System and method for determining vascular health and vascular ageing index

Abstract

A smart wearable device 100 to determine vascular health and vascular ageing index of a user is described The smart wearable device 100 includes a PPG sensor 202, an accelerometer 204, hydration sensor 206, and temperature sensor 208 to acquire physiological and contextual data of the user. A processing unit 210 filters the PPG waveform using the motion data, hydration level, temperature data, and circadian rhythm to generate a filtered waveform. From this, morphological and temporal features are extracted. Behavioral and physiological modulators, such as sleep-stress score and VO₂ max-based cardio age, are also computed. These inputs form a multi-parametric feature set used by a machine learning model to generate a vascular ageing index.

Description

SYSTEM AND METHOD FOR DETERMINING VASCULAR HEALTH AND VASCULAR AGEING INDEXFIELD OF INVENTION

[0001] The present invention generally relates to a wearable health monitoring device. More specifically, the present invention is related to a smart wearable device capable of determining vascular health and vascular ageing index of users.BACKGROUND OF THE INVENTION

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.

[0003] The assessment of cardiovascular health of users has traditionally relied on clinical measurements such as blood pressure, pulse rate, electrocardiograms (ECG), and imagingbased diagnostic tools. While effective, such methods often require bulky equipment, skilled personnel, and controlled environments, making them less suited for continuous or real-time monitoring. With the growing need for proactive and preventive healthcare, particularly in tracking vascular health and detecting early signs of vascular ageing of the users, there has been a surge of interest in wearable technologies capable of performing such evaluations in a user-friendly, non-invasive manner.

[0004] Photoplethysmography (PPG) has emerged as a prominent optical technique for monitoring blood volume changes in the microvascular bed of tissue of the users. Many current-generation smart wearables incorporate PPG sensors to track heart rate and blood oxygen levels. However, such implementations typically extract only superficial physiological metrics and fall short in deriving deeper vascular health indicators, such as arterial stiffness or vascular ageing indices. Furthermore, motion artifacts, hydration variability, circadian rhythm influences, and environmental temperature fluctuations often compromise the accuracy and clinical reliability of such measurements.

[0005] While some existing solutions attempt to process PPG signals for advanced cardiovascular insights, they lack robustness in dynamic real-life scenarios. Most do not integrate motion correction mechanisms or consider user-specific physiological parameters in their analysis. Moreover, conventional solutions rely heavily on waveform morphology alone, without incorporating behavioral or contextual physiological modulators that influence vascular state of the user. These solutions also fail to integrate temporally sensitive parameters such as Heart Rate Variability (HRV) and post-exercise recovery dynamics, which can offer critical insights into cardiovascular adaptability and ageing.

[0006] Thus, there remains a need of a smart wearable device for capable of determining vascular health and vascular ageing index of the users.OBJECTS OF THE INVENTION

[0007] A general objective of the invention is to provide a smart wearable device capable determining vascular health of a user in real-time.

[0008] Another object of the present invention is to provide a smart wearable device capable determining vascular ageing index of the user.

[0009] Another object of the present invention is to extract morphological, temporal, and contextual features from PPG waveform data and associated sensors, to provide a holistic and adaptive assessment of vascular ageing.

[0010] Another object of the present invention is to incorporate behavioral and physiological modulators to dynamically adjust vascular ageing estimates in response to real- life changes.

[0011] SUMMARY OF THE INVENTION

[0012] This summary is provided to introduce aspects related to the present invention of a smart wearable device capable of determining vascular health and vascular ageing index of users and the aspects are further described below in the detailed description. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.

[0013] In an embodiment of the present disclosure, a smart wearable device is disclosed. The smart wearable device comprises a photoplethysmography (PPG) sensor configured to generate PPG waveform. The PPG waveform indicate changes in blood volume over time of a user. The smart wearable device further comprises an accelerometer configured to detect motion of the user and generate corresponding motion data. The smart wearable device further comprises a hydration sensor configured to determine hydration level of the user. The smart wearable device further comprises a temperature sensor configured to determine temperature data corresponding to a skin surface of the user. The smart wearable device further comprises a processing unit communicatively coupled to a memory, the PPG sensor, the accelerometer, the hydration sensor and the temperature sensor. The memory stores historical trend and log data of the user, user specific data and program instructions. The program instructions are executed by the processing unit. The processing unit is configured to receive the PPG waveform, the motion data the hydration level and the temperature data. The processing unit is further configured to determine a circadian rhythm profile of the user based on time information and the historical trend and log data. The processing unit is further configured to filter the PPG waveform based on at least one of the motion data, the hydration level, the temperature data and the circadian rhythm profile. The processing unit is further configured to extract one or more features from filtered PPG waveform. The processing unit is further configured to determine one or more behavioral and physiological modulators of the user based on one or more extracted features and user specific data. The processing unit is further configured to generate a feature set by combining the one or more extracted features and the behavioral and physiological modulators of the user. The processing unit is further configured to determine a vascular ageing index of the user based on generated feature set.

[0014] In an aspect of the present disclosure the smart wearable device is a smart ring.

[0015] In another aspect of the present disclosure, the smart wearable device is coupled to a user device via a wireless module.

[0016] In another aspect of the present disclosure, the smart wearable device is connected to a server to store and process one or more information collected by the smart wearable device. The one or more information includes at least one of the PPG waveforms, the motion data, the user specific data, the filtered waveform data, the first derivative waveform, the second derivative waveform, the vascular ageing index and historical trend and log data.

[0017] In another aspect of the present disclosure, the smart wearable device further comprises a battery module to support continuous operation over a prolonged period.

[0018] In another aspect of the present disclosure, the user specific data comprises at least one of age, gender, height, weight of the user.

[0019] In another aspect of the present disclosure, the user specific data is transferred to the memory of the smart wearable device via the user device.

[0020] In another aspect of the present disclosure, the one or more features extracted from the PPG waveform include at least one of waveform morphology, heart rate variability (HRV), pulse wave velocity, and post-exercise recovery slope.

[0021] In another aspect of the present disclosure, the one or more behavioral and physiological modulators comprises at least one of a sleep-stress score and a VO2 max-based cardio age model.

[0022] In another aspect of the present disclosure, the user access details of vascular health, the vascular ageing index and the historical trend and log data via a software application executable on the user device.

[0023] In another embodiment of the present disclosure, a method is disclosed. The method comprises receiving PPG waveform, motion data, hydration level and temperature data corresponding to a skin surface of the user via a photoplethysmography (PPG) sensor, an accelerometer, a hydration sensor and a temperature sensor respectively. The method further comprises determining a circadian rhythm profile of the user based on time information and historical trend and log data. The method further comprises filtering the PPG waveform based on at least one of the motion data, the hydration level, the temperature data and the circadian rhythm profile via a processing unit. The method further comprises extracting one or more features from filtered PPG waveform via the processing unit. The method further comprises retrieving, user specific data stored in memory via the processing unit. The method further comprises determining one or more behavioral and physiological modulators of the user based on one or more extracted features and the user specific data via the processing unit. The method further comprises generating a feature set by combining the one or more extracted features and the behavioral and physiological modulators of the user via the processing unit. The methodfurther comprises determining a vascular ageing index of the user based on generated feature set via the processing unit.

[0024] In another aspect of the present disclosure the smart wearable device is a smart ring.

[0025] In another aspect of the present disclosure, the smart wearable device is coupled to a user device via a wireless module.

[0026] In another aspect of the present disclosure, the smart wearable device is connected to a server to store and process one or more information collected by the smart wearable device. The one or more information includes at least one of the PPG waveforms, the motion data, the user specific data, the filtered waveform data, the first derivative waveform, the second derivative waveform, the vascular ageing index and historical trend and log data.

[0027] In another aspect of the present disclosure, the smart wearable device further comprises a battery module to support continuous operation over a prolonged period.

[0028] In another aspect of the present disclosure, the user specific data comprises at least one of age, gender, height, weight of the user.

[0029] In another aspect of the present disclosure, the user specific data is transferred to the memory of the smart wearable device via the user device.

[0030] In another aspect of the present disclosure, the one or more features extracted from the PPG waveform include at least one of waveform morphology, heart rate variability (HRV), pulse wave velocity, and post-exercise recovery slope.

[0031] In another aspect of the present disclosure, the one or more behavioral and physiological modulators comprises at least one of a sleep-stress score and a VO2 max-based cardio age model.

[0032] In another aspect of the present disclosure, the user access details of vascular health, the vascular ageing index and the historical trend and log data via a software application executable on the user device.BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings constitute a part of the description and are used to provide further understanding of the present invention. The drawings illustrate exemplary embodiments of the present invention and, together with the description, serve to explain the principles of the present invention.

[0034] Fig. 1 illustrates a working environment of a smart wearable device for determining vascular health and vascular ageing index of user, in accordance with an embodiment of the present invention.

[0035] Fig. 2 illustrates a block diagram of the smart wearable device for determining vascular health and vascular ageing index of the user, in accordance with an embodiment of the present invention.

[0036] Fig. 3a illustrates a Photoplethysmography (PPG) waveform generated by the photodetector, in accordance with an embodiment of the present invention.

[0037] Fig. 3b illustrates a filtered PPG waveform, in accordance with an embodiment of the present invention.

[0038] Fig. 3c illustrates a first derivative PPG waveform, in accordance with an embodiment of the present invention.

[0039] Fig. 3d illustrates a second derivative PPG waveform, in accordance with an embodiment of the present invention.

[0040] Fig. 4 illustrates a zoomed section of the second derivative PPG waveform, in accordance with an embodiment of the present invention.

[0041] Fig. 5 illustrates a flowchart depicting a method for determining vascular health and vascular ageing index of the user, in accordance with an embodiment of the present invention.

[0042] A more complete understanding of the present invention and its embodiments thereof may be acquired by referring to the following description and the accompanying drawings.DETAILED DESCRIPTION OF THE INVENTION

[0043] Exemplary embodiments now will be described with reference to the accompanying drawings. The disclosure may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey its scope to those skilled in the art. The terminology used in the detailed description of the particular exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting. In the drawings, like numbers refer to like elements.

[0044] It is to be noted, however, that the reference numerals used herein illustrate only typical embodiments of the present subject matter, and are therefore, not to be considered for limiting its scope, for the subject matter may admit to other equally effective embodiments.

[0045] The specification may refer to “an”, “another”, “one” or “some” embodiment(s) in several locations.

[0046] This does not necessarily imply that each such reference is to the same embodiment(s), or that the feature only applies to a single embodiment. Single features of different embodiments may also be combined to provide other embodiments.

[0047] As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless expressly stated otherwise. It will be further understood that the terms “include”, “comprises”, “including” and / or “comprising” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It will be understood that when an element is referred to as being “connected” or “coupled” to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Furthermore, “connected” or “coupled” as used herein may include operatively connected or coupled. As used herein, the term “and / or” includes any and all combinations and arrangements of one or more of the associated listed items.

[0048] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure pertains. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent withtheir meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0049] The detailed description includes specific details for the purpose of providing a thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without these specific details.

[0050] The present invention relates to a smart wearable device configured to non- invasively determine the vascular health and vascular ageing index of a user in real time. The smart wearable device integrates a Photoplethysmography (PPG) sensor, accelerometer, hydration sensor, and temperature sensor within a compact form factor such as a smart ring to capture blood volume fluctuations, motion activity, and contextual physiological data. A processing unit performs context-aware filtering of the PPG signal using motion data, hydration level, skin temperature, and circadian rhythm profile to enhance signal quality. The processing unit extracts a combination of morphological and temporal features and computes behavioral and physiological modulators such as sleep- stress scores and VO2 max-based cardio age. These parameters are fused into a multi-parametric feature set and input to a machine learning model trained on clinical datasets to generate a vascular ageing index. The vascular ageing index supports dynamic, bidirectional tracking of vascular age and enables early detection of vascular deterioration or improvements driven by lifestyle interventions.

[0051] Fig. 1 illustrates a working environment of a smart wearable device 100 for determining vascular health and vascular ageing index of user, in accordance with an embodiment of the present invention. The working environment may comprise the smart wearable device 100, a user device 102, and a server 104, all of which are operatively interconnected via one or more wireless communication protocols. In one embodiment, the smart wearable device 100 may be implemented as a smart ring configured to be worn on the finger of the user. However, it should be understood that the smart wearable device 100 is not limited to a ring and may alternatively be implemented in the form of other wearable accessories such as a smart watch, smart band, or wristband capable of performing similar physiological monitoring functions. The smart ring may be fabricated from a hypoallergenic skin-friendly material, such as silicone, thermoplastic polyurethane (TPU), stainless steel, ceramic, or a combination thereof, to ensure comfort, durability, and safe prolonged contact with user skin.

[0052] The smart wearable device 100 may comprise a Photoplethysmography (PPG) sensor, which is configured to emit and receive one or more light signals to generate raw PPG waveform. The raw PPG waveform represents variations or changes in blood volume in the vascular tissue over time of a user, correlating with cardiac cycles. The smart wearable device 100 may further comprises an accelerometer configured to detect and measure motion of the user, thereby generating corresponding motion data which is used for compensating motion artifacts present in the raw PPG waveform. The smart wearable device 100 may further comprises a hydration sensor configured to determine hydration level of the user and a temperature sensor configured to determine skin surface temperature of the user. These contextual parameters are used to normalize and improve waveform quality and personalize physiological assessment based on environmental and physiological states.

[0053] The smart wearable device 100 further includes a processing unit communicatively coupled to a memory, the PPG sensor, the accelerometer, the hydration sensor and the temperature sensor. The memory stores historical trend and log data of the user, user-specific data such as age, gender, height, and weight, and further stores program instructions, which when executed by the processing unit, enable signal processing operations to be carried out on the acquired physiological data. The processing unit is configured to receive raw PPG waveform, the motion data, the hydration level, the temperature data, and derive a circadian rhythm profile of the user based on time information and historical trend and log data. The processing unit is further configured perform context-aware filtering based on at least one of the motion data, the hydration level, the temperature data, and derived circadian rhythm, to obtain a filtered PPG waveform.

[0054] The processing unit is further configured to extract one or more features from the filtered PPG waveform. The one or more features may include morphological features and temporal features. The processing unit generate a first derivative PPG waveform is from the filtered waveform to compute the rate of change in blood volume over time and further generate a second derivative PPG waveform to compute the acceleration of the change in blood volume. From the second derivative waveform, a set of distinct waveform points, such as U, V, X, Y, and Z, are extracted. Such extracted points are used to compute ratio metrics indicative of arterial stiffness and vascular ageing.

[0055] Additionally, the processing unit extracts one or more temporal features from the filtered PPG waveform, including but not limited to Heart Rate Variability (HRV), post-exercise recovery slope, and pulse wave velocity along with the waveform points. Further, the processing unit determines one or more behavioral and physiological modulators of the user, including a sleep-stress score based on recovery trends and a VO2 max-based cardio age model based on aerobic fitness benchmarks. These modulators are computed using both user-specific data and historical trend and log data of the user stored in memory.

[0056] The one or more extracted features and the behavioral and physiological modulators are combined to generate a context-aware feature set that represents the physiological, behavioral, and environmental profile of the user. The processing unit may input this feature set into a machine learning model trained on clinical waveform datasets to determine a vascular ageing index that dynamically reflects the biological vascular age of the user, including real-time lifestyle-driven modifiability.

[0057] The smart wearable device 100 is operatively coupled to a user device 102, such as a smartphone, tablet, or personal computer (PC), via a wireless module, which may comprise at least one of Bluetooth, Wi-Fi, or Near Field Communication (NFC). A dedicated software application executing on the user device 102 receives information regarding the health of the user from the smart wearable device 100. The software application displays the vascular ageing index, current vascular health status, and enables the user to view historical trends and log data over selected time periods. The software application may also facilitate the input and update of user-specific data, which can be transferred to the memory of the smart wearable device 100. In one embodiment the software application may additionally display estimated biological vascular age, cardio fitness score, and recovery-based stress index, as derived from the feature set and model outputs.

[0058] In one embodiment, the smart wearable device 100 may be further coupled to a server 104, either directly via the onboard wireless communication module or indirectly through the user device 102. The server 104 may be configured to store and process information acquired and generated by the smart wearable device 100. The information may include, but is not limited to, the raw PPG waveform, filtered PPG waveform, the motion data, user-specific data, first and second derivative PPG waveforms, extracted waveform points (U, V, X, Y, Z), vascular ageing index, and corresponding historical logs or trend data. Additionally, the server may store contextual parameters such as the hydration level, the temperature data and the circadian rhythm profile, behavioral and physiological modulators, and the feature set used in vascular age determination. The smart wearable device 100 or the user device 102 maytransmits such information to the server 104 using one or more wireless module, such as Bluetooth, Wi-Fi, or cellular networks.

[0059] In an alternate embodiment, the server 104 may also be configured to perform processing operations functionally equivalent to those performed by the processing unit of the smart wearable device 100. The operations may include: filtering the PPG waveform based on the motion data the hydration level, the temperature data, and circadian rhythm profile, extracting the one or more features from the filtered PPG waveform including temporal and morphological features, determining the behavioral and physiological modulators including sleep- stress score and a VO2 max-based cardio age model, generating the feature set by combining the extracted features and modulators and determining the vascular ageing index using a personalized machine learning model trained on clinical waveform datasets. By delegating such computational tasks to the server 104, processing efficiency may be improved, and battery usage on the wearable device may be minimized. Such configuration also enables centralized processing, cloud-based analytics, and remote access by healthcare professionals, thereby facilitating clinical monitoring, large-scale health assessments, or telemedicine applications.

[0060] Fig. 2 illustrates a block diagram of the smart wearable device 100 for determining vascular health and vascular ageing index of the user, in accordance with an embodiment of the present invention. In one embodiment, the smart wearable device 100 is implemented as a smart ring configured to be worn on the finger of the user. However, it should be understood that the smart wearable device 100 is not limited to a ring and may alternatively be implemented in the form of other wearable accessories such as a smart watch, smart band, and wristband capable of performing similar physiological monitoring functions. The smart ring may be fabricated from a hypoallergenic skin-friendly material, such as silicone, Thermoplastic Polyurethane (TPU), stainless steel, ceramic, or a combination thereof, to ensure comfort, durability, and safe prolonged contact with the user skin.

[0061] The smart wearable device 100 may comprises a Photoplethysmography (PPG) sensor 202. The PPG sensor 202 of the smart wearable device 100 is configured to non- invasively detect volumetric changes of blood circulation in the vascular tissues by utilizing optical sensing principles. Specifically, the PPG sensor 202 may comprises a light-emitting element, such as a light-emitting diode (LED), and a light-detecting element, such as a photodiode or photodetector. The LED emits light typically in the infrared, red, or greenspectrum onto the surface of the user's skin. The underlying blood vessels absorb a portion of such light, while the remaining light is reflected back to the surface, where it is detected by the photodiode. As the blood volume in the blood vessels fluctuates with each cardiac cycle, the amount of reflected light varies correspondingly. Such variations in light intensity are converted into an analog electrical signal by the photodetector, which is subsequently digitized to generate a raw PPG waveform representing changes in blood volume over time of the user.

[0062] The smart wearable device 100 may further comprises an accelerometer 204. The accelerometer 204 is configured to detect and quantify user motion across multiple axes (typically three: x, y, and z). The accelerometer generates motion data corresponding to acceleration forces experienced by the smart wearable device 100 due to body movement, posture changes, or external disturbances. Such motion data is essential for identifying and mitigating motion artifacts that may corrupt the PPG waveform that is in raw form, thereby improving the accuracy and reliability of subsequent physiological assessments.

[0063] The smart wearable device 100 may further comprises a hydration sensor 206 configured to estimate the hydration level of the user by measuring skin impedance or bioelectrical properties across the skin surface. The hydration sensor 206 emits a low-intensity electrical signal through the outer layer of the skin and measures the resistance or conductance of the skin tissue, which varies with the water content in the body. Since hydration levels influence vascular tone, blood volume, and the morphology of PPG waveforms, the hydration data is utilized during PPG signal filtering and contextual normalization to enhance the accuracy of vascular ageing estimation.

[0064] The smart wearable device 100 may further comprises a temperature sensor 208 configured to measure skin temperature of the user using a thermistor or infrared sensing element. The temperature sensor 208 continuously monitors peripheral skin temperature, which can reflect underlying thermoregulatory responses, metabolic activity, and circadian rhythm state. As vascular properties are sensitive to temperature-induced vasodilation or constriction, the acquired temperature data is used to adjust filtering parameters and interpret vascular features in context, thereby improving the reliability of the vascular ageing index.

[0065] The smart wearable device 100 may further comprises a processing unit 210 and a memory 212. The processing unit 210 is configured to perform various signal processing and analytical functions required to determine vascular health and vascular ageing index of theuser. The memory 212 is coupled to the processing unit 210 and is configured to store userspecific data including, but not limited to, the user’s age, gender, height, and weight. The memory 212 may further stores historical trend and log data of the user, including longitudinal physiological data, recovery trends, and fitness parameters. Additionally, the memory 212 stores a set of executable program instructions which, when executed by the processing unit 210, enable it to perform data acquisition, context- aware signal filtering, feature extraction, determination of behavioral and physiological modulators, generation of a feature set, and vascular ageing index determination.

[0066] The processing unit 210 may include one or more general purpose processors (e.g., INTEL® or Advanced Micro Devices® (AMD) microprocessors) and / or one or more special purpose processors (e.g., digital signal processors or Xilinx® System On Chip (SOC) Field Programmable Gate Array (FPGA) processor), MIPS / ARM-class processor, a microprocessor, a digital signal processor, an application specific integrated circuit, a microcontroller, a state machine, or any type of programmable logic array.

[0067] The memory 212 may include, but is not limited to, non-transitory machine- readable storage devices such as hard drives, magnetic tape, floppy diskettes, optical disks, Compact Disc Read-Only Memories (CD-ROMs), and magneto-optical disks, semiconductor memories, such as ROMs, Random Access Memories (RAMs), Programmable Read-Only Memories (PROMs), Erasable PROMs (EPROMs), Electrically Erasable PROMs (EEPROMs), flash memory, magnetic or optical cards, or other type of media / machine- readable medium suitable for storing electronic instructions.

[0068] Upon execution of the stored program instructions, the processing unit 210 begins by receiving raw PPG waveform data from the PPG sensor 202 and motion data from the accelerometer 204. Additionally, the processing unit 210 receives hydration level of the user from the hydration sensor 206, and temperature data from the temperature sensor 208, and derives the circadian rhythm profile based on time information and the historical trend and log data of the user. The historical trend and log data may include but are not limited to longitudinal records of sleep-wake cycles, resting heart rate, hydration variability, temperature trends, motion patterns, and prior vascular ageing scores. The processing unit 210 performs a preprocessing step where the raw PPG waveform is filtered to mitigate noise and distortions caused by user movements. The filtering operation is motion adaptive and utilizes the motion data from the accelerometer to determine the extent and timing of user motion. Based on thelevel of detected activity, the processing unit 210 may applies one or more signal processing filters such as moving average filters or adaptive bandpass filters configured to suppress frequency components corresponding to motion artifacts, thereby preserving only the physiologically relevant portions of the PPG signal to generate a filtered PPG waveform.

[0069] The filtering operation applied to the raw PPG waveform may be further refined through dynamic adjustments based on physiological and contextual parameters, specifically the hydration level, the temperature data, and the circadian rhythm profile of the user. Such parameters are acquired from onboard sensors and time -based data and are used to adaptively modify the filtering behavior to account for real-time changes in the user’s physiological and environmental state. Such adaptive filtering constitutes a form of context-aware normalization.

[0070] In particular, when the hydration sensor 206 detects low hydration levels, which can cause peripheral vasoconstriction and reduced blood volume in capillaries, the processing unit 210 may adjust the filtering algorithm to increase sensitivity to weaker pulse signals, preventing loss of signal fidelity. Similarly, the temperature sensor 208 provides input on thermal-induced vascular changes. For example, cooler skin temperatures often correspond to reduced peripheral perfusion, requiring the filtering algorithm to suppress low-amplitude noise while preserving valid pulse morphology.

[0071] Furthermore, the circadian rhythm profile is inferred by the processing unit 210 based on the time-of-day data, combined with historical sleep-wake cycle patterns and motion trends. During certain circadian phases (e.g., late night or early morning), natural physiological changes such as reduced heart rate or altered autonomic activity may affect the PPG waveform's baseline and amplitude. The system accounts for these predictable fluctuations by tuning filter parameters (e.g., cutoff frequency, filter gain) to preserve meaningful vascular features and avoid overcompensation.

[0072] The filtered PPG waveform represents changes in blood volume over time, reflecting pulsatile nature of blood flow with each heartbeat. The filtered PPG waveform contains both pulsatile (AC) and superimposed (DC) components. The AC component comes from heart's rhythmic changes in blood volume during each heartbeat. The DC component is influenced by factors including breathing, sympathetic nervous system activity, and body temperature regulation. The filtered PPG waveform has two distinct phases including anupswing of the pulse known as anacrotic, which mainly reflects systole, and a downswing called catacrotic, representing diastole.

[0073] Once the filtered PPG waveform is obtained, the processing unit 210 is configured to extract morphological features from the filtered PPG waveform. The processing unit 210 computes a first derivative of the filtered PPG waveform to generate a first derivative PPG waveform using numerical differentiation techniques, where the change in signal amplitude over successive time intervals is calculated to estimate the rate of change in blood volume. The first derivative PPG waveform represents the rate of change in blood volume over time and provides an estimation of the velocity of blood flow within the vascular system of the user. By analyzing this velocity profile, the smart wearable device 100 may identify key dynamic characteristics of the pulse wave such as the systolic upstroke, which corresponds to the rapid increase in blood volume due to heart contraction. Such features help in understanding how efficiently blood is being pumped and can serve as preliminary indicators of vascular responsiveness and overall vascular health.

[0074] Upon computation of the first derivative, the processing unit 210 generates a second derivative PPG waveform by further applying a differentiation operation to the first derivative PPG waveform. The second derivative reflects the acceleration and deceleration of the rate of change in blood volume, thereby capturing more subtle dynamic aspects of the pulse waveform. The second derivative waveform emphasizes inflection points and curvature transitions, which may not be apparent in the original or first derivative waveforms. The second derivative PPG waveform is further analyzed to extract specific waveform points denoted as U, V, X, Y, and Z, where each point corresponds to a distinct physiological event in the pulse cycle.

[0075] The processing unit 210 is configured to compute a vascular ageing index of the user based on a comprehensive set of physiological indicators. These indicators include ratio metrics derived from the second derivative PPG waveform, such as X / U, Z / U, V / U, and Y / U, which reflect arterial stiffness and elasticity. Specifically, the ratio X / U and Z / U indicate arterial stiffness, while the ratio V / U signifies increased arterial stiffness and the ratio Y / U signifies decreased arterial stiffness. In addition to these morphological ratios, the processing unit 210 determine temporal features such as heart rate variability (HRV) and post-exercise recovery slope, which are computed from time-series analysis of the filtered PPG waveform. The HRV is derived by measuring the variations in the time intervals between successive pulsepeaks and reflects autonomic nervous system regulation of cardiac function. A higher HRV typically indicates better cardiovascular adaptability and parasympathetic dominance, whereas a lower HRV may suggest increased sympathetic tone or physiological stress.

[0076] The post-exercise recovery slope is calculated by analyzing the rate at which heart rate returns to baseline following a physical activity event or elevated exertion phase. This slope reflects the recovery efficiency of the cardiovascular system and the responsiveness of the vascular bed. Together, these temporal features enable assessment of dynamic vascular responsiveness, circulatory adaptability, and overall autonomic function, which are integral to characterizing vascular health and age-related changes. The extracted waveform-based and temporal metrics are further combined with user-specific data including, but not limited to, the user's age, gender, height, and weight, which are initially provided via a companion software application on the user device 102 and securely stored in memory 212.

[0077] Furthermore, the processing unit 210 determines one or more behavioral and physiological modulators of the user based on the one or more extracted features and the user specific data stored in the memory 212. These modulators may include, but are not limited to, sleep-stress scores and VO2 max-derived cardio age model. The sleep-stress score is computed by correlating sleep quality metrics (e.g., sleep duration, deep sleep ratio, interruptions) with physiological indicators of stress such as elevated nocturnal heart rate or HRV suppression. The VO2 max-based cardio age is estimated by evaluating the user’s oxygen consumption efficiency during exertional activity or recovery, offering a physiologically grounded surrogate for biological cardiac age. These behavioral and physiological modulators provide essential context for interpreting the vascular ageing index and enhance the personalization of vascular health assessment by incorporating the user’s daily lifestyle, physical conditioning, and longterm physiological trends.

[0078] A feature set is then generated by the processing unit 210 by combining the morphological features, the temporal features, and the behavioral and physiological modulators. This feature set is used as input to a machine learning model trained on clinical datasets to output a personalized vascular ageing index. The machine learning model may include, but is not limited to, regression models, decision trees, or neural networks that are configured to identify patterns corresponding to vascular ageing. The machine learning model may be stored and executed either locally on the processing unit 210 of the smart wearable device 100 or remotely on the server 104.

[0079] The resulting vascular ageing index represents a dynamic, context-aware, and individualized score reflecting the user's vascular health relative to a normative population. In one embodiment, the vascular ageing index is further configured to reflect bidirectional modifiability based on short- and long-term behavioral or physiological changes. The score may dynamically decrease (improve) or increase (worsen) based on evidence of vascular health trends detected through the extracted features and modulators. This score functions as a surrogate biomarker for arterial stiffness, vascular elasticity, and overall cardiovascular efficiency, enabling early detection of vascular deterioration or validation of healthy vascular ageing.

[0080] The vascular ageing index and relevant intermediate results related to the vascular health of the user may be stored in the memory 212 and periodically synchronized to the user device 102 (e.g., smartphone, tablet and PC) via the wireless module 214. The wireless module 214 may support one or more wireless communication protocols including but not limited to Bluetooth®, Bluetooth Low Energy (BLE), Wi-Fi, Near Field Communication (NFC), or other short-range or long-range wireless communication technologies. The wireless module 214 enables secure bidirectional communication between the smart wearable device 100 and the user device 102 for the purposes of configuration, data transmission, software updates, and user interaction.

[0081] The user device 102 may include a software application interface configured to receive, decrypt, and visualize the data transmitted from the smart wearable device 100. The software application may display the vascular ageing index, vascular health results and historical trend and log data in a user-friendly format, such as numerical scores, traffic-light indicators, percentile comparisons, and graphical trend plots. In one embodiment, the smart wearable device 100 may be configured to transmit the raw and / or processed data to the server 104 via the wireless module 214. The server 104 may be equipped with similar or more advanced processing capabilities than the onboard processing unit 210.

[0082] The server 104 may execute a set of processing instructions analogous to those stored in the memory 212, including filtering, derivative computation, feature extraction, determination of the behavioral and physiological modulators, construction of the feature set and vascular index computation using a trained machine learning model. Data received by the server 104 may be processed in real-time or batch mode and stored within secure server-sidestorage systems. The processed results are then relayed back to the user device 102 for display to the user.

[0083] The smart wearable device 100 may further comprises a battery module 216. The battery module 216 provides electrical power to the smart wearable device 100 and its constituent components. The battery module 216 may include rechargeable lithium-ion, lithium-polymer, or other suitable battery technologies capable of supporting extended operation in a compact form factor. The battery module 216 may be coupled with a power management circuit that controls charging, power distribution, and energy-efficient operation of the device components to maximize battery life.

[0084] Fig. 3a illustrates a PPG waveform generated by the photodetector, in accordance with an embodiment of the present invention. The PPG waveform depicted is a raw electrical signal corresponding to variations in the intensity of light reflected from the user's skin, as detected by the photodetector of the PPG sensor 202. Such variations arise due to cyclic changes in blood volume within the vascular tissues during each cardiac cycle. The raw PPG waveform comprises both pulsatile components representing the rhythmic fluctuations in blood volume associated with heartbeats and non-pulsatile components influenced by factors such as respiration and thermoregulation. Such unprocessed signal forms the foundational data input for subsequent stages of signal filtering, derivative computation, and physiological analysis within the smart wearable device 100.

[0085] Fig. 3b illustrates a filtered PPG waveform, in accordance with an embodiment of the present invention. The raw PPG waveform is subjected to motion-adaptive filtering techniques that utilize motion data of the user from the accelerometer 204 to minimize disturbances arising from sensor displacement, skin deformation, blood flow irregularities, and environmental influences such as ambient temperature. By detecting the direction and magnitude of motion, the accelerometer 204 enables the processing unit 210 to apply adaptive filters such as moving average or bandpass filters, thereby isolating the physiologically relevant PPG signal. The filtering operation is further enhanced through context-aware normalization by incorporating real-time hydration level, skin surface temperature, and derived circadian rhythm profile of the user to dynamically adjust filter parameters and preserve valid pulse morphology.

[0086] The resulting filtered PPG waveform, as shown in Fig. 3b, is plotted with sample number (representing time) on the x-axis and signal amplitude on the y-axis, and accurately captures blood volume variations over time. Such PPG waveform includes both an alternating current (AC) component linked to cardiac-induced pulsations and a direct current (DC) component associated with slower physiological modulations such as respiration, sympathetic activity, and thermoregulation. The PPG waveform is characterized by two primary phases: an anacrotic phase representing the systolic upstroke and a catacrotic phase denoting the diastolic downswing, each corresponding to distinct periods within the cardiac cycle.

[0087] Fig. 3c illustrates a first derivative PPG waveform, in accordance with an embodiment of the present invention. As described above, the processing unit 210 of the smart wearable device 100 is configured to compute the first derivative of the filtered PPG waveform to estimate the rate of change in blood volume over time. The first derivative waveform is obtained by applying a numerical differentiation technique, wherein the difference between consecutive amplitude values of the filtered PPG waveform is calculated over a fixed sampling interval. The computation is represented by the following equation:First Derivative = [PPG (t) - PPG (t-1)] / At . (1)

[0088] In the above equation, PPG (t) denotes the filtered PPG waveform amplitude at a current time point t, PPG (t-1) represents the signal amplitude at the immediately preceding time point, and At is the time interval between these two sampling points. The resulting first derivative PPG waveform represents the velocity of blood flow within the vascular tissues and serves as a key physiological indicator used by the processing unit 210 to evaluate vascular responsiveness and overall vascular health.

[0089] Fig. 3d illustrates a. second derivative PPG waveform, in accordance with an embodiment of the present invention. Upon generation of the first derivative PPG waveform, the processing unit 210 further computes a second derivative PPG waveform to capture the acceleration or deceleration in the rate of change of blood volume over time. This is achieved by performing a numerical differentiation on the first derivative waveform. Specifically, the second derivative is calculated by taking the difference between successive values of the first derivative over a defined time interval. The computation is represented mathematically as follows:Second Derivative = [First Derivative (t) -First Derivative (t— 1 )] / At . (2)

[0090] In the above equation, First Derivative (t) denotes the value of the first derivative at the current time t, First Derivative (t— 1) represents the preceding value, and At is the time interval between consecutive data points. The resulting second derivative PPG waveform provides insight into the dynamic inflection points and curvature variations of the pulse signal, which are not evident in the raw or first derivative PPG waveform.

[0091] Fig. 4 illustrates a zoomed section of the second derivative PPG waveform, in accordance with an embodiment of the present invention. The enlarged view of the second derivative PPG waveform highlights five distinct waveform points, denoted as U, V, X, Y, and Z. Among these, points U, X, and Z correspond to positive waves, while points V and Y represent negative waves. In particular, the ratio X / U and Z / U represent the degree of arterial stiffness, V / U ratio indicates increased arterial stiffness, typically observed with advancing age, while Y / U ratio indicates a decrease in arterial stiffness. These waveform points, derived from inflection and curvature changes in the second derivative PPG signal, capture critical physiological trends in the user’s vascular system. Features such as waveform rise time, peak amplitude, and morphological shape are utilized to assess vascular responses and blood dynamics. For instance, the systolic amplitude reflects pulsatile changes in blood volume at the measurement site, whereas the time interval between systolic and diastolic peaks provides insight into large artery stiffness.

[0092] The PPG waveform further enables analysis of the blood volume displaced over time during the cardiac cycle which act as an essential metric indicative of vascular ageing. The amplitude of peak pulses within the second derivative PPG waveform correlates with age- related arterial stiffness, where arteriosclerosis, characterized by thickening and loss of arterial elasticity, contributes to increased vascular resistance and decreased compliance. Accordingly, the evaluation of second derivative PPG signals facilitates an understanding of vascular adaptation, particularly in response to variations in blood viscosity and arterial wall integrity.

[0093] Fig. 5 illustrates a flowchart depicting a method for determining vascular health and vascular ageing index of the user, in accordance with an embodiment of the present invention. In this regard, each block may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functionsnoted in the blocks may occur out of the order noted in the drawings. For example, two blocks shown in succession in Fig. 5 may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Any process descriptions or blocks in flow charts should be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and alternate implementations are included within the scope of the example embodiments in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved. In addition, the process descriptions or blocks in flow charts should be understood as representing decisions made by a hardware structure such as a state machine.

[0094] At step 502, the processing unit initiates data acquisition by receiving raw PPG waveform data from the PPG sensor and corresponding motion data from the accelerometer of the smart wearable device. The PPG sensor, which includes a light-emitting diode and a photodiode, detects optical intensity variations resulting from pulsatile blood flow beneath the user's skin. Simultaneously, the accelerometer captures motion signals along three orthogonal axes to quantify body movements or positional shifts that may introduce artifacts into the PPG signal.

[0095] In addition, the processing unit receives the hydration level from the hydration sensor and the temperature data from the temperature sensor integrated into the smart wearable device. Time information is also captured by the processing unit to enable temporal context awareness. Both the PPG and motion data streams along with the hydration level, the temperature data, and time information are temporarily stored in the memory for subsequent processing.

[0096] At step 504, the processing unit determines a circadian rhythm profile of the user based on the time of day and historical trend and log data. The time information may be derived from a real-time clock or timestamp associated with incoming physiological data, while the historical trend and log data may include prior PPG readings, activity logs, and sleep-wake cycles. The processing unit analyzes this combined data to characterize the user's daily physiological rhythm, such as periods of rest, activity, or circadian dips, which can influence vascular tone and waveform morphology.

[0097] At step 506, the processing unit applies multi-modal, context- aw are filtering to the raw PPG waveform. This filtering process integrates not only motion data from the accelerometer but also the hydration level data from the hydration sensor, the temperature data from the temperature sensor, and the derived circadian rhythm profile. These parameters are utilized to dynamically adjust filter weights and select appropriate filtering techniques, such as adaptive bandpass filtering or context-dependent denoising, to suppress physiological and environmental artifacts while preserving morphological integrity of the signal. The filtered PPG waveform maintains both AC and DC components necessary for subsequent vascular feature extraction.

[0098] At step 508, the processing unit extracts one or more features from the filtered PPG waveform. These features include, but are not limited to waveform morphology, heart rate variability (HRV), pulse wave velocity (PWV), and post-exercise recovery slope. The morphological features include AC amplitude, dicrotic notch position, and area under the pulse waveform, which reflect arterial compliance and vascular tone. The temporal features such as time to peak, beat-to-beat interval, and variability over successive pulses capture dynamic changes in circulatory timing and autonomic regulation.

[0099] At step 510, the processing unit retrieves user-specific data from the memory. This includes demographic information such as age, gender, height, weight, and other long-term physiological baselines including resting heart rate, known cardiovascular conditions, or medication history. This data provides the personalized context required to interpret the extracted waveform features relative to the user’s unique physiological profile.

[0100] At step 512, the processing unit determines one or more behavioral and physiological modulators of the user. These modulators are derived based on the extracted PPG waveform features with user-specific data retrieved from memory (. The one or more behavioral and physiological modulators comprise a sleep-stress score and a VO2 max-based cardio age model. The sleep-stress score reflects the user's recovery state and autonomic balance, while the VO2 max-based cardio age model estimates cardiovascular fitness and aerobic capacity. These modulators influence vascular ageing by accounting for dynamic, non- structural factors affecting vascular performance and are integrated to personalize the vascular ageing index calculation.

[0101] At step 514, the processing unit generates a unified feature set by combining the one or more features and the behavioral and physiological modulators. This combined feature set forms a multi-dimensional input vector that encapsulates both signal-driven and user- contextual elements critical to vascular assessment. Data normalization and feature selection techniques may be applied at this stage to refine the input for downstream inference.

[0102] At step 516, the processing unit computes a vascular ageing index of the user based on the generated feature set. This index is determined using a machine learning model stored locally on the device or embedded within a secure edge inference framework, trained on labeled datasets representative of population-level vascular health trends. The model evaluates the physiological features and modulators to estimate vascular age relative to chronological age, indicating arterial stiffness, compliance, and overall circulatory efficiency. The index supports bidirectional interpretability, allowing assessment of both deterioration and improvement trends over time.

[0103] The final vascular ageing index provides a quantitative measure of the user’s vascular health relative to normative standards. A lower index reflects healthy arterial flexibility, whereas a higher index may indicate early-stage vascular ageing. The computed index, along with detailed waveform analytics, can be displayed to the user via a connected user interface, stored locally for longitudinal tracking, or transmitted wirelessly to a remote server for extended analytics and clinical use.

[0104] The present invention offers a compact, non-invasive solution for real-time vascular health monitoring using a smart wearable device, such as a ring. By integrating multiwavelength PPG, accelerometer, hydration, and temperature sensors, the device captures comprehensive physiological signals. Advanced processing techniques enable motion-adaptive filtering, context-aware normalization, and multi-parametric feature extraction including waveform morphology and HRV. The system further incorporates behavioral and physiological modulators, such as sleep- stress score and VO2 max -based cardio age, to deliver a personalized vascular ageing index. This allows continuous, user-specific assessment of arterial stiffness and vascular trends, overcoming the limitations of bulky, clinic-dependent systems.

[0105] Although implementations a smart wearable device capable of determining vascular health and vascular ageing index of users have been described in language specific tostructural features and / or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as examples of a smart wearable device capable of determining vascular health and vascular ageing index of users.

[0106] The invention has been described above with reference to numerous embodiments and specific examples. Many variations will suggest themselves to those skilled in this art in light of the above detailed description. All such obvious variations are within the full intended scope of the appended claims.

Claims

WE CLAIM:

1. A smart wearable device (100), comprising: a photoplethysmography (PPG) sensor (202) configured to generate PPG waveform, wherein the PPG waveform indicate changes in blood volume over time of a user; an accelerometer (204) configured to detect motion of the user and generate corresponding motion data; a hydration sensor (206) configured to determine hydration level of the user; a temperature sensor (208) configured to determine temperature data corresponding to a skin surface of the user; a processing unit (210) communicatively coupled to a memory (212), the PPG sensor (202), the accelerometer (204), the hydration sensor (206) and the temperature sensor (208), wherein the memory (212) stores historical trend and log data of the user, user specific data and program instructions, wherein when the program instructions are executed by the processing unit (210), causes the processing unit (210) to: receive the PPG waveform, the motion data, the hydration level and the temperature data; determine a circadian rhythm profile of the user based on time information and the historical trend and log data; filter the PPG waveform based on at least one of the motion data, the hydration level, the temperature data and the circadian rhythm profile; extract one or more features from filtered PPG waveform; determine one or more behavioral and physiological modulators of the user based on one or more extracted features and the user specific data; generate a feature set by combining the one or more extracted features and the behavioral and physiological modulators of the user; anddetermine a vascular ageing index of the user based on generated feature set.

2. The smart wearable device (100) as claimed in claim 1, wherein the smart wearable device (100) is a smart ring.

3. The smart wearable device (100) as claimed in claim 1, wherein the smart wearable device (100) is coupled to a user device (102) via a wireless module (214).

4. The smart wearable device (100) as claimed in claim 1, wherein the smart wearable (100) device is connected to a server (104) to store and process one or more information collected by the smart wearable device (100), wherein the one or more information includes at least one of the PPG waveform, the motion data, the user specific data, the hydration level, the temperature data, the user specific data, the filtered PPG waveform, the vascular ageing index and historical trend and log data.

5. The smart wearable device (100) as claimed in claim 1, wherein the smart wearable device (100) further comprises a battery module (216) to support continuous operation over a prolonged period.

6. The smart wearable device (100) as claimed in claim 1, wherein the user specific data comprises at least one of age, gender, height, weight of the user.

7. The smart wearable device (100) as claimed in claim 8, wherein the user specific data is transferred to the memory (212) of the smart wearable device (100) via the user device (102).

8. The smart wearable device (100) as claimed in claim 1, wherein the one or more features extracted from the PPG waveform include at least one of waveform morphology, heart rate variability (HRV), pulse wave velocity, and post-exercise recovery slope.

9. The smart wearable device (100) as claimed in claim 1, wherein the one or more behavioral and physiological modulators comprises at least one of a sleep-stress score and a VO2 max-based cardio age model.

10. The smart wearable device (100) as claimed in claim 1, wherein the user access details of vascular health, the vascular ageing index and the historical trend and log data via a software application executable on the user device (102).

11. A method (500) comprising: receiving, via a photoplethysmography (PPG) sensor (202), an accelerometer (204), a hydration sensor (206), and a temperature sensor (208), PPG waveform, motion data, hydration level and temperature data corresponding to a skin surface of the user respectively; determining, via a processing unit (210), a circadian rhythm profile of the user based on time information and historical trend and log data; filtering, via a processing unit (210), the PPG waveform based on at least one of the motion data, the hydration level, the temperature data and circadian rhythm profile; extracting, via the processing unit (210), one or more features from filtered PPG waveform; retrieving, via the processing unit (210), user specific data stored in memory (212); determining, via the processing unit (210), one or more behavioral and physiological modulators of the user based on one or more extracted features and the user specific data; generating, via the processing unit, a feature set by combining the one or more extracted features and the behavioral and physiological modulators of the user; and determining, via the processing unit (210), a vascular ageing index of the user based on generated feature set.

12. The method (500) as claimed in claim 11, wherein the smart wearable device (100) is a smart ring.

13. The method (500) as claimed in claim 11, wherein the smart wearable device (100) is coupled to a user device (102) via a wireless module (214).

14. The method (500) as claimed in claim 11, wherein the smart wearable (100) device is connected to a server (104) to store and process one or more information collected by the smart wearable device (100), wherein the one or more information includes at least one of the PPG waveform, the motion data, the user specific data, the hydration level, the temperature data, the user specific data, the filtered PPG waveform, the vascular ageing index and historical trend and log data.

15. The method (500) as claimed in claim 11, wherein the smart wearable device (100) further comprises a battery module (216) to support continuous operation over a prolonged period16. The method (500) as claimed in claim 11, wherein the user specific data comprises at least one of age, gender, height, weight of the user.

17. The method (500) as claimed in claim 16, wherein the user specific data is transferred to the memory (212) of the smart wearable device (100) via the user device (102).

18. The method (500) as claimed in claim 11, wherein the one or more features extracted from the PPG waveform include at least one of waveform morphology, heart rate variability (HRV), pulse wave velocity, and post-exercise recovery slope.

19. The method (500) as claimed in claim 11, wherein the one or more behavioral and physiological modulators comprises at least one of a sleep-stress score and a VO2 maxbased cardio age model.

20. The method (500) as claimed in claim 1, wherein the user access details of vascular health, the vascular ageing index and the historical trend and log data via a software application executable on the user device (102).

Images