial nutrients that facilitate numerous bodily functions, including nerve transmission, muscle contraction, and the regulation of fluid balance. They enable electrical signaling throughout the body, which is vital for maintaining optimal health. Despite their importance, many people remain oblivious to their electrolyte levels and the need for regular monitoring of the same, leading to potential health complications such as disrupted heart rhythms, dizziness, and fatigue.

[0004] Current solutions for monitoring electrolyte levels primarily focus on on-demand methods, such as portable dehydration monitoring systems that analyze heart rate variability (HRV) and urine color. Further, the current solution has notably explored monitoring potassium levels through electrocardiogram (ECG) data, however, these methods are limited to sporadic checks rather than continuous monitoring. This lack of continuous assessment significantly diminishes usability in real-world scenarios where proactive health management is essential. Furthermore, existing solutions do not adequately address the calibration of ECG data with data from other sensors to provide a comprehensive score for electrolyte balance.

[0005] Furthermore, methods, such as blood sampling for electrolyte concentration analysis, are time-consuming and often impractical, as users may not recognize when testing is necessary. Moreover, sensor (such as ECG sensor, PPG sensor, etc.) based solutions are typically reactive rather than preventive, failing to offer personalized recommendations for maintaining electrolyte balance.

[0006] Also, currently there is no solution that continuously tracks electrolyte levels and alerts users by indicating electrolyte imbalances before they lead to serious health issues. Thus, it is evident that the limitations of current technologies underscore the necessity for a novel solution capable of continuously monitoring electrolyte levels and providing timely alerts in case of electrolyte imbalances.

[0007] This section is provided to introduce certain aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.

[0008] An aspect of the present disclosure may relate to a method for determining electrolyte imbalance of a user. The method comprises receiving a Photoplethysmogram (PPG) data comprising a plurality of PPG features. Further, the method comprises identifying one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical electrocardiogram (ECG) features with the plurality of PPG features. Furthermore, the method comprises determining an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.

[0009] Another aspect of the present disclosure may relate to an electronic device for determining electrolyte imbalance of a user. The electronic device comprises at least one processor comprising processing circuitry and at least one memory including one of more instructions. The one of more instructions are executed by the at least one processor individually or collectively, to cause the electronic device to: 1) receive a Photoplethysmogram (PPG) data comprising a plurality of PPG features; 2) identify one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical ECG features with the plurality of PPG features; and 3) determine an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.

[0010] Yet another aspect of the present disclosure may relate to a non-transitory computer readable storage medium storing one of more instructions for determining electrolyte imbalance of a user. The one of more instructions, when executed by at least one processor of an electronic device, cause the electronic device, to receive a Photoplethysmogram (PPG) data comprising a plurality of PPG features. Further, the one of more instructions when executed by the at least one processor causes the electronic device to identify one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical ECG features with the plurality of PPG features. Furthermore, the one of more instructions when executed by the at least one processor causes the electronic device to determine an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.

[0011] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary implementations of the disclosed methods and devices in which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes disclosure of electrical components, electronic components or circuitry commonly used to implement such components.

[0012] FIG. 1 illustrates an exemplary block diagram of an electronic device for determining electrolyte imbalance of a user, in accordance with the exemplary implementation of the present disclosure.

[0013] FIG. 2 illustrates another exemplary block diagram of an electronic device for determining electrolyte imbalance of a user, in accordance with the exemplary implementation of the present disclosure.

[0014] FIG. 3 illustrates an exemplary method flow diagram of a method for determining electrolyte imbalance of a user, in accordance with the exemplary implementation of the present disclosure.

[0015] FIG. 4 illustrates an exemplary block diagram of a de-noising module to map a plurality of historical ECG features with a plurality of PPG features, in accordance with the exemplary implementation of the present disclosure.

[0016] FIG. 5A illustrates an exemplary tabular representation of a relationship between one or more electrolytes and a plurality of ECG features, in accordance with the exemplary implementation of the present disclosure.

[0017] FIG. 5B illustrates an exemplary tabular representation of a relationship between one or more electrolytes and a plurality of ECG features, in accordance with the exemplary implementation of the present disclosure.

[0018] FIG. 5C illustrates an exemplary tabular representation of a relationship between one or more electrolytes and a plurality of ECG features, in accordance with the exemplary implementation of the present disclosure.

[0019] FIG. 6A illustrates an exemplary graphical representation depicting elimination of a low-frequency interference from an ECG signal, in accordance with the exemplary implementation of the present disclosure.

[0020] FIG. 6B illustrates an exemplary graphical representation of refined set of historical ECG features, in accordance with the exemplary implementation of the present disclosure.

[0021] FIG. 6C illustrates an exemplary graphical representation of refined set of historical ECG features, in accordance with the exemplary implementation of the present disclosure.

[0022] FIG. 7A illustrates an exemplary graphical representation depicting elimination of a low-frequency interference from a PPG signal, in accordance with the exemplary implementation of the present disclosure.

[0023] FIG. 7B illustrates an exemplary graphical representation depicting elimination of a low-frequency interference from a PPG signal, in accordance with the exemplary implementation of the present disclosure.

[0024] FIG. 8A illustrates an exemplary graphical representation depicting elimination of a high-frequency interference, in accordance with the exemplary implementation of the present disclosure.

[0025] FIG. 8B illustrates an exemplary graphical representation depicting elimination of a high-frequency interference, in accordance with the exemplary implementation of the present disclosure.

[0026] FIG. 8C illustrates an exemplary graphical representation depicting elimination of a high-frequency interference, in accordance with the exemplary implementation of the present disclosure.

[0027] FIG. 8D illustrates an exemplary graphical representation depicting elimination of a high-frequency interference, in accordance with the exemplary implementation of the present disclosure.

[0028] FIG. 9A illustrates an exemplary graphical representation depicting one or more time domain ECG features, in accordance with the exemplary implementation of the present disclosure.

[0029] FIG. 9B illustrates an exemplary graphical representation depicting one or more frequency domain ECG features, in accordance with the exemplary implementation of the present disclosure.

[0030] FIG. 9C illustrates an exemplary graphical representation depicting one or more time-frequency domain ECG features, in accordance with the exemplary implementation of the present disclosure.

[0031] FIG. 10, illustrates an exemplary flow diagram depicting a process of identifying the plurality of historical ECG features as one of the normal feature and the irregular feature, in accordance with the exemplary implementation of the present disclosure.

[0032] FIG. 11A illustrates an exemplary graphical representation of mapping a plurality of historical electrocardiogram (ECG) features with a plurality of PPG features, in accordance with the exemplary implementation of the present disclosure.

[0033] FIG. 11B illustrates an exemplary graphical representation of mapping a plurality of historical electrocardiogram (ECG) features with a plurality of PPG features, in accordance with the exemplary implementation of the present disclosure.

[0034] FIG. 11C illustrates an exemplary graphical representation of mapping a plurality of historical electrocardiogram (ECG) features with a plurality of PPG features, in accordance with the exemplary implementation of the present disclosure.

[0035] FIG. 11D illustrates an exemplary graphical representation of mapping a plurality of historical electrocardiogram (ECG) features with a plurality of PPG features, in accordance with the exemplary implementation of the present disclosure.

[0036] FIG. 12A illustrates an exemplary presentation of labelled ECG features annotated with corresponding diagnostic outcome, in accordance with the exemplary implementation of the present disclosure.

[0037] FIG. 12B illustrates an exemplary presentation of labelled ECG features annotated with corresponding diagnostic outcome, in accordance with the exemplary implementation of the present disclosure.

[0038] FIG. 12C illustrates an exemplary presentation of labelled ECG features annotated with corresponding diagnostic outcome, in accordance with the exemplary implementation of the present disclosure.

[0039] FIG. 12D illustrates an exemplary presentation of labelled ECG features annotated with corresponding diagnostic outcome, in accordance with the exemplary implementation of the present disclosure.

[0040] FIG. 12E illustrates an exemplary presentation of labelled ECG features annotated with corresponding diagnostic outcome, in accordance with the exemplary implementation of the present disclosure.

[0041] FIG. 12F illustrates an exemplary presentation of labelled ECG features annotated with corresponding diagnostic outcome, in accordance with the exemplary implementation of the present disclosure.

[0042] FIG. 13 illustrates an exemplary process for identifying the one or more irregular PPG features, in accordance with the exemplary implementation of the present disclosure.

[0043] FIG. 14A illustrates an exemplary presentation for identifying one or more irregular PPG features, in accordance with the exemplary implementation of the present disclosure.

[0044] FIG. 14B illustrates an exemplary presentation for identifying one or more irregular PPG features, in accordance with the exemplary implementation of the present disclosure.

[0045] FIG. 14C illustrates an exemplary presentation for identifying one or more irregular PPG features, in accordance with the exemplary implementation of the present disclosure.

[0046] FIG. 15 illustrates an exemplary presentation of an on-device artificial intelligence engine for identifying an electrolyte level, in accordance with the exemplary implementation of the present disclosure.

[0047] FIG. 16 illustrates an exemplary an on-device artificial intelligence engine for detecting and / or predicting an electrolyte imbalance, in accordance with the exemplary implementation of the present disclosure.

[0048] The foregoing shall be more apparent from the following more detailed description of the disclosure.

[0049] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter may each be used independently of one another or with any combination of other features. An individual feature may not address any of the problems discussed above or might address only some of the problems discussed above.

[0050] The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.

[0051] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, devices, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail.

[0052] Also, it is noted that individual embodiments may be described as a process which is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations may be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure.

[0053] The word "exemplary" and / or "demonstrative" is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as "exemplary" and / or "demonstrative" is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms "includes," "has," "contains," and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive―in a manner similar to the term "comprising" as an open transition word―without precluding any additional or other elements.

[0054] As used herein, "a user equipment", "a user device", "a smart-user-device", "a smart-device", "an electronic device", "a mobile device", "a master device", "a handheld device", "a wireless communication device", "a mobile communication device", "a communication device", may be any electrical, electronic and / or computing device or equipment, capable of implementing the features of the present disclosure. The user equipment / device may include, but is not limited to, a mobile phone (or referred herein as a phone), smart phone, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, wearable device or any other computing device which is capable of implementing the features of the present disclosure.

[0055] As used herein, "memory", "storage unit" or "memory unit" refers to a machine or computer-readable medium including any mechanism for storing information in a form readable by a computer or similar machine. For example, a computer-readable medium includes read-only memory ("ROM"), random access memory ("RAM"), magnetic disk storage media, optical storage media, flash memory devices or other types of machine-accessible storage media. The storage unit stores at least the data (e.g. one or more instructions) that may be required by one or more units of the electronic device to perform their respective functions.

[0056] As used herein "interface" or "user interface" refers to a shared boundary across which two or more separate components of an electronic device exchange information or data. The interface may also be referred to a plurality of rules or protocols that define communication or interaction of one or more modules or one or more units with each other, which also includes the methods, functions, or procedures that may be called.

[0057] As used herein, a wearable device is an electronic device that is designed to be used while being worn by a user of such electronic device. Wearable devices may include but not limited to smartwatches and smart rings. The wearable devices may work in conjunction with a master device or independent of the master device such as a smartphone through a connectivity mechanism such as a Wi-Fi connectivity or a Bluetooth connectivity or the like.

[0058] All modules, units, components used herein, unless explicitly excluded herein, may be software modules or hardware processors, the processors being a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASIC), Field Programmable Gate Array circuits (FPGA), any other type of integrated circuits, etc.

[0059] As used herein, a "processing unit" or "processor" or "operating processor" may include one or a plurality of processors. At this time, one or a plurality of processors may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU). The at least one processor may comprise processing circuitry.

[0060] At least one of the plurality of modules / units may be implemented through an AI model. A function associated with AI may be performed through the non-volatile memory, the volatile memory, and the processor.

[0061] The one or more of a plurality of processors control the processing of the input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.

[0062] Here, being provided through learning means that, by applying a learning algorithm to a plurality of learning data, a predefined operating rule or AI model of a desired characteristic is made. The learning may be performed in a device itself in which AI according to an embodiment is performed, and / or may be implemented through a separate server / electronic device.

[0063] The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include, but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.

[0064] The learning algorithm is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0065] As discussed in the background section, the current known solutions have several shortcomings. In order to overcome the shortcomings of the current known solutions the present disclosure discloses a non-invasive solution for detecting and predicting electrolyte imbalances, providing both continuous and on-demand monitoring capabilities. For continuous monitoring, an embodiment of the disclosure integrates photoplethysmography (PPG) data with electrocardiogram (ECG) data, analyzing features from the time, frequency, and time-frequency domains. This calibration enables real-time tracking of electrolyte changes reflected in the ECG, generating a comprehensive score that indicates the user's overall electrolyte health. Whereas the on-demand monitoring feature focuses on specific ECG data characteristics while continuously self-calibrating PPG data to enhance efficiency. An embodiment of the disclosure not only tracks fluctuations in electrolyte levels but also evaluates the risk of potential disorders by monitoring both increases and decreases in these levels. Further, an embodiment of the disclosure also encompasses denoising ECG and PPG data to eliminate noise artifacts, normalizing processed data using a Z-Score, and employing a data training engine to capture critical features from ECG signals. Further, an embodiment of the disclosure provides an irregular PPG beat detector that continuously monitors mapped PPG data to trigger alerts for any signs of electrolyte imbalance. Additionally, an electrolyte health scorer computes comparative scores across multiple electrolytes, such as potassium, sodium, calcium, phosphorus, magnesium, and chloride, while an insight generator offers personalized recommendations to improve electrolyte balance based on individual health scores. An embodiment of the disclosure addresses the limitations of existing solutions by enabling proactive management of electrolyte levels in real-time without invasive procedures.

[0066] Some of the objects of the present disclosure, which at least one implementation disclosed herein satisfies are listed herein below.

[0067] It is an object of the present disclosure to provide a solution for determining electrolyte imbalance of a user.

[0068] It is another object of the present disclosure to provide a non-invasive solution for continuously monitoring electrolyte balance using a smart wearable device.

[0069] It is another object of the present disclosure to provide a solution for determining electrolyte imbalance using biosensors, enabling both on-demand and continuous monitoring of key electrolytes sodium, potassium, calcium, magnesium, phosphorus, and chloride.

[0070] It is another object of the present disclosure to provides a solution that generates a comprehensive electrolyte health score that correlates with individual health parameters, enhancing users' understanding of their electrolyte status.

[0071] It is another object of the present disclosure to provides a solution that utilises Photoplethysmogram (PPG) data calibrated with electrocardiogram (ECG) data for facilitating continuous tracking of electrolyte levels and improving the accuracy and responsiveness to electrolyte fluctuations.

[0072] It is another object of the present disclosure to provide a solution that generates personalized precautionary recommendations aimed at mitigating the risk of sudden electrolyte imbalances, promoting proactive health management.

[0073] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0074] Referring to FIG. 1, an exemplary block diagram of an electronic device 100 for determining electrolyte imbalance of a user in accordance with the exemplary implementation of the present disclosure is shown. The electronic device 100 comprises at least one processor 102 and at least one memory 104. Also, all of the components / units of the electronic device 100 are assumed to be connected to each other unless otherwise indicated below. Also, in Fig. 1 only a few units are shown, however, the electronic device 100 may comprise multiple such units, or the electronic device 100 may comprise any such numbers of said units, as required to implement the features of the present disclosure. Further, in an implementation, the electronic device 100 may reside in the wearable device to implement the features of the present disclosure.

[0075] Particularly, for determining electrolyte imbalance of a user, the processor 102 is configured to receive a Photoplethysmogram (PPG) data comprising a plurality of PPG features. The plurality of PPG features comprises one or more time domain PPG features, one or more frequency domain PPG features, and one or more time-frequency domain PPG features.

[0076] Further, the processor 102 is configured to identify one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical ECG features with the plurality of PPG features. The PPG data and the plurality of historical ECG features are received from at least one smart wearable device of the user. Further, the plurality of historical ECG features comprises one or more time domain ECG features, one or more frequency domain ECG features, and one or more time-frequency domain ECG features. Also, each historical ECG feature from the plurality of historical ECG features is identified as one of a normal feature and an irregular feature based on a comparison of the one or more historical ECG features with a trained dataset. The trained dataset comprises a plurality of historical ECG features and an electrolyte level corresponding to each historical ECG feature from the plurality of historical ECG features. Furthermore, the identification of said each historical ECG feature from the plurality of historical ECG features as one of the normal feature and the irregular feature is based on the electrolyte level corresponding to the said each historical ECG feature from the plurality of historical ECG features. Moreover, for identifying the one or more irregular PPG features, the PPG data is analyzed at one of a continuous basis, a periodic basis, and an on-demand basis, using an on-device artificial intelligence engine.

[0077] Furthermore, the processor 102 is configured to determine an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features. Also, the processor 102 may provide an alert on at least one of a user device and a smart wearable device based on the determined imbalance of the one or more electrolytes of the user. The processor 102, may further generate an electrolyte health score based on the determined imbalance of the one or more electrolytes of the user. The electrolyte health score indicates a balance of the one or more electrolytes in a body of the user. Thereafter, the processor 102 may provide the electrolyte health score on at least one of a user device and a smart wearable device.

[0078] Referring to FIG. 2, an exemplary block diagram of the electronic device 200 for determining electrolyte imbalance of a user, in accordance with exemplary embodiments of the present disclosure is shown. Further, the electronic device 200, in an implementation, comprises the exemplary modules to implement one or more features of the present disclosure. These exemplary modules / unit as shown in FIG. 2, in an implementation, may be implemented by the processor 102 of the electronic device 100. As shown in FIG. 2, the exemplary modules of the electronic device 200 may be an input sensor module 202, a data denoising module 204, a live data processing module 208, a data training module 206, and an insight generator unit 210. Each of these modules may be explained in detail with reference to one or more figures in the forthcoming description. Further, for determining electrolyte imbalance of the user, other associated software components may also be used in conjunction with the electronic device 100 and the electronic device 200.

[0079] The input sensor module 202 may receive data such as Photo PlethysmoGraphy (PPG) Data and an Electrocardiogram (ECG) data from one or more sensors such as Heart Rate Monitoring (HRM) sensor 202a and Electrocardiogram (ECG) sensor 202b.

[0080] The data denoising module 204 may further comprise a low frequency noise remover (LF noise remover) module 402, a high frequency noise remover (HF noise remover) module 406, and a Z-score generator module 408. Further, the functionality of each of the low frequency noise remover (LF noise remover) module 402, the high frequency noise remover (HF noise remover) module 406, and the Z-score generator module 408 is described in detail in reference to the figure 4 below in the forthcoming description.

[0081] The data training module 206 may further comprise an ECG feature analyser 206a, an ECG component marker 206b and a PPG calibrator 206c. Further, the ECG feature analyser 206a of the data training module 206 may be configured to extract various features from a de-noised ECG signal, including time, frequency, and time-frequency domain characteristics of its different components. Furthermore, the ECG component marker 206b of the data training module 206 may be configured to analyse the various features of different components to identify both normal and irregular parts of an ECG signal (as depicted in FIG. 11). Furthermore, the PPG calibrator 206c of the data training module 206 may be configured to map the various identified features of the ECG signal and the PPG signal in a time domain, a frequency domain, and a time-frequency domain.

[0082] Now referring to FIG 11D, in an exemplary implementation, the data training module 206, a data received from two or more sensors of the input sensor module 202, such as a PPG sensor and an ECG sensor, exhibits distinct properties, with the ECG sensor operating at a sampling rate of 500Hz and the PPG sensor at 25Hz. Further, the PPG calibrator 206c of the data training module 206 may calibrate the data in two stages: initially at the default sampling rate of each sensor and subsequently at an up sampled rate (i.e., increasing the sampling rate of a signal or dataset) for the PPG sensor to align its data more closely with that of the ECG sensor. Furthermore, in another implementation, in order to calibrate the data, the PPG calibrator 206c may down sample (i.e., reducing the number of samples in a dataset) the ECG data to enhance compatibility with the PPG readings, ensuring that both sensors can effectively contribute to accurate physiological measurements despite their differing operational characteristics.

[0083] The live data processing module 208 may further comprise an irregular PPG beat detector 208a, an electrolyte health scorer 208b and an electrolyte imbalance monitor 208c. Further, the irregular PPG beat detector 208a of the live data processing module 208 may be configured to continuously monitor the PPG data to generate an alert in case of an imbalanced electrolyte. Furthermore, the electrolyte health scorer 208b of the live data processing module 208 may be configured to generate an electrolyte health score that indicates the electrolyte health in the body according to its composition based on the detected electrolyte imbalance. Furthermore, the electrolyte imbalance monitor 208c of the live data processing module 208 may be configured to measure the electrolyte imbalance of the user imbalance using an on-demand method with the data received from the input sensor unit 202 based on the electrolyte health score.

[0084] Further, the insight generator module 210 is configured to provide the electrolyte health score on at least one of the user device and / or the smart wearable device, wherein the user device may be a master device of the smart wearable device, however the disclosure is not limited thereto. In an implementation, the insight generator module 210 sends one or more alerts on at least one of the user device and / or the smart wearable device based on the determined imbalance of one or more electrolytes in the user.

[0085] Referring to FIG. 3, wherein the FIG. 3 illustrates flow diagram of a method 300 for determining electrolyte imbalance of a user, in accordance with exemplary implementations of the present disclosure. In an implementation the method 300 is performed by a electronic device 100. Further, in another implementation, the method 300 is performed by the electronic device 200. Furthermore, in another implementation, the method 300 is performed by the electronic device 100 in conjunction with the electronic device 200, wherein at least one of the electronic device 100 and the electronic device 200 may be present in a user equipment (UE) to implement the features of the present disclosure. The method 300 as depicted in FIG. 3 starts at step 302.

[0086] Next, at step 304, the method 300 comprises receiving a Photoplethysmogram (PPG) data comprising a plurality of PPG features. As used herein, the Photoplethysmogram (PPG) data may refer to a graphical representation of the changes in blood flow and oxygenation associated with the user. In an embodiment of the present disclosure, the PPG data is measured through one or more non-invasive sensors, such as a green LED sensors, an infrared (IR) LED sensors, a red LED sensors, an ambient light sensors (ALS), and any other such like sensors that may be appreciated by a person skilled in art to measure the PPG data of the user. Further, in an implementation, said one or more non-invasive sensors emits light through the skin and detects changes in reflection, then the one or more non-invasive sensors capture rhythmic patterns of blood flow to generate a waveform that reflects a physiological state of the user. Further, the PPG data tracks the variations in light absorption by blood vessels and provides insights related to cardiovascular activity, such as heart rate, blood pressure, and oxygen saturation.

[0087] Further, in accordance with present disclosure as disclosed herein, the plurality of PPG features comprises one or more time domain PPG features, one or more frequency domain PPG features, and one or more time-frequency domain PPG features.

[0088] As used herein, the one or more time domain PPG features may refer to one or more attributes associated with the user that are detected from the PPG data based on a shape of the graphical representation of the PPG data and a timing associated with the PPG data, wherein the PPG data is received from the one or more non-invasive sensors during a cardiac cycle of the user. Further, the one or more time domain PPG features may comprise axis and appearance plane along a J-formation, an atrioventricular node, a ventricular activation, a ventricular recovery, a J point, a ventricular depolarization, a ventricular re-polarization and any other such like features that may be appreciated by a person skilled in the art. Further, as used herein, the J-formation represents a transition from a state of the ventricular depolarization to a state of the ventricular re-polarization.

[0089] As used herein, the one or more frequency domain PPG features may refer to one or more attributes associated with the user that are detected from the PPG data based on analyzing frequency components of the PPG data in order to extract information at least from one of a power spectrum density information associated with the PPG data, a dominant atrial cycle length information associated with the PPG data, a spectral characteristics information associated with the PPG data and any other such like information. Further, the information may be extracted by using techniques such as a Hilbert transform technique, a discrete Fourier transform technique, and a logarithmic power spectrum technique.

[0090] As used herein, the one or more time-frequency domain PPG features may refer to one or more attributes associated with the user that are detected from the PPG data based on analysis of combination of time and frequency parameters of the PPG data in order to detect dynamic change(s) associated with the PPG data. Further, the dynamic change(s) may be detected by utilizing techniques such as a short-time Fourier transform technique, a Wigner-Ville distribution technique, a cone-shaped kernel technique, and any other such like techniques. Next, at step 306, the method 300 comprises identifying one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical ECG features with the plurality of PPG features.

[0091] Further, in an implementation of the present disclosure, the PPG data and the plurality of historical ECG features are received from at least one smart wearable device of the user. As used herein, the smart wearable device may refer to a portable, technology-enabled accessory worn on a body by the user to track, monitor, and analyse a data related to user. The smart wearable device may comprise a plurality of devices such as smartwatches, fitness trackers, smart glasses, and / or smart jewellery that use sensors and / or a computer readable code to collect data on physical activity, health metrics, and environmental factors. As used herein, one or more ECG features from the plurality of historical ECG features may refer to measurable characteristics associated with the heart activity of the user that may be extracted from electrocardiogram (ECG) signals (hereinafter also referred as ECG signals) by using the one or more non-invasive sensors. The one or more ECG features may provide information related to electrical functioning, rhythm, and the health status of the heart. The one or more ECG features may be associated with time-based measurements of the characteristics, such as heart rate and intervals between heartbeats, as well as a frequency-based analysis of the characteristics, such as heart rate variability and power spectral density. Additionally, the ECG features may encompass morphological characteristics, for example, a shape and amplitude of specific waves (P, QRS, and T) that reflect atrial and ventricular contractions and recoveries. In an exemplary implementation of the present disclosure, the plurality of PPG features for mapping with the plurality of ECG features, based on a time-based and a frequency-based analysis of the characteristics are depicted in Table 1 below.

[0092] DomainFeatureSignificanceTimeInflection Point AreaRatio of area under systolic and diastolic notchAugmentation IndexRatio of amplitude of systolic and diastolic notchAlternative Augmentation IndexRatio of difference of systolic and diastolic notch by systolic notchSystolic Peak OutputRatio of systolic peak time and its amplitudePulse WidthHalf height of systolic peakP2P IntervalDistance between two consecutive systolic peaksDistance between start and end of waveformRatio of systolic peak time to P2P intervalRatio of diastolic peak time to P2P intervalRatio of heights to different peaks......FrequencyPeak 1Amplitude of first peak post fast fourier transformPeak 2Amplitude of second peak post fast fourier transformPeak 3Amplitude of third peak post fast fourier transformFFTF 1Fast fourier transform frequency of peak 1FFTF 2Fast fourier transform frequency of peak 2FFTF 3Fast fourier transform frequency of peak 3A2HzArea under curve from 0-2Hz for FFTA25HzArea under curve from 2-5Hz of FFTFmaxHighest frequency in signal spectrumMmaxMagnitude of FmaxRatio between A2Hz and A25HzRatio between peak1 and peak2Ratio between peak1 and peak3......

[0093] Further, in a preferred implementation, the present disclosure may comprise a data denoising module 204 (as shown in FIG. 2). Further, the data denoising module 204 may comprise a low frequency noise remover (LF noise remover) module 402, a de-trending module 404, a high frequency noise remover (HF noise remover) module 406, and a Z-score generator module 408.

[0094] Further, as disclosed herein, the LF Noise Remover module 402 processes the plurality of historical ECG features and the PPG data to eliminate a low-frequency interference, specifically between 0.05 Hz and 1 Hz (as depicted in FIG. 6A, FIG. 6B, and FIG. 7 respectively). Further, it is to be noted that the low-frequency interference often originates from chest wall movement due to breathing, body movements, poor electrode contact, and skin electrode impedance. Thus, by removing the low-frequency interference, the LF Noise Remover module 402 generates detrended and baseline-wandered ECG signals (i.e., low-frequency fluctuations in an electrocardiogram (ECG) signal that are not of cardiac origin) in order to facilitate accurate analysis of the plurality of historical ECG features and the PPG data.

[0095] Further, the de-trending module 404 may further refine the plurality of historical ECG features and the plurality of PPG data by eliminating residual trends and drifts, i.e., correcting for noise caused by respiration, movement, and electrode issues (for instance FIG. 6C depicts refined set of historical ECG features). The de-trending module 404 in order to refine the plurality of historical ECG features and the PPG data may focus on frequencies between 0.05 Hz and 1 Hz to prevent signal distortion and maintain the integrity of the plurality of historical ECG features and the PPG data.

[0096] Further, the HF Noise remover module 406 targets a high-frequency interference in the plurality of historical ECG features and the PPG data, specifically electrical line noise, power line interference, and muscle artifacts. The HF Noise remover module 406 filters out these noise components, i.e., the high-frequency interference. The HF Noise remover module 406 removes the high-frequency interference to enhance the plurality of historical ECG features and the PPG data in order to enable precise analysis of cardiac activity of the user. For instance, FIG. 8 depicts a graphical representation of an ECG data with filtered out high frequency noise.

[0097] The Z-score generator module 408 standardizes the plurality of historical ECG features and the PPG data generated by removing the high-frequency interference and the low-frequency interference, so as to ensure comparability across the plurality of historical ECG features and the PPG data. The Z-score generator module 408 may normalize the plurality of historical ECG features and the PPG data to generate Z-scores i.e., to generate a value that is bounded within predetermined ranges, in order to facilitate comparability. The Z-score generator module 408 in order to generate the Z-score may utilize one or more score generation rules. Further, in an exemplary implementation of the present disclosure, the score generation rule to generate a Z-score may utilize an equation (depicted as Math Figure 1 below).

[0098]

[0099] wherein: a Data PointECG,PPGrepresent a bounded value determined based on mean & Standard Deviation of respective ECG and PPG Data Points.

[0100] Further, in accordance with present disclosure as disclosed herein, the plurality of historical ECG features comprises one or more time domain ECG features, one or more frequency domain ECG features, and one or more time-frequency domain ECG features.

[0101] As used herein, as depicted in FIG. 9A the one or more time domain ECG features refers to one or more attributes associated with the user that are detected from the plurality of historical ECG features based on a shape of the graphical representation of the plurality of historical ECG features and a timing associated with the plurality of historical ECG features, wherein the plurality of historical ECG features is received from the one or more non-invasive sensors over a period of time during a cardiac cycle of the user. Further, the one or more time domain ECG features may comprise axis and appearance plane along a J- formation, an atrioventricular node, a ventricular activation, a ventricular recovery, a J point, a ventricular depolarization, a ventricular re-polarization and any other such like features that may be appreciated by a person skilled in the art. Further, as used herein, the J-formation represents a transition from a state of the ventricular depolarization to a state of the ventricular re-polarization. Further, in an exemplary implementation, the one or more time domain ECG features in accordance with the present disclosure are as depicted in Table 2 below:

[0102] Feature NameTime Domain ECG FeaturesTentative ValuePonset / OffsetStarting / Ending data point for artial depolarization (activation)<= 0.12sPR IntervalImpulse conduction from atria to ventricles0.12s - 0.22sQRSOnset / offsetStarting / Ending data point for depolarization of ventricle~ 0.22sJ PointST elevation & depression in most users~ (0.44-0.45s)J-60 PointST depression in exercise stress testing of user~ 0.46sST Depression / ElevationBelow / Above the level PR segmentJ Point / PR SegmentT waveRapid repolarization of contractile cells......QTcTotal duration of ventricular depolarization & repolarizationQT duration / sqrt(RR_Interval)+ / - AUCQRSArea under positive / negative part of peaks of QRS complexchanges user to user+ / - AUJTArea under positive / negative valleys of ST-T intervalchanges user to user

[0103] As used herein, as depicted in FIG. 9B the one or more frequency domain ECG features refers to one or more attributes associated with the user that are detected from the plurality of historical ECG features based on analyzing frequency components of the plurality of historical ECG features to extract information from at least one of a power spectrum density information associated with the plurality of historical ECG features, a dominant atrial cycle length information associated with the plurality of historical ECG features, a spectral characteristics information associated with the plurality of historical ECG features, a peak frequency, a peak amplitude, a very low frequency (LF) bandpower, a low frequency bandpower, a high frequency (HF) bandpower, a ratio of LF and HF bandpower, a frequency domain entropy, a frequency domain variance, and any other such like information. Further, the information may be extracted by using techniques such as a Hilbert transform technique, a discrete Fourier transform technique, and a logarithmic power spectrum technique. Further, in an exemplary implementation, the one or more frequency domain ECG features in accordance with the present disclosure are as depicted in Table 3 below:

[0104] FrequencyRangeFrequency Domain ECG FeaturesLow0.05 - 0.5HzP-Wave, T-WaveMedium0.5 - 10HzQRS Complex, ST SegmentHigh10 - 100HzHigh frequency Noise

[0105] As used herein, as depicted in FIG. 9C the one or more time-frequency domain ECG features refers to one or more attributes associated with the user that are detected from the plurality of historical ECG features based on analysis of combination of time and frequency parameters of the plurality of historical ECG features to detect a dynamic changes associated with ECG features of the user. Further, the dynamic changes may be detected by utilizing techniques such as a short-time Fourier transform technique, a Wigner-Ville distribution technique, a cone-shaped kernel technique, and any other such like techniques. Further, in an exemplary implementation, Table 4 depicts the analysis of combination of time and frequency parameters of the plurality of historical ECG features to detect dynamic changes associated with ECG features of the user in accordance with the present:

[0106] FrequencyAnalysisLowLow Frequency of QRS Complex, Related to depolarization of ventriclesMediumMedium Frequency of QRS Complex, Related to rapid depolarization of ventriclesHighHigh frequency of QRS Complex, Related to rapid repolarization of the ventricles

[0107] Further, in an exemplary implementation, the one or more time domain ECG features mapped with the one or more time domain PPG features in accordance with the present disclosure as depicted in Table 5 below.

[0108] Time Domain PPG featuresTime Domain ECG featuresRatio of area under systolic and diastolic notchRatio of area under QRS complex and T waveRatio of amplitude of systolic and diastolic notchRatio of R wave peak and T wave peakRatio of difference of systolic and diastolic notch by systolic notchRatio of difference of R wave peak and T wave peak by R wave peakRatio of systolic peak time and its amplitudeRatio of difference of QRS offset and QRS onset by R wave peakHalf height of systolic peakDifference between R peak point and P peak pointDistance between two consecutive systolic peaksR-R intervalDistance between start and end of waveformSum of PT interval and TU intervalRatio of systolic peak time to peak to peak intervalRatio of R peak to RR intervalRatio of diastolic peak time to peak to peak intervalRatio of T wave to RR intervalSlope of dichroitic notchSlope of J point

[0109] Further, in an exemplary implementation, mapping of the one or more frequency domain ECG features with the frequency domain PPG features in accordance with the present disclosure as depicted in Table 6 below.

[0110] Frequency Domain PPG FeaturesFrequency Domain ECG FeaturesAmplitude of first peak post fast fourier transform (FFT)Fast fourier transform for P wave peakAmplitude of second peak post fast fourier transformFast fourier transform for R wave peakAmplitude of third peak post fast fourier transformFast fourier transform for T wave peakFast fourier transform frequency of peak 1Frequency of first harmonic (FFH)Fast fourier transform frequency of peak 2Frequency of second harmonic (FSH)Fast fourier transform frequency of peak 3Frequency of third harmonic (FTH)Area under curve from 0-2Hz of FFTArea under fast fourier transform of P wave and T waveArea under curve from 2-5Hz of FFTArea under fast fourier transform of QRS complexHighest frequency in signal spectrumFrequency for highest amplitude PSD of ECG wavelet (heart rate frequency)Magnitude of FmaxAmplitude for highest amplitude PSD of ECG wavelet (power of HR frequency)Ratio between A2Hz and A25HzRatio of (VLF + LF ) to Total powerRatio between peak1 and peak2Ratio of VLF to LF bandRatio between peak1 and peak3Ratio of VLF to HF band

[0111] Further, in an exemplary implementation, mapping of the one or more time-frequency domain ECG features with the one or more time-frequency domain PPG features in accordance with the present disclosure as depicted in Table 7 below.

[0112] Time-Frequency Domain PPG FeaturesTime-Frequency Domain ECG FeaturesInstantaneous Frequency (IF) of systolic peakInstantaneous Frequency (IF) of R PeakInstantaneous Frequency (IF) of diastolic peakInstantaneous Frequency (IF) of T wave peakTime-Frequency Energy Distribution (TFED) of 1st harmonicTime-Frequency Energy Distribution (TFED) of PRTFED of second harmonicTFED of ST segmentInstantaneous Amplitude of diachronic notchInstantaneous Amplitude IA of J pointTime-Frequency Marginal Spectrum (TFMS) of max slopeTime-Frequency Marginal Spectrum (TFMS) of J pointSpectral Power Density of PPG waveletSpectral Power Density of ECG waveletTime-Frequency Entropy (TFE) of systolic waveTime-Frequency Entropy (TFE) of QRS complexTFE of Diastolic waveTFE of T waveTime-Frequency Coherence (TFC) of systolic peak to diastolic peakTime-Frequency Coherence (TFC) of R peak to T wave Peak

[0113] Further, it is to be noted that the plurality of historical ECG features mapped with the plurality of PPG features as illustrated in Table 5, Table 6, and Table 7 are exemplary and non-limiting in nature and are provided solely for illustrative purposes and should not be construed as restricting the scope of the present disclosure. Further, it is also to be noted that the mapped features i.e., the plurality of historical ECG features mapped with the plurality of PPG features, may encompass any other suitable features that would be apparent to a person skilled in the art and that may be implemented to achieve the objectives of the present disclosure.

[0114] Furthermore, in accordance with present disclosure as disclosed herein, each historical ECG feature from the plurality of historical ECG features is identified as one of a normal feature and an irregular feature based on a comparison of the one or more historical ECG features with a trained dataset.

[0115] Further, in an implementation of the present disclosure as disclosed herein, the identification of said each historical ECG feature from the plurality of historical ECG features as one of the normal feature and the irregular feature is based on the electrolyte level corresponding to said each historical ECG feature from the plurality of historical ECG features.

[0116] Referring to FIG. 10, wherein the FIG. 10, illustrates an exemplary flow diagram depicting a process of identifying the plurality of historical ECG features as one of the normal feature and the irregular feature, in accordance with the exemplary implementation of the present disclosure. As depicted in FIG.10 in conjunction with FIG. 11 and FIG. 12, each historical ECG feature from the plurality of historical ECG features is categorized as either the normal feature and / or the irregular feature through a comparative analysis of each historical ECG feature with the trained dataset 1004. As used herein, the trained dataset 1004 refers to a comprehensive and annotated collection of electrocardiogram (ECG) features aggregated from diverse populations to train and validate an artificial intelligence / machine learning (AI / ML) based model. The trained dataset 1004 may comprise labelled ECG features annotated with corresponding diagnostic outcomes, such as normal, abnormal, or specific cardiac conditions, and includes representative samples from various demographics, age groups, and health statuses. The trained dataset 1004 is generated in a manner so as to ensure a distribution of normal and abnormal features (as depicted in FIG. 12) for facilitating accurate training of the AI / ML model.

[0117] Further, in an embodiment, the trained dataset 1004 serves as a reference point for comparing the plurality of historical ECG features to recognize patterns and anomalies, identify deviations from normal cardiac activity, and classify features as the normal feature and the irregular feature. In said embodiment, by comparing the plurality of historical ECG features with the trained dataset 1004, the solution of the present disclosure identifies deviations from normal cardiac activity, flagging features that exceed predetermined thresholds and / or exhibit abnormal morphological characteristics, wherein the comparison involves assessing parameters such as heart rate variability, P-wave duration, QRS complex morphology, and T-wave amplitude against the trained dataset 1004. Each historical ECG feature that is found to be deviating from the trained dataset 1004 is classified as the irregular feature, while those within acceptable ranges from the trained dataset 1004 are deemed the normal feature.

[0118] Further, the trained dataset 1004 comprises a plurality of historical ECG features and an electrolyte level corresponding to each historical ECG feature from the plurality of historical ECG features.

[0119] Referring to FIG 13, wherein the FIG. 13 illustrates an exemplary process for identifying the one or more irregular PPG features, in accordance with the exemplary implementation of the present disclosure. Further, the PPG data is analyzed at one of a continuous basis, a periodic basis, and an on-demand basis, using an on-device artificial intelligence engine. As used herein, the on-demand basis may refer to the analysis of PPG data as needed, initiated by the user. The on-demand basis analysis option allows the user to request an immediate assessment of the PPG data for identifying the one or more irregular PPG features.

[0120] In an embodiment, the on-device artificial intelligence engine identifies the one or more irregular PPG features by analyzing the PPG data (as depicted in FIG. 14). In said embodiment the on-device artificial intelligence engine as depicted in FIG. 15 may utilize plurality of historical ECG features from the plurality of historical ECG features identified as the irregular feature and the electrolyte level corresponding to each historical ECG feature. Thereafter, the on-device artificial intelligence engine compares the PPG data to the trained dataset 1004 to detects deviations from normal patterns associated with the PPG data in order to identify the one or more irregular PPG features. Further, in an implementation of present disclosure, output of the on-device artificial intelligence engine may be stored in the trained dataset 1004 for future use.

[0121] Next, at step 308, the method 300 comprises determining an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.

[0122] As used herein, the imbalance of one or more electrolytes may refer to an abnormal level of essential minerals, such as sodium, potassium, calcium, magnesium, chlorine, and phosphorus, at a given time in the body of the user. Further, in an implementation, the imbalance may be determined when the levels of one or more electrolytes deviate from a normal range associated with the plurality of PPG features, wherein the imbalance is detected by identifying the one or more irregular PPG features and an electrolyte level associated with the one or more irregular PPG features.

[0123] Referring to FIG. 5, wherein the FIG. 5 illustrates an exemplary tabular representation of a relationship between one or more electrolytes and a plurality of ECG features, in accordance with the exemplary implementation of the present disclosure. Further, an inverse relationship exists between sodium (Na+) and potassium (K+) such as in cases of hypokalemia (low potassium levels), hypernatremia (high sodium levels) as the body attempts to maintain fluid balance and cellular function. Conversely, hyperkalemia (high potassium levels) frequently coincides with hyponatremia (low sodium levels), reflecting the delicate equilibrium maintained by these electrolytes in regulating cellular activity and fluid balance.

[0124] Similarly, phosphate (PO43-) and calcium (Ca2+) demonstrate an inverse correlation. Hypocalcemia (low calcium levels) is typically associated with hyperphosphatemia (high phosphate levels), while hypercalcemia (high calcium levels) often leads to hypophosphatemia (low phosphate levels). This relationship underscores the importance of these minerals in bone health and metabolic processes, as they bind and influence each other's availability in the bloodstream.

[0125] Furthermore, a hypomagnesemia (low magnesium levels) frequently occurs alongside hypokalemia and / or hypocalcemia, illustrating a broader association where low magnesium can exacerbate imbalances in both potassium and calcium. This interplay highlights the complexity of electrolyte homeostasis, where disturbances in one electrolyte can cascade into imbalances of others, emphasizing the necessity for careful monitoring and management in clinical settings to ensure optimal health outcomes.

[0126] As depicted in Fig. 5 ECG features are identified as region of interest based on the above-mentioned conditions such as hypokalemia, and hypercalcemia etc.

[0127] Further, in a preferred implementation of the present disclosure, the present disclosure further comprises providing an alert on at least one of a user device and a smart wearable device 1302 based on the determined imbalance of the one or more electrolytes of the user.

[0128] As disclosed herein, in an implementation, the present disclosure may utilize an on-device artificial intelligence engine for detecting and / or predicting an electrolyte imbalance, in accordance with the exemplary implementation of the present disclosure as depicted in FIG 16. Further, the on-device artificial intelligence engine may provide real-time alerts and guidance to the user upon detecting and / or predicting an electrolyte imbalance. The on-device artificial intelligence engine, in order to provide the real-time alerts, may analyze the PPG data for identifying the one or more irregular PPG features and the determined imbalance of the one or more electrolytes of the user based on the identification of the one or more irregular PPG features. Thereafter, in another implementation, the on-device artificial intelligence engine may also generate personalized recommendations for restoring the determined imbalance of the one or more electrolytes, considering factors such as a health profile of the user, an activity level of the user, and dietary habits of the user.

[0129] Further, in an implementation of the present disclosure, the generated personalized recommendations for restoring the determined imbalance of the one or more electrolytes in accordance with the present disclosure are provided below in Table 8.

[0130] ElectrolyteSuggestionsPotassiumIncrease intake of bananas, oranges, avocados, spinach, and potatoes.SodiumReduce processed foods, fast food, and salty snacks.CalciumIncorporate dairy products, leafy green vegetables, and fortified foods.PhosphorusFound in meat, poultry, fish, dairy, and legumes.ChlorideNaturally present in table salt.MagnesiumWhole grains, nuts, seeds, leafy green vegetables.

[0131] Further, in another implementation of the present disclosure, the present disclosure further comprises generating an electrolyte health score based on the determined imbalance of the one or more electrolytes of the user, wherein the electrolyte health score indicates a balance of the one or more electrolytes in body of the user.

[0132] In an implementation of the present disclosure, the electrolyte health score (depicted as score in Table 9) may be generated using one or more score generation techniques, including but not limited to statistical analysis, machine learning algorithms, or heuristic models. The one or more score generation techniques may process an electrolyte concentration level associated with the determined imbalance of the one or more electrolytes of the user and their respective reference ranges to quantify the degree of imbalance (as depicted in table 9 below).

[0133] In an exemplary implementation, an exemplary score generation technique for generating the electrolyte health score may be based on anticipated and / or intervened electrolyte imbalance(s). Said score generation technique may utilize a predictive model that incorporates both historical data and real-time inputs from an electronic health record (EHR) of the user. Further, the predictive model may analyze various parameters, including previous electrolyte levels, medical history (such as weight), demographics, and relevant health conditions, to predict potential imbalances. Thereafter, by integrating the output of the predictive model with current electrolyte measurements, a comprehensive electrolyte health score may be generated that reflects the overall electrolyte health of the user at a given time. Said electrolyte health score may indicate the current state of electrolyte balance while taking into account anticipated changes.

[0134] ElectrolyteLevelsValuesScoreWeightDemographicsPotassiumLow<3.5 mmol / L0 - 7920......PotassiumHigh>5.5 mmol / L0 - 7920......PotassiumNormal3.5-5.5 mmol / L80 - 10020......SodiumLow<135 mmol / L0 - 7415......SodiumHigh>145 mmol / L0 - 7415......SodiumNormal135-145 mmol / L75 - 10015......CalciumLow<2.1 mmol / L0 - 8420......CalciumHigh>2.5 mmol / L0 - 8420......CalciumNormal2.1-2.6 mmol / L85 - 10020......MagnesiumLow<3.5 mmol / L0 - 6915......MagnesiumHigh>5.5 mmol / L0 - 6915......MagnesiumNormal3.5-5.5 mmol / L70 - 10015......ChlorineLow<135 mmol / L0 - 8915......ChlorineHigh>145 mmol / L0 - 8915......ChlorineNormal135-145 mmol / L90 - 10015......PhosphorusLow<2.1 mmol / L0 - 7915......PhosphorusHigh>2.6 mmol / L0 - 7915......PhosphorusNormal2.1-2.6 mmol / L80 - 10015......

[0135] Further, in another implementation, said exemplary score generation technique to generate the electrolyte health score may utilize the following Math Figure 2 provided below:

[0136]

[0137] wherein:

[0138] UserScore represent a quantified value indicating a level of potential imbalance of a particular electrolyte, and

[0139] Precedence represents a predefined importance level associated with the particular electrolyte.

[0140] In another implementation, the comprehensive electrolyte health score may be generated based on a fuzzy logic in a scenario where the EHR of a predetermined duration associated with the user are available. Furthermore, said fuzzy logic in order to generate the comprehensive electrolyte health score may utilize the Math Figure 3 given below.

[0141]

[0142] wherein:

[0143] μ(E)depicts a membership functions for an electrolyte level, and

[0144] WeightErepresents a weight assigned to an electrolyte.

[0145] and wherein the membership functions for an electrolyte level is determined based on the Math Figure 4 given below.

[0146]

[0147] wherein: αN represent a midpoint of range of values associated with the electrolyte, and

[0148] βA represent a slope of range of values associated with the electrolyte.

[0149] Furthermore, in said implementation the present disclosure further comprises providing the electrolyte health score on at least one of a user device and a smart wearable device 1302.

[0150] Thereafter, the method 300 terminates at step 310.

[0151] An embodiment of the disclosure discloses a method 300 for determining electrolyte imbalance of a user, the method 300 comprising: receiving a Photoplethysmogram (PPG) data comprising a plurality of PPG features; identifying one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical electrocardiogram (ECG) features with the plurality of PPG features; and determining an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.

[0152] An embodiment of the disclosure discloses wherein the PPG data and the plurality of historical ECG features are received from at least one smart wearable device of the user.

[0153] An embodiment of the disclosure discloses wherein the plurality of historical ECG features comprises one or more time domain ECG features, one or more frequency domain ECG features, and one or more time-frequency domain ECG features.

[0154] An embodiment of the disclosure discloses wherein the plurality of PPG features comprises one or more time domain PPG features, one or more frequency domain PPG features, and one or more time-frequency domain PPG features.

[0155] An embodiment of the disclosure discloses wherein each historical ECG feature from the plurality of historical ECG features is identified as one of a normal feature and an irregular feature based on a comparison of the one or more historical ECG features with a trained dataset.

[0156] An embodiment of the disclosure discloses wherein the trained dataset comprises the plurality of historical ECG features and an electrolyte level corresponding to the each historical ECG feature from the plurality of historical ECG features.

[0157] An embodiment of the disclosure discloses wherein the identification of the each historical ECG feature from the plurality of historical ECG features as one of the normal feature and the irregular feature is based on the electrolyte level corresponding to the each historical ECG feature from the plurality of historical ECG features.

[0158] An embodiment of the disclosure discloses wherein for identifying the one or more irregular PPG features, the PPG data is analyzed at one of a continuous basis, a periodic basis, and an on-demand basis, using an on-device artificial intelligence engine.

[0159] An embodiment of the disclosure discloses the method (300) further comprises: providing an alert on at least one of a user device and a smart wearable device based on the determined imbalance of the one or more electrolytes of the user.

[0160] An embodiment of the disclosure discloses the method (300) further comprises: generating an electrolyte health score based on the determined imbalance of the one or more electrolytes of the user, wherein the electrolyte health score indicates a balance of the one or more electrolytes in body of the user, and providing the electrolyte health score on at least one of a user device and a smart wearable device.

[0161] An embodiment of the disclosure discloses an electronic device (100) for determining electrolyte imbalance of a user, the electronic device (100) comprising: at least one processor (102) comprising processing circuitry, and at least one memory (104) including one of more instructions, wherein the one of more instructions are executed by the at least one processor (102), to cause the electronic device (100) to: receive, a Photoplethysmogram (PPG) data comprising a plurality of PPG features; identify, one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical electrocardiogram (ECG) features with the plurality of PPG features; and determine an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.

[0162] An embodiment of the disclosure discloses wherein the PPG data and the plurality of historical ECG features are received from at least one smart wearable device of the user.

[0163] An embodiment of the disclosure discloses wherein the one of more instructions are executed by the at least one processor (102), to cause the electronic device (100) to: provide an alert on at least one of a user device and a smart wearable device based on the determined imbalance of the one or more electrolytes of the user.

[0164] An embodiment of the disclosure discloses wherein the one of more instructions are executed by the at least one processor (102), to cause the electronic device (100) to: generate an electrolyte health score based on the determined imbalance of the one or more electrolytes of the user, wherein the electrolyte health score indicates a balance of the one or more electrolytes in body of the user, and provide the electrolyte health score on at least one of a user device and a smart wearable device.

[0165] An embodiment of the disclosure discloses a non-transitory computer-readable medium storing one of more instructions, wherein the one of more instructions, when executed by at least one processor of an electronic device (100), cause the electronic device (100) to perform the method of the disclosure.

[0166] Thus, the present disclosure provides a novel solution for determining electrolyte imbalance of a user. Further, the preset disclosure discloses a technically advanced solution that determines electrolyte imbalance of the user by utilizing biosensors. Also, the solution enables both on-demand and continuous monitoring of key electrolyte sodium, potassium, calcium, magnesium, phosphorus, and chloride. This dual capability provides users with a comprehensive electrolyte health score that correlates with their individual health parameters, enhancing their understanding of electrolyte status. The integration of PPG data calibrated with ECG data facilitates continuous tracking, improving the accuracy and responsiveness to changes in electrolyte levels.

[0167] Additionally, the solution of the preset disclosure generates personalized precautionary suggestions to mitigate the risk of sudden electrolyte imbalances, promoting proactive health management. By sub-categorizing atrial fibrillation in relation to specific electrolyte imbalances, the solution aids in early detection of potential disorders and tailors interventions to individual needs. The incorporation of a data denoising engine ensures high-quality data comparability across different sensors, further enhancing the reliability of the monitoring process. Overall, the solution as disclosed in the present disclosure effectively addresses the limitations of existing on-demand solutions by providing a continuous, user-friendly method for managing electrolyte health.

[0168] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter to be implemented merely as illustrative of the disclosure and not as limitation.

Claims

1.A method (300) for determining electrolyte imbalance of a user, the method (300) comprising:receiving a Photoplethysmogram (PPG) data comprising a plurality of PPG features;identifying one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical electrocardiogram (ECG) features with the plurality of PPG features; anddetermining an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.2.The method (300) as claimed in claim 1, wherein the PPG data and the plurality of historical ECG features are received from at least one smart wearable device of the user.3.The method (300) as claimed in any one of claims 1 to 2, wherein the plurality of historical ECG features comprises one or more time domain ECG features, one or more frequency domain ECG features, and one or more time-frequency domain ECG features.4.The method (300) as claimed in any one of claims 1 to 3, wherein the plurality of PPG features comprises one or more time domain PPG features, one or more frequency domain PPG features, and one or more time-frequency domain PPG features.5.The method (300) as claimed in any one of claims 1 to 4, wherein each historical ECG feature from the plurality of historical ECG features is identified as one of a normal feature and an irregular feature based on a comparison of the one or more historical ECG features with a trained dataset.6.The method (300) as claimed in claim 5, wherein the trained dataset comprises the plurality of historical ECG features and an electrolyte level corresponding to the each historical ECG feature from the plurality of historical ECG features.7.The method (300) as claimed in claim 6, wherein the identification of the each historical ECG feature from the plurality of historical ECG features as one of the normal feature and the irregular feature is based on the electrolyte level corresponding to the each historical ECG feature from the plurality of historical ECG features.8.The method (300) as claimed in any one of claims 1 to 7, wherein for identifying the one or more irregular PPG features, the PPG data is analyzed at one of a continuous basis, a periodic basis, and an on-demand basis, using an on-device artificial intelligence engine.9.The method (300) as claimed in claim 1, the method (300) further comprises:providing an alert on at least one of a user device and a smart wearable device based on the determined imbalance of the one or more electrolytes of the user.10.The method (300) as claimed in claim 1, the method (300) further comprises:generating an electrolyte health score based on the determined imbalance of the one or more electrolytes of the user, wherein the electrolyte health score indicates a balance of the one or more electrolytes in body of the user, andproviding the electrolyte health score on at least one of a user device and a smart wearable device.11.An electronic device (100) for determining electrolyte imbalance of a user, the electronic device (100) comprising:at least one processor (102) comprising processing circuitry, andat least one memory (104) including one of more instructions, wherein the one of more instructions are executed by the at least one processor (102), to cause the electronic device (100) to:receive, a Photoplethysmogram (PPG) data comprising a plurality of PPG features;identify, one or more irregular PPG features from the PPG data based on a mapping of a plurality of historical electrocardiogram (ECG) features with the plurality of PPG features; anddetermine an imbalance of one or more electrolytes of the user based on the identification of the one or more irregular PPG features.12.The electronic device (100) as claimed in claim 11, wherein the PPG data and the plurality of historical ECG features are received from at least one smart wearable device of the user.13.The electronic device (100) as claimed in claim 11, wherein the one of more instructions are executed by the at least one processor (102), to cause the electronic device (100) to:provide an alert on at least one of a user device and a smart wearable device based on the determined imbalance of the one or more electrolytes of the user.14.The electronic device (100) as claimed in claim 11, wherein the one of more instructions are executed by the at least one processor (102), to cause the electronic device (100) to:generate an electrolyte health score based on the determined imbalance of the one or more electrolytes of the user, wherein the electrolyte health score indicates a balance of the one or more electrolytes in body of the user, andprovide the electrolyte health score on at least one of a user device and a smart wearable device.15.A non-transitory computer-readable medium storing one of more instructions, wherein the one of more instructions, when executed by at least one processor of an electronic device (100), cause the electronic device (100) to perform the method of any one of claims 1 to 10.

Images