Description:HEALTH-MONITORING WEARABLE DEVICE AND METHOD FOR DETECTION AND PERSONALIZED INSIGHTS

FIELD OF INVENTION
[0001] The present disclosure relates to health monitoring and diagnostic devices, and particularly relates to noninvasive health-monitoring wearable device and method for detection and personalized insights.
BACKGROUND
[0002] With the increasing prevalence of chronic diseases such as respiratory, diabetes, cardiovascular conditions, and metabolic disorders, the need for continuous health monitoring has become paramount. Existing health monitoring methods primarily focus on periodic clinical tests or require invasive procedures that may not be feasible for regular use. Also, there are limited options of ambulatory regular health monitoring at personal end that is non clinical monitoring.
[0003] For instance, disease like diabetes is a chronic condition characterized by elevated blood sugar levels. It occurs when the body either does not produce enough insulin (type 1) or becomes resistant to insulin (type 2). Without timely diagnosis and management, diabetes can lead to serious complications such as blindness, kidney failure, and nerve damage. It also significantly increases the risk of strokes and coronary heart disease. However, with early detection and proper management, individuals can improve their quality of life and effectively manage the condition.
[0004] The increasing global burden of chronic diseases such as cardiovascular conditions (such as COPD, Congestive heart failure), diabetes, respiratory diseases (such as Asthma), and mental disorders, there is a growing demand for solutions that can provide proactive health management. Conventional medical assessments such as blood tests, ECGs, or regular doctor visits offer valuable information but typically occur sporadically and do not provide continuous, real-time insights into an individual's health. As a result, many health issues go undetected until they progress to more severe stages, reducing the effectiveness of treatment.
[0005] Several blood-based methods are available for detection and monitoring. However, these approaches are invasive, require specialized laboratory equipment, the usage frequency is limited, require consumables for each measure, and are not always portable. It also involve blood sampling. Wearable devices such as fitness trackers and smartwatches have gained popularity for monitoring activity levels, heart rate, and physiological parameters.
[0006] Consequently, efforts have been made previously to provide health monitoring devices to detect abnormalities. For instance, U.S. Patent Application no. US15/465,069 discloses a method and system for continuous monitoring of health parameters during exercise. The system includes one or more wearable devices affixed on the user with a chest strap or adhesive sticker, coupled with an application running on a computing device (smartphone/smartwatch), and provides the user or the concerned personnel with various insights about the general health of the user. Although, the device monitors activity levels and heart rate, but it does not provide comprehensive, condition-specific insights or personalized health management.
[0007] Further, it is well-known that a person’s breath contains various volatile and nonvolatile organic compounds that may reflect their metabolic and health status. For instance, research such as Szulejko et al.’s article "Evidence for Cancer Biomarkers in Exhaled Breath" highlights the presence of cancer biomarkers in the breath. Also CO2 is a marker of nutrition (carbohydrate and fat) metabolism, respiratory or cardiovascular conditions.
[0008] In this context, Indian patent application no. 202021000591 discloses method and apparatus for breath-based biomarker detection and analysis. The invention provides a device for non-invasive monitoring and/or detection of diabetes in a subject based on detection of volatile organic compounds (VOCs) in the exhaled breath of a subject. However, the device limits itself to detection of diabetes using carbon nanotube-based array sensor and does not provide a comprehensive health analysis along with personalized health recommendations for user. It relies on a handheld breath-analysis tool for breath collection through mouth, limiting use to specific conditions and scenarios.
[0009] Another technology is disclosed by U.S. Patent application US14/907,302 which provides determining respiratory gas exchange in a subject. The method includes providing a representative inhale-exhale cycle breathing volume over time profile; and using data relating to oxygen consumption or carbon dioxide production during the inhale-exhale cycle that met the correspondence criterion to determine a metabolic property in the subject.
[0010] Similarly, Lumen Metabolic Tracker is a hand-held tracker device to track metabolism of a person by analyzing exhaled CO₂. However, it faces several limitations:
• It uses a single-breath CO₂ analyzer to estimate metabolic state, focusing on metabolic flexibility rather than comprehensive health tracking.
• It is limited to CO₂ levels from breath, primarily offering data on carbohydrate vs. fat usage for energy derived from RQ.
• The breath sample collection is from mouth and recommended method is inhale hold exhale.
• The device operation requires controlled breathing for each measurement, demanding user compliance and specific breath-holding techniques.
• It also relies on a handheld breath-analysis tool for breath collection through mouth, limiting use to specific conditions and scenarios.
• It relies on established methods of breath analysis without significant advancements in multi-parameter tracking or scalability.
[0011] Therefore, there remains a need for a wearable health-monitoring device capable of detecting early signs of various health conditions, providing personalized insights, and offering continuous, non-invasive monitoring of multiple health metrics.
[0012] Hence, design and development of a non-invasive solution for diagnosing diabetes based on a subject's breath profile and breath analytes, providing a more convenient and effective diagnostic method along with the other physiological sensing e.g sensing pulse parameters, with high reliability is presented by the invention. The present disclosure discloses a health-monitoring wearable device and method for detection and personalized insights. The device provides real-time, continuous monitoring of various health parameters allowing for more accurate and up-to-date health data compared to periodic measurements.
[0013] The present invention overcomes the limitations of the prior arts (such as Lumen Metabolic Tracker) and offers several advantages:
• It utilizes non-invasive optical sensors and a breath sensor capable of detecting CO₂, acetone and other parameters to assess metabolism. This approach provides continuous or multi-sensing tracking of metabolic, respiratory and cardiovascular parameters. The device is specifically meant to capture the breath sample from nose while natural tidal breathing. The device is specifically meant to be built with one or more breath sensors as per requirement to capture the profile of one or more parameters from breath samples of natural tidal breathing.
• It captures multiple parameters such as heart rate, heart rate variability, breath rate, skin temperature, breath CO2, breath temperature, breath humidity and other breath biomarkers, and motion artifacts, allowing for a holistic view of metabolic and overall health.
• It monitors natural breathing patterns, ensuring usability without requiring the user to perform controlled breathing.
• It employs advanced machine learning algorithms based on input from multiple sensors to derive various secondary physiological parameters and health metrics using primary sensed parameters, to provide personalized, real-time feedback and trend analysis across multiple metrics over time.
• It is designed for passive or minimal user input, with automated data collection, syncing, and calibration. Suitable for both continuous monitoring and spot-checks. It does not require any special modulated breathing method, spot measures also possible just in natural resting state.

OBJECTS OF THE INVENTION
[0014] It is an object of the present disclosure which provides health-monitoring wearable devices and methods for detection and personalized insights.
[0015] It is an object of the present disclosure which provides a real-time, continuous monitoring of various health parameters along with the opportunity to collect and analyse normal breath air as and when required for multiparametric assessment allowing for more accurate and up-to-date health data compared to periodic and forced breath measurements of CO2.

SUMMARY
[0016] The present disclosure is directed towards a wearable device for health monitoring and detection with personalized health insights. The wearable device comprising of atleast two of sensors selected from a plurality of sensors, wherein the plurality of sensors including an Acetone sensor, a CO₂ sensor, and a photoplethysmography (PPG) sensor; a breath chamber connected to the plurality of sensors to collect user breath via an inlet; atleast one printed circuit board (PCB) configured to receive and process data from the plurality of sensors, wherein the PCB includes an integrated processing module to continuously analyze the real-time user data including breath and physiological parameters; a wireless module including Bluetooth and/or Wi-Fi to enable real-time data transmission; and a battery for powering the wearable device.
[0017] In an aspect of the present disclosure, the plurality of sensors further including an IR temperature sensor, a 6-axis MEMS motion tracking sensor, a humidity sensor, and a temperature sensor. The integrated processing module (4) is configured to utilize machine learning to process user data to determine a plurality of metrics including breath CO₂ concentration with end tidal CO2 concentration (ETCO₂), respiratory quotient (RQ), energy expenditure derived from volume of CO₂ production, oxygen consumption, Heart rate, Heart rate variability, breath humidity, breath temperature, Breath rate and skin temperature. The integrated processing module is configured to process the user data and the plurality of metrics derived from the plurality of sensors to determine blood glucose, glucose utilisation rate, lactate threshold, metabolic risk score, stress, anxiety, and sleep quality. The integrated processing module is configured to process the user data and the plurality of metrics for identification of a pathological state of the user including diabetes, chronic obstructive pulmonary disease (COPD), asthma, congestive heart failure (CHF), and other metabolic conditions.
[0018] In an aspect of the present disclosure, the integrated processing module is configured to process the user data and the plurality of metrics for identification of a nasal cycle/nostril dominance and thus to assess the physiological state. The integrated processing module is configured to generate integrated health data based upon the user data and the pathological state of the user. The integrated processing module is configured to utilize machine learning to generate personalized recommendations for the user upon receiving integrated health data. The wearable device is configured to connect with atleast one display through wire or wirelessly to atleast one external device including a mobile phone and/or a computer, and wherein the wearable device further including atleast one band or strap or clip or ring configured to secure the device on a wrist or other suitable body part of the user.
[0019] The present disclosure is also directed towards a method for health monitoring and detection with personalized health insights by a wearable device. The method comprising of continuously monitoring breath and physiological parameters of a user by a plurality of sensors, wherein the plurality of sensors including atleast two of sensors selected from an Acetone sensor, a CO₂ sensor, and a PPG sensor; transmitting real-time user data from the plurality of sensors to an integrated processing module in a PCB; analyzing the user data using machine learning to determine a plurality of metrics including maximum CO₂ (ETCO₂) concentration, end tidal CO2 concentration, RQ, and energy expenditure derived from CO₂ production; identifying abnormality in the plurality of metrics to determine atleast one pathological state including diabetes, COPD, asthma, CHF, and other metabolic conditions; analysing user data using machine learning for identifying abnormality in the plurality of metrics to early detect atleast one pathological state including diabetes, COPD, asthma, CHF, mental health, reproductive health and other metabolic conditions; integrating health data of the user including the breath and physiological parameters to determine physiological and the pathological state of the user; and generating personalized nutritional and lifestyle recommendations based on the integrated health data.
[0020] In an aspect of the present disclosure, the method further comprising of transmitting the integrated health data to an external server for processing via wired or wireless communication; displaying results and recommendations on a connected mobile application; and validating CO₂-derived plurality of metrics against conventional clinical diagnostic methods for enhanced accuracy.

BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0022] FIG. 1 illustrates a diagram of wearable device for health monitoring and detection with personalized health insights in accordance with embodiments of the present disclosure.
[0023] FIG. 2 illustrates a diagram of a top view of the wearable device in accordance with embodiments of the present disclosure.
[0024] FIG. 3 illustrates an exemplary design of the wearable device of the present disclosure.
[0025] FIG. 4 illustrates another exemplary design of the wearable device of the present disclosure.
[0026] FIG. 5 illustrates a tabular presentation of sensed parameters and processing to generate comprehensive health profile by the wearable device in accordance with embodiments of the present disclosure.
[0027] FIG. 6 illustrates exemplary health metrics of user as shown in application display screen.
[0028] FIG. 7 illustrates exemplary continuous health monitoring and personalized recommendations in application display screen.
[0029] FIG. 8 (a) illustrates exemplary user score output and personalized recommendations in application display screen, (b) illustrates Metabolic health summary of user in application display screen.

DETAILED DESCRIPTION
[0030] Aspects of the present disclosure relate to health-monitoring wearable device and method for detection and personalized insights.
[0031] The following is a detailed description of embodiments of the disclosure. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[0032] The present disclosure is directed towards a wearable device and method for health monitoring and detection with personalized health insights. In an embodiment of the present disclosure, Figure 1 discloses a wearable device for health monitoring and detection with personalized health insights. The wearable device comprising of atleast two of sensors selected from a plurality of sensors. The plurality of sensors includes an Acetone sensor, a CO₂ sensor (41), and a photoplethysmography (PPG) sensor (42). The Acetone sensor is utilized for sensing acetone levels in human breath. The commercial CO₂ sensor (41) is for continuous breath-by-breath monitoring of exhaled CO₂ levels in human breath. The PPG sensor is used to detect volumetric changes in blood in peripheral circulation at the surface of the skin to provide information related to cardiovascular system.
[0033] The plurality of sensors further includes an IR temperature sensor, a 6-axis MEMS motion tracking sensor, a breath air humidity sensor, and a breath air temperature sensor located in the wearable device. The IR temperature sensor is for skin temperature monitoring. The 6-axis MEMS motion tracking device measures activity and posture analysis of user. The humidity and temperature sensor is for measuring the breath temperature and the extent of water loss in the user breath. The sensors exposed to user skin sense various physiological parameters through the skin.
[0034] A specially designed breath chamber (3) is provided to locate breath air sensors and to collect and expose adequate breath air to sensor so as to precisely monitor user breath profile of each breath cycle. The breath chamber (3) is connected to the plurality of sensors to collect user breath via an inlet (1) as well as to sense the correct usage. The exhaled user breath enters through the inlet (1) and exits through an outlet (2). The breath chamber (3) collects breath from the user and exposes it adequately to sensors for analysis. The wearable device can further include atleast one band configured to secure the device on a wrist of the user. The wearable device can further modified to include atleast one band or strap or ring or clip to be configured to secure the device on a suitable part of the body of the user e.g finger, wrist, palm, ear, face, arm, neck etc.
[0035] Atleast one printed circuit board (PCB) (or multiple PCBs) configured to receive and process data from the plurality of sensors is provided in the wearable device. The PCB includes an integrated processing module (4) to continuously analyze the real-time user data including breath and physiological parameters. The PCB aggregates and processes sensor data. The PCB includes a Motherboard (43) and a Daughterboard/s (44).
[0036] The wearable device has wireless Bluetooth and Wi-Fi connectivity for seamless data transfer and real-time health tracking. A wireless module including Bluetooth and/or Wi-Fi to enable real-time data transmission and a battery (5) for powering the wearable device is present.
[0037] In an embodiment of the present disclosure, the integrated processing module (4) is configured to utilize machine learning to process user data to determine a plurality of metrics. The CO₂ sensor (41) monitors exhaled CO₂ levels and sends data to the integrated processing module (4). The module (4) determines metrics including maximum CO₂ (ETCO₂) concentration or end tidal CO2 concentration, respiratory quotient (RQ- a ratio of CO2 produced to O2 consume in unit time), and energy expenditure derived from CO₂ production. The end-tidal CO₂ (ETCO₂) concentration is used to assess respiratory efficiency and gas exchange. The respiratory quotient (RQ) indicates metabolic substrate utilization. The energy expenditure based on CO₂ production and O2 consumption, reflects overall metabolic activity.
[0038] In an embodiment of the present disclosure, the integrated processing module (4) is configured to process the user data and the plurality of metrics for identification of a pathological state of the user. The breath-by-breath CO₂ monitoring along with other breath parameters provides dynamic insights into the progression and management of metabolic, respiratory and cardiovascular conditions including chronic obstructive pulmonary disease (COPD), asthma, and congestive heart failure (CHF). The abnormal ETCO₂ levels are used to detect early signs of respiratory or cardiovascular distress, enabling timely intervention and disease progression for chronic conditions.
[0039] In an embodiment of the present disclosure, the integrated processing module (4) is configured to generate integrated health data based upon the user data and the pathological state of the user. The integrated processing module (4) utilizes algorithms and means to integrate CO₂ data with other physiological parameters, including heart rate from the PPG sensor; breathing rate and breath inhalation exhalation profiles, nostril dominance; motion data from the MEMS sensor; and ETCO₂ trends over time. The module (4) generates a comprehensive health profile e.g blood glucose, glucose utilisation rate, lactate threshold, Metabolic risk score, nostril dominance, body temperature, % of calories from fat etc. for the user. Figure 5 shows sensing of vitals and processing to generate comprehensive health profile.
[0040] In an embodiment of the present disclosure, the wearable device is configured to connect through wire/wirelessly to atleast one external device including a mobile phone and/or a computer having atleast one display. A dedicated mobile application is installed in the mobile phone and/or a computer which displays real-time sensing and results. Figure 6 demonstrates various health metrics of a user as shown in application display.
[0041] In an embodiment of the present disclosure, the integrated processing module (4) is configured to utilize machine learning to generate personalized recommendations for the user upon receiving integrated health data. The personalized recommendation algorithm utilizes the health profile to generate tailored lifestyle advice, optimizing health outcomes for users and assisting in disease management. Tailored recommendations generated includes lifestyle measures, fitness plans, nutritional advice and disease management strategies. Figure 7 and 8 demonstrates personalized recommendations for a user based on the processing of the health data as shown in application display.
[0042] Device can be connected to the mobile device or computer and comprise a personalized health status and related recommendation algorithm to generates tailored nutritional and lifestyle advice based on integrated health data. The health parameter display/output on mobile screen. Personalized insights for a user can be displayed including present status, weekly and monthly trends etc.
[0043] The method for health monitoring and detection with personalized health insights by the wearable device. The method comprising of continuously monitoring breath and physiological parameters of a user by a plurality of sensors, wherein the plurality of sensors including atleast two of sensors selected from an Acetone sensor, a CO₂ sensor (41), and a PPG sensor (42); transmitting real-time user data from the plurality of sensors to an integrated processing module (4) in a PCB; analyzing the user data using machine learning to determine a plurality of metrics including maximum CO₂ concentration with end tidal CO2 concentration (ETCO₂), RQ, and energy expenditure derived from CO₂ production; identifying abnormality in the plurality of metrics to determine atleast one pathological state including diabetes, COPD, asthma, CHF, and other metabolic conditions; analysing user data using machine learning for identifying abnormality in the plurality of metrics to early detect atleast one pathological state including diabetes, COPD, asthma, CHF, mental health and other metabolic conditions; integrating health data of the user including the breath and physiological parameters and the pathological state of the user; and generating personalized lifestyle recommendations based on the integrated health data.
[0044] The continuous monitoring of exhaled breath CO₂ levels is done using CO₂ sensor (41) during breath analysis. The analyzing of CO₂ data is done to determine maximum CO₂ concentration with ETCO₂, respiratory quotient (RQ), glucose utilisation rate and energy expenditure. Abnormal ETCO₂ levels or patterns are identified which are indicative of conditions such as diabetes, COPD, asthma, or CHF. Integrating CO₂ data with heart rate, breathing rate, nostril dominance, and other physiological parameters is done to determine physical health, mental health, metabolic health and reproductive health and personalized lifestyle recommendations are generated based on the integrated health profile to manage and monitor health.
[0045] In an embodiment of the present disclosure, the method further comprising of transmitting the integrated health data to an external server for processing via wired or wireless communication; displaying results and recommendations on a connected mobile application; and validating CO₂-derived plurality of metrics against conventional clinical diagnostic methods for enhanced accuracy.
[0046] Personalized recommendation system
The recommendation system in the wearable device is designed to provide personalized and evidence-based lifestyle recommendations to users based on their physiological data and preferences.
Working of the personalized recommendation system:
• Stage 1: Demographic Recommendation System (Minimal User Input)-
During the initial stage, when a user registers, they provide basic demographic information through a questionnaire. The system analyzes this information and predicts suitable tags or categories based on the user's profile. These tags are then matched with relevant content categories stored in the content banks. The system prioritizes and presents the most suitable content to the user to follow, ensuring a relevant and personalized experience for users from the start.
• Stage 2: Hybrid Model (Demographic and Content-Based)-
As the user interacts with the application and builds trust, the system seeks more input in an engaging way, such as through activities or quizzes. The algorithm observes the user's performance based on the parameters monitored in relation to choices in these activities. It also considers the user's content preferences and choices up to that point. By combining this information with the initial data, the system refines its ability to provide even more relevant content recommendations.
• Stage 3: Hybrid Model (Content-Based and Collaborative Filtering)-
In the final stage, the system primarily relies on content-based recommendations and collaborative filtering. Collaborative filtering involves identifying users with similar content preferences and suggesting content that one user has found beneficial to others with similar preferences. No new user input is required at this stage. The algorithm continuously observes the user's data, choices and adapts its recommendations accordingly. It monitors the user database for any changes and keeps learning from user interests and interactions.
[0047] Examples of the personalized recommendations
1) Stage 1: Demographic Recommendation System (Minimal User Input)
User Scenario: New User with Limited Input
Recommendations:
• Welcome to BreathAI! We've analyzed your basic information, and based on your profile your stress level has been higher since the last three days, here's a curated selection for you.
• Explore "Relaxation Techniques for Beginners," a collection of easy-to-follow relaxation exercises.
• Discover "Calm Your Mind with Meditation," a series of guided meditation sessions.
• We recommend "Understanding Stress and Its Impact," a helpful guide to stress management.
2) Stage 2: Hybrid Model (Demographic and Content-Based)
User Scenario: User Building Trust with the Application
Recommendation:
• Congratulations on your progress! We'd like to get to know you better. Try our "Stress Quiz" to gain insights into your stress levels and preferences.
• Based on your quiz results and content choices, we suggest exploring "Conscious slow Breathing for Stress Relief" for effective stress management.
• You've shown an interest in relaxation content. Check out "Soundscapes for Peaceful Sleep" for improved sleep quality.
3) Stage 3: Hybrid Model (Content-Based and Collaborative Filtering)
User Scenario: Application Adapting to User Behavior
Recommendation:
• Great job so far! Your progress is being tracked, and we're tailoring recommendations to your preferences.
• Considering your current mood score of 4/10, sleep score of 65/100, and stress score of 85/100, here are personalized recommendations to help improve your well-being:
• For Improving Mood (4/10): (a) Conscious breathing lessons: 1.1, 5.1, 5.2, 6.1, 4.5. (b) Gut Health
• For Improving Sleep (65/100): (a) Conscious breathing lessons: 1.1, 5.1, 5.5, 5.6, 5.7, 6.1, 6.6, 6.8. (b) Curated calming sounds (background music) (c) Brown waves (d) Binaural (e) Gut Health (f) 7-day Pranayama
• For Reducing Stress (85/100): (a) Nadishodhan (b) Ujjayi (c) Conscious breathing lessons: 1.1, 5.1, 5.2, 6.1, 6.6, 4.1 (d) 7-day Pranayama (e) Gut Health
• For improving metabolic score and glucose level: (a) Diet recommendations (b) Reduce carbohydrate proportion in diet
[0048] Novelty and advantages of the present invention:
• It introduces a new type of combinations of sensors, and a unique algorithm, addressing limitations of single-metric breath-based devices and enhancing versatility and scalability.
• It is specifically designed to be useful to integrate for more and more biomarkers in breath, for non-invasive health monitoring.
• It considers the need of regular monitoring with ease at user level for the regular fitness and management of chronic health conditions like diabetes, COPD, asthma.
[0049] These tailored recommendations aim to address specific aspects of your well-being based on your individual scores. The wearable device facilitates long-term tracking of respiratory conditions, offering real-time alerts for deteriorating ETCO₂ levels indicative of exacerbations in COPD, asthma, or CHF. The device facilitates the vital parameter measurement and used in the mass/community health monitoring or screening device and also used as a home tool to monitor vitals at home. The device is a noninvasive physiological sensing and data collecting wearable device.
[0050] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.
, Claims:We Claim:
1. A wearable device for health monitoring and detection with personalized health insights, comprising of:
atleast two of sensors selected from a plurality of sensors, wherein the plurality of sensors including an Acetone sensor, a CO₂ sensor (41), and a photoplethysmography (PPG) sensor (42);
a breath chamber (3) connected to the plurality of sensors to collect and analyse user breath via an inlet (1);
atleast one printed circuit board (PCB) configured to receive and process data from the plurality of sensors, wherein the PCB includes an integrated processing module (4) to continuously analyze the real-time user data including breath and physiological parameters;
a wireless module including Bluetooth and/or Wi-Fi to enable real-time data transmission; and
a battery (5) for powering the wearable device,
wherein the plurality of sensors further including an IR temperature sensor, a 6-axis MEMS motion tracking sensor, a humidity sensor, and a temperature sensor either in combination or independently.
2. The wearable device as claimed in claim 1, wherein the integrated processing module (4) is configured to utilize machine learning to process user data to determine a plurality of metrics including breath CO₂ concentration with end tidal CO2 concentration (ETCO₂), respiratory quotient (RQ), energy expenditure derived from CO₂ production, oxygen consumption, volume of breath, Heart rate, Heart rate variability, breath humidity, breath temperature, Breath rate and skin temperature.
3. The wearable device as claimed in claim 2, wherein the integrated processing module (4) is configured to process the user data and the plurality of metrics derived from the plurality of sensors to determine blood glucose, glucose utilisation rate, lactate tolerance, mental health, physical health, reproductive health, stress and sleep quality.
4. The wearable device as claimed in claim 3, wherein the integrated processing module (4) is configured to process the user data and the plurality of metrics for identification and management of a pathological state of the user including diabetes, chronic obstructive pulmonary disease (COPD), asthma, congestive heart failure (CHF), and other metabolic conditions.
5. The wearable device as claimed in claim 2, wherein the integrated processing module (4) is configured to process the user data and the plurality of metrics for identification of a nasal cycle/nostril dominance and thus to assess the physiological state.
6. The wearable device as claimed in claim 4, wherein the integrated processing module (4) is configured to generate integrated health data based upon the user data and the pathological state of the user.
7. The wearable device as claimed in claim 6, wherein the integrated processing module (4) is configured to utilize machine learning to generate personalized recommendations for the user upon receiving integrated health data.
8. The wearable device as claimed in claim 1, wherein the wearable device is configured to connect with atleast one display through wire or wirelessly to atleast one external device including a mobile phone and/or a computer, and wherein the wearable device further including atleast one band configured to secure the device on a wrist of the user.
9. A method for health monitoring and detection with personalized health insights by a wearable device, wherein the method comprising of:
continuously or spot monitoring breath and physiological parameters of a user by a plurality of sensors, wherein the plurality of sensors including atleast two of sensors selected from an Acetone sensor, a CO₂ sensor (41), a PPG sensor (42), Humidity sensors and temperature sensors;
transmitting real-time user data from the plurality of sensors to an integrated processing module (4) in a PCB;
analyzing the user data using machine learning to determine a plurality of metrics including maximum CO₂ (ETCO₂) concentration, end tidal CO2 concentration, RQ, and energy expenditure derived from CO₂ production;
identifying abnormality in the plurality of metrics to determine atleast one pathological state including COPD, asthma, CHF, lung cancer, diabetes and other metabolic conditions;
analysing user data using machine learning for identifying abnormality in the plurality of metrics to early detect atleast one pathological state including diabetes, COPD, asthma, CHF, mental health, reproductive health and other metabolic conditions;
integrating health data of the user including the breath and physiological parameters to monitor current health status and to predict and monitor the pathological state of the user; and
generating personalized lifestyle recommendations based on the integrated health data.
10. The method as claimed in claim 9, wherein the method further comprising of:
transmitting the integrated health data to an external server for processing via wired or wireless communication;
displaying results and recommendations on a connected mobile application; and
validating CO₂-derived plurality of metrics against conventional clinical diagnostic methods for extending ease, feasibility and applicability and for enhanced accuracy.
11. The method as claimed in claim 9, wherein the continuously monitoring by the plurality of sensors further including an IR temperature sensor, and a 6-axis MEMS motion tracking sensor.
12. The method as claimed in claim 9, wherein the analyzing the user data using machine learning to determine a plurality of metrics to determine nasal cycle dominance and hydration status.