A combined process for detecting and predicting multiple medical episodes alone or in combination

Abstract

A combined process for detecting and predicting multiple medical episodes—such as seizures, falls, and cardiac events—alone or in combination, using wearable sensor data. The system continuously collects physiological and movement data from one or more wearable devices and integrates it with personal historical data, including medical history, age, gender, and known conditions. User-specific settings define thresholds and emergency response preferences. Artificial Intelligence and machine learning models analyse the integrated data to detect and predict medical episodes by identifying patterns and refining accuracy over time through user feedback and updated historical data. The system also monitors deviations in Activities of Daily Life as indicators of potential risk. When a medical episode is detected or predicted, alerts are sent to caregivers or healthcare providers. This personalised, adaptive method enhances early intervention and real-time support, enabling improved healthcare outcomes through timely detection and prediction of medical episodes.

Description

A COMBINED PROCESS FOR DETECTING AND PREDICTING MULTIPLE MEDICAL EPISODES ALONE OR IN COMBINATIONTechnical Field

[0001] The present invention relates to systems and methods for detecting and predicting multiple medical episodes alone or in combination.

[0002] The invention has been developed primarily for use in detecting and predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user and will be described hereinafter with reference to this application. However, it will be appreciated that the invention is not limited to this particular field of use.Background

[0003] Any discussion of the background art throughout the specification should in no way be considered as an admission that such background art is prior art, nor that such background art is widely known or forms part of the common general knowledge in the field in Australia or worldwide as at the priority date of the present application.

[0004] All references, including any patents or patent applications, cited in this specification are hereby incorporated by reference, which means that it should be read and considered by the reader as part of this text. That the document, reference, patent application or patent cited in this text is not repeated in this text is merely for reasons of conciseness.

[0005] The advancement of health monitoring systems has played a vital role enhancing the care and safety of individuals, especially in the medical and elderly care sectors. Traditionally, these systems have focused on tracking patient location, ensuring medical compliance, and monitoring physiological parameters. While such systems are instrumental in managing health care, they exhibit limitations in their ability to provide a holistic view of an individual’s health status at any given moment. This is particularly evident in scenarios requiring the detection and communication of specific medical episodes, such as falls, seizures, cardiac events or sleepwalking events, which demand a nuanced understanding and response that existing technologies fall short of providing.

[0006] Historically, fall detection in elderly individuals has been approached through either image-based surveillance, raising significant privacy concerns, or through wearable sensors that monitor physical activity and posture changes. Despite these efforts, challenges persist, especially with wearables like wrist-mounted sensors, which are prone to high false-positive rates due to the limb’s freedom of movement. These issues highlight the complexity of accurately detecting falls, given the varied manners in which they can occur.

[0007] Moreover, the detection of medical episodes such as epileptic seizures currently relies on post-event analysis rather than pre-emptive alerts. Existing technologies, including implanteddevices and external monitoring equipment, only signal once an episode has occurred, missing the critical window for early intervention.

[0008] Additionally, gait analysis as a preventive measure for falls is emerging yet underdeveloped. Wearable sensors and complex monitoring systems have introduced new possibilities for assessing risk factors associated with falls. However, the trade-off between the quality and quantity of data collected, the need for non-intrusiveness, and the technology’s affordability has hindered widespread adoption. A significant gap remains in providing real-time feedback and guidance that is accessible, non-technical, and respectful of users’ privacy and comfort.

[0009] There is a need to provide systems and methods that mitigates one or more of the above problems and / or limitations of the existing art. There is a clear and pressing need for a solution that can provide solution to shortcomings of existing systems by optimally utilising the vast amount of data generated by various sensors and health monitoring devices, machine learning processes to predict and detect a wide range of medical episodes with greater accuracy and specificity.

[0010] Any discussion of the background art throughout the specification should in no way be considered as an admission that such background art is prior art, nor that such background art is widely known or forms part of the common general knowledge in the field in Australia or any other country.Summary

[0011] It is an object of the present invention to overcome or substantially ameliorate one of the deficiencies of the prior art or to at least provide a useful alternative.

[0012] In accordance with a first aspect of the present invention, there is provided a method for detecting and predicting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising steps of: continuously collecting a physiological and movement data from one or more sensors of one or more wearable devices worn by the user; using user specific settings associated with a personal profile unique to the user, where the personal profile includes predefined thresholds, historical health data, and emergency response preferences, combining personal historical data of the user with the collected physiological and movement data to generate an integrated data, where the personal historical data includes medical history, age, gender, and known medical conditions of the user; storing and encrypting the collected physiological and movement data and the personal historical data in a data storage module; analysing the integrated data based on the user specific settings to detect the occurrence of medical episodes and to predict potential medical episodes using a data analysis module, wherein the analysis includes identifying patterns indicative of medical episodes;updating the personal historical data based on the physiological and movement data detected by the one or more sensors; applying machine learning models on the personal historical data to recognize signs of medical episodes while refining detection based on user specific settings; in order to improve the medical episode detection and prediction accuracy over time; receiving feedback from the user regarding their current health status and dynamically refining the integrated data to improve accuracy of medical episode prediction and detection; and generating and sending alerts to one or more stakeholders, including caregivers and healthcare providers, when one or more medical episodes is detected or predicted, or when deviations in movement patterns indicate a potential risk

[0013] In accordance with a second aspect of the present invention, there is provided a system for detecting and predicting medical episodes from the group of seizure, fall, cardiac and combinations thereof in a user, comprising: a physiological and movement data collection module configured to continuously collect data from one or more sensors of wearable devices worn by the user; a data integration module to combine personal user data with collected physiological and movement data to provide integrated data; a data storage module for storing and encrypting collected physiological and movement and personal data; a data analysis module is configured to analyse the integrated data using the user-specific settings for detecting and predicting medical episodes and apply machine learning models to refine analyses based on the user feedback; and an alert and feedback module for generating alerts to stakeholders, including caregivers and healthcare providers, and receiving user feedback, wherein the feedback is used to dynamically refine the integrated data and improve the accuracy of medical episode prediction and detection.

[0014] In accordance with a third aspect of the present invention, there is provided a method of detecting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user comprising: receiving data from one or more sensors of wearable devices of a user; analysing the received data from one or more sensors; comparing the analysed data with predetermined data; detecting occurrence of the one or more medical episodes; and sending an alert to one or more stakeholders; wherein the step of receiving data comprises a step of continuously reading data from the one or more sensors; wherein the step of comparing comprises a step of determining predetermined data by combining threshold data and historical data; andwherein the step of detecting comprises a step of receiving feedback from the user and a step of triggering an alert to the one or more stakeholders after receiving one or more predetermined feedback values.

[0015] In accordance with a fourth aspect of the present invention, there is provided a system for detecting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising: a data reception module configured to continuously read data from one or more sensors of wearable devices of a user; a data analysis module for analysing the received data from the data reception module and identifying patterns in the data that are indicative of one or more medical episodes; a comparison module for comparing the analysed data with predetermined data, wherein the comparison module is further configured to determine predetermined data as a function of threshold data and historical data specific to the user; a detection module for detecting the occurrence of the one or more medical episodes based on the comparison of the analysed data with predetermined data, wherein the detection module is configured to receive feedback from the user and trigger an alert to one or more stakeholders after receiving one or more predetermined feedback values; and an alert module for sending an alert when triggered by the detection module, wherein the alert module is configured to transmit information to stakeholders along with relevant data and episode severity assessment.

[0016] In accordance with a fifth aspect of the present invention, there is provided a method for predicting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising: continuously collecting physiological and movement data from one or more sensors of wearable devices worn by a user; storing the collected physiological and movement data in a data storage module; combining personal data of the user with the collected physiological and movement data to generate integrated data, wherein the personal data of the user includes medical history, age, gender, and known medical conditions of the user; analysing the integrated data by a prediction module; generating a prediction of a potential medical episode based on the analysed integrated data by the prediction module; and receiving feedback from the user regarding their current health status, wherein the feedback is used to dynamically refine the integrated data to improve the accuracy of medical episode prediction over time.

[0017] In accordance with a sixth aspect of the present invention, there is provided a system for predicting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising:a physiological and movement data collection module configured to continuously collect physiological and movement data from one or more sensors of wearable devices worn by a user; a data storage module configured to store and encrypt the collected physiological and movement and personal data of the user; a data integration module configured to integrate personal data of the user with the collected physiological and movement data to provide integrated data, wherein the personal user data includes medical history, age, gender, and known medical conditions of the user; a data analysis module configured to analyse the integrated data; a prediction generation module configured to generate a prediction of a potential medical episode based on the analysed integrated data; and a feedback module configured to receive feedback from the user regarding their current health status, wherein the feedback is used by the data integration module to dynamically refine the integrated data, to improve the accuracy of medical episode prediction over time.

[0018] In accordance with a seventh aspect of the present invention, there is provided a method for detecting and predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The method comprising steps of continuously collecting a physiological and movement data from one or more sensors of wearable devices worn by the user, combining personal historical data of the user with the collected physiological and movement data to generate an integrated data, where the personal historical data includes medical history, age, gender, and known medical conditions of the user, storing and encrypting the collected physiological and movement data and the personal historical data in a data storage module, analysing the integrated data to detect the occurrence of medical episodes and to predict potential medical episodes using a data analysis module, wherein the analysis includes identifying patterns indicative of medical episodes, updating the personal historical data based on the physiological and movement data detected by the one or more sensors, applying machine learning models on the personal historical data to recognize signs of medical episodes while refining detection based on user specific in order to improve the medical episode detection and prediction accuracy over time, receiving feedback from the user regarding their current health status and dynamically refining the integrated data to improve accuracy of medical episode prediction and detection and generating and sending alerts to one or more stakeholders, including caregivers and healthcare providers, when one or more medical episodes is detected or predicted, or when deviations in movement patterns indicate a potential risk.

[0019] Advantageously in this seventh aspect, the method provides for advanced healthcare monitoring with an ability to detect and predict a range of medical episodes, such as seizures, falls, and cardiac events, by integrating data from both wearable devices and personal health records. This method combines real-time physiological and movement data with a user’s detailed personal history — encompassing medical history, age, gender, and known health conditions — to form a comprehensive dataset. Integrated data. The essence of this method lies in its capability to analyse this extensive integrated dataset to identify patterns that signal potential health issues.Leveraging evolving machine learning models, it dynamically refines its ability to spot early signs of these episodes, making use of data points that were previously separate or not fully utilized. This approach not only allows for immediate detection of health episodes but also improves the prediction of future ones, shifting from a reactive to a proactive stance in patient care. In contrast to prior solutions that focus on isolated incidents without the ability to adapt, this integrated method offers a personalized, secure, and intelligent solution for the early detection and prevention of complex health episodes, thereby setting a new standard in adaptive and holistic healthcare monitoring.

[0020] In one embodiment, the one or more sensors are configured to detect a plurality of physiological and movement parameters including, but not limited to heart rate, blood oxygen, blood pressure, body temperature, skin conductance, respiratory rate, and movement patterns.

[0021] In one embodiment, the data analysis module applies deep learning and machine learning models specifically trained to recognize early signs of medical episodes relevant to the user’s known medical conditions, including analysing user’s movement, Heart rate patterns, blood oxygen, skin temperature, sleep patterns, and classifying the user’s Activities of Daily Life (ADL).

[0022] In one embodiment, a further step of generating and displaying visual analytics is provided for review of the user’s physiological and movement data trends by user and stakeholder, including caregivers and healthcare providers. Preferably, the step of generating and displaying visual analytics comprises an Artificial Intelligence prediction model which is employed to create a dashboard for displaying alerts and warnings for user and stakeholders including caregivers and healthcare providers.

[0023] In accordance with a eighth aspect of the present invention, there is provided a system for detecting and predicting medical episodes from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The system comprising a physiological and movement data collection module configured to continuously collect data from one or more sensors of wearable devices worn by the user, a data integration module to combine personal user data with collected physiological and movement data to provide integrated data, a data storage module for storing and encrypting collected physiological and movement and personal data, a data analysis module is configured to analyse the integrated data for detecting and predicting medical episodes and apply machine learning models to refine analyses based on the user feedback and an alert and feedback module for generating alerts to stakeholders, including caregivers and healthcare providers, and receiving user feedback, wherein the feedback is used to dynamically refine the integrated data and improve the accuracy of medical episode prediction and detection.

[0024] Advantageously in this eighth aspect, this system offers significant technical advancement over prior art in the field of health monitoring by offering a comprehensive system for detecting and predicting various medical episodes such as seizures, falls, and cardiac events,individually or in combination. Unlike existing solutions, this system seamlessly integrates continuous physiological and movement data collection from wearable device sensors with personal user data, creating an integrated dataset that is both stored and encrypted for enhanced privacy and security. One of the key elements of this system is the data analysis module, which employs machine learning models to refine analyses based on user feedback, thereby improving accuracy and reliability over time. Moreover, the inclusion of an alert and feedback module facilitates dynamic communication with stakeholders like caregivers and healthcare providers, and leverages user feedback to continuously enhance the system’s predictive capabilities.

[0025] In one embodiment, the physiological and movement data collection module is further configured to collect data related to a comprehensive range of physiological and movement parameters and the prediction generation module refines analysed integrated data using contextual data such as, but not limited to, time of day, user location, and recent physical activity.

[0026] In one embodiment, the system further comprising a visual analytics display module configured to generate and display visual analytics of the user’s physiological and movement data trends to stakeholders, enhancing the interactive review and monitoring capabilities for users, caregivers, and healthcare providers.

[0027] In one embodiment, the visual analytics display module further configured to employ Artificial Intelligence prediction model to create a dashboard for displaying alerts and warnings for user and stakeholders including, but not limited to, caregivers and healthcare providers.

[0028] In accordance with a ninth aspect of the present invention, there is provided a method of detecting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The method comprising the steps of receiving data from one or more sensors of wearable devices of a user, analysing the received data from one or more sensors, comparing the analysed data with predetermined data, detecting occurrence of the one or more medical episodes, sending an alert to one or more stakeholders, wherein the step of receiving data comprises a step of continuously reading data from the one or more sensors, wherein the step of comparing comprises a step of determining predetermined data by combining threshold data and historical data and wherein the step of detecting comprises a step of receiving feedback from the user and a step of triggering an alert to the one or more stakeholders after receiving one or more predetermined feedback values.

[0029] Advantageously in this ninth aspect there is provided a combined process is employed to analyse data from wearable device sensors, offering a refined approach that combines threshold data with the historical user data. This integration enables a more accurate and personalized detection of multiple medical episodes compared to prior art, which often relies solely on predetermined thresholds or simple anomaly detection techniques. Threshold settings are tied to a personal profile unique to each user, allowing the system to personalize the medical episode detection based on individual health characteristics and preferences. Additionally, themethod introduces a dynamic feedback loop with the user, enhancing detection accuracy by incorporating user feedback into the episode verification process. This allows for the fine-tuning of alert mechanisms, ensuring that stakeholders are notified only upon confirmation of the episode, thereby reducing false positives. The continuous data gathering from sensors, combined with the innovative use of combined algorithmic analysis and user feedback, represents a leap forward in proactive health monitoring and emergency response systems.

[0030] In one embodiment, the one or more sensors are configured to detect a plurality of physiological and movement parameters including, but not limited to, heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

[0031] In one embodiment, the analysed data is real-time value of a plurality of physiological and movement parameters including, but not limited to, heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

[0032] In one embodiment, further a step of updating the threshold data and the historical data based on real-time data detected by the one or more sensors to improve medical episode detection accuracy over time is provided.

[0033] In one embodiment, the threshold data of each of the one or more medical episode specific for the user is updated based on receiving one or more predetermined feedback values from the user.

[0034] In one embodiment, the historical data of each of the one or more medical episode specific for the user is updated, by using Machine Learning one or more predetermined feedback values comprises a Medical Episode event or near Medical Episode Event and analysis of data of one or more medical episodes previously detected.

[0035] In one embodiment, the data of one or more medical episodes previously detected comprises the details of medical episode, values of a range of physiological and movement parameters including, but not limited to, heart rate, blood oxygen, blood pressure, body temperature, and movement patterns at the time of occurrence of the medical episode.

[0036] In one embodiment, the receiving one or more predetermined feedback values include manual input regarding user current health status or automated input based on user reactions or responses detected by the one or more sensors.

[0037] In one embodiment, the step of sending an alert includes transmitting information to the one or more stakeholders, from the group of caregivers, healthcare providers, along with relevant data and episode severity assessment.

[0038] In one embodiment, the step of analysing data comprising a step of identifying patterns indicative of one or more medical episodes.

[0039] In accordance with a tenth aspect of the present invention, there is provided a system for detecting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The system comprising a data reception module configured to continuously read data from one or more sensors of wearable devices of a user, a data analysis module for analysing the received data from the data reception module and identifying patterns in the data that are indicative of one or more medical episodes, a comparison module for comparing the analysed data with predetermined data, wherein the comparison module is further configured to determine predetermined data as a function of threshold data and historical data specific to the user, a detection module for detecting the occurrence of the one or more medical episodes based on the comparison of the analysed data with predetermined data, wherein the detection module is configured to receive feedback from the user and trigger an alert to one or more stakeholders after receiving one or more predetermined feedback values and an alert module for sending an alert when triggered by the detection module, wherein the alert module is configured to transmit information to stakeholders along with relevant data and episode severity assessment.

[0040] Advantageously in this tenth aspect, there is provided a comprehensive approach to detect a wide range of medical episodes, including seizures, falls, and cardiac events, through the use of wearable devices is provided. Unlike existing systems, which often focused on detecting a single type of medical episode or utilized simplistic detection algorithms, this system integrates a combined algorithmic approach that enhances detection accuracy and responsiveness. Additionally, the system’s ability to incorporate user feedback into the detection process not only enhances accuracy through adaptive learning but also empowers users in their healthcare management.

[0041] In one embodiment, the one or more sensors configured to detect a plurality of physiological and movement parameters including, but not limited to, heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

[0042] In one embodiment, the analysed data is real-time value of a plurality of physiological and movement parameters including, but not limited to, heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

[0043] In one embodiment, the threshold data and the historical data is continuously updated by the data analysis module based on real-time data detected by one or more sensors to improve episode detection accuracy over time.

[0044] In one embodiment, the threshold data of each of the one or more medical episodes specific for the user is updated by the data analysis module based on receiving one or more predetermined feedback values from the user by the detection module.

[0045] In one embodiment, the historical data of each of the one or more medical episode specific for the user is updated, by using Machine Learning one or more predetermined feedbackvalues comprises a Medical Episode event or near Medical Episode Event and analysis of data of one or more medical episodes previously detected.

[0046] In one embodiment, the data of one or more medical episodes previously detected comprises the details of medical episode, values of a range of physiological and movement parameters including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns at the time of occurrence of the medical episode.

[0047] In one embodiment, the detection module is further configured to receive feedback from the user, which can include manual input regarding their current health status or automated input based on user reactions or responses detected by the one or more sensors.

[0048] In accordance with a eleventh aspect of the present invention, there is provided a method for predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The method comprising the steps of continuously collecting physiological and movement data from one or more sensors of wearable devices worn by a user, storing the collected physiological and movement data in a data storage module, combining personal data of the user with the collected physiological and movement data to generate integrated data, wherein the personal data of the user includes medical history, age, gender, and known medical conditions of the user, analysing the integrated data by a prediction module, generating a prediction of a potential medical episode based on the analysed integrated data by the prediction module and receiving feedback from the user regarding their current health status, wherein the feedback is used to dynamically refine the integrated data to improve the accuracy of medical episode prediction over time.

[0049] Advantageously in this eleventh aspect, the method provides innovative integration of physiological and movement data, collected in real-time from wearable devices, with personal user data including medical history, age, gender, and known medical conditions. This combination produces a comprehensive dataset that is analysed to predict one or more potential medical episodes more accurately, i.e., one combined process to detect multiple medical episodes. A distinctive feature of this method is the incorporation of user feedback regarding their current health status, which dynamically refines the data integration process. This continuous refinement mechanism enhances the precision of the predictions over time, addressing a significant limitation in prior art by evolving the system’s understanding of the user’s health. This technical advancement not only elevates the reliability of medical episode predictions but also personalizes the monitoring system to the user’s unique health profile, thereby improving preventive healthcare measures and patient outcomes. The user’s unique health profile holds user-specific settings to improve the detection and prediction of medical episodes, such as seizures, falls, cardiac events, or combinations thereof, using data collected from wearable sensors. These settings are tied to a personal profile unique to each user, allowing the system to personalize the medical episode detection based on individual health and medical condition characteristics.

[0050] In one embodiment, the step of continuously collecting physiological and movement data further includes collecting data related to the user’s heart rate, blood pressure, body temperature, skin conductance, respiratory rate and movement patterns, and other wearable sensors.

[0051] In one embodiment, the step of analysing the integrated data include applying deep learning models specifically trained to recognize early signs of medical episodes relevant to the user’s known medical conditions.

[0052] In one embodiment, the step of analysing the integrated data further includes applying machine learning models to analyse the integrated data including user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns for classifying the user’s Activities of Daily Life (ADL) and identifying patterns indicative of potential medical episodes.

[0053] In one embodiment, the step of storing data includes encrypting the physiological and movement and personal data of the user for privacy and security.

[0054] In one embodiment, the step of generating a prediction of a potential medical episode is further refined using contextual data such as time of day, user location, and recent physical activity.

[0055] In one embodiment, the dynamically refining the integrated data includes implementing adaptive learning techniques to refine the model as more physiological and movement data is collected.

[0056] In one embodiment, a step of generating and displaying visual analytics of the user’s physiological and movement data trends is provided for user and stakeholder’s review. Preferably, the one or more stakeholders are from the group of caregivers, healthcare providers.

[0057] In accordance with a twelfth aspect of the present invention, there is provided a system for predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The system comprising a physiological and movement data collection module configured to continuously collect physiological and movement data from one or more sensors of wearable devices worn by a user, a data storage module configured to store and encrypt the collected physiological and movement and personal data of the user, a data integration module configured to integrate personal data of the user with the collected physiological and movement data to provide integrated data, wherein the personal user data includes medical history, age, gender, and known medical conditions of the user, a data analysis module configured to analyse the integrated data, a prediction generation module configured to generate a prediction of a potential medical episode based on the analysed integrated data, a feedback module configured to receive feedback from the user regarding their current health status, wherein the feedback is used by the data integration module to dynamically refine the integrated data, to improve the accuracy of medical episode prediction over time.

[0058] Advantageously in this twelfth aspect, the system significantly advances personal health monitoring by integrating continuous physiological and movement data from wearable devices with personal user data, including medical history, to predict medical episodes like seizures, falls, and cardiac events. Unlike existing solutions, it enhances prediction accuracy through a novel feedback mechanism that refines data integration with user health status feedback, dynamically evolving with the user’s health profile. This architecture, coupled with data encryption for privacy, represents a pioneering approach in utilizing combined algorithms and Artificial Intelligence models for proactive, preventive and personalized health care, setting a new standard in predictive analytics and user safety.

[0059] In one embodiment, the physiological and movement data collection module is further configured to collect data related to the user’s heart rate, blood oxygen, blood pressure, body temperature, skin conductance, respiratory rate, and movement patterns.

[0060] In one embodiment, the data analysis module is configured to apply machine learning models to analyse the integrated data including user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns for classifying the user’s Activities of Daily Life (ADL) and identifying patterns indicative of potential medical episodes.

[0061] In one embodiment, the prediction generation module is further configured to refine the analysed integrated data using contextual data such as time of day, user location, and recent physical activity.

[0062] In one embodiment, the feedback module includes an interactive interface on wearable devices or an associated mobile application.

[0063] In one embodiment, the data integration module is configured to dynamically refine the integrated data by implementing adaptive learning techniques to refine the model as more physiological and movement data is collected.

[0064] In one embodiment, the system further provides a visual analytics display module configured to generate and display visual analytics of the user’s physiological and movement data trends to stakeholders. Preferably, the one or more stakeholders are from the group of caregivers, healthcare providers.

[0065] Also disclosed herein is a non-transitory computer storage medium, comprising instructions stored therein, wherein the instructions, when executed by a processor, cause the processor to perform any of the method steps of the above-described aspects and embodiments.

[0066] It should be noted that a server, computing device, and computer readable storage medium associated with the aspects and embodiments described above and herein provide the same or similar advantages as the advantages provided by the corresponding computer implemented method, some of which are described herein. Additionally, the server and / orcomputing device provides the advantage of deployment across a computer network, such as the Internet, providing distribution, access, and economy of scale advantages. Furthermore, the computer readable storage medium provides further advantages, such allowing the deployment of computer instructions for installation and execution by one or more computing devices.

[0067] Other aspects and embodiments of the invention are also disclosed in the detailed description and exemplary examples of the systems and methods for detecting and predicting multiple medical episodes alone or in combination, and it will be appreciated that specific features disclosed in regard to a particular aspect, embodiment or example are readily and optionally included and\or interchangeable with specific features disclosed in regard to a different aspect, embodiment or example.Brief Description of the Drawings

[0068] Notwithstanding any other forms which may fall within the scope of the present invention, a preferred embodiment of the invention will now be described, by way of example only, with reference to the accompanying drawings in which:Figure 1 illustrates a system for detecting and predicting medical episodes from the group of seizure and / or fall and / or cardiac and / or in combination in a user, in accordance with an embodiment of the present invention;Figure 2 illustrates a method for detecting and predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user, in accordance with an embodiment of the present invention;Figure 3 illustrates an exemplary implementation of the method shown in Figure 2 above, in accordance with an embodiment of the present invention;Figure 4 illustrates an exemplary demonstration of the working of the method shown in Figure 2, in accordance with an embodiment of the present invention;Figure 5 illustrates an exemplary implementation of the method as shown in Figure 2, in accordance with an embodiment of the present invention;Figure 6 illustrates an example of system of Figure 1 , in accordance with a preferred embodiment of the present invention;Figure 7 illustrates an example of automatic detection of fall medical episode shown in Figure 6, in accordance with an embodiment of the present invention;Figure 8 illustrates another example of automatic detection of fall and near fall medical episode shown in Figure 6, in accordance with an embodiment of the present invention;Figure 9 illustrates an example indicating real fall data with convulsion on the 3rdphase of the fall during detection of fall medical episode in Figure 7, in accordance with an embodiment of the present invention;Figure 10 illustrates an example indicating allowed convulsions during 3rdphase of a fall between multiple TOTF of example shown in Figure 7, in accordance with an embodiment of the present invention;Figure 11 illustrates an example of automatic detection of seizure medical episode showing in Figure 6, in accordance with an embodiment of the present invention;Figure 12 illustrates an example of automatic detection of seizure and near seizure medical episode shown in Figure 6, in accordance with an embodiment of the present invention;Figure 13 illustrates an example of automatic detection of cardiac medical episode shown in Figure 6, in accordance with an embodiment of the present invention;Figure 14 illustrates another example of automatic detection of cardiac medical episode and near cardiac medical episode shown in Figure 6, in accordance with an embodiment of the present invention;Figure 15 illustrates an example indicating data from a combined 3 or more processes running and detecting seizure, fall, tachycardia, SpO2, and others by employing method shown in Figure 2, in accordance with an embodiment of the present invention;Figure 16 illustrates an example indicating real data for combined seizure and fall process by employing method shown in Figure 2, in accordance with an embodiment of the present invention;Figure 17 illustrates a system for detecting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination, using predetermined values accordingly, in a user is provided, in accordance with an embodiment of the present invention;Figure 18 illustrates a method for employing the system as shown in Figure 17 for detecting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided, in accordance with an embodiment of the present invention;Figure 19 illustrates a system for predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided, in accordance with an embodiment of the present invention; andFigure 20 illustrates a method for employing the system as shown in Figure 19 for predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided, in accordance with an embodiment of the present invention.

[0069] In the drawings, like structures are referred to by like numerals throughout the several views. The drawings shown are not necessarily to scale, with emphasis instead generally being placed upon illustrating the principles of the present invention.Detailed Description

[0070] It should be noted in the following description that like or the same reference numerals in different embodiments denote the same or similar features.

[0071] Further, the various embodiments described herein below include specific method steps in an exemplary order, but a wide variety of other such method steps could be implemented within the scope of the invention, including additional steps, omission of some steps, or performing the method in a different order.

[0072] Figure 1 illustrates a system 100 for detecting and predicting medical episodes from the group of seizure and / or fall and / or cardiac and / or in combination in a user 101 , in accordance with an embodiment of the present invention. As shown in Figure 1 , the system 100 comprising a physiological and movement data collection module 104 configured to continuously collect data from one or more sensors of wearable devices 102 worn by the user 101 , a data integration module 106 to combine personal user data with collected physiological and movement data to provide integrated data, a data storage module 108 for storing and encrypting collected physiological and movement and personal data, a data analysis module 110 is configured to analyse the integrated data for detecting and predicting medical episodes and apply machine learning models to refine analyses based on the user feedback. Further, the system comprising an alert and feedback module 112 for generating alerts to stakeholders, including caregivers and healthcare providers, and receiving user feedback, wherein the feedback is used to dynamically refine the integrated data and improve the accuracy of medical episode prediction and detection. The modules may be communicatively coupled with each other through a communication bus, wirelessly, or other suitable communication protocol as would be suitable in light of this disclosure.

[0073] As shown in Figure 1 , the system 100 is designed with the primary objective of enhancing medical care through the detection and prediction of multiple medical episodes. These episodes may include, but are not limited to, seizures, falls, cardiac events, or any combination thereof, which significantly impact the health and well-being of users 101 . In an embodiment, the user 101 is provided with a wearable device 102 having one or more sensors, which are configured to detect a plurality of physiological and movement parameters In an embodiment, the user 101 may have multiple wearable devices to monitor a number of varied physiological and movement parameters. In the embodiments of the invention as described herein, the wearable device 102 may be selected from a group of, but not limited to, smartwatches or medical monitoring bands or smart ring, body skin patch and other health wearable devices. The wearable sensors of the embodiments of the invention as described herein may include one or more of, but are not limited to, photoplethysmography (PPG) sensors for measuring heart rate,electrocardiogram (ECG) sensors for monitoring cardiac activity and detecting irregular heart rhythms, accelerometers and gyroscopes for capturing movement, activity levels, and identifying events such as falls or seizures, blood oxygen SpO2sensors for determining blood oxygen saturation, skin temperature sensors for monitoring peripheral temperature changes, galvanic skin response (GSR) sensors for measuring skin conductance related to stress or seizure activity, respiration rate sensors such as piezoelectric or bioimpedance-based sensors for tracking breathing patterns, optical or capacitive pressure sensors for non-invasive blood pressure monitoring, and bioelectrical impedance analysis (BIA) sensors for assessing body composition metrics including fat percentage, muscle mass, and water content.

[0074] The physiological and movement data collection module 104 is in communication with one or more sensors of the wearable device 102 to continuously gather vital physiological and movement data of the user 101 and provide real-time data to the data integration module 106.

[0075] The data integration module 106 plays a pivotal role in enhancing the system’s 100 analytical depth by merging the collected physiological and movement data with personal user information associated with a personal profile unique to each user, allowing the system to personalize the medical episode detection based on individual health characteristics and preferences. This incorporation creates an integrated dataset that not only reflects real-time physiological and movement conditions but also incorporates personal health history, thereby allowing for a more accurate analysis of the user’s 101 health status. The user's unique health profile holds user-specific settings to improve the detection and prediction of medical episodes, such as, for example, seizures, falls, cardiac events, or combinations thereof, using data collected from wearable sensors. These settings are tied to a personal profile unique to each user, allowing the system to personalize the medical episode detection based on individual health and medical condition characteristics. These medical condition settings are tied to the personal profile unique to each user, allowing the system to personalize the medical episode detection based on individual health characteristics and medical conditions.

[0076] In the embodiments and examples described herein, the user’s unique personal profile includes data of predetermined values for detection of fall including, for example, with reference to Figure 8, one or more of: maximum fall time of the user (MET) 807, time to detect on the floor (TTDOTF) 805, time on the floor TOTF 805 and 806, Acceleration sensitivity (AS) 809, on the ground sensitivity OTGS 803 and High Acceleration threshold (HA) 801. Further, these predetermined values for detection of near fall also includes one or more of: near maximum fall time of the user NMFT 808, near time to detect on the floor (NTTDOTF) 806, near time on the floor (NTOTF) 811 and 812, near acceleration sensitivity (NAS) 810, near on the ground sensitivity (NOTGS) 804 and near high acceleration threshold (NHA) 802. These 12 settings are unique to each user and are used by the automatic detection process described herein and in the examples to determine the occurrence of fall and near fall medical episode(s).

[0077] Ensuring the privacy and security of the collected data, the data storage module 108 is configured to safely store and encrypt the wealth of personal and physiological and movement data generated by the system 100. This module ensures that all sensitive health information is kept secure, addressing both user privacy concerns and regulatory compliance requirements.

[0078] The data analysis module 110 employs machine learning models to analyse integrated data including, for example, personal historical data of the user is combined with the collected physiological and movement data, to identify patterns or indicators suggestive of imminent (or potential future) medical episodes. The machine learning models are continually refined through adaptive learning processes that incorporate user feedback, enhancing the system’s 100 predictive accuracy and reliability over time.

[0079] The alert and feedback module 112, which serves a dual function. First, it generates timely alerts to stakeholders, such as caregivers or healthcare providers, upon the detection or prediction of a medical episode, facilitating immediate and appropriate response actions. Secondly, it collects feedback from users regarding the alerts’ accuracy and relevance, enabling the system 100 to dynamically refine its data analysis models. This feedback loop not only empowers user 101 by involving them in the monitoring process but also ensures that the system 100 evolves to meet the user’s needs more effectively.

[0080] Together, these modules form an integrated system that seamlessly combines data collection, analysis, and user interaction to detect and predict medical episodes accurately. Through its advanced data processing techniques, the system 100 not only enhances the ability to provide timely and personalized medical care but also significantly contributes to improving the overall quality of life for users.

[0081] The system 100 further comprising a visual analytics display module 114 configured to generate and display visual analytics of the user’s physiological and movement data trends to stakeholders, enhancing the interactive review and monitoring capabilities for users, caregivers, and healthcare providers. Preferably, the visual analytics display module 114 employs Artificial Intelligence prediction model to create a dashboard for displaying alerts and warnings for user and stakeholders including, but not limited to, caregivers and healthcare providers.

[0082] Figure 2 illustrates a method 200 for detecting and predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user, in accordance with a preferred embodiment of the present invention. As shown in Figure 2, at step 202, a physiological and movement data from one or more sensors of wearable devices worn by the user is continuously collected. This data collection is ongoing, ensuring a steady stream of information regarding the user’s physiological and movement state is captured in real time through these devices.

[0083] At step 204, personalised historical data of the user is combined with the collected physiological and movement data to generate an integrated data. The personal historical data ofthe user includes, but not limited to, medical history, age, gender, and known medical conditions of the user including, for example, but not limited to, the user’s movement patterns, Heart rate patterns, blood oxygen, skin temperature, sleep patterns, and classifying the user’s Activities of Daily Life (ADL), and the like.

[0084] At step 206, the collected physiological and movement data and the personal historical data is encrypted and stored in a data storage module.

[0085] At step 208, the occurrence of medical episodes is detected, and potential medical episodes are predicted by using a data analysis module. The analysis of the data analysis module includes identifying patterns indicative of medical episodes such as an actual medical episode where the user requires urgent assistance or a near medical episode which just requires close monitoring of user’s physiological and movement parameters. Further, at step 208, the data analysis module applies deep learning and machine learning models specifically trained to recognize early signs of medical episodes relevant to the user’s known medical conditions, including analysing user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns, and classifying the user’s Activities of Daily Life (ADL).

[0086] At step 210, personal historical data of the user is updated, preferably on real-time basis, in reference to the continuously collected physiological and movement data by the one or more sensors of the wearable device worn by the user.

[0087] At step 212, actual feedback is received from the user regarding their current health status and based on the realistic input from the user the integrated data is refined to improve accuracy of medical episode prediction and detection. This ensures that stakeholders are not alarmed but only notified as warnings in near medical episode scenarios to avoid wastage of resources as well as avoid unnecessary panic.

[0088] At step 214, machine learning and artificial intelligence models are applied on the personal historical data to recognize signs of medical episodes in order to improve the medical episode detection and prediction accuracy over time. An example of application of machine learning models on the basis of disclosed method is illustrated in Figure 5 below.

[0089] The Machine Learning (ML) Model components of the aspects and embodiments of the invention as described herein are configured, for example, as a convolutional neural network (CNN) trained to classify fall, seizure, and non-episode events using labelled time-series data collected from wearable sensors (e.g., accelerometer, gyroscope, and heart rate sensors, among others) in conjunction with the user’s unique user profile settings as disclosed above and in the following examples. The training dataset typically includes multiple activity classes annotated by clinical experts and / or user feedback. The ML model processes input data by first applying preprocessing techniques to normalize sensor signals and remove noise. The model then transforms raw data from each of the sensors into a higher-dimensional representation suitable for downstream feature extraction. During training, the model optimizes internal parameters —such as filter weights and learned coefficients — via backpropagation to minimize classification error. The final layer outputs probability values indicating the likelihood of different types of medical episodes. These probabilities are then passed to a weighting system for final decisionmaking.

[0090] Furthermore, deep learning methods such as convolutional neural networks CNNs or recurrent neural networks (RNN) have been shown to provide state-of-the-art results on challenging activity recognition tasks with little or no data feature engineering. The Machine Learning model of the presently described systems and methods is optionally configured to learn an internal representation of the time-series data and ideally achieve comparable performance to models fit on a version of the dataset with engineered features. The trained model can classify inputs generated by users for different types of activity, such as walking, sitting, running, sleeping, falling, fit, etc., by capturing user activities in fixed-size time-windows and continuously sending them to the Machine Learning model.

[0091] At step 216, alerts are generated and relayed to one or more stakeholders, including caregivers and healthcare providers, when one or more medical episodes is detected or predicted. These alerts are well defined as per the actual medical episode scenario and helps each and every stakeholder to understand the urgency of the situation as well as guide them how to react to the particular situation. Further, at step 216, visual analytics are generated and displayed to the user and stakeholders, including caregivers and healthcare providers, enable detail review of the user’s physiological and movement data trends. Preferably, the visual analytics are generated by employing Artificial Intelligence prediction model to create a dashboard for displaying alerts and warnings for user and stakeholders including caregivers and healthcare providers.Examples

[0092] The following examples provide exemplary embodiments of the systems and methods for detecting and predicting multiple medical episodes as described herein. It will be appreciated that each of the features particularised with respect to each of the exemplary example described below are optionally interchangeable with additional embodiments or examples of the systems and methods as disclosed herein.Example 1

[0093] Figure 3 illustrates an exemplary implementation 300 of the method shown in Figure 2 above. As shown in Figure 3, a user 301 wearing a wearable device 302. The wearable device 302 has one or more sensors to detect physiological and movement parameters of the user 301 , including heart rate, blood oxygen, blood pressure, body temperature, skin conductance, respiratory rate, and movement patterns. The continuous physiological and movement data collection from the wearable device 302 is captured at a data collection module 304.

[0094] The data collection module 304 is feeding the physiological and movement data to: a Machine learning module 306 which enables in improving detection and prediction of a number of medical episodes by improving the user’s 301 historical health profile 308. Further, this real-time updated historical data of the user 301 is stored and encrypted in a data storage module 310; and a data analysis module 314 which is configured to run a combined process to detect multiple medical episodes by analysing an integrated data formed by combination of continuous physiological and movement data in real-time and the user’s historical data.

[0095] Further, the machine learning module 314 applies deep learning and machine learning models specifically trained to recognize early signs of medical episodes relevant to the user’s known medical conditions, including analysing user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns, and classifying the user’s Activities of Daily Life (ADL).

[0096] Further, the data analysis module 314 is connected to a medical episode detection information module 312. The medical episode detection information module 312 comprises the information about specific conditions related to a number of medical episodes such as fall, seizure, cardiac event and their corresponding reference condition based on the data improved by the machine learning module 306.

[0097] The data analysis module 314 is further configured to determine whether the user 301 requires immediate help or not.

[0098] In the case where the user 301 requires immediate assistance then the data analysis module 314 trigger 316 the alert module 322, which is configured to generate and send alerts to one or more stakeholders, such as, but not limited to, caregivers and healthcare service providers.

[0099] In the case where the user 301 does not require immediate assistance the data analysis module 314 keep running the combined process to detect multiple medical episodes on the basis of continuous analysis of the integrated data.

[0100] The data storage module 310 is connected with a health data analysis module 312 which is configured to continuously analysing the updated historical data the user 301 and provide the relevant information such as statistics related to each of the medical episode under monitoring, movement of the user 301 , reaction of stakeholders in the event of immediate attention notification etc. Further, health data analysis module 312 generates this information in the form of visual analytics and provide it to the user 301 and stakeholders for their review anytime anywhere.

[0101] The data storage module 310 is also connected with an Artificial Intelligence (Al) prediction module 320 which is configured to predict occurrence of one or more medical episodesand may be trigger 318 warning from the module 324 to generate and send alert to the user as well as stakeholders.Example 2

[0102] Figure 4 illustrates an exemplary demonstration 400 of the working of the method shown in Figure 2 above.

[0103] As shown in Figure 4, physiological and movement data such as heart rate and movement pattern is collected from the wearable device 402 worn by the user 401. This physiological and movement data is used to train machine learning model 405 which improves historical data of the user in real-time and data analysis module 406 which runs a combined process to detect multiple medical episodes by comparing physiological and movement data detected and threshold predetermined values related to occurrence of medical episode or near medical episode.

[0104] Thereafter, a data comparison module compares the information provided by machine learning model and data analysis module, and at the decision step 407, determines whether an actual medical episode is detected or not.

[0105] In case a medical episode is detected, which can be fall or seizure or cardiac medical episode or any combination of these medical episodes, then feedback module 408 prompts the user if they need immediate help, or they suffered with one or more medical episodes, but they can manage on their own or they have not observed any symptoms of any of the medical episodes.

[0106] Based on the input received from the user, alerts are generated and sent to stakeholders by an alert module 409 or a warning module 410, or the information is provided to a feedback module 411.

[0107] The feedback module 411 relays the information to data processing module 412 which updates the user’s historical data profile and threshold information of one or more medical episodes for the user. The data processing module provides this updated data to the data storage module 413 for storing this updated information after encryption and the data storage module feeds this updated information to the machine learning module 405 to further improve the detection and prediction of multiple medical episodes by using combined process.

[0108] Further, the data processing module 412 updates the threshold medical episode settings in the wearable device 402 of the user 401 to avoid any false alerts in the future events.Example 3

[0109] Figure 5 illustrates an exemplary implementation of step 406 of the method as shown in Figure 4 above representing a Medical Episode (ME) detecting process. Figure s provides alogic flow diagram of a system that combines the probability weighting of the output from a threshold-based algorithm 501 with the output from a machine learning model 502. This logic is applied to the detection of Medical Episodes, including but not limited to seizures, falls, cardiac events, or any combination thereof.

[0110] As shown in Figure s, the machine learning model 502 applied, at step 214, on the personal historical data to recognize signs of medical episodes in order to improve the medical episode detection and prediction accuracy over time, receives inputs in respect of user’s profile database 505. This database contains historical data regarding events that have been previously learned or experienced by the user, suggesting a personalized approach to decision-making. Additionally, the system retrieves a Predefined Probability Threshold (PPT) 503 set by the analyse of the integrated data 208, or manually by the user or healthcare provider. This threshold acts as a critical value that will later serve as a benchmark to determine the outcome of the event prediction process.

[0111] Further, the machine learning model 502 begins with integration of values from two distinct decision-making processes i.e., the Threshold-Based Process (TB) and a Machine Learning Model (ML). Each of these methodologies comes with its own weight (TB weight and ML weight) and computed probability (TB probability and ML probability), as explained in the above figures. As shown in Figure 5, a weighting system 504 is employed to blend the probabilities provided by both TB and ML, anchored on the principle that the sum of TB weight and ML weight must be unity, ensuring that the overall contribution is proportionately distributed. As described above, the Machine Learning Model component is configured as, for example, as a convolutional neural network (CNN) trained to classify fall, seizure, and non-episode events using labelled time-series data collected from wearable sensors (e.g., accelerometer, gyroscope, and heart rate). The training dataset includes multiple activity classes annotated by clinical experts and / or user feedback. The ML model processes input data by first applying preprocessing techniques to normalize sensor signals and remove noise. The model then transforms the raw sensor data into a higher-dimensional representation suitable for downstream feature extraction. During training, the model optimizes internal parameters — such as filter weights and learned coefficients — via backpropagation to minimize classification error. The final layer outputs probability values indicating the likelihood of different types of medical episodes. These probabilities are then passed to the weighting system for final decision-making.

[0112] As explained in the above figures and as shown in Figure 5, the probability of the event occurrence using both the threshold-based (TB) and machine learning (ML) methods is computed independently. As explained above, the TB calculation typically involves predefined criteria or thresholds that, when surpassed, indicate the likelihood of an event. Conversely, the ML model predicts the probability based on pattern recognition within the accumulated data over time. Subsequent to these calculations, the step 214 of method 200 assigns the weights for TB and ML. These assigned weights are adaptable and may be adjusted based on the learning and thespecific circumstances of each event at steps 208 and 210 of the method 200 elaborated in Figure 2 above In the example depicted in graph 507, it can be observed that, over time, a higher weight is attributed to the output of the machine learning model 502 compared to the threshold-based algorithm 501 , reflecting the system’s increasing reliance on learned behaviour patterns.

[0113] As shown in Figure 5, the calculated TB and ML probabilities, in conjunction with their respective weights, are then synthesized to deduce the final probability 505 of the multiple medical episodes, termed as the Final Medical Episode (ME) Probability. This enables decision-making where the Final ME Probability is compared with the user’s PPT. If the calculated probability exceeds the PPT, the system anticipates the event ME will occur; if not, the event is predicted not to occur. Further, the method 200 exhibits adaptability by incorporating a set of predefined exceptions 506 that could potentially alter the TB weight. These exceptions account for variances such as an unusual occurrence of ME, a very near ME event, or other atypical threshold-based data that might bias the predictions. Therefore, the disclosed method 200 does not firmly rely on its initial weight settings and can improved in response to exceptional data inputs.Example 4

[0114] Figure 6 illustrates an example 600 of system 100 of Figure 1 , where medical episodes from the group of seizure or fall or cardiac event in a user is detected are detected alone or in combination.

[0115] As shown in Figure 6, the physiological and movement data of the user is collected from one or more wearable devices worn by the user and provided as input 601 and 602 to data analysis module (combined process) 603 to analysis the value of integrated data. Thereafter, the value of integrated data is compared with threshold values stored in user-specific settings associated with the personal profile of the user. These threshold values are configured to correspond to multiple medical episodes, such as seizure 604 or fall 605 or cardiac 606. If these threshold values higher than the predetermined values for one or more aforesaid medical episodes, then an alert indicating occurrence seizure and / or fall and / or cardiac is generated and sent to the user and stakeholders. The user-specific settings associated with the personal profile contain threshold values (settings) that are automatically updated based on the continuously collected sensor data and the application of machine learning algorithms. As a result, the threshold values are dynamically adjusted to reflect changes in the user’s medical condition. Alternatively, these threshold values may also be updated manually by the user, a caregiver, or a healthcare provider via an application running on a mobile device.

[0116] Figure 7 illustrates an example 700 of automatic detection of fall medical episode shown in Figure 6. As shown in Figure 7, 6 fall predetermined values are employed to detect one of the medical episodes i.e., fall by employing method shown in Figure 2. These 6 predetermined values are detection of maximum fall time of the user (MFT) 704, time to detect on the floor(TTDOTF) 703, time on the floor TOTF 706 and 707, Acceleration sensitivity (AS) 705, on the ground sensitivity OTGS 702 and high acceleration threshold (HA) 701. These 6 settings, which are part of the user’s personal profile, are unique to each user and are used by the automatic detection process to determine the occurrence of fall medical episode.

[0117] Figure s illustrates another example 800 of automatic detection of fall and near fall medical episode shown in Figure 6. As shown in Figure s, 12 predetermined values are employed to detect one of the medical episodes or near medical episode i.e., fall detection and near fall detection by employing method shown in Figure 2. The 6 predetermined values for detection of fall are maximum fall time of the user (MFT) 807, time to detect on the floor (TTDOTF) 805, time on the floor TOTF 805 and 806, Acceleration sensitivity (AS) 809, on the ground sensitivity OTGS 803 and High Acceleration threshold (HA) 801. Further, the 6 predetermined values for detection of near fall are near maximum fall time of the user NMFT 808, near time to detect on the floor (NTTDOTF) 806, near time on the floor (NTOTF) 811 and 812, near acceleration sensitivity (NAS) 810, near on the ground sensitivity (NOTGS) 804 and near high acceleration threshold (NHA) 802. These 12 settings, which are part of the user’s personal profile, are unique to each user and are used by the automatic detection process to determine the occurrence of fall and near fall medical episode.

[0118] Figure 9 illustrates an example 900 indicating real fall data with convulsion 902 on the 3rd phase of the fall during detection of fall medical episode in Figure 7 above. This real confirmed data recorded fall is shown in the graph of Figure 9, with reference to TTFOTF 903, TOTF 904 and 905 and OTGS 906, as also referenced in Figure 7 and Figure 8. These three parameters may be used for detecting the immobility of the user 102 in the third phase of a fall. The settings TTFOTF, TOTF and OTGS, are changeable by the user him / herself. In some embodiments, this may be affected through a mobile app executed on a portable digital device, which gives the user full control of the customization of how the device detects the third phase of the fall as immobility on the floor. For example, people may have a lot of convulsions or shaking after a fall when on the floor. Alternatively, they may exhibit long-term immobility on the floor or short-term immobility on the floor. Even a very short time may be set by the user to detect all falls with no immobility time on the floor.

[0119] Figure 10 illustrates an example 1000 indicating allowed multiple convulsions during 3rd phase of a fall between multiple (4 in this example) TOTF 1001 of example shown in Figure 7 above.

[0120] Figure 11 illustrates an example 1100 of automatic detection of seizure medical episode showing in Figure 6. As shown in Figure 11 , 3 seizure settings, from user-specific settings associated with the user personal profile unique to the user, are employed to detect one of the medical episodes i.e., seizure by employing method shown in Figure 2. These 3 predetermined values are duration of shake (DOS) 1103, maximum pause changing direction time (MP) 1102 and shaking speed, minimum force (SS) 1101.

[0121] Figure 12 illustrates another example 1200 of automatic detection of seizure and near seizure medical episode shown in Figure 6. As shown in Figure 12, 6 predetermined values are employed to detect one of the medical episodes or near medical episode i.e., seizure and near seizure by employing method shown in Figure 2. The 3 predetermined values for detection of seizure are duration of shake (DOS) 1205, maximum pause changing direction time (MP) 1204 and shaking speed, minimum force (SS) 1201 and the 3 predetermined values for detection of near seizure are near duration of shake NDOS 1206, near maximum pause changing direction time (NMP) 1203 and near shaking speed, minimum force (NSS) 1202. These 6 settings, which are part of the user’s personal profile, are unique to each user and are used by the automatic detection process to determine the occurrence of seizure and near seizure medical episode.

[0122] Figure 13 illustrates an example 1300 of automatic detection of cardiac medical episode shown in Figure 6. As shown in Figure 13, 4 cardiac predetermined values from user-specific settings associated with the user personal profile unique to the user, are employed to detect one of the medical episodes i.e., tachycardia and bradycardia by employing method shown in Figure 2. These 4 predetermined values are low heart rate (LHR) 1303, time of bradycardia (TOB) 1304, high heart rate (HHR) 1301 , time of tachycardia (TOT) 1302.

[0123] Figure 14 illustrates another example 1400 of automatic detection of cardiac medical episode and near cardiac medical episode shown in Figure 6. As shown in Figure 14, 8 cardiac predetermined values are employed to detect one of the medical episodes i.e., tachycardia and bradycardia or one of the near medical episodes i.e., near tachycardia and near bradycardia by employing method shown in Figure 2. These 4 predetermined values are low heart rate (LHR) 1406, time of bradycardia (TOB) 1408, high heart rate (HHR) 1401 , time of tachycardia (TOT) 1402 to detect tachycardia and bradycardia and 4 predetermined values are near low heart rate NLHR 1405, near time of bradycardia NTOB 1407, near high heart rate NHHR 1404, near time of tachycardia NTOT 1403 to detect near tachycardia and bradycardia.

[0124] Figure 15 illustrates an example 1500 indicating data from a combined 3 or more processes running and detecting seizure 1502, fall 1503, tachycardia 1501 , SpO2 1504, and others by employing method 200 shown in Figure 2.

[0125] Figure 16 illustrates an example 1600 indicating real data for combined seizure and fall process by employing method 200 shown in Figure 2.

[0126] Figure 17 illustrates a system 1700 for detecting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided, in accordance with another embodiment of the present invention. As shown in Figure 17, the system comprising a data reception module 1703 receiving data from wearable sensors 1702, a data analysis module 1704, a comparison module 1706, a detection module 1708 and an alert module 1710.

[0127] The data reception module 1703 is configured to continuously read data from one or more sensors of wearable devices 1702 of a user 1701. Preferably, the one or more sensors configured to detect a plurality of physiological and movement parameters including, but not limited to, heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

[0128] The data analysis module 1704 may analyse the received data from the data reception module 1702 and identifying patterns in the data that are indicative of one or more medical episodes. The analysed data may be real-time value of a plurality of physiological and movement parameters including, but not limited to, heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

[0129] The comparison module 1706 may compare the analysed data with predetermined data. The comparison module 1706 determines predetermined data as a function of threshold data and historical data specific to the user stored in the data storage module 1707. Further, the storage module 1707 comprises the data of one or more medical episodes previously detected i.e., details of medical episode, values of a range of physiological and movement parameters including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns at the time of occurrence of the medical episode. These medical condition settings are tied to the personal profile unique to each user, allowing the system to personalize the medical episode detection based on individual health characteristics and medical conditions.

[0130] Further, the threshold data and historical data may be continuously updated by the data analysis module 1704 based on real-time data detected by one or more sensors to improve episode detection accuracy over time. Furthermore, the historical data of each of the one or more medical episode specific for the user is updated, by using Machine Learning one or more predetermined feedback values comprises a Medical Episode event or near Medical Episode Event and analysis of data of one or more medical episodes previously detected.

[0131] The detection module 1708 is configured for detecting the occurrence of the one or more medical episodes based on the comparison of the analysed data with predetermined data. Further, the detection module 1708 is configured to receive feedback from the user 1701 and trigger an alert to one or more stakeholders after receiving one or more predetermined feedback values. Furthermore, the detection module 1708 receives feedback from the user 1701 , which includes, but not limited to, manual input regarding their current health status or automated input based on user reactions or responses detected by the one or more sensors of the wearable device 1702.

[0132] The alert module 1710 may send an alert when triggered by the detection module 1708, wherein the alert module 1710 is configured to transmit information to stakeholders along with relevant data and episode severity assessment.

[0133] Figure 18 illustrates a method 1800 for employing the system 1700 for detecting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The method 1800 includes: at step 1802, receiving data from one or more sensors of wearable devices of a user; at step 1804, analysing the received data from one or more sensors; at step 1808, comparing the analysed data with predetermined data; at step 1806, detecting occurrence of one or more medical episodes based on the comparison; and at step 1810, sending an alert to one or more stakeholders.

[0134] Figure 19 illustrates a system 1900 for predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The system comprising a physiological and movement data collection module 1903, a data storage module 1904, a data integration module 1905, a data analysis module 1907, a prediction generation module 1908 and a feedback module 1909.

[0135] The physiological and movement data collection module 1903 continuously collects physiological and movement data from one or more sensors of wearable devices 1902 worn by a user 1901. Preferably, the physiological and movement data collection module 1903 collects data related to the user’s heart rate, blood oxygen, blood pressure, body temperature, skin conductance, respiratory rate, and movement patterns.

[0136] The data storage module 1904 stores and encrypts the collected physiological and movement and personal data of the user.

[0137] The data integration module 1905 integrates personal data of the user with the collected physiological and movement data to provide integrated data. The personal user data includes, but not limited to, medical history, age, gender, and known medical conditions of the user. Further, the data integration module 1905 uses feedback from the feedback module 1909 to dynamically refine the integrated data, to improve the accuracy of medical episode prediction over time. Furthermore, the data integration module 1905 is configured to dynamically refine the integrated data by implementing adaptive learning techniques, using Machine Learning and Artificial Intelligence, to refine the model as more physiological and movement data is collected.

[0138] The data analysis module 1907 analyses the integrated data. Further, the data analysis module 1907 applies machine learning models to analyse the integrated data including user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns for classifying the user’s Activities of Daily Life (ADL) and identifying patterns indicative of potential medical episodes. Furthermore, deep learning methods such as convolutional neural networks CNNs or recurrent neural networks (RNN) have been shown to provide state-of-the-art results on challenging activity recognition tasks with little or no data feature engineering. The Machine Learning model can learn an internal representation of the time-series data and ideally achievecomparable performance to models fit on a version of the dataset with engineered features. The trained model can classify inputs generated by users for different types of activity, such as walking, sitting, running, sleeping, falling, fit, etc., by capturing user activities in fixed-size time-windows and continuously sending them to the Machine Learning model.

[0139] The prediction generation module 1908 generates a prediction of a potential medical episode based on the analysed integrated data. Further, the prediction generation module 1908 refines the analysed integrated data using contextual data such as time of day, user location, and recent physical activity. The CNN model can predict a probability value for each class of activity. Our research has shown that the obtained precision by the convolution model, based on CNN, over trial data is 94%.

[0140] The feedback module 1909 receives feedback from the user regarding their current health status. Preferably, the feedback module 1909 includes an interactive interface on wearable devices or an associated mobile application. The user may respond with feedback 400 of either; I need help; I had a medical episode but I am okay; or I did not have a medical episode. Further, the feedback module 1909 is connected with a visual analytics display module (not shown) configured to generate and display visual analytics of the user’s physiological and movement data trends to stakeholders. Preferably, the one or more stakeholders are from the group of caregivers, healthcare providers.

[0141] Figure 20 illustrates a method 2000 for employing the system 1900 for predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user is provided. The method 2000 includes: at step 202, continuously collecting physiological and movement data from one or more sensors of wearable devices worn by the user; at step 2004, storing the collected physiological and movement data in a data storage module; at step 2006, analysing the integrated data by a prediction module; at step 2008, combining personal data of the user with the collected physiological data to generate integrated data; at step 2010, generating a prediction of a potential medical episode based on the analysed integrated data by the prediction module; and at step 2012, receiving feedback from the user regarding their current health status.Interpretation

[0142] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly sodefined herein. For the purposes of the present invention, additional terms are defined below. Furthermore, all definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms unless there is doubt as to the meaning of a particular term, in which case the common dictionary definition and / or common usage of the term will prevail.

[0143] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular articles “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise and thus are used herein to refer to one or to more than one (i.e., to “at least one”) of the grammatical object of the article. By way of example, the phrase “an element” refers to one element or more than one element.

[0144] Throughout this specification, unless the context requires otherwise, the words “comprise”, “comprises” and “comprising” will be understood to imply the inclusion of a stated step or element or group of steps or elements but not the exclusion of any other step or element or group of steps or elements.

[0145] The term “real-time” for example “displaying real-time data,” refers to the display of the data without intentional delay, given the processing limitations of the system and the time required to accurately measure the data.

[0146] As used herein, the term “exemplary” is used in the sense of providing examples, as opposed to indicating quality. That is, an “exemplary embodiment” is an embodiment provided as an example, as opposed to necessarily being an embodiment of exemplary quality for example serving as a desirable model or representing the best of its kind.

[0147] The phrase “and / or,” as used herein in the specification and in the claims, should be understood to mean “either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with “and / or” should be construed in the same fashion, i.e., “one or more” of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the “and / or” clause, whether related or unrelated to those elements specifically identified. Thus, as a non-limiting example, a reference to “A and / or B”, when used in conjunction with open-ended language such as “comprising” can refer, in one embodiment, to A only (optionally including elements other than B); in another embodiment, to B only (optionally including elements other than A) ; in yet another embodiment, to both A and B (optionally including other elements); etc.

[0148] As used herein in the specification and in the claims, “or” should be understood to have the same meaning as “and / or” as defined above. For example, when separating items in a list, “or” or “and / or” shall be interpreted as being inclusive, i.e., the inclusion of at least one, but also including more than one of a number or list of elements, and, optionally, additional unlisted items.

[0149] As used herein in the specification and in the claims, the phrase “at least one,” in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed within the list of elements and not excluding any combinations of elements in the list of elements. This definition also allows that elements may optionally be present other than the elements specifically identified within the list of elements to which the phrase “at least one” refers, whether related or unrelated to those elements specifically identified. Thus, as a non-limiting example, “at least one of A and B” (or, equivalently, “at least one of A or B,” or, equivalently “at least one of A and / or B”) can refer, in one embodiment, to at least one, optionally including more than one, A, with no B present (and optionally including elements other than B); in another embodiment, to at least one, optionally including more than one, B, with no A present (and optionally including elements other than A); in yet another embodiment, to at least one, optionally including more than one, A, and at least one, optionally including more than one, B (and optionally including other elements); etc.Bus

[0150] In the context of this document, the term “bus” and its derivatives, while being described in a preferred embodiment as being a communication bus subsystem for interconnecting various devices including by way of parallel connectivity such as Industry Standard Architecture (ISA), conventional Peripheral Component Interconnect (PCI) and the like or serial connectivity such as PCI Express PCIe, Serial Advanced Technology Attachment (Serial ATA) and the like, should be construed broadly herein as any system for communicating data.Module

[0151] The module(s) is envisaged to include computing capabilities such as a memory unit (not shown) configured to store machine readable instructions. The machine-readable instructions may be loaded into the memory unit from a non-transitory machine-readable medium such as, but not limited to, CD-ROMs, DVD-ROMs, and Flash Drives. Alternately, the machine-readable instructions may be loaded in a form of a computer software program into the memory unit. The memory unit in that manner may be selected from a group comprising EPROM, EEPROM and Flash memory. In accordance with some embodiments, the modules 104, 106, 108, 110, 112, 114 may further include one or more processors, memory units, a communication bus, and a wireless communication interface. The wireless communication interface may be configured to securely transmit and receive data between the user’s wearable device and a secure cloud-based infrastructure, such as a Software-as-a-Service SaaS platform. This secure cloud infrastructure may host various backend services, including data analysis, threshold processing, alert management, and user-specific profile storage. The cloud-based system may also provide secure APIs for third-party integrations, caregiver access, or healthcare provider dashboards, enabling real-time synchronization and continuous monitoring of the user’s health status.Communication between the modules and the cloud may utilize standard secure protocols, such as HTTPS, TLS, or VPN tunnels, ensuring the integrity and confidentiality of transmitted data

[0152] Further, the module includes a processor or plurality of high-speed computing processors with multiple cores (not shown) operably connected with the memory unit. In various embodiments, the processor is one of, but not limited to, a general-purpose processor, an application specific integrated circuit ASIC and a field-programmable gate array FPGA.In Accordance With

[0153] As described herein, ‘in accordance with’ may also mean ‘as a function of’ and is not necessarily limited to the integers specified in relation thereto.Composite Items

[0154] As described herein, ‘a computer implemented method’ should not necessarily be inferred as being performed by a single computing device such that the steps of the method may be performed by more than one cooperating computing devices.

[0155] Similarly objects as used herein such as ‘web server’, ‘server’, ‘client computing device’, ‘computer readable medium’ and the like should not necessarily be construed as being a single object, and may be implemented as a two or more objects in cooperation, such as, for example, a web server being construed as two or more web servers in a server farm cooperating to achieve a desired goal or a computer readable medium being distributed in a composite manner, such as program code being provided on a compact disk activatable by a license key downloadable from a computer network.Database

[0156] In the context of this document, the term “database” and its derivatives may be used to describe a single database, a set of databases, a system of databases or the like. The system of databases may comprise a set of databases wherein the set of databases may be stored on a single implementation or span across multiple implementations. The term “database” is also not limited to refer to a certain database format rather may refer to any database format. For example, database formats may include MySQL, MySQLi , XML or the like.Wireless

[0157] An embodiment of the present disclosure may include or otherwise be embodied using devices conforming to other network standards and for other applications, including, for example other WLAN standards and other wireless standards. Applications that can be accommodated include IEEE 802.1 1 wireless LANs and links, and wireless Ethernet.

[0158] In the context of this document, the term “wireless” and its derivatives may be used to describe circuits, devices, systems, methods, techniques, communications channels, etc., that may communicate data through the use of modulated electromagnetic radiation through a non-solid medium. The term does not imply that the associated devices do not contain any wires, although in some embodiments they might not. In the context of this document, the term “wired”, and its derivatives may be used to describe circuits, devices, systems, methods, techniques, communications channels, etc., that may communicate data through the use of modulated electromagnetic radiation through a solid medium. The term does not imply that the associated devices are coupled by electrically conductive wires.Processes

[0159] Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification discussions utilizing terms such as “processing”, “computing”, “calculating”, “determining”, “analysing” or the like, refer to the action and / or processes of a computer or computing system, or similar electronic computing device, that manipulate and / or transform data represented as physical, such as electronic, quantities into other data similarly represented as physical quantities.Processor

[0160] In a similar manner, the term “processor” may refer to any device or portion of a device that processes electronic data, e.g., from registers and / or memory to transform that electronic data into other electronic data that, e.g., may be stored in registers and / or memory. A “computer” or a “computing device” or a “computing machine” or a “computing platform” may include one or more processors.

[0161] The methodologies described herein are, in one embodiment, performable by one or more processors that accept computer-readable (also called machine-readable) code containing a set of instructions that when executed by one or more of the processors carry out at least one of the methods described herein. Any processor capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken are included. Thus, one example is a typical processing system that includes one or more processors. The processing system further may include a memory subsystem including main RAM and / or a static RAM, and / or ROM.Computer-Readable Medium

[0162] Furthermore, a computer-readable carrier medium may form, or be included in a computer program product. A computer program product can be stored on a computer usable carrier medium, the computer program product comprising a computer readable program means for causing a processor to perform a method as described herein.Networked or Multiple Processors

[0163] In alternative embodiments, the one or more processors operate as a standalone device or may be connected, e.g., networked to other processor(s), in a networked deployment, the one or more processors may operate in the capacity of a server or a client machine in server-client network environment, or as a peer machine in a peer-to-peer or distributed network environment. The one or more processors may form a web appliance, a network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine.

[0164] Note that while some diagram(s) only show(s) a single processor and a single memory that carries the computer-readable code, those in the art will understand that many of the components described above are included, but not explicitly shown or described in order not to obscure the inventive aspect. For example, while only a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.Additional Embodiments

[0165] Thus, one embodiment of each of the methods described herein is in the form of a computer-readable carrier medium carrying a set of instructions, e.g., a computer program that are for execution on one or more processors. Thus, as will be appreciated by those skilled in the art, embodiments of the present invention may be embodied as a method, an apparatus such as a special purpose apparatus, an apparatus such as a data processing system, or a computer-readable carrier medium. The computer-readable carrier medium carries computer readable code including a set of instructions that when executed on one or more processors cause a processor or processors to implement a method. Accordingly, aspects of the present invention may take the form of a method, an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of carrier medium (e.g., a computer program product on a computer-readable storage medium) carrying computer-readable program code embodied in the medium.Carrier Medium

[0166] The software may further be transmitted or received over a network via a network interface device. While the carrier medium is shown in an example embodiment to be a single medium, the term “carrier medium” should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store the one or more sets of instructions. The term “carrier medium” shall also be taken to include any medium that is capable of storing, encoding, or carrying a set of instructions for execution by one or more of the processors and that cause the one or more processors to perform any one or moreof the methodologies of the present invention. A carrier medium may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media.Implementation

[0167] It will be understood that the steps of methods discussed are performed in one embodiment by an appropriate processor (or processors) of a processing (i.e., computer) system executing instructions (computer-readable code) stored in storage. It will also be understood that the invention is not limited to any particular implementation or programming technique and that the invention may be implemented using any appropriate techniques for implementing the functionality described herein. The invention is not limited to any particular programming language or operating system.Means for Carrying Out a Method or Function

[0168] Furthermore, some of the embodiments are described herein as a method or combination of elements of a method that can be implemented by a processor of a processor device, computer system, or by other means of carrying out the function. Thus, a processor with the necessary instructions for carrying out such a method or element of a method forms a means for carrying out the method or element of a method. Furthermore, an element described herein of an apparatus or system embodiment is an example of a means for carrying out the function performed by the element for the purpose of carrying out the invention.Connected

[0169] Similarly, it is to be noticed that the term connected, when used in the claims, should not be interpreted as being limitative to direct connections only. Thus, the scope of the expression a device A connected to a device B should not be limited to devices or systems wherein an output of device A is directly connected to an input of device B. It means that there exists a path between an output of A and an input of B which may be a path including other devices or means. “Connected” may mean that two or more elements are either in direct physical or electrical contact, or that two or more elements are not in direct contact with each other but yet still co-operate or interact with each other.Embodiments

[0170] Reference throughout this specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment but may. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner, aswould be apparent to one of ordinary skill in the art from this disclosure, in one or more embodiments.

[0171] Similarly, it should be appreciated that in the above description of example embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description of Specific Embodiments are hereby expressly incorporated into this Detailed Description of Specific Embodiments, with each claim standing on its own as a separate embodiment of this invention.

[0172] Furthermore, while some embodiments described herein include some, but not other features included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention, and form different embodiments, as would be understood by those in the art. For example, in the following claims, any of the claimed embodiments can be used in any combination.Specific Details

[0173] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures, and techniques have not been shown in detail in order not to obscure an understanding of this description.

[0174] It will be appreciated that the methods / apparatus / devices / systems described / illustrated above at least substantially provide a system and method for pathology specimen collection.

[0175] The system and method for pathology specimen collection described herein, and / or shown in the drawings, are presented by way of example only and are not limiting as to the scope of the invention. Unless otherwise specifically stated, individual aspects and components of the system and method for pathology specimen collection may be modified, or may have been substituted therefore known equivalents, or as yet unknown substitutes such as may be developed in the future, or such as may be found to be acceptable substitutes in the future. The system and method for pathology specimen collection may also be modified for a variety of applications while remaining within the scope and spirit of the claimed invention, since the range of potential applications is great, and since it is intended that the present invention be adaptable to many such variations.Terminology

[0176] In describing the preferred embodiment of the invention illustrated in the drawings, specific terminology will be resorted to for the sake of clarity. However, the invention is not intended to be limited to the specific terms so selected, and it is to be understood that each specific term includes all technical equivalents which operate in a similar manner to accomplish a similar technical purpose. Terms such as “forward”, “rearward”, “radially”, “peripherally”, “upwardly”, “downwardly”, and the like are used as words of convenience to provide reference points and are not to be construed as limiting terms.Different Instances of Objects

[0177] As used herein, unless otherwise specified the use of the ordinal adjectives “first”, “second”, “third”, etc., to describe a common object, merely indicate that different instances of like objects are being referred to and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.Comprising and Including

[0178] In the claims which follow and in the preceding description of the invention, except where the context requires otherwise due to express language or necessary implication, the word “comprise” or variations such as “comprises” or “comprising” are used in an inclusive sense, i.e., to specify the presence of the stated features but not to preclude the presence or addition of further features in various embodiments of the invention.

[0179] Any one of the terms including or which includes or that includes as used herein is also an open term that also means including at least the elements / features that follow the term, but not excluding others. Thus, including is synonymous with and means comprising.

[0180] Throughout this specification, unless the context requires otherwise, the words “comprise”, “comprises” and “comprising” will be understood to imply the inclusion of a stated step or element or group of steps or elements but not the exclusion of any other step or element or group of steps or elements. Any one of the terms “including” or “which includes” or “that includes” as used herein is also an open term that also means including at least the elements / features that follow the term, but not excluding others. Thus, “including” is synonymous with and means “comprising”.

[0181] In the claims, as well as in the summary above and the description below, all transitional phrases such as “comprising”, “including”, “carrying”, “having”, “containing”, “involving”, “holding”, “composed of”, and the like are to be understood to be open-ended, i.e., to mean “including but not limited to”. Only the transitional phrases “consisting of” and “consisting essentially of” alone shall be closed or semi-closed transitional phrases, respectively.Scope of Invention

[0182] Thus, while there has been described what are believed to be the preferred embodiments of the invention, those skilled in the art will recognize that other and further modifications may be made thereto without departing from the spirit of the invention, and it is intended to claim all such changes and modifications as fall within the scope of the invention. For example, any formulas given above are merely representative of procedures that may be used. Functionality may be added or deleted from the block diagrams and operations may be interchanged among functional blocks. Steps may be added or deleted to methods described within the scope of the present invention.

[0183] Although the invention has been described with reference to specific examples, it will be appreciated by those skilled in the art that the invention may be embodied in many other forms.

[0184] Those skilled in the art will appreciate that the invention described herein is susceptible to variations and modifications other than those specifically described. The invention includes all such variation and modifications. The invention also includes all of the steps, features, formulations, and compounds referred to or indicated in the specification, individually or collectively and any and all combinations of any two or more of the steps or features.

[0185] Even though particular combinations of features are recited in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of possible implementations. In fact, many of these features may be combined in ways not specifically recited in the claims and / or disclosed in the specification. Although each dependent claim listed below may directly depend on only one claim, the disclosure of possible implementations includes each dependent claim in combination with every other claim in the claim set.Chronological Order

[0186] For the purpose of this specification, where method steps are described in sequence, the sequence does not necessarily mean that the steps are to be carried out in chronological order in that sequence, unless there is no other logical manner of interpreting the sequence.Markush Groups

[0187] In addition, where features or aspects of the invention are described in terms of Markush groups, those skilled in the art will recognise that the invention is also thereby described in terms of any individual member or subgroup of members of the Markush group.Industrial Applicability

[0188] It is apparent from the above, that the arrangements described are applicable to the medical industry, and specifically to systems and methods for detecting and predicting medical episodes selected from the group of seizure and / or fall and / or cardiac and / or in combination in a user.

Claims

CLAIMS:1 . A method for detecting and predicting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising steps of: continuously collecting a physiological and movement data from one or more sensors of one or more wearable devices worn by the user; using user-specific settings associated with a personal profile unique to the user, where the personal profile includes predefined thresholds, historical health data, and emergency response preferences, combining personal historical data of the user with the collected physiological and movement data to generate an integrated data, where the personal historical data includes medical history, age, gender, and known medical conditions of the user; storing and encrypting the collected physiological and movement data and the personal historical data in a data storage module; analysing the integrated data based on the user-specific settings to detect the occurrence of medical episodes and to predict potential medical episodes using a data analysis module, wherein the analysis includes identifying patterns indicative of medical episodes; updating the personal historical data based on the physiological and movement data detected by the one or more sensors; applying machine learning models on the personal historical data to recognize signs of medical episodes while refining detection based on user-specific settings; in order to improve the medical episode detection and prediction accuracy over time; receiving feedback from the user regarding their current health status and dynamically refining the integrated data to improve accuracy of medical episode prediction and detection; and generating and sending alerts to one or more stakeholders, including caregivers and healthcare providers, when one or more medical episodes is detected or predicted, or when deviations in movement patterns indicate a potential risk.

2. The method of Claim 1 , wherein the one or more sensors are configured to detect a plurality of physiological and movement parameters based on user-specific settings to optimize detection of medical episodes, including, but not limited to heart rate, blood oxygen, blood pressure, body temperature, skin conductance, respiratory rate, and movement patterns.

3. The method of either Claim 1 or Claim 2, wherein the data analysis module applies deep learning and machine learning models specifically trained to recognize early signs of medical episodes relevant to the user’s known medical conditions and user-specific settings, including analysing user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns, and classifying the user’s Activities of Daily Life (ADL).

4. The method of any one of the preceding claims, further comprising a step of generating and displaying visual analytics of the user’s physiological and movement data trends for user and stakeholder, including caregivers and healthcare providers, review.

5. The method of Claim 4, wherein the step of generating and displaying visual analytics comprises of employing Artificial Intelligence prediction model to create a dashboard for displaying alerts and warnings for user and stakeholders including caregivers and healthcare providers.

6. A system for detecting and predicting medical episodes from the group of seizure, fall, cardiac and combinations thereof in a user, comprising: a physiological and movement data collection module configured to continuously collect data from one or more sensors of wearable devices worn by the user; a data integration module to combine personal user data with collected physiological and movement data to provide integrated data; a data storage module for storing and encrypting collected physiological and movement and personal data; a data analysis module is configured to analyse the integrated data using the user-specific settings for detecting and predicting medical episodes and apply machine learning models to refine analyses based on the user feedback; and an alert and feedback module for generating alerts to stakeholders, including caregivers and healthcare providers, and receiving user feedback, wherein the feedback is used to dynamically refine the integrated data and improve the accuracy of medical episode prediction and detection.

7. The system of Claim 6, wherein the physiological and movement data collection module is further configured to collect data related to a comprehensive range of physiological and movement parameters and the prediction generation module refines analysed integrated data using contextual data such as time of day, user location, and recent physical activity.

8. The system of either Claim 6 or Claim 7, further comprising a visual analytics display module configured to generate and display visual analytics of the user’s physiological and movement data trends to stakeholders, enhancing the interactive review and monitoring capabilities for users, caregivers, and healthcare providers.

9. The system of Claim 8, wherein the visual analytics display module further configured to employ Artificial Intelligence prediction model to create a dashboard for displaying alerts and warnings for user and stakeholders including caregivers and healthcare providers.

10. A method of detecting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user comprising: receiving data from one or more sensors of wearable devices of a user; analysing the received data from one or more sensors; comparing the analysed data with predetermined data; detecting occurrence of the one or more medical episodes; and sending an alert to one or more stakeholders;wherein the step of receiving data comprises a step of continuously reading data from the one or more sensors; wherein the step of comparing comprises a step of determining predetermined data by combining threshold data and historical data; and wherein the step of detecting comprises a step of receiving feedback from the user and a step of triggering an alert to the one or more stakeholders after receiving one or more predetermined feedback values.1 1 . The method as claimed in Claim 10, wherein the one or more sensors are configured to detect a plurality of physiological and movement parameters including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

12. The method as claimed in either Claim 10 or Claim 1 1 , wherein the analysed data is real-time value of a plurality of physiological and movement parameters based on user-specific settings to optimize detection of medical episodes, including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

13. The method as claimed in any one of Claims 10 to 12, wherein the method further includes a step of updating the threshold data and the historical data based on real-time data detected by the one or more sensors to improve medical episode detection accuracy over time.

14. The method as claimed in any one of Claims 10 to 13, wherein the threshold data of each of the one or more medical episode specific for the user is updated based on receiving one or more predetermined feedback values from the user.

15. The method as claimed in any one of Claims 10 to 14, wherein the historical data of each of the one or more medical episode specific for the user is updated, by using Machine Learning one or more predetermined feedback values comprises of Medical Episode event or near Medical Episode Event and analysis of data of one or more medical episodes previously detected.

16. The method as claimed in Claim 15, wherein the data of one or more medical episodes previously detected comprises details of medical episode, values of a range of physiological and movement parameters including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns at the time of occurrence of the medical episode.

17. The method as claimed in any one of Claims 10 to 16, wherein the receiving one or more predetermined feedback values include manual input regarding user current health status or automated input based on user reactions or responses detected by the one or more sensors.

18. The method as claimed in any one of Claims 10 to 17, wherein the step of sending an alert includes transmitting information to the one or more stakeholders, from the group of caregivers, healthcare providers, along with relevant data and episode severity assessment.

19. The method as claimed in any one of Claims 10 to 18, wherein the step of analysing data comprising a step of identifying patterns indicative of one or more medical episodes.

20. A system for detecting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising: a data reception module configured to continuously read data from one or more sensors of wearable devices of a user; a data analysis module for analysing the received data from the data reception module and identifying patterns in the data that are indicative of one or more medical episodes; a comparison module for comparing the analysed data with predetermined data, wherein the comparison module is further configured to determine predetermined data as a function of threshold data and historical data specific to the user; a detection module for detecting the occurrence of the one or more medical episodes based on the comparison of the analysed data with predetermined data, wherein the detection module is configured to receive feedback from the user and trigger an alert to one or more stakeholders after receiving one or more predetermined feedback values; and an alert module for sending an alert when triggered by the detection module, wherein the alert module is configured to transmit information to stakeholders along with relevant data and episode severity assessment.

21. The system as claimed in Claim 20, wherein the one or more sensors configured to detect a plurality of physiological and movement parameters including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

22. The system as claimed in either Claim 20 or claim 21 , wherein the analysed data is real-time value of a plurality of physiological and movement parameters including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns.

23. The system as claimed in any one of Claims 20 to 22, wherein the threshold data and the historical data is continuously updated by the data analysis module based on real-time data detected by one or more sensors to improve episode detection accuracy over time.

24. The system as claimed in any one of Claims 20 to 23, wherein the threshold data of each of the one or more medical episodes specific for the user is updated by the data analysis module based on receiving one or more predetermined feedback values from the user by the detection module.

25. The system as claimed in any one of Claims 20 to 24, wherein the historical data of each of the one or more medical episode specific for the user is updated, by using Machine Learning one or more predetermined feedback values comprises of Medical Episode event or near Medical Episode Event and analysis of data of one or more medical episodes previously detected.

26. The system as claimed in Claim 25, wherein the data of one or more medical episodes previously detected comprises details of medical episode, values of a range of physiological and movement parameters including but not limited to heart rate, blood oxygen, blood pressure, body temperature, and movement patterns at the time of occurrence of the medical episode.

27. The system as claimed in any one of Claims 20 to 26, wherein the detection module is further configured to receive feedback from the user, which can include manual input regarding their current health status or automated input based on user reactions or responses detected by the one or more sensors.

28. A method for predicting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising: continuously collecting physiological and movement data from one or more sensors of wearable devices worn by a user; storing the collected physiological and movement data in a data storage module; combining personal data of the user with the collected physiological and movement data to generate integrated data, wherein the personal data of the user includes medical history, age, gender, and known medical conditions of the user; analysing the integrated data by a prediction module; generating a prediction of a potential medical episode based on the analysed integrated data by the prediction module; and receiving feedback from the user regarding their current health status, wherein the feedback is used to dynamically refine the integrated data to improve the accuracy of medical episode prediction over time.

29. The method as claimed in Claim 28, wherein the step of continuously collecting physiological and movement data further includes collecting data related to the user’s heart rate, blood pressure, body temperature, skin conductance, respiratory rate and movement patterns, and other wearable sensors.

30. The method as claimed in either Claim 28 or Claim 29, wherein the step of analysing the integrated data include applying deep learning models specifically trained to recognize early signs of medical episodes relevant to the user’s known medical conditions.

31. The method as claimed in Claim 30, wherein the step of analysing the integrated data further includes applying machine learning models to analyse the integrated data including user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns for classifying the user’s Activities of Daily Life (ADL), and identifying patterns indicative of potential medical episodes.

32. The method as claimed in any one of Claims 28 to 31 , wherein the step of storing data includes encrypting the physiological and movement and personal data of the user for privacy and security.

33. The method as claimed in any one of Claims 28 to 32, wherein the step of generating a prediction of a potential medical episode is further refined using contextual data such as time of day, user location, and recent physical activity.

34. The method as claimed in any one of Claims 28 to 33, wherein the dynamically refining the integrated data includes implementing adaptive learning techniques to refine the model as more physiological and movement data is collected.

35. The method as claimed in any one of Claims 28 to 34, further comprising generating and displaying visual analytics of the user’s physiological and movement data trends for user and stakeholders review.

36. The method as claimed in Claim 35, wherein the one or more stakeholders are from the group of caregivers, healthcare providers.

37. A system for predicting medical episodes selected from the group of seizure, fall, cardiac and combinations thereof in a user, comprising: a physiological and movement data collection module configured to continuously collect physiological and movement data from one or more sensors of wearable devices worn by a user; a data storage module configured to store and encrypt the collected physiological and movement and personal data of the user; a data integration module configured to integrate personal data of the user with the collected physiological and movement data to provide integrated data, wherein the personal user data includes medical history, age, gender, and known medical conditions of the user; a data analysis module configured to analyse the integrated data; a prediction generation module configured to generate a prediction of a potential medical episode based on the analysed integrated data; and a feedback module configured to receive feedback from the user regarding their current health status, wherein the feedback is used by the data integration module to dynamically refine the integrated data, to improve the accuracy of medical episode prediction over time.

38. The system as claimed in Claim 37, wherein the physiological and movement data collection module is further configured to collect data related to the user’s heart rate, blood oxygen, blood pressure, body temperature, skin conductance, respiratory rate and movement patterns.

39. The system as claimed in either Claim 37 or Claim 38, wherein the data analysis module is configured to apply machine learning models to analyse the integrated data including user’s movement, heart rate patterns, blood oxygen, skin temperature, sleep patterns for classifying the user’s Activities of Daily Life (ADL) and identifying patterns indicative of potential medical episodes.

40. The system as claimed in any one of Claims 37 to , wherein the prediction generation module is further configured to refine the analysed integrated data using contextual data such as time of day, user location, and recent physical activity.

41. The system as claimed in any one of Claims 37 to 40, wherein the feedback module includes an interactive interface on wearable devices or an associated mobile application.

42. The system as claimed in any one of Claims 37 to 41 , wherein the data integration module is configured to dynamically refine the integrated data by implementing adaptive learning techniques to refine the model as more physiological and movement data is collected.

43. The system as claimed in any one of Claims 37 to 42, further comprising a visual analytics display module configured to generate and display visual analytics of the user’s physiological and movement data trends to stakeholders.

44. The system as claimed in Claim 43, wherein the one or more stakeholders are from the group of caregivers, healthcare providers.

Images