Description:DESCRIPTION OF INVENTION
FIELD OF THE INVENTION
The present invention generally related to the healthcare devices.
More particularly, the present invention integrates AI-enhanced analysis of biosensors, biomarkers, and derived VCG (Vectorcardiogram) Data for monitoring comprehensive health including cardiac and positional health assessment with real-time advisory using array of interactive decision-making tools.
BACKGROUND OF THE INVENTION
In the healthcare and medical field, an ECG, or electrocardiogram, is a common medical test that measures the electrical activity of the heart. It is a painless and non-invasive procedure where electrodes are placed on the skin of the chest, arms, and legs. These electrodes detect the electrical impulses generated by the heart as it beats and relay this information to a machine that produces a graphical representation called an electrocardiogram.
The ECG provides valuable information about the heart's rhythm and can help diagnose various heart conditions, such as arrhythmias, heart attacks, and other abnormalities. By examining the waves and patterns on the ECG, doctors can assess the health of the heart and make informed decisions about treatment. It is a quick and essential tool used in hospitals, clinics, and emergency settings to evaluate cardiac health and monitor patients with heart conditions.
Whereas, A VCG, or vectorcardiogram, is a more advanced form of cardiac testing that provides a three-dimensional view of the heart’s electrical activity. Unlike the ECG, which represents heart activity in two dimensions, the VCG shows the direction and magnitude of electrical forces in the heart from multiple angles. This detailed information helps cardiologists understand the precise electrical pathways within the heart.
By combining data from the VCG with that of the ECG, healthcare providers can gain a more comprehensive understanding of a patient’s heart health. The VCG is particularly useful in diagnosing complex heart conditions and assessing the effectiveness of treatments. While it is a more specialized test and not as commonly performed as the ECG, the VCG offers valuable insights into the heart's functioning and can aid in creating personalized treatment plans for patients.
VCG provides a more comprehensive depiction of cardiac function by capturing not only the temporal aspects but also the spatial orientation of electrical activity within the heart. This richer data representation enables more accurate identification and characterization of various cardiovascular conditions, leading to enhanced diagnostic accuracy and improved patient management.
In contemporary clinical practice, the augmentation of traditional electrocardiography (ECG) with Vector Cardiogram (VCG) represents a significant advancement in cardiovascular health assessment. VCG provides a nuanced depiction of cardiac function by not only capturing the temporal aspects but also the spatial orientation of electrical activity within the heart. This richer data representation facilitates more precise identification and characterization of various cardiovascular conditions, thereby enhancing diagnostic accuracy and refining patient management strategies.
VCG offers profound insights into cardiac dynamics that may elude detection through standard ECG recordings alone. By visualizing the direction and magnitude of electrical impulses, VCG can elucidate subtle abnormalities in cardiac depolarization and repolarization processes. This capability proves invaluable in detecting early signs of cardiovascular disease and evaluating the effectiveness of therapeutic interventions.
Despite these advancements, several challenges persist within the realm of cardiovascular health monitoring:
Standardization Deficiencies: The absence of standardized protocols hampers the widespread adoption and utility of VCG in clinical settings. Further refinement is particularly necessary for capturing signals indicative of arrhythmias or ischemia, ensuring consistency and reliability in diagnostic assessments.
Complexity of Existing Solutions: Current iterations of Holter monitors, designed for continuous cardiac monitoring, are encumbered by complexity. These devices typically involve cumbersome setups such as belts and limb straps, compromising their wearability and user experience. Consequently, there remains a dearth of truly wearable 12-lead ECG solutions that seamlessly integrate into patients' daily routines.
Limitations in Comprehensive Signal Acquisition: A singular device may not suffice to capture the full spectrum of cardiac electrical activity. Existing efforts to bridge this gap have focused on orientation-driven cardiac electrical activity, aiming to enhance the comprehensiveness of data collection. However, further advancements are needed to optimize signal acquisition and processing for holistic cardiac health monitoring.
Given the intricate interdependencies within biological systems, isolated measurements of electrical activities offer only partial insights. Thus, there is a pressing need for more comprehensive approaches to biological signal measurement and processing. Integration of advanced artificial intelligence (AI) and machine learning (ML) techniques holds promise in deriving “Smart VCG” solutions, which amalgamate diverse biosensor data into ECG analyses. This convergence facilitates enhanced diagnostic capabilities and personalized health assessments, thereby revolutionizing cardiovascular care delivery.
The present invention addresses the challenges posed by the existing state of the art and describes a vector-based AI-driven device for advanced health monitoring using biological and cardiac signals with wearable technology to monitor the health and more specifically to monitor the cardio vascular health.
OBJECTS OF THE INVENTION
The primary object of the present invention is to provide a comprehensive vector-based AI-driven wearable health monitoring device to monitor various health conditions;
Further object of the present invention is to provide an advanced health monitoring device, wearable at any given point of time, briefly onto the body of an individual;
Further object of the present invention is to provide a convenient device to measure the vital signs of the human body and support timely action for better treatment for the patient.
SUMMARY OF THE INVENTION
Embodiments of the present disclosure present technological improvements as a solution to one or more of the above-mentioned technical problems recognized by the inventor in existing techniques.
The present disclosure seeks to provide a vector-based AI-driven device (100) for advanced health monitoring using biological and cardiac signals for continuous cardiovascular health monitoring. It encompasses a sophisticated array of components and functionalities designed to provide accurate data collection, seamless connectivity, and advanced analytical capabilities.
According to an aspect of the invention, the vector-based AI-driven device (100) mainly comprises of, electrodes, a photodiode, a gyrometer biosensor, an inbuilt GSM, WiFi and BLE on the circuit board. The device employs a unique electrode configuration, with electrodes arranged in both Pythagoras triangle and Mason-Likar patterns. This arrangement ensures optimal sensing for limb and chest leads, facilitating precise monitoring of cardiac activity.
According to further aspects, the practical design elements of the present invention enhance user experience, including replaceable adhesive electrodes (201a-201h) for convenience and comfort during prolonged usage. The device also features a rechargeable battery capable of providing continuous operation for extended periods, as well as user-friendly controls such as an On/Off switch and various charging mechanisms.
According to further aspect of the present invention, the vector-based AI-driven device (100) also comprises of a mobile application to display results and connected via Bluetooth technology with the device.
According to an aspect of the present invention, the body vitals are continuously being sensed and communicated using GSM, BLE, And WIFI Protocols to a Cloud Software application.
According to an aspect of the present invention, the raw data is transmitted from the device (100) to the cloud server in the background using GSM, BLE, And WIFI protocols for further processing of the data and to provide better and more accurate results.
According to an aspect of the present invention, the present invention provides a display, displaying accurate results in real-time in the mobile application dashboard for the patient/doctor to view. The patient would be provided with an option to view indicative values.
According to an aspect of the present invention, the device utilizes advanced AI/ML algorithms to seamlessly integrate and analyze various biosensor signals such as Heart Rate, Heart Rate Variability, Oxygen Saturation, Blood Pressure, Respiratory Rate, Body Position, Gait analysis, and Non-Invasive Blood Glucose levels.
According to an aspect of the present invention, the algorithms are built in the form of API in the backend cloud server to store, process and analyze the data. Once the data is analyzed, the report is generated.
According to an aspect of the present invention to provide alert notification to the patient in advance after generating the predictive analytic reports. The notifications and alerts would be customized as per the patient's condition and the doctor’s recommendation.
With its comprehensive monitoring capabilities and analytical features, the wearable device holds significant potential for clinical applications. It can aid in early detection of cardiovascular abnormalities, facilitate remote patient monitoring, and support healthcare providers in making informed decisions regarding patient care.
In summary, this invention represents a significant advancement in cardiovascular health monitoring technology, offering a holistic solution for continuous monitoring, data analysis, and patient management. Its innovative design, integrated sensors, and connectivity features position it as a valuable tool for both patients and healthcare professionals in the field of cardiology
The objects and the advantages of the invention are achieved by the process elaborated in the present disclosure.
BRIEF DESCRIPTION OF DRAWINGS
The foregoing Summary, as well as the following detailed description of preferred embodiments of the invention, will be better understood when read in conjunction with the drawings as well as experimental results. The accompanying drawings constitute a part of this specification and illustrate one or more embodiments of the invention. Preferred embodiments of the invention are described in the following with reference to the drawings, which are for the purpose of illustrating the present preferred embodiments of the invention and not for the purpose of limiting the same. The objects and advantages of the present invention will become apparent when the disclosure is read in conjunction with the following figures, wherein
Figure 1 shows the bottom view of the vector-based AI-driven device (100);
Figure 2 shows the position of the vector-based AI-driven device (100) on the human body;
Figure 3 shows the flowchart of the working principle of the vector-based AI-driven device (100).
DETAILED DESCIPTION OF THE INVENTION
The following detailed description illustrates embodiments of the present disclosure and ways in which the disclosed embodiments can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practicing the present disclosure are also possible.
The present invention provides a vector-based AI-driven device (100) for advanced health monitoring using biological and cardiac signals for continuous cardiovascular health monitoring of the patients and more specifically, cardio vascular conditions.
The present invention adopts a three-layered approach for its wearable device:
Hardware Layer: This layer includes the physical components and assembly of the device, such as high-quality sensors for capturing vital signs like ECG and Blood Pressure. Careful selection and assembly ensure reliability and user comfort.
Firmware Layer: This layer consists of embedded software controlling hardware operation, managing tasks like data acquisition and communication protocols. It optimizes power usage, data integrity, and seamless integration with software.
Software Layer: At the top, the user interface software receives real-time data from the device via GSM, providing intuitive visualization, analytics, and alerts. Machine learning algorithms enable personalized insights for users and healthcare professionals, enhancing diagnostic accuracy and proactive health management.
The present invention is illustrated with reference to the accompanying drawings, throughout which reference numbers indicate corresponding parts in the various figures. These reference numbers are shown in brackets in the following description.
According to an embodiment of the present invention, the said device (100) for continuous cardiovascular health monitoring mainly comprises of plurality of electrodes (201a, 201b, 201c, 201d, 201e, 201f, 201g, 201h) placed as per the Pythagoras triangle, a photodiode (202) placed on the rear side of the device (100), a gyrometer biosensor (203) placed on the circuit board of the device (100) and an inbuilt GSM, WiFi and Bluetooth low energy protocol (BLE) on the circuit board of the device (100).
According to an embodiment of the present invention, the device (100) is connected to a mobile application to display the results via a Bluetooth connection, more specifically through Bluetooth low energy protocol.
According to preferred embodiment of the present invention, the body vitals are continuously being sensed using of electrodes (201a, 201b, 201c, 201d, 201e, 201f, 201g, 201h), photodiode (202) and gyrometer biosensor (203) communicated using GSM, BLE, And WIFI Protocols to a cloud server.
According to an embodiment of the present invention and referring to the figure 1, wherein eight ECG female snaps (201a, 201b, 201c, 201d, 201e, 201f, 201g, 201h, 201i, 201j) are arranged in a triangular configuration for limb leads (201a, 201b, 201c), Mason-Likar configuration for chest leads (201d, 201e, 201f, 201g, 201h) and a photodiode (202) at the centre of the bottom portion of the limb leads triangular configuration patch. The device (100) senses the electrical signals, green, red and IR signals from all the sensors every millisecond and amplifies the data as per the required amplitude. From the device (100), the sensed data is transferred every one millisecond to the cloud server for further processing. The wearable device (100) is designed in such a way that it is portable, convenient and easy to use. Also, the device (100) is designed by keeping all gender of patients or users to use for 24 hours and more by only changing the adhesive electrodes. The device (100) is built with a rechargeable battery that has the capacity to work for twenty-four hours if used at full length. If it is on standby mode, it can hold the battery for three days. The device is provided with an On/Off Switch that may be a slide switch and push On/Off or membrane switch. Further, the device is provided with a charging dock or charging cable or wireless charging to charge the device (100).
According to an embodiment of the present invention and referring to figure 2, the device (100) is affixed to the human body wherein, conventional adhesive electrodes are placed above the chest area and the electrodes of the wearable device snap-fits the adhesive electrodes. If anyone electrode is not connected properly to the human body, an alert notification will be sent to mobile and to others concerned.
The device is placed 1cm below the chest and center of the esophagus or trachea. The conventional adhesive electrodes (201a, 201b, 201c, 201d, 201e, 201f, 201g, 201h) are placed above the chest area and the eight electrodes of the wearable device (100) snap-fits the adhesive electrodes. If anyone electrode is not connected properly to the human body, an alert notification will be sent to mobile and to others concerned.
According to an embodiment of the present invention, by affixing the device (100) to the human body (301), it senses the signals from all the sensors and transmits the data to the cloud server for further processing. The device (100) has the capability to store the data for three days continuously if it is not connected to the cloud server. Once the device (100) gets connected to the cloud server, all the data is transferred to the cloud server.
Figure 3 is the flowchart of the working principle of the device (100) of the present invention, wherein the said device (100) is connected to cloud server through GSM, BLE and WIFI and then affixed to the human body and press the switch.
ECG and PPG, XYZ coordinates (402) from ADS1298/ADS1198 (ECG sensor) (403) and Max30100/101/102/105 (PPG sensor) (404), ADXL345 (Accelerometer) are recorded respectively.
From XYZ coordinates (402), one can measure the number of steps walked by the user, and also the sleep analysis, body posture and fall detection of the user or patient.
The device (100) is configured to generate the 12 ECG signals using 10 electrodes connected to the eight ADC channels. Lead I, Lead II, and V1 to V6 are computed in the analog domain, while the augmented leads and Lead III are computed digitally. Formulas used to derive augmented leads are:
LEAD III: LL - RA - LA = LEAD II - LEAD I
aVR: RA - (LA + LL) / 2 = - (LEAD I + LEAD II) / 2
aVL: LA - (RA +LL) / 2 = LEAD I - LEAD II / 2
aVF: LL - (RA + LA) / 2 = LEAD II - LEAD I /2
Wherein,
• LA = Left Arm
• LL = Left Leg
• RA = Right Arm
Later 12-lead ECG is converted into a vectorcardiogram (VCG) using an array of methodologies like the Kors transformation matrix. It involves applying a mathematical transformation to the ECG leads to derive the XYZ coordinates of the heart's electrical activity. The Kors transformation matrix is a mathematical matrix that maps the electrical potentials measured in the 12-lead ECG to the X, Y, and Z coordinates of the VCG.
From ECG (403), the device (100) derives Heart Rate, Heart Rate Variability using RR intervals, VCG. The device (100) also finds the abnormalities in the Heart, wherein the list of abnormalities includes Bradycardia, Tachycardia, Atrial Fibrillation, Atrial Flutter, Supraventricular Tachycardia, Long QT syndrome, Premature Atrial Contraction and Premature Ventricular Contraction.
The Heart Rate is calculated based on RR interval, i.e. Heart Rate = 60/R-R interval (sec)
One way of measuring of Heart Rate Variability (HRV) is using RMSSD (root mean square of successive differences) by calculating each successive time difference between heartbeats in milli-seconds and each of the values is squared and the result is averaged before the square root of the total is obtained.
Display
Tachycardia is defined to be auto-captured and presented where the heart rate is greater than 100 and two or more part beats to avoid noise captures.
Bradycardia is defined to be auto-captured and presented where the heart rate is less than 60 and two or more part beats to avoid noise captures.
Atrial Fibrillation is defined to be if P wave is missing or QRS complexes > 120ms or Enlarged R-Wave (long period of time)
Atrial Flutter is defined to be if loss of the isoelectric baseline or “Saw-tooth” pattern of inverted flutter waves are detected;
Supraventricular Tachycardia is defined to be if HR is 180 to 200 bpm;
Premature Ventricular contractions is defined to be if Broad QRS complex (= 120 ms) with abnormal morphology;
From Photodiode Sensor (PPG) (404) the wearable device (100) measures SPO2, and Temperature.
From ECG (403) and PPG (404), Pulse Transit time (PTT)(406) is calculated, which is used to predict Blood Pressure.
From PPT (406), the cuff less BP (407) is derived, PTT is the time taken for the arterial pulse pressure wave to travel from the aortic valve to a peripheral site.
This can be predicted using AI/ML models (405) like Regression Analysis.
Processing ECG (403) and PPG (404) data from wearable device (100) of the present invention and simultaneously obtain data from Sphygmomanometer and perform regression analysis for the features and Cuff based Bp and develop a trained model (405) for predicting the BP (411) from ECG and PPG.
The ECG (403) and PPG (404) data derives PTT (406) information and these parameters are given to train the model (405) to predict BP (411).
Calculate steps and sleep analysis of the user or patient from the data provided by gyrometer sensor ADXL345 sensor (402).
Display ECG graph, BP, Oxygen Saturation, Heart Rate, Temperature, in the handheld device
The RMSSD reflects the beat-to-beat variance in HR and is the primary time-domain measure used to estimate the changes reflected in HRV
The AI/ML model (405) is trained by collecting the data from the hospitals and data sources from ECG and PPG sensors. Initially the data is stored in a sql database. The PTT (406) data is taken from the wearable device (100) and cuff BP (407) from the data collected from the hospitals.
From the extracted data, the regression analysis model (408) is trained and further the AI/ML model is trained with pre-classified ECG data sets (409). By providing these data to the model, the model is trained (410) and checked for the model’s accuracy in prediction against the actual output. Then the PTT derived from the wearable device (100) is given to the trained model (410) that in turn predicts the BP (411).
In accordance with the exemplary embodiment of the present invention, the customized reports would be generated by the server periodically on demand, reviewed by the Subject Matter Experts/Paramedic Staff/Doctor, if any feedback required for the patient will be provided in the report. All the reports can be viewed or downloaded from the mobile application in the pdf format.
In accordance with the exemplary embodiment of the present invention, the measurement of each vital parameter is designed and trained using the data models based on the algorithms. The wearable device processes the measured signals using customized algorithms to enable in providing the output accurately.
In accordance with the exemplary embodiment of the present invention, the patient or user would have the option to record the log in the mobile application. This logging system will help reduce the false positives and makes the algorithm more trained using the data logging system.
In accordance with the exemplary embodiment of the present invention, the list of vitals measured in phase 1 are ECG, PPG, Heart Rate, Pulse Rate, Respiratory Rate, Blood Pressure, SPO2, Skin Temperature, and HRV. Further, the list of vitals measured in phase 2 are Non-Invasive Blood sugar, distance/steps/calories/MET, sleep analysis, respiratory rate, remainders – sedentary/drinking water, fall detection and body posture.
Please provide the analysis details in detailed like the values that are used for predicting the anomalies in the recorded data and the process involved in predicting the risk.
ECG sensor has the ability to detect anomalies in the ECG readings. Conduction path (Skin) must exist between all the electrodes (201a, 201b, 201c, 201d, 201e, 201f, 201g, 201h) of the device. Otherwise, ECG sensor is not placed properly.
PPG sensor has the ability to detect anomalies in the PPG readings. – If the PPG data range is in between 15,000 to 20,000 then the device not placed properly on the body.
According to an embodiment of the present invention, the raw data is transmitted from the wearable device to the cloud server in the background using Global System for Mobile Communication (GSM), Bluetooth Low Energy Protocol (BLE), And WIFI protocols for further processing of the data and to provide better and more accurate results.
The raw sensor data sent by the device (100) and mobile application get processed using complex computational process to get different parameters that helps in building the reports and the processed parameters data is stored in the database tables. The processed parameter data is compared with the previous stored data in the database using different data AI/ML modelling methods that aid in analyzing the data and for feature reporting.
According to an embodiment of the present invention, the device (100) utilizes advanced AI/ML algorithms to seamlessly integrate and analyze various biosensor signals such as Heart Rate, Heart Rate Variability, Oxygen Saturation, Blood Pressure, Respiratory Rate, Body Position, Gait analysis, and Non-Invasive Blood Glucose levels.
Additionally, it incorporates clinical biomarkers, genetic/multiomics data, and demographic information including Age, Gender, Height, Weight, Habits, and Location. Through this comprehensive approach, the Device provides personalized insights into cardiovascular health, enabling precise risk assessment and tailored interventions.
Since the device (100) is worn by an individual patient, the device is ideal for personalized medical treatment. Each treatment plan downloaded into the mobile application can be individualized according to the patient's needs. Therefore, the device (100) would significantly enhance the effectiveness of individualized treatments for patients. In particular, treatments can be dynamically adjusted according to the current condition of the user or patient as indicated by the vital signals that are currently measured from the user.
According to an embodiment of the present invention, The AI/ML models are built by Linear Regression, Logistic Regression, Decision Trees, Random Forest, Support Vector Machines (SVM), Naive Bayes, K-Nearest Neighbours (K-NN), Principal Component Analysis (PCA), K-Means Clustering, Gradient Boosting Machines (GBM), AdaBoost, XGBoost, Lasso Regression, Ridge Regression, Elastic Net Regression, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM), Gated Recurrent Units (GRU), Autoencoders, Generative Adversarial Networks (GAN), Two-Event Related Moving-Averages and Fractional Fourier Transform algorithms for VCG.
The models are trained by providing the ECG dataset that are classified library that contains certain attributes like ECG signal value and time stamp. The AI/ML models are checked for accuracy in predicting the anomalies in the processed data and trained in making accurate predictions for any new dataset that is given as input, with these predictions the model’s performance gets improved. The dataset is obtained from both abstract sources, including secondary data analysis, simulation models, and observational studies, as well as non-abstract sources such as sensor data, IoT devices, government databases, and academic research.
According to an embodiment of the present invention, the algorithms are built in the form of API in the backend cloud server. Once the raw data is sent as input to the APIs, the processed data is posted in different database tables. All the data in database tables get analyzed with the previous records using Artificial Intelligence/Machine Learning AI/ML models. Once the data is processed in the AI/ML models, a predictive analytic report would be generated.
The analyzed results would be displayed in real-time in the handheld mobile device. The patient will have only the option to view indicative values. The customized software installed in the handheld devices enables to view the results and generate, daily or weekly reports which may be downloaded in a pdf format.
The above description is only a preferred embodiment of the present invention, and it should be understood that the description of the above embodiments is only for helping to understand the method of the present invention and its core idea, and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the present invention. , Claims:CLAIMS:
We claim,
1. A vector-based AI-driven device (100) for advanced health monitoring using biological and cardiac signals, the said device comprising
- a plurality of electrodes (201a, 201b, 201c, 201d, 201e, 201f, 201g, 201h) arranged in a Pythagoras triangle configuration for limb leads and a Mason-Likar configuration for chest leads;
- a photodiode (202) positioned at the center of the limb leads triangular configuration patch;
- a gyrometer biosensor (203) located on a circuit board of the device (100);
- inbuilt GSM (Global System for Mobile Communication), WiFi, and BLE (Bluetooth Low Energy Protocol) communication modules embedded within device’s circuitry, ensuring seamless connectivity for data transmission;
- a mobile application interconnected via BLE for real-time data visualization;
- a rechargeable battery;
wherein the device (100) is configured to continuously sense body vitals including ECG (Electrocardiogram), PPG (Photoplethysmography), and XYZ coordinate data using the electrodes (201a-201h), photodiode (202), and gyrometer biosensor (203), and communicate the sensed data to a mobile application via Bluetooth low energy protocol for user viewing.
2. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the device (100) is affixed to a human body (301) with conventional adhesive electrodes (201a-201h) placed above the chest area, and the electrodes of the device (100) snap-fit the adhesive electrodes and in case of improper connection of any electrode to the human body, an alert notification is promptly transmitted to mobile devices and relevant stakeholders.
3. The vector-based AI-driven device (100) as claimed in Claim 1, wherein raw data from eight leads derives four ECG leads using the ADS1198 library in the device firmware in real-time.
4. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the device (100) stores sensed data for up to three days when not connected to a cloud server, and wherein the sensed data is transferred to the cloud server once connected.
5. The vector-based AI-driven device (100) as claimed in Claim 1, wherein raw sensor data is transmitted from the device (100) to the cloud server using GSM, Bluetooth Low Energy Protocol (BLE), and WiFi protocols for further processing and analysis leading to the generation of the report.
6. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the said device (100) integrates the Two-Event Related Moving-Averages (TERMA) with Fractional Fourier Transform (FrFT) techniques to enhance the analysis of Vectorcardiography (VCG) signals, thereby improving the accuracy of heart disease diagnosis.
7. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the AI/ML models are trained using pre-classified ECG datasets, said datasets being categorized through a computational process to facilitate proactive VCG predictive analysis, thereby enabling the generation of predictive analytic reports for dissemination to patients, doctors, or other relevant stakeholders.
8. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the cloud server integrates an API (405) designed to process incoming data, conduct analysis on the processed data, and perform comparisons with historical datasets utilizing AI/ML models.
9. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the mobile application displays analyzed real time results, views, generates, daily or weekly reports which are downloadable in a pdf format.
10. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the device integrates artificial intelligence module which analyzes real-time sensor data and provides interpreted health insights on the display unit, generating predictive analytical reports and features an artificial intelligence processor that is configured to run machine learning algorithms on the device (100), with said artificial intelligence module syncing from and to the cloud when connected to internet.
11. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the adhesive electrodes (201a-201h) are designed to be easily replaceable, allowing for continuous usage by patients or users of all genders for 24 hours or more.
12. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the rechargeable battery provides continuous operation for up to twenty-four hours at full usage and up to three days in standby mode.
13. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the device has an On/Off Switch, selected from the group consisting of a slide switch, push On/Off button, or membrane switch.
14. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the device (100) includes a charging mechanism selected from the group consisting of a charging dock, charging cable, or wireless charging capability for convenient recharging.
15. The vector-based AI-driven device (100) as claimed in Claim 1, wherein the ECG sensor is configured to detect anomalies in ECG readings, and conduction paths (Skin) must exist between all electrodes (201a-201h) for proper placement of the device; failure to establish conduction paths indicates improper placement.
16. The vector-based AI-driven device (100) as claimed in Claim 1, wherein PPG sensor is capable of detecting anomalies in PPG readings, and if the PPG data range falls between 15,000-20,000, it indicates improper placement of the device.