System and method for determining calibrated blood pressure from biophotonic signals using machine learning

Abstract

A system and method for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via bio-photonic signals using motion estimation and machine learning models, for blood pressure profiling, are provided. The system comprises an optical device to emit coherent laser light on single or multiple points on biological tissues at one or more anatomical sites; an image-capturing sensor capture optical data comprising a dynamically changing speckle pattern formed by reflected laser light from one or more anatomical sites; and a server configured to: obtain the dynamically changing speckle pattern formed by the reflected laser light from the image-capturing sensor; and determine, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern. The blood pressure includes central blood pressure, peripheral blood pressure, pulmonary arterial pressure, atrium and ventricle blood pressure, and cerebral blood pressure.

Description

[0001] SYSTEM AND METHOD FOR DETERMINING CALIBRATED BLOOD PRESSURE FROM BIOPHOTONIC SIGNALS USING MACHINE LEARNING

[0002] TECHNICAL FIELD

[0003] [1] The present disclosure relates generally to physiological monitoring systems and more particularly to non-invasive system and method for determining calibrated blood pressure of a subject from biophotonic signals using machine learning analysis, for blood pressure profiling.

[0004] BACKGROUND

[0005] [2] Monitoring of bio-vitals such as heart sounds, respiratory sounds, heart rate (HR), blood pressure (BP), respiration rate (RR), and oxygen saturation (SpO2) is crucial for health management, disease detection, and optimizing treatments. There is a significant and ongoing trend towards developing non-invasive and convenient methods for physiological monitoring. However, the traditional techniques often necessitate direct contact with the user’ s body, posing challenges, particularly in ambulatory settings or for continuous monitoring.

[0006] [3] Various technologies are currently employed for physiological assessment. Wearable devices, such as smartwatches, fitness bands, patches, and sensor-integrated clothing, commonly incorporate optical sensing techniques. Such optical sensing techniques typically involve illuminating a skin area using light sources such as light-emitting diodes (LEDs), and detecting variations in reflected or scattered light using optical detectors like photodiodes. Techniques such as photoplethysmography (PPG) are frequently used to derive physiological parameters, including heart rate and blood oxygen saturation. Additionally, there is ongoing exploration into integrating multiple types of sensors within a single device or platform to enhance monitoring capabilities.

[0007] [4] Furthermore, the application of computational algorithms, including machine learning (ML), deep learning (DL), and artificial intelligence (Al), to analyze data gathered from wearable sensors is an established practice. These algorithms are utilized for diverse functions, such as extracting relevant features from complex time-series sensor data, monitoring physiological signs to detect potential illness or adverse conditions, predicting future health states or outcomes, and sometimes adapting recommendations or alerts based on the collected data. Concepts like analyzing physiological trends over extended periods (longitudinal analysis) and incorporating user-specific information (like demographics) into the analysis are also known areas of investigation. Efforts are continually made to improve the quality and reliability of signals obtained from cuff-less blood pressure devices and wearable sensors.

[0008] [5] Despite these ongoing developments, significant challenges and limitations remain in the field of non-invasive, physiological monitoring. Accurately measuring certain key vital signs continuously, conveniently, and without requiring user calibration remains difficult. For example, obtaining reliable, cuffless blood pressure measurements that meet clinical accuracy standards is a well-known challenge for many existing technologies. Furthermore, many existing optical techniques may primarily analyze bulk changes in light absorption or scattering like PPG (photoplethysmography sensors), potentially overlooking subtle but information-rich dynamic patterns in the light interacting with the tissue surface caused by physiological pressure processes.

[0009] [6] Moreover, ensuring high signal quality and robustness against motion artifacts is a persistent issue for sensors worn during daily activities. Integrating advanced, multiparameter sensing capabilities into comfortable, unobtrusive, and diverse form factors suitable for long-term use also poses design and technical difficulties. While computational analysis is employed, there remains a need for more sophisticated and robust analysis pipelines capable of extracting comprehensive and subtle features from sensor data, performing highly accurate classification or prediction tailored to specific conditions and individual users, and generating genuinely actionable insights for diagnostics, prognostics, or personalized therapeutic guidance.

[0010] [7] Therefore, a need persists for improved systems and methods that can accurately and reliably capture a broader range of physiological information non-invasively using versatile form factors, while also providing advanced analytical capabilities to translate this data into meaningful health assessments and interventions.

[0011] SUMMARY

[0012] [8] The present disclosure relates generally to physiological monitoring and, more particularly, to a system and method for non-invasively determining calibrated blood pressure of a subject for blood pressure profiling by analyzing dynamic biophotonic signals obtained from biological tissue using one or more machine learning models.

[0013] [9] It is an object of the present disclosure to provide a biophotonic based physiological monitoring system and method. More particularly, the present disclosure relates to a system and method for providing accurate, non-invasive determination of calibrated blood pressure, using signal processing and machine learning techniques.

[0010] According to a first aspect, there is provided a system for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via biophotonic signals using motion estimation and machine learning models, for blood pressure profiling. The system comprises an optical device configured to emit coherent laser light on single or multiple points on the biological tissues at one or more anatomical sites of a subject either sequentially or simultaneously, so as to generate a speckle pattern comprising real-time optical displacement data indicative of tissue micro structure changes and movement in blood vessels during each heartbeat, the one or more anatomical sites includes neck, chest, arms, legs, pulmonary valve area of heart, atrium and ventricle region of the heart, and head. The system further includes one or more image-capturing sensors configured to capture optical data comprising a dynamically changing speckle pattern formed by reflected laser light from one or more anatomical sites of the subject. The system also includes a server communicatively connected to the optical device and the image-capturing sensors. The server comprises a memory storing a database and a set of modules; and a processor configured to execute the set of modules. The server is configured to: obtain the dynamically changing speckle pattern formed by the reflected laser light from the image-capturing sensors; and determine, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern. The blood pressure includes central blood pressure (CBP) associated with the neck, peripheral blood pressure associated with the arms and legs, pulmonary arterial pressure associated with the pulmonary valve area of the heart, atrium and ventricle blood pressure associated with the atrium and ventricle region of the heart, and cerebral blood pressure associated with the head.

[0014]

[0011] In some embodiments, the processor is further configured to synchronize the dynamically changing speckle pattern obtained from one or more anatomical sites using a time reference to ensure precise temporal alignment of optical displacement data; align the temporally synchronized optical signals with corresponding blood pressure data derived from machine learning models, such that pressure waveforms from different anatomical sites are analyzed in a unified time domain; analyze temporally aligned signals to extract pulse wave dynamics, including pulse wave velocity, waveform morphology, transit times between anatomical sites, and reflection indices indicative of vascular conditions; determine arterial stiffness by calculating regional or segmental pulse wave velocity and evaluating time- differentiated displacement and pressure propagation across central and peripheral anatomical sites; and estimate hemodynamic parameters, including regional blood flow characteristics, pressure gradients, vascular resistance, and cardiac output based on integrated pressure profiles and optical motion data.

[0015]

[0012] In some embodiments, the processor is configured to determine the central blood pressure (CBP) including systolic and diastolic blood pressure from the dynamically changing speckle pattern by (i) applying motion description modelling analysis on the dynamically changing speckle pattern for measuring dynamic changes in carotid artery and / or aorta motion and blood vessel displacement, (ii) utilizing a motion description model to estimate pulse and pressure wave propagation in the carotid artery, (iii) extracting velocity profiles, displacement derivatives, and frequency components from optical data, (iv) implementing an Al-based data-driven model to estimate extracted optical parameters with absolute calibration blood pressure values, (v) analyzing microvascular fluctuations and flow turbulence within the carotid artery and / or aorta to refine CBP estimation, and (vi) determining the central blood pressure based on the correlation between carotid artery hemodynamics and CBP-related physiological markers;

[0016]

[0013] In some embodiments, the processor is configured to determine nonsimultaneous or simultaneous peripheral blood pressure and blood pressure differentials across arms and legs from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern to detect arterial pulsation and pulsation timing differences across the arms and legs, (ii) computing inter-limb pulse wave velocity (PWV) to assess vascular stiffness, (iii) utilizing speckle tracking to measure flow resistance in small arteries and capillaries, (iv) calculating ankle-brachial index (ABI) by comparing transit delays between brachial and ankle arteries using timing, (v) correlating the extracted parameters with vascular health indicators to detect conditions such as peripheral artery disease (PAD), and (vi) determining simultaneous peripheral blood pressure based on the computed arterial pulsation parameters, vascular resistance, and ABI measurements;

[0017]

[0014] In some embodiments, the processor is configured to determine pulmonary arterial pressure (PAP) from the dynamically changing speckle pattern by (i) applying the motion description modelling on the dynamically changing speckle pattern to estimate right ventricular ejection dynamics influencing PAP on pulmonary valve, (ii) utilizing specklebased flow mapping to measure resistance variations in pulmonary arteries and track highspeed fluctuations associated with pulmonary hypertension, (iii) extracting optical displacement data in real-time and processing using an Al-driven PAP estimation model, (iv) computing mean pulmonary arterial pressure (mPAP) based on the correlation between motion description modelling on speckle images parameters and pulmonary hemodynamic characteristics, (v) spatiotemporal speckle modeling based features (capturing localized chest wall and right ventricular outflow tract movements), and respiratory gating to account for intrathoracic pressure variations, (vi) derive pulmonary vascular resistance (PVR) through correlation of estimated flow velocities with measured or inferred mean PAP, and further enhance accuracy by fusing data from motion description modelling on speckle image based pulse waveform (or) ECG for more precise alignment of cardiac events;

[0018]

[0015] In some embodiments, the processor is configured to determine the atrium and ventricle pressure from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern for tracking to analyze jugular venous pulse (JVP) motion, detecting venous distension and collapse patterns, (ii) utilizing high-frame-rate optical imaging to detect myocardial contractions and extracting strain patterns, (iii) implementing Al-driven segmentation to distinguish systolic and diastolic myocardial strain dynamics, (iv) deriving left ventricular end-diastolic pressure (LVEDP) using optical pulse transit time (PTT)-based arterial phase shift analysis, (v) determining right atrial pressure (RAP) from variations in optical pulse transit time and venous waveform changes, (vii) performing cardiac wall motion mapping through speckle tracking and phasebased optical analysis to estimate left ventricular pressure variation, (viii) employing hemodynamic modeling to correlate the extracted optical motion parameters with intraventricular pressure dynamics to determine the atrium and ventricle blood pressure, (ix) analyzing morphological features in the JVP waveform, including a-wave, c-wave, and v- wave, and correlating these with myocardial strain patterns to detect arrhythmias, valvular dysfunction, or conduction abnormalities (x) synchronizing optical data acquisition with an ECG or respiratory gating signal, when available, to improve the timing accuracy of PTT- based metrics and capture intrathoracic pressure variations that influence atrial and ventricular pressures, (xi) implementing a continuous or adaptive calibration model that refines the correlation between measured optical parameters and reference intraventricular pressures from known invasive or clinical standards, thus enhancing accuracy over time and across varying patient profiles, and (xii) providing real-time or near-real-time alerts or trend analyses to identify acute hemodynamic changes including fluid overload, increased right atrial pressure, or left ventricular dysfunction, facilitating early intervention in conditions including heart failure or valvular disease.

[0019]

[0016] In some embodiments, the processor is configured to determine the cerebral blood pressure from the dynamically changing speckle pattern by (i) processing the dynamically changing speckle pattern using motion description modelling and speckle contrast analysis to derive arterial pulsatility and flow resistance in middle cerebral artery (MCA), (ii) utilizing phase-based optical pulse timing to evaluate cerebrovascular resistance (CVR) by measuring pressure-dependent flow variations across brain regions, (iii) estimating intracranial pressure (ICP) fluctuations by analyzing arterial waveform shifts detected through motion description modelling algorithms, and (iv) determining cerebral blood pressure based on the derived CPP, MCA pulsatility, CVR, and ICP estimations using an Al-driven cerebral blood pressure estimation model.

[0020]

[0017] In some embodiments, the coherent laser light from the optical device is directed towards the neck or chest region to generate the dynamically changing speckle pattern for central blood pressure determination.

[0021]

[0018] In some embodiments, the coherent laser light from the optical device is directed towards upper and lower limbs to generate the dynamically changing speckle pattern for simultaneous peripheral blood pressure determination.

[0022]

[0019] In some embodiments, the coherent laser light from the optical device is directed towards the chest wall to generate the dynamically changing speckle pattern for pulmonary arterial pressure determination.

[0023]

[0020] In some embodiments, the coherent laser light from the optical device is directed towards the neck region and the chest region to generate the dynamically changing speckle pattern for atrium and ventricle blood pressure determination.

[0024]

[0021] In some embodiments, the coherent laser light from the optical device is directed towards the head (cerebral tissue) to generate the dynamically changing speckle pattern for cerebral blood pressure determination.

[0025]

[0022] In some embodiments, the one or more image-capturing sensors are selected from a group comprising a Complementary Metal-Oxide-Semiconductor (CMOS) camera, a Charge-Coupled Device (CCD) camera, a mouse optical sensor, a Raspberry Pi camera, an infrared (IR) camera, a smartphone camera, or a virtual reality device camera.

[0026]

[0023] In some embodiments, the optical device emits coherent laser light at wavelengths ranging from 400 nanometers (nm) to 2500 nm, with a power output between 0.01 milliwatts (mW) and 5 mW.

[0027]

[0024] In some embodiments, the one or more image-capturing sensors is configured to acquire data at a sampling frequency ranging from 60 Hz to 1.6k Hz.

[0028]

[0025] In some embodiments, the processor employs a motion estimation model including at least one of a motion description method, a block matching algorithm, a phase- based method, a gradient-based method or a feature-based method to process the dynamically changing speckle pattern formed by the reflected light to determine the blood pressure.

[0029]

[0026] In some embodiments, the system is further configured to measure one or more pressures selected from the group consisting of central (neck), peripheral (arms, legs), pulmonary, cardiac (atrium and ventricle), and cerebral either individually or simultaneously, such that any subset or combination of these anatomical sites can be assessed in parallel or at different times, based on user selection or automated detection criteria.

[0030]

[0027] According to a first aspect, there is provided a method for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via biophotonic signals using motion estimation and machine learning models. The method comprises emitting, using an optical device, coherent laser light on single or multiple points on the biological tissues at one or more anatomical sites of a subject either sequentially or simultaneously, so as to generate a speckle pattern comprising real-time optical displacement data indicative of tissue microstructure changes and movement in blood vessels during each heartbeat, the one or more anatomical sites includes neck, chest, arms, legs, pulmonary valve area of heart, atrium and ventricle region of the heart, and head; capturing optical data comprising a dynamically changing speckle pattern formed by reflected laser light from one or more anatomical sites of the subject; and determining, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern. The blood pressure includes central blood pressure (CBP) associated with the neck, peripheral blood pressure associated with the arms and legs, pulmonary arterial pressure associated with the pulmonary valve area of the heart, atrium and ventricle blood pressure associated with the atrium and ventricle region of the heart, and cerebral blood pressure associated with the head.

[0031]

[0028] The described system provides a non-invasive, multi-site, and real-time approach to blood pressure monitoring by leveraging bio-photonic signals and advanced machine learning models. Unlike conventional cuff-based or catheter-based techniques, this system offers the unique capability to estimate calibrated blood pressure across multiple anatomical regions simultaneously including central, peripheral, pulmonary, cardiac, and cerebral sites without physical contact or invasive intervention. This enables early detection of region-specific abnormalities, such as pulmonary hypertension, cerebral hypoperfusion, or cardiac dysfunction, with high temporal resolution and patient comfort. The integration of speckle-based optical motion tracking and synchronized pressure waveform analysis also allows for comprehensive cardiovascular profiling, supporting predictive diagnostics, personalized treatment planning, and continuous health monitoring in both clinical and remote settings.

[0032]

[0029] Therefore, in contradistinction to existing solutions which may be limited in accuracy or the range of parameters derived, the system and method of the present disclosure provide improved non-invasive physiological monitoring by leveraging analysis of dynamic biophotonic signals and advanced machine learning, well suited for continuous health tracking, diagnostics, and personalized medicine applications.

[0033]

[0030] These and other aspects of the disclosure will be apparent from the implementation(s) described below.

[0034] BRIEF DESCRIPTION OF THE DRAWINGS

[0035]

[0031] The embodiments herein will be better understood from the following detailed descriptions with reference to the drawings, in which:

[0036]

[0032] FIG. 1 is a block diagram illustrating a system for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via bio-photonic signals using motion estimation and machine learning models in accordance with the present disclosure.

[0037]

[0033] FIG. 2 is an exemplary optical device in accordance with the present disclosure.

[0038]

[0034] FIG. 3 is a block diagram of a server of FIG. 1 in accordance with the present disclosure.

[0039]

[0035] FIG. 4 is a block diagram of a blood pressure determining module of FIG. 3 in accordance with the present disclosure.

[0040]

[0036] FIGS. 5A and 5B illustrate a method for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via bio-photonic signals using motion estimation and machine learning models in accordance with the present disclosure.

[0041]

[0037] FIG. 6 illustrates temporal and spectral representations of pulse signals extracted from bio-photonic measurements in accordance with the present disclosure.

[0042]

[0038] FIG. 7 illustrates spectrograms visualize frequency components over time in accordance with the present disclosure.

[0043]

[0039] FIG. 8 illustrates systolic and diastolic mean absolute errors for determined blood pressure in accordance with the present disclosure.

[0044]

[0040] FIG. 9 is a schematic diagram of a computer architecture for executing the embodiments in accordance with the present disclosure. DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

[0045]

[0041] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0046]

[0042] As mentioned, there remains a need for a non-invasive approach for physiological monitoring. The present disclosure provides a system and method for non- invasively determining.

[0047]

[0043] Terms such as "a first", "a second", "a third", and "a fourth" (if any) in the summary, claims, and foregoing accompanying drawings of the disclosure are used to distinguish between similar objects and are not necessarily used to describe a specific sequence or order. It should be understood that the terms so used are interchangeable under appropriate circumstances so that the implementations of the disclosure described herein are, for example, capable of being implemented in sequences other than the sequences illustrated or described herein. Furthermore, the terms "include" and "have" and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, a method, a system, a product, or a device that includes a series of steps or units, is not necessarily limited to expressly listed steps or units but may include other steps or units that are not expressly listed or that are inherent to such process, method, product, or device.

[0048]

[0044] Referring now to the drawings and more particularly to FIGS. 1 through 9, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.

[0049]

[0045] FIG. 1 is a block diagram illustrating a system 100 for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via biophotonic signals using motion estimation and machine learning models in accordance with the present disclosure. The system 100 includes an optical device 104, one or more imagecapturing sensors 106, and a server 110. The server 108 is communicatively connected to the one or more image-capturing sensors 106. The optical device 104 is configured to emit coherent laser light on one or more body regions of a subject. The optical device 104 is configured to emit coherent laser light or other structured light onto one or more body regions of a subject 102, including but not limited to head, neck, chest, back, stomach, hand, leg area, or other body regions. Coherent laser light refers to electromagnetic radiation emitted by a laser source in which the light waves maintain a constant phase relationship over time and space. In some embodiments, the optical device 104 may include one or more laser diodes, collimating optics, and beam-shaping components to produce a controlled and uniform illumination field. The coherent light source utilizes wavelengths ranging from 400 nanometres (nm) to 2500 nm for optimal analysis, emitting a power output between 0.1 milliwatts (mW) and 5 mW. In some embodiments, the optical device 104 may be integrated with wavelength control mechanisms for wavelength-specific tissue penetration or speckle pattern formation to facilitate motion capture through reflected light intensity variations. The optical device 104 emits the laser light through an optical amplification, based on stimulated emission of electromagnetic radiation which means that emitted photons (light particles) have same frequency and phase, traveling in the same direction and maintaining a consistent wavelength. This coherence enables the laser light to be highly absorbed, creating a tight beam with minimal divergence. The coherent laser light is directed towards the user's skin, either directly or through clothing. In some embodiments, the optical device 104 may be a handheld device, a mobile phone, a Kindle, a Personal Digital Assistant (PDA), a tablet, a music player, a computer, a laptop, an electronic notebook, or a Smartphone. In some embodiments, the optical device 104 may be wearable.

[0050]

[0046] The one or more image-capturing sensors 106 is configured to detect and capture the light reflected from the illuminated body region. The one or more image-capturing sensor 106 may include a Complementary Metal-Oxide-Semiconductor (CMOS) camera, a Charge-Coupled Device (CCD) camera, a mouse optical sensor, a Raspberry Pi camera, an infrared (IR) camera, a smartphone camera, or a virtual reality device camera, and may operate in visible, near-infrared, or multispectral imaging modes. In some embodiments, the one or more image-capturing sensors 106 may be a high-frequency camera. In some embodiments, the one or more image-capturing sensors 106 may be handheld, a camera, an infrared (IR) camera, a smartphone, a mobile phone, a virtual reality device, or any kind of imagingcapturing device. In some embodiments, the number of image-capturing sensors 106 may be increased proportionally to the number of laser sources used, in order to ensure adequate spatial resolution, signal coverage, and synchronized data acquisition across multiple illumination sites. The one or more image-capturing sensors 106 capture the temporal and spatial variations in the reflected light as a sequence of image frames, forming either a video stream or a set of reflected light images. The speckle pattern comprising real-time optical displacement data indicative of tissue microstructure changes and movement in blood vessels during each heartbeat. The one or more image-capturing sensors 106 acquire the reflected light at a high sampling frequency of at least 600 Hz to 1.2 kilohertz (k Hz), exceeding 1.6 kHz. In some embodiments, the one or more image-capturing sensors 106 acquire the reflected light at sampling frequency, typically at least 20 Hz and often exceeding 200 Hz. The data characterized reflected light may be a reflected light image or a video of the subject 102 that is recorded by the one or more image-capturing sensors 106. The data characterized reflected light may be an MPEG-4 Part 14 (MP4) format file or a numerical array. The data characterized reflected light comprises low and high frequency components. More particularly, the data characterized reflected light encodes information about skin vibrations caused by physiological activity associated with the subject 102.

[0051]

[0047] The speckle pattern comprising real-time optical displacement data yields diverse physiological insights depending on the anatomical region being imaged. From the forehead or temporal region, data related to cerebral blood flow pulsations and superficial vessel dynamics can be extracted, supporting non-invasive cerebral pressure estimation. The neck, particularly around the carotid artery, provides access to the central blood pressure waveforms, arterial wall displacement, and serves as a reference for pulse wave velocity (PWV) calculations. Imaging over the chest captures cardiac-induced micro-vibrations, aortic and pulmonary pulse waves, and respiratory-induced motion, allowing insights into cardiac mechanics and pulmonary pressure. The arms, forearms, and wrists reveal peripheral pulse waveform morphology, transit times, and vascular stiffness, aiding in peripheral blood pressure estimation and resistance evaluation. The legs and ankles provide delayed pulse waveforms and reflections useful for assessing systemic circulation and peripheral artery disease. Over the abdomen, displacement signals reflect abdominal aortic pulse waves and respiratory motion, which can assist in evaluating aortic health and diaphragmatic function. Across these regions, the speckle data encodes motion through amplitude variation, phase shifts, and frequency patterns, each indicative of tissue microstructure changes and blood vessel movement during the cardiac cycle, supporting a comprehensive, multi-site, noncontact cardiovascular monitoring framework.

[0052]

[0048] Optionally, the one or more image-capturing sensors 106 may include supplementary components. For instance, a lens and / or filter assembly may be employed in conjunction with a sensor module of the one or more image-capturing sensors 106 to optimize light capture, potentially focus the reflected light, and filter out unwanted ambient light using techniques like bandpass filtering. Motion sensors, such as accelerometers and gyroscopes, may be included to detect user movement, allowing a software system to compensate for motion artifacts in the captured data. A communication module, such as Bluetooth or Wi-Fi, can facilitate wireless data transmission between the one or more image-capturing sensors 106 and external devices or networks, such as cloud servers or Electronic Health Record (EHR) systems. A microcontroller or similar processing unit manages the operation of the hardware components, facilitates data transfer, synchronizes data streams, and may perform on-edge computing tasks, including initial data filtering, pre-processing, and data anonymization, governed by firmware / middleware.

[0053] [1] In some embodiments, the optical device 104 and the one or more imagecapturing sensors 106 are integrated into a single unit. The integrated unit facilitates precise optical alignment, reduces system footprint, and improves portability and ease of use for non- invasive physiological monitoring. The integrated unit may include a shared housing that encapsulates the coherent light source and the image sensor, along with necessary optical elements such as lenses, mirrors, filters, and beam shapers. This arrangement supports synchronized light emission and image acquisition, allowing for real-time collection of reflected light signals from the subject’s body region. The integrated unit may also contain embedded electronics for on-board pre-processing, power regulation, and wireless communication with the server 110. In some embodiments, the integrated unit can be configured as a standalone wearable device worn directly on the user's body, such as an armband, a wrist-worn device (like a watch or bracelet), a finger-worn device (like a ring), or an ear-worn device (like an earplug or integrated into a hearing aid / headphone). Alternatively, the coherent laser source and image sensor modules can be integrated into various existing wearable items, including but not limited to headbands, straps, ankle bracelets, helmets, chokers, glasses, garments (shirts, bras, underpants, gloves, shoes), wearable patches adhering to the skin, or other wearable medical devices. Furthermore, the module can be integrated into non-wearable devices where the laser is positioned to interact with the user's body, directly or through clothing. Examples include integration into other medical or wellness devices, fitness equipment, mobile phones, smart mirrors, bed sensors, toilets or toilet seats, chairs, tables, doors, car components, or even a computer mouse. Multiple such apparatuses or integrated modules may be deployed simultaneously on a single user or across multiple users, synchronized to capture data from various body locations concurrently, providing a comprehensive physiological assessment. The disclosed embodiments are exemplary, and the system can be adapted to numerous other form factors and integration scenarios.

[0049] In some embodiments, the optical device 104 and the one or more imagecapturing sensors 106 are separate units, thereby enabling flexibility in positioning and targeting, enabling the system to adapt to different use cases or subject anatomies. For example, the optical device 104 may be placed at a fixed angle relative to the one or more image-capturing sensors 106 is positioned independently to optimize the viewing angle, field of view, or minimize specular reflections. The separation also allows for customizable baselines in stereo or multi-angle setups for enhanced depth resolution or motion triangulation. In such modular systems, synchronization between the optical and imaging devices may be achieved via wired or wireless signalling protocols, ensuring temporal coherence between emitted and reflected light frames. Both configurations such as integrated unit and separate units may include calibration procedures to account for environmental variables such as ambient lighting, distance variations, or motion artefacts.

[0054]

[0050] The server 110 is communicatively coupled with the optical device 104 and the one or more image-capturing sensors 106 via a network 108. The network 108 may be a wireless network, a wired network, a combination of a wireless network and a wired network, or an Internet. The server 110 includes one or more processors and memory storing computer- readable instructions. When executed, the processor is configured to obtain the dynamically changing speckle pattern formed by the reflected laser light from the one or more imagecapturing sensors; and determine, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern, wherein the blood pressure includes central blood pressure (CBP) associated with the neck, peripheral blood pressure associated with the arms and legs, pulmonary arterial pressure associated with the pulmonary valve area of the heart, atrium and ventricle blood pressure associated with the atrium and ventricle region of the heart, and cerebral blood pressure associated with the head.

[0055]

[0051] The present invention may be implemented in various form factors, including but not limited to wearable configurations or other portable and compact designs. Such adaptations enable the invention to be effectively utilized in diverse settings, including clinical environments, at-home use, and pharmacies. The selection and design of an appropriate form factor for a given application would be within the capabilities of a person skilled in the art, based on the disclosure provided herein and the specific requirements of the intended use case.

[0056]

[0052] FIG. 2 is an exemplary optical device 200 in accordance with the present disclosure. It is to be noted that the optical device 200 is for exemplary purpose only and that various modifications and alternative configurations may be employed without departing from the scope of the present disclosure. In some embodiments, the optical device 200 comprises a coherent light source, such as a laser diode or vertical-cavity surface-emitting laser (VCSEL), configured to emit light of a specified wavelength and coherence suitable so as to generate real-time optical displacement data indicative of tissue microstructure changes and movement in blood vessels during each heartbeat. The optical device 200 may include collimating and focusing optics, beam-shaping elements, and optical isolators to maintain beam quality and reduce back reflections. The optical device 200 emits coherent laser light at wavelengths ranging from 400 nanometers (nm) to 2500 nm, with a power output between 0.01 milliwatts (mW) and 5 mW.

[0057] [1] In some embodiments, the optical device 200 further comprises one or more beam steering or scanning modules, such as galvanometric mirrors, MEMS-based scanning units, or optical prisms, to dynamically direct the light beam across specific regions of interest on the subject’s body (e.g., neck, chest, or abdomen). Additionally, the optical device 104 may include polarization controllers or filters to enhance signal specificity based on the reflective properties of the skin and subcutaneous tissue.

[0058] [2] The optical device 200 may be configured to operate in continuous wave (CW) or pulsed modes depending on a desired temporal resolution, safety thresholds, and power consumption requirements. In some embodiments, the optical device 200 may be integrated with photodetectors or optoelectronic receivers to capture backscattered or reflected light, which is then routed to the one or more image-capturing sensors 106 or directly processed for motion analysis.

[0059] [3] In some embodiments, the optical device 200 further equipped with wavelength-tunable components or multi-wavelength sources to enable spectroscopic analysis or differentiation of blood oxygenation levels and tissue composition. Such multispectral capabilities can enhance diagnostic utility in clinical and remote health monitoring environments. The optical device 200 may also incorporate wireless communication modules to transmit acquired data to external processing systems, mobile devices, or cloud-based platforms for further analysis, storage, or remote consultation.

[0060] [4] In some embodiments, the coherent laser light from the optical device 200 is directed towards the neck or chest region to generate the dynamically changing speckle pattern for central blood pressure determination. In some embodiments, the coherent laser light from the optical device 200 is directed towards upper and lower limbs to generate the dynamically changing speckle pattern for simultaneous peripheral blood pressure determination. In some embodiments, the coherent laser light from the optical device 200 is directed towards the chest wall to generate the dynamically changing speckle pattern for pulmonary arterial pressure determination. In some embodiments, the coherent laser light from the optical device 200 is directed towards the neck region and the chest region to generate the dynamically changing speckle pattern for atrium and ventricle blood pressure determination. In some embodiments, the coherent laser light from the optical device 200 is directed towards the head (cerebral tissue) to generate the dynamically changing speckle pattern for cerebral blood pressure determination.

[0061] [5] FIG. 3 is a block diagram of the server 110 of FIG. 1 in accordance with the present disclosure. The server 110 includes a database 300, an input receiving module 302, a blood pressure determining module 304, a synchronization module 306, an aligning module 308, a pulse wave dynamics extraction module 310, an arterial stiffness determining module 312, and a hemodynamic parameter determining module 314. It is to be understood that the delineation of these modules is for illustrative purposes only. In some embodiments, one or more of the modules may be combined into a single module, or subdivided into multiple submodules, depending on implementation requirements, computational architecture, or software design preferences. Additionally, the functionalities described herein may be implemented using a combination of hardware, software, firmware, or any suitable processing logic. The database 300 is configured to store, manage, and organize a wide range of data necessary for the operation of the server 110 and the overall system described herein. In some embodiments, the database 300 stores raw and processed optical data received from the optical device 200, including time-stamped pulse waveforms, tissue displacement signals, and reflective intensity measurements. The database 300 may also maintain subject-specific metadata such as age, sex, height, weight, and baseline cardiovascular parameters, which may be used to personalize hemodynamic analyses and improve diagnostic accuracy. In some embodiments, the database 300 includes structured tables or document-based repositories for storing intermediate outputs generated by modules such as the blood pressure determining module 304 or the pulse wave dynamics extraction module 310. This enables efficient access and retrieval of specific data subsets for further analysis, visualization, or longitudinal tracking. The database 300 may also store synchronization markers and alignment metadata used by the synchronization module 306 and aligning module 308 to correlate pulse wave data with cardiac events or respiratory cycles.

[0062] [6] To support real-time performance and scalability, the database 300 may employ a hybrid storage architecture that includes both in-memory data structures for high-speed access and persistent disk storage for long-term archiving and compliance with data retention policies. In some embodiments, the database 300 supports encryption, role-based access control, and audit logging to ensure the confidentiality, integrity, and traceability of sensitive health data. Additionally, the database 300 may interface with external health information systems or cloud-based storage services through secure APIs, facilitating interoperability and remote access for authorized healthcare providers.

[0063] [7] The input receiving module 302 is configured to receive optical data comprising a dynamically changing speckle pattern formed by reflected laser light from one or more anatomical sites of the subject. The speckle pattern is generated as a result of interference among multiple scattered light waves returning from tissue microstructures, including skin, blood vessels, and subcutaneous layers. The captured speckle pattern minute provides information regarding physiological motions such as arterial pulsations, respiratory-induced tissue shifts, and microvascular dynamics. The received optical data may be formatted as timeseries signals or image sequences and may include associated metadata such as frame rate, sampling frequency, illumination wavelength, and acquisition timestamp. In some embodiments, the input receiving module 302 interfaces directly with photodetectors, camera sensors, or pre-processing electronics, and may include signal conditioning components (e.g., noise filtering, gain control, or normalization) to ensure the fidelity and usability of the captured data for downstream analysis modules.

[0064] [8] The blood pressure determining module 304 is configured to determine, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern. The blood pressure includes central blood pressure (CBP) associated with the neck, peripheral blood pressure associated with the arms and legs, pulmonary arterial pressure associated with the pulmonary valve area of the heart, atrium and ventricle blood pressure associated with the atrium and ventricle region of the heart, and cerebral blood pressure associated with the head. By extracting relevant temporal and spatial feature such as, but not limited to, speckle contrast fluctuations, phase shifts, frequency components, and propagation delays — the module can infer both absolute and relative blood pressure values.

[0065] [9] In some embodiments, the blood pressure determining module 304 employs supervised and / or unsupervised learning models trained on labeled datasets that include ground-truth blood pressure measurements from clinical instruments. The models may include, but are not limited to, regression models, convolutional neural networks (CNNs), recurrent neural networks (RNNs), or hybrid architectures tailored to capture temporal dependencies and spatial correlations in the optical data. The central blood pressure is estimated from optical data acquired from regions like the neck, corresponding to the aortic root and carotid arteries, offering insight into pressure near the heart’s central outflow. The peripheral blood pressure is derived from optical data at extremities such as the arms or legs, reflecting systemic arterial pressure at distal locations. The pulmonary arterial pressure is estimated from signals associated with the thoracic or precordial regions, potentially aligned with pulmonary valve and artery motion, useful for evaluating pulmonary hypertension. The atrial and ventricular blood pressure is assessed by analyzing patterns in the chest area corresponding to atrial and ventricular movement, aiding in the detection of cardiac anomalies such as heart failure or valve dysfunction. The cerebral blood pressure is derived from optical data captured at cranial or upper neck regions, providing valuable insights into cerebrovascular hemodynamics and risks related to stroke or intracranial pressure changes.

[0066]

[0010] In some configurations, the module may also incorporate contextual data such as heart rate, pulse transit time, or respiratory rate to improve prediction accuracy. Additionally, the blood pressure determining module 304 may operate in real-time, providing continuous, non-invasive blood pressure monitoring suitable for both clinical and remote health monitoring scenarios

[0067]

[0011] The synchronization module 306 is configured to synchronize the dynamically changing speckle pattern obtained from one or more anatomical sites using a time reference to ensure precise temporal alignment of optical displacement data. In some embodiments, the synchronization process involves tagging each speckle data stream with high-resolution timestamps generated by an internal clock, GPS-based timing system, or a synchronized external reference (e.g., ECG or respiration monitor), allowing for accurate correlation of physiological events across the body. The temporal alignment is critical for capturing coherent relationships among optical signals originating from multiple sites such as comparing pulse wave arrival times between the carotid artery and the radial artery, or analyzing the propagation of hemodynamic waves through cardiac chambers and peripheral vasculature. The synchronization module 306 may implement buffering mechanisms, interpolation algorithms, or clock drift correction techniques to accommodate minor variations in sampling intervals and data acquisition latency. In some embodiments, the synchronization module 306 may operate in tandem with wearable or external biosensors (e.g., electrocardiography, photoplethysmography, accelerometry) to align the speckle data with specific physiological events, such as the R-peak of the ECG signal or respiratory phase transitions. This enables phase-locked signal analysis and enhances the accuracy of derived parameters like pulse transit time, cardiac cycle timing, and respiratory-driven modulation of blood flow. Moreover, the synchronization module 306 may facilitate multi-modal data fusion, allowing the system to integrate speckle-based optical displacement data with concurrently acquired datasets for improved signal interpretation, feature extraction, and physiological modeling. The synchronized output is then routed to downstream modules such as the aligning module 308 and the pulse wave dynamics extraction module 310 for further spatial and temporal processing.

[0068]

[0012] The aligning module 308 is configured to align the temporally synchronized optical signals with corresponding blood pressure data derived from machine learning models, such that pressure waveforms from different anatomical sites are analyzed in a unified time domain. The alignment ensures that dynamic hemodynamic patterns such as pulse wave propagation, reflection, and augmentation can be compared across spatially separated locations in a physiologically meaningful manner. In some embodiments, the aligning module 308 employs signal processing techniques such as dynamic time warping (DTW), crosscorrelation, or phase shift analysis to fine-tune the temporal correspondence between optical displacement signals and the estimated blood pressure waveforms. Such methods enable compensation for signal latency, transit time variations, and acquisition offsets that may arise due to hardware limitations, anatomical differences, or asynchronous data streams. The aligning module 308 may also reference fiducial points such as the foot, peak, or dicrotic notch of the pressure waveform to anchor alignment across multiple signals. By aligning the characteristic points, the system 100 can more precisely evaluate pulse transit time, vascular compliance, and inter-site pressure differentials, which are key indicators of arterial stiffness and cardiovascular function. In some embodiments, the aligning module 308 supports adaptive or context-aware alignment strategies that adjust based on subject-specific physiological conditions (e.g., heart rate variability, arrhythmias, or respiration-induced waveform shifts). Additionally, the aligning module 308 may generate a composite, time-aligned dataset that facilitates ensemble analysis across anatomical sites, feeding into downstream modules such as the pulse wave dynamics extraction module 310 and the arterial stiffness determining module 312 for further diagnostic interpretation.

[0069]

[0013] The pulse wave dynamics extraction module 310 is configured to analyze temporally aligned signals to extract pulse wave dynamics, including pulse wave velocity, waveform morphology, transit times between anatomical sites, and reflection indices indicative of vascular conditions. By leveraging high temporal resolution and spatial fidelity of the synchronized and aligned optical data, the pulse wave dynamics extraction module 310 computes pulse wave velocity (PWV), waveform morphology, pulse transit times (PTT) between anatomical sites, and reflection indices, all of which provide insight into vascular tone, arterial stiffness, and peripheral resistance. In some embodiments, the pulse wave dynamics extraction module 310 performs signal decomposition and feature extraction using signal processing techniques, including Fourier transforms, wavelet analysis, derivative-based detection, and envelope tracking. The pulse wave velocity (PWV) is calculated by measuring the time it takes for the pulse wave to travel between two anatomical locations (e.g., carotid to femoral). A higher PWV is generally associated with increased arterial stiffness and cardiovascular risk. The pulse transit time is determined by evaluating the delay between the arrival of a pulse wave at different measurement sites. PTT variations may reflect changes in blood pressure, vascular tone, or autonomic nervous system activity. The waveform morphology: includes assessment of waveform shape, amplitude ratios, inflection points, and area under the curve. These features help distinguish between normal and pathological conditions, such as arterial stiffening, valve dysfunction, or peripheral vascular disease. The reflection indices are derived by quantifying the magnitude and timing of reflected pulse waves, which originate from points of impedance mismatch within the arterial system (e.g., bifurcations, stiffened vessels). The reflection indices are useful for evaluating vascular aging and the presence of atherosclerotic lesions.

[0070]

[0014] In certain implementations, the pulse wave dynamics extraction module 310 may use adaptive filtering, machine learning-based classifiers, or predictive modeling to improve the robustness and accuracy of extracted parameters under varying physiological and environmental conditions. Additionally, it may operate in conjunction with historical or baseline datasets stored in the database 300 to track longitudinal trends and detect early deviations from normal hemodynamic patterns.

[0071]

[0015] The arterial stiffness determining module 312 is configured to determine arterial stiffness by calculating regional or segmental pulse wave velocity and evaluating time- differentiated displacement and pressure propagation across central and peripheral anatomical sites. In some embodiments, the arterial stiffness determining module 312 calculates regional PWV by determining the transit time of pulse waves between two or more anatomical locations (e.g., carotid-to-femoral, neck-to-wrist, or chest-to-leg) and dividing the known physical distance between those points by the measured transit time. Segmental PWV may be assessed by isolating shorter arterial paths (e.g., thoracic aorta, radial artery) to localize stiffness and provide higher spatial resolution in vascular profiling.

[0072]

[0016] Additionally, the arterial stiffness determining module 312 evaluates time- differentiated displacement data, extracted from the dynamically changing speckle patterns, to quantify the rate of tissue motion induced by underlying pulse pressure. This enables detection of subtle changes in vessel wall compliance that may not be apparent in traditional pressure- only measurements. By combining optical displacement signals with pressure waveform characteristics such as upstroke velocity, pulse amplitude, and augmentation index the arterial stiffness determining module 312 builds a detailed profile of how arterial walls respond to pulsatile blood flow. In some embodiments, the arterial stiffness determining module 312 leverages machine learning models trained on clinical datasets to improve the accuracy of stiffness estimation in the presence of noise or signal variability. The arterial stiffness determining module 312 may also incorporate physiological context such as age, sex, heart rate, or blood pressure history from the database 300 to personalize stiffness metrics and interpret values in relation to normative baselines.

[0073]

[0017] The hemodynamic parameter determining module 314 is configured to estimate hemodynamic parameters, including regional blood flow characteristics, pressure gradients, vascular resistance, and cardiac output based on integrated pressure profiles and optical motion data. The hemodynamic parameter determining module 314 synthesizes information obtained from preceding processing stages including aligned pulse waveforms, arterial stiffness indices, and displacement dynamics to derive clinically relevant metrics that characterize the cardiovascular system’s functionality under both resting and dynamic conditions. In some embodiments, the hemodynamic parameter determining module 314 computes regional blood flow characteristics by evaluating the temporal and spatial variations in optical tissue motion patterns, which are directly influenced by underlying volumetric blood flow. Combined with pressure waveform data, the module calculates pressure gradients across vascular segments, such as between central (e.g., aortic arch) and peripheral (e.g., radial artery) sites, which reflect the effort required for blood to perfuse different regions of the body. To improve accuracy and robustness, the hemodynamic parameter determining module 314 may integrate machine learning regression models trained on multi-modal cardiovascular datasets, allowing it to generalize across a wide range of physiological and pathological conditions. In certain implementations, the hemodynamic parameter determining module 314 can adaptively tune its estimation algorithms based on contextual variables such as subject age, body surface area, posture, or activity level, which are accessed via the database 300. The output of the hemodynamic parameter determining module 314may be presented as time-resolved trends or summary reports, supporting clinical decision-making in acute care, chronic monitoring, or telehealth environments. Additionally, these parameters can be continuously tracked to detect deviations from baseline or to evaluate responses to therapeutic interventions.

[0018] FIG. 4 is a block diagram of the blood pressure determining module 304 of FIG. 3 in accordance with the present disclosure. The blood pressure determining module 304 includes a central blood pressure determining module 402, a peripheral blood pressure determining module 404, a pulmonary arterial pressure determining module 406, an atrium and ventricle blood pressure determining module 408, and a cerebral blood pressure determining module 410. The central blood pressure determining module 402 is configured to determine the central blood pressure (CBP) including systolic and diastolic blood pressure from the dynamically changing speckle pattern by (i) applying motion description modelling analysis on the dynamically changing speckle pattern for measuring dynamic changes in carotid artery and / or aorta motion and blood vessel displacement, (ii) utilizing a motion description model to estimate pulse and pressure wave propagation in the carotid artery, (iii) extracting velocity profiles, displacement derivatives, and frequency components from optical data, (iv) implementing an Al-based data-driven model to estimate extracted optical parameters with absolute calibration blood pressure values, (v) analyzing microvascular fluctuations and flow turbulence within the carotid artery and / or aorta to refine CBP estimation, and (vi) determining the central blood pressure based on the correlation between carotid artery hemodynamics and CBP-related physiological markers. The Al-based model may comprise deep learning architectures such as convolutional neural networks (CNNs) for spatiotemporal pattern recognition, recurrent neural networks (RNNs) or long short-term memory networks (LSTMs) for sequential time-series modeling of displacement and velocity signals, and ensemble methods (e.g., random forests or gradient boosting) for feature importance ranking and error correction. The Al-based model is trained using annotated dataset comprising synchronized optical displacement data and reference CBP measurements acquired via invasive or non-invasive gold-standard techniques. It can further incorporate domain adaptation techniques to generalize across diverse skin tones, anatomical variations, and device placements. In some embodiments, the Al-based model includes a calibration framework that continuously refines its estimates using baseline or periodic reference readings from a cuff-based system, thereby improving long-term stability and individual-specific accuracy. It may also feature uncertainty quantification mechanisms, such as Bayesian inference or Monte Carlo dropout, to provide confidence intervals along with CBP predictions. Additionally, the Al-based model supports real-time processing, enabling continuous, noncontact central blood pressure monitoring in both clinical and ambulatory settings.

[0074]

[0019] The peripheral blood pressure determining module 404 is configured to determine non-simultaneous or simultaneous peripheral blood pressure and blood pressure differentials across arms and legs from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern to detect arterial pulsation and pulsation timing differences across the arms and legs, (ii) computing inter-limb pulse wave velocity (PWV) to assess vascular stiffness, (iii) utilizing speckle tracking to measure flow resistance in small arteries and capillaries, (iv) calculating ankle- brachial index (ABI) by comparing transit delays between brachial and ankle arteries using motion description modelling timing, (v) correlating the extracted parameters with vascular health indicators to detect conditions such as peripheral artery disease (PAD), and (vi) determining simultaneous peripheral blood pressure based on the computed arterial pulsation parameters, vascular resistance, and ABI measurements. To enhance accuracy and personalization, the module incorporates an Al-based computational framework, which includes machine learning and deep learning models trained on large, annotated datasets that pair optical motion data with ground-truth peripheral pressure values (e.g., cuff-based measurements at brachial, femoral, and ankle sites). In some embodiments, convolutional neural networks (CNNs) are employed to extract spatial features from speckle patterns, while recurrent neural networks (RNNs) or LSTMs model temporal dependencies in pulsation and transit delays. Feature fusion models may integrate multiple time-domain and frequencydomain descriptors including waveform slopes, acceleration phases, and delay differentials into a unified prediction of peripheral pressure. Additionally, the peripheral blood pressure determining module 404 may utilize transfer learning techniques to adapt the model to individual users, accounting for limb asymmetry, tissue density variation, and skin tone differences. The Al model can also be designed with confidence scoring and anomaly detection capabilities, enabling the identification of outliers or unusual physiological patterns that may require clinical attention. In real-time applications, the model continuously refines its predictions using adaptive calibration methods and can alert for inter-limb pressure differentials suggestive of arterial blockage, stenosis, or early-stage PAD.

[0075]

[0020] The pulmonary arterial pressure determining module 406 is configured to determine pulmonary arterial pressure (PAP) from the dynamically changing speckle pattern by (i) applying the motion description modelling on the dynamically changing speckle pattern to estimate right ventricular ejection dynamics influencing PAP on pulmonary valve, (ii) utilizing speckle-based flow mapping to measure resistance variations in pulmonary arteries and track high-speed fluctuations associated with pulmonary hypertension, (iii) extracting optical displacement data in real-time and processing using an Al-driven PAP estimation model, (iv) computing mean pulmonary arterial pressure (mPAP) based on the correlation between motion description modelling on speckle images parameters and pulmonary hemodynamic characteristics, (v) spatiotemporal speckle modeling based features (capturing localized chest wall and right ventricular outflow tract movements), and respiratory gating to account for intrathoracic pressure variations, (vi) derive pulmonary vascular resistance (PVR) through correlation of estimated flow velocities with measured or inferred mean PAP, and further enhance accuracy by fusing data from motion description modelling on speckle image based pulse waveform (or) ECG for more precise alignment of cardiac events. The Al-based PAP estimation model integrates learned patterns from labeled data to predict PAP values with high temporal resolution.

[0076]

[0021] The atrium and ventricle blood pressure determining module 408 is configured to determine the atrium and ventricle pressure from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern for tracking to analyze jugular venous pulse (JVP) motion, detecting venous distension and collapse patterns, (ii) utilizing high-frame-rate optical imaging to detect myocardial contractions and extracting strain patterns, (iii) implementing Al-driven segmentation to distinguish systolic and diastolic myocardial strain dynamics, (iv) deriving left ventricular end- diastolic pressure (LVEDP) using optical pulse transit time (PTT)-based arterial phase shift analysis, (v) determining right atrial pressure (RAP) from variations in optical pulse transit time and venous waveform changes, (vii) performing cardiac wall motion mapping through speckle tracking and phase-based optical analysis to estimate left ventricular pressure variation, (viii) employing hemodynamic modeling to correlate the extracted optical motion parameters with intraventricular pressure dynamics to determine the atrium and ventricle blood pressure, (ix) analyzing morphological features in the JVP waveform, including a-wave, c-wave, and v-wave, and correlating these with myocardial strain patterns to detect arrhythmias, valvular dysfunction, or conduction abnormalities (x) synchronizing optical data acquisition with an ECG or respiratory gating signal, when available, to improve the timing accuracy of PTT-based metrics and capture intrathoracic pressure variations that influence atrial and ventricular pressures, (xi) implementing a continuous or adaptive calibration model that refines the correlation between measured optical parameters and reference intraventricular pressures from known invasive or clinical standards, thus enhancing accuracy over time and across varying patient profiles, and (xii) providing real-time or near-real-time alerts or trend analyses to identify acute hemodynamic changes including fluid overload, increased right atrial pressure, or left ventricular dysfunction, facilitating early intervention in conditions including heart failure or valvular disease. The system employs convolutional neural networks (CNNs) for spatial feature extraction of myocardial strain patterns and jugular venous pulse (JVP) morphology, and recurrent neural networks (RNNs), such as long short-term memory (LSTM) networks, to model temporal relationships in pulsatile dynamics across cardiac cycles.

[0077]

[0022] For robust segmentation and phase differentiation, the module uses Al-based segmentation algorithms potentially powered by U-Net architectures — to distinguish between systolic and diastolic myocardial activity, identify JVP waveform phases (a-wave, c-wave, v- wave), and isolate optical markers of myocardial contractility and wall motion. These segmented outputs are passed through feature fusion layers, where they are combined with parameters derived from pulse transit time (PTT), phase shift analyses, and strain rate mapping to form a multidimensional input for pressure estimation models.

[0078]

[0023] An embedded pressure estimation model, potentially built on regression-based deep learning or transformer architectures, maps these fused features to reference pressure values such as right atrial pressure (RAP), left ventricular end-diastolic pressure (LVEDP), and mean ventricular pressure, leveraging supervised learning from datasets paired with invasive catheterization measurements or echocardiographic references.

[0079]

[0024] The cerebral blood pressure determining module 410 is configured to determine the cerebral blood pressure from the dynamically changing speckle pattern by (i) processing the dynamically changing speckle pattern using motion description modelling and speckle contrast analysis to derive arterial pulsatility and flow resistance in middle cerebral artery (MCA), (ii) utilizing phase-based optical pulse timing to evaluate cerebrovascular resistance (CVR) by measuring pressure-dependent flow variations across brain regions, (iii) estimating intracranial pressure (ICP) fluctuations by analyzing arterial waveform shifts detected through motion description modelling algorithms, and (iv) determining cerebral blood pressure based on the derived CPP, MCA pulsatility, CVR, and ICP estimations using an Al-driven cerebral blood pressure estimation model. The Al-driven model is configured to handle complex, multidimensional optical input data such as dynamic speckle intensity fluctuations, displacement trajectories, frequency spectra, and phase shifts to infer cerebral hemodynamic parameters. The Al-driven model may employ deep learning architectures like multi-branch CNNs for spatial feature extraction and bidirectional LSTM networks for capturing temporal dynamics in pulsatility and waveform evolution. Additionally, the Al-driven model can include attention mechanisms to selectively focus on waveform segments most indicative of ICP changes or MCA flow disruptions.

[0025] Trained on extensive datasets that combine optical motion data, transcranial Doppler (TCD) readings, ECG signals, and, where available, invasive ICP measurements, the Al model learns to map speckle-derived features to physiological outputs such as mean cerebral arterial pressure (MCAP), CVR, and ICP trends. The model can also implement domain adaptation layers to account for anatomical variability (e.g., skull thickness, skin tone, vascular branching) and context-aware learning that incorporates auxiliary signals like heart rate, breathing rate, or systemic blood pressure to improve accuracy.

[0080]

[0026] FIGS. 5A and 5B illustrate a method for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via bio-photonic signals using motion estimation and machine learning models in accordance with the present disclosure. For purposes of clarity and to avoid redundancy, the descriptions of the hardware elements such as the optical device, image-capturing sensor, and processing units previously outlined in FIGS. 1-4 are not repeated herein. Rather, FIGS. 5A and 5B focus on the procedural flow of operations carried out by the system components for signal acquisition, processing, feature extraction, machine learning-based analysis, and blood pressure determination. The method can be implemented in real-time or offline modes depending on the system configuration and application requirements. It is further noted that to avoid repetition, detailed technical descriptions of each step are omitted here as they have been comprehensively explained in association with the corresponding modules in earlier sections. The method can be implemented in real-time or offline modes depending on the system configuration and application requirements. At step 502, the method includes emitting coherent laser light on single or multiple points on the biological tissues at one or more anatomical sites of a subject. At step 504, the method includes capturing optical data comprising a dynamically changing speckle pattern formed by reflected laser light from one or more anatomical sites of the subject. At step 506, the method includes determining, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern, wherein the blood pressure includes central blood pressure (CBP) associated with the neck, peripheral blood pressure associated with the arms and legs, pulmonary arterial pressure associated with the pulmonary valve area of the heart, atrium and ventricle blood pressure associated with the atrium and ventricle region of the heart, and cerebral blood pressure associated with the head. At step 510, the method includes synchronizing the dynamically changing speckle pattern obtained from one or more anatomical sites using a time reference to ensure precise temporal alignment of optical displacement data. At step 512, the method includes aligning the temporally synchronized optical signals with corresponding blood pressure data derived from machine learning models, such that pressure waveforms from different anatomical sites are analyzed in a unified time domain. At step 514, the method includes analyzing temporally aligned signals to extract pulse wave dynamics, including pulse wave velocity, waveform morphology, transit times between anatomical sites, and reflection indices indicative of vascular conditions. At step 516, the method includes determining arterial stiffness by calculating regional or segmental pulse wave velocity and evaluating time-differentiated displacement and pressure propagation across central and peripheral anatomical sites. At step 518, the method includes estimating hemodynamic parameters, including regional blood flow characteristics, pressure gradients, vascular resistance, and cardiac output based on integrated pressure profiles and optical motion data.

[0081]

[0027] FIG. 6 illustrates temporal and spectral representations of pulse signals extracted from bio-photonic measurements in accordance with the present disclosure. The firs graphical representation 602 displays the bio-photonic signal, which comprises high- frequency fluctuations and transient features captured from dynamically changing speckle patterns generated by reflected coherent light (e.g., laser or VCSEL) interacting with vascular tissue. The bio-photonic signal encodes fine-grained motion and displacement data associated with microvascular and macrovascular dynamics, including arterial wall motion and pulsatile blood flow.

[0082]

[0028] The second graphical representation 604 illustrates corresponding pulse waveform, derived from the bio-photonic signal through signal processing techniques such as temporal filtering, envelope detection, and noise suppression. The pulse waveform highlights the cyclical nature of the cardiac pulse, capturing individual heartbeat events and the associated amplitude modulations. The periodic peaks observed correspond to systolic expansions, while the inter-peak intervals provide information about pulse rate variability and vascular compliance.

[0083]

[0029] The transformation from the bio-photonic signal to the refined pulse waveform demonstrates the system’s capability to extract clinically relevant hemodynamic information in a non-invasive and real-time manner. These signals may be further analyzed to estimate parameters such as pulse wave velocity, arterial stiffness, blood pressure, and cardiac output, leveraging both temporal patterns and spectral components. The visualization in FIG. 6 underscores the robustness of the optical system in resolving physiological events with high sensitivity and temporal resolution, enabling advanced cardiovascular monitoring and health assessment through compact, light-based biosensing platforms

[0030] FIG. 7 illustrates spectrogram visualizations of the bio-photonic experimental signal, highlighting the evolution of frequency components over time in accordance with the present disclosure. The spectrograms, segmented into three time intervals (0-10 seconds, 10- 20 seconds, and 20-30 seconds), capture the dynamic spectral distribution of the signal within the cardiovascular-relevant frequency band of 0.8 Hz to 8 Hz, encompassing typical physiological rhythms including cardiac pulses, respiratory modulations, and low-frequency vascular oscillations.

[0084]

[0031] The vertical axis in each subplot represents the frequency domain, while the horizontal axis indicates time progression. The intensity and brightness of each region in the spectrogram correspond to the amplitude (or energy) of specific frequency components at given time instances, enabling temporal tracking of dominant oscillatory patterns and harmonics. The spectrogram visualizations reveal modulations in signal intensity and frequency clustering, potentially reflective of changing cardiovascular states, such as: variations in pulse frequency and its harmonics due to changes in heart rate, detection of respiratory-induced pressure modulations, and identification of vascular impedance fluctuations or microvascular autoregulatory activity. The spectrogram enables the extraction of frequency-domain biomarkers which are essential for non-invasive estimation of hemodynamic parameters such as arterial stiffness, vascular tone, and heart rate variability (HRV). Moreover, these patterns can serve as input to Al-based time-frequency analysis models to improve personalized cardiovascular monitoring, anomaly detection, and longitudinal trend analysis.

[0085]

[0032] FIG. 8 illustrates systolic and diastolic mean absolute errors for determined blood pressure, demonstrating the performance of the optical blood pressure estimation model in accordance with the present disclosure. The mean absolute error for systolic blood pressure (SBP) is observed to be 4.66 mmHg, while the diastolic blood pressure (DBP) shows a lower error of 3.26 mmHg. This performance falls within the acceptable error range. The results confirm the efficacy of the Al-based optical model, which integrates speckle pattern analysis, motion description modelling tracking, pulse waveform modeling, and machine learning calibration to derive accurate BP values.

[0086]

[0033] FIG. 9 is a schematic diagram of a computer architecture 600 for executing the embodiments in accordance with the present disclosure. This schematic drawing illustrates a hardware or computer configuration of a server 110 / computer system / computing device in accordance with the embodiments herein. For instance, the server 110 comprises the computer architecture 900 for executing one or more functions in determining one or more physiological parameters. The computer architecture 600 includes at least one processing device CPU 10 that may be interconnected via system bus 14 to various devices such as a random-access memory (RAM) 12, read-only memory (ROM) 16, and an input / output (I / O) adapter 18. The I / O adapter 18 can connect to peripheral devices, such as disk units 38 and program storage devices 40 that are readable by the system. The system can read the inventive instructions on the program storage devices 40 and follow these instructions to execute the methodology of the embodiments herein. The system further includes a user interface adapter 22 that connects a keyboard 28, mouse 30, speaker 32, microphone 34, and / or other user interface devices such as a touch screen device (not shown) to the bus 14 to gather user input. Additionally, a communication adapter 20 connects the bus 14 to a data processing network 42, and a display adapter 24 connects the bus 14 to a display device 26, which provides a graphical user interface (GUI) 36 of the output data in accordance with the embodiments herein, or which may be embodied as an output device such as a monitor, printer, or transmitter, for example.

[0087]

[0034] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope.

Claims

What is claimed is:

1. A system for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via bio-photonic signals using motion estimation and machine learning models, for blood pressure profiling, the system comprising: an optical device configured to emit coherent laser light on single or multiple points on the biological tissues at one or more anatomical sites of a subject either sequentially or simultaneously, so as to generate a speckle pattern comprising real-time optical displacement data indicative of tissue microstructure changes and movement in blood vessels during each heartbeat, wherein the one or more anatomical sites includes neck, chest, arms, legs, pulmonary valve area of heart, atrium and ventricle region of the heart, and head; one or more image-capturing sensors configured to capture optical data comprising a dynamically changing speckle pattern formed by reflected laser light from one or more anatomical sites of the subject; and a server communicatively connected to the optical device and the image-capturing sensor, wherein the server comprises a memory storing a database and a set of modules; and a processor configured to execute the set of modules, wherein the server is configured to, obtain the dynamically changing speckle pattern formed by the reflected laser light from the image-capturing sensor; and determine, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern, wherein the blood pressure includes central blood pressure (CBP) associated with the neck or chest area, peripheral blood pressure associated with the arms and legs, pulmonary arterial pressure associated with the pulmonary valve area of the heart, atrium and ventricle blood pressure associated with the atrium and ventricle region of the heart, and cerebral blood pressure associated with the head.

2. The system as claimed in claim 1, wherein the processor is further configured to synchronize the dynamically changing speckle pattern obtained from one or more anatomical sites using a time reference to ensure precise temporal alignment of optical displacement data; align the temporally synchronized optical signals with corresponding blood pressure data derived from machine learning models, such that pressure waveforms from different anatomical sites are analyzed in a unified time domain;analyze temporally aligned signals to extract pulse wave dynamics, including pulse wave velocity, waveform morphology, transit times between anatomical sites, and reflection indices indicative of vascular conditions; determine arterial stiffness by calculating regional or segmental pulse wave velocity and evaluating time-differentiated displacement and pressure propagation across central and peripheral anatomical sites; and estimate hemodynamic parameters, including regional blood flow characteristics, pressure gradients, vascular resistance, and cardiac output based on integrated pressure profiles and optical motion data.

3. The system as claimed in claim 1, wherein the processor is configured to determine the central blood pressure (CBP) including systolic and diastolic blood pressure from the dynamically changing speckle pattern by (i) applying motion description modelling analysis on the dynamically changing speckle pattern for measuring dynamic changes in carotid artery and / or aorta motion and blood vessel displacement, (ii) utilizing a motion description model to estimate pulse and pressure wave propagation in the carotid artery, (iii) extracting velocity profiles, displacement derivatives, and frequency components from optical data, (iv) implementing an Al-based data-driven model to estimate extracted optical parameters with absolute calibration blood pressure values, (v) analyzing microvascular fluctuations and flow turbulence within the carotid artery and / or aorta to refine CBP estimation, and (vi) determining the central blood pressure based on the correlation between carotid artery hemodynamics and CBP-related physiological markers.

3. The system as claimed in claim 1, wherein the processor is configured to determine nonsimultaneous or simultaneous peripheral blood pressure and blood pressure differentials across arms and legs from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern to detect arterial pulsation and pulsation timing differences across the arms and legs, (ii) computing inter-limb pulse wave velocity (PWV) to assess vascular stiffness, (iii) utilizing speckle tracking to measure flow resistance in small arteries and capillaries, (iv) calculating ankle-brachial index (ABI) by comparing transit delays between brachial and ankle arteries using motion description modelling timing, (v) correlating the extracted parameters with vascular health indicators to detect conditions including peripheral artery disease (PAD), and (vi) determining simultaneous peripheral blood pressure based on the computed arterial pulsation parameters, vascular resistance, and ABI measurements.

4. The system as claimed in claim 1, wherein the processor is configured to determine pulmonary arterial pressure (PAP) from the dynamically changing speckle pattern by (i) applying the motion description modelling on the dynamically changing speckle pattern to estimate right ventricular ejection dynamics influencing PAP on pulmonary valve, (ii) utilizing speckle-based flow mapping to measure resistance variations in pulmonary arteries and track high-speed fluctuations associated with pulmonary hypertension, (iii) extracting optical displacement data in real-time and processing using an Al-driven PAP estimation model, (iv) computing mean pulmonary arterial pressure (mPAP) based on the correlation between motion description modelling on speckle images parameters and pulmonary hemodynamic characteristics, (v) spatiotemporal speckle modeling based features (capturing localized chest wall and right ventricular outflow tract movements), and respiratory gating to account for intrathoracic pressure variations, (vi) derive pulmonary vascular resistance (PVR) through correlation of estimated flow velocities with measured or inferred mean PAP, and further enhance accuracy by fusing data from motion description modelling on speckle image based pulse waveform (or) ECG or PPG for more precise alignment of cardiac events.

5. The system as claimed in claim 1, wherein the processor is configured to determine the atrium and ventricle blood pressure from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern for tracking to analyze jugular venous pulse (JVP) motion, detecting venous distension and collapse patterns, (ii) utilizing high-frame-rate optical imaging to detect myocardial contractions and extracting strain patterns, (iii) implementing Al-driven segmentation to distinguish systolic and diastolic myocardial strain dynamics, (iv) deriving left ventricular end- diastolic pressure (LVEDP) using optical pulse transit time (PTT)-based arterial phase shift analysis, (v) determining right atrial pressure (RAP) from variations in optical pulse transit time and venous waveform changes, (vii) performing cardiac wall motion mapping through speckle tracking and phase-based optical analysis to estimate left ventricular pressure variation, (viii) employing hemodynamic modeling to correlate the extracted optical motion parameters with intraventricular pressure dynamics to determine the atrium and ventricle blood pressure, (ix) analyzing morphological features in the JVP waveform, including a-wave, c-wave, and v- wave, and correlating these with myocardial strain patterns to detect arrhythmias, valvular dysfunction, or conduction abnormalities (x) synchronizing optical data acquisition with an ECG or respiratory gating signal, when available, to improve the timing accuracy of PTT-based metrics and capture intrathoracic pressure variations that influence atrial and ventricularpressures, (xi) implementing a continuous or adaptive calibration model that refines the correlation between measured optical parameters and reference intraventricular pressures from known invasive or clinical standards, thus enhancing accuracy over time and across varying patient profiles, and (xii) providing real-time or near-real-time alerts or trend analyses to identify acute hemodynamic changes including fluid overload, increased right atrial pressure, or left ventricular dysfunction, facilitating early intervention in conditions including heart failure or valvular disease.

6. The system as claimed in claim 1, wherein the processor is configured to determine the cerebral blood pressure from the dynamically changing speckle pattern by (i) processing the dynamically changing speckle pattern using motion description modelling and speckle contrast analysis to derive arterial pulsatility and flow resistance in middle cerebral artery (MCA), (ii) utilizing phase-based optical pulse timing to evaluate cerebrovascular resistance (CVR) by measuring pressure-dependent flow variations across brain regions, (iii) estimating intracranial pressure (ICP) fluctuations by analyzing arterial waveform shifts detected through motion description modelling algorithms, and (iv) determining cerebral blood pressure based on the derived CPP, MCA pulsatility, CVR, and ICP estimations using an Al-driven cerebral blood pressure estimation model.

7. The system as claimed in claim 1, wherein the coherent laser light from the optical device is directed towards the neck or the chest to generate the dynamically changing speckle pattern for central blood pressure determination.

8. The system as claimed in claim 1, wherein the coherent laser light from the optical device is directed towards upper and lower limbs to generate the dynamically changing speckle pattern for simultaneous peripheral blood pressure determination.

9. The system as claimed in claim 1, wherein the coherent laser light from the optical device is directed towards the chest wall to generate the dynamically changing speckle pattern for pulmonary arterial pressure determination.

10. The system as claimed in claim 1, wherein the coherent laser light from the optical device is directed towards the neck region and the chest region to generate the dynamically changing speckle pattern for atrium and ventricle blood pressure determination.

11. The system as claimed in claim 1, wherein the coherent laser light from the optical device is directed towards the head (cerebral tissue) to generate the dynamically changing speckle pattern for cerebral blood pressure determination.

12. The system as claimed in claim 1, wherein the one or more image-capturing sensors is selected from a group comprising a Complementary Metal-Oxide-Semiconductor (CMOS) camera, a Charge-Coupled Device (CCD) camera, a mouse optical sensor, a Raspberry Pi camera, an infrared (IR) camera, a smartphone camera, or a virtual reality device camera.

13. The system as claimed in claim 1, wherein the optical device emits coherent laser light at wavelengths ranging from 400 nanometers (nm) to 2500 nm, with a power output between 0.01 milliwatts (mW) and 5 mW.

14. The system as claimed in claim 1, wherein the image-capturing sensor is configured to acquire data at a sampling frequency ranging from 60 Hz to 1.6k Hz.

15. The system as claimed in claim 1, wherein the processor employs a motion estimation model including at least one of a motion description method, a block matching algorithm, a phase-based method, a gradient-based method or a feature-based method to process the dynamically changing speckle pattern formed by the reflected light to determine the blood pressure.

16. The system as claimed in claim 1, wherein the system is further configured to measure one or more pressures selected from the group consisting of central (neck), peripheral (arms, legs), pulmonary, cardiac (atrium and ventricle), and cerebral either individually or simultaneously, such that any subset or combination of these anatomical sites can be assessed in parallel or at different times, based on user selection or automated detection criteria.

17. A method for non-invasively determining calibrated blood pressure from one or multiple regions of a subject via bio-photonic signals using motion estimation and machine learning models, the method comprising: emitting, using an optical device, coherent laser light on single or multiple points on the biological tissues at one or more anatomical sites of a subject either sequentially or simultaneously, so as to generate a speckle pattern comprising real-time optical displacement data indicative of tissue microstructure changes and movement in blood vessels during each heartbeat, wherein the one or more anatomical sites includes neck, chest, arms, legs, pulmonary valve area of heart, atrium and ventricle region of the heart, and head;capturing, using one or more image-capturing sensors, optical data comprising a dynamically changing speckle pattern formed by reflected laser light from one or more anatomical sites of the subject; and determining, using statistical and machine learning-based modelling, blood pressure associated with the one or more anatomical sites by analysing the dynamically changing speckle pattern, wherein the blood pressure includes central blood pressure (CBP) associated with the neck or chest, peripheral blood pressure associated with the arms and legs, pulmonary arterial pressure associated with the pulmonary valve area of the heart, atrium and ventricle blood pressure associated with the atrium and ventricle region of the heart, and cerebral blood pressure associated with the head.

18. The method as claimed in claim 17, wherein the method further comprises synchronizing the dynamically changing speckle pattern obtained from one or more anatomical sites using a time reference to ensure precise temporal alignment of optical displacement data; aligning the temporally synchronized optical signals with corresponding blood pressure data derived from machine learning models, such that pressure waveforms from different anatomical sites are analyzed in a unified time domain; analyzing temporally aligned signals to extract pulse wave dynamics, including pulse wave velocity, waveform morphology, transit times between anatomical sites, and reflection indices indicative of vascular conditions; determining arterial stiffness by calculating regional or segmental pulse wave velocity and evaluating time-differentiated displacement and pressure propagation across central and peripheral anatomical sites; and estimating hemodynamic parameters, including regional blood flow characteristics, pressure gradients, vascular resistance, and cardiac output based on integrated pressure profiles and optical motion data.

19. The method as claimed in claim 17, wherein the method determines the central blood pressure (CBP) including systolic and diastolic blood pressure from the dynamically changing speckle pattern by (i) applying motion description modelling analysis on the dynamically changing speckle pattern for measuring dynamic changes in carotid artery and / or aorta motion and blood vessel displacement, (ii) utilizing a motion description model to estimate pulse and pressure wave propagation in the carotid artery, (iii) extracting velocity profiles, displacementderivatives, and frequency components from optical data, (iv) implementing an Al-based data- driven model to estimate extracted optical parameters with absolute calibration blood pressure values, (v) analyzing microvascular fluctuations and flow turbulence within the carotid artery and / or aorta to refine CBP estimation, and (vi) determining the central blood pressure based on the correlation between carotid artery hemodynamics and CBP-related physiological markers;20. The method as claimed in claim 17, wherein the method determines non-simultaneous or simultaneous peripheral blood pressure and blood pressure differentials across arms and legs from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern to detect arterial pulsation and pulsation timing differences across the arms and legs, (ii) computing inter-limb pulse wave velocity (PWV) to assess vascular stiffness, (iii) utilizing speckle tracking to measure flow resistance in small arteries and capillaries, (iv) calculating ankle-brachial index (AB I) by comparing transit delays between brachial and ankle arteries using motion description modelling timing, (v) correlating the extracted parameters with vascular health indicators to detect conditions including peripheral artery disease (PAD), and (vi) determining simultaneous peripheral blood pressure based on the computed arterial pulsation parameters, vascular resistance, and ABI measurements;21. The method as claimed in claim 17, wherein the method determines the pulmonary arterial pressure (PAP) from the dynamically changing speckle pattern by (i) applying the motion description modelling on the dynamically changing speckle pattern to estimate right ventricular ejection dynamics influencing PAP on pulmonary valve, (ii) utilizing speckle-based flow mapping to measure resistance variations in pulmonary arteries and track high-speed fluctuations associated with pulmonary hypertension, (iii) extracting optical displacement data in real-time and processing using an Al-driven PAP estimation model, (iv) computing mean pulmonary arterial pressure (mPAP) based on the correlation between motion description modelling on speckle images parameters and pulmonary hemodynamic characteristics, (v) spatiotemporal speckle modeling based features (capturing localized chest wall and right ventricular outflow tract movements), and respiratory gating to account for intrathoracic pressure variations, (vi) derive pulmonary vascular resistance (PVR) through correlation of estimated flow velocities with measured or inferred mean PAP, and further enhance accuracy by fusing data from motion description modelling on speckle image based pulse waveform (or) ECG for more precise alignment of cardiac events;22. The method as claimed in claim 17, wherein the method determines the atrium and ventricle pressure from the dynamically changing speckle pattern by (i) applying motion description modelling on the dynamically changing speckle pattern for tracking to analyze jugular venous pulse (JVP) motion, detecting venous distension and collapse patterns, (ii) utilizing high- frame-rate optical imaging to detect myocardial contractions and extracting strain patterns, (iii) implementing Al-driven segmentation to distinguish systolic and diastolic myocardial strain dynamics, (iv) deriving left ventricular end-diastolic pressure (LVEDP) using optical pulse transit time (PTT)-based arterial phase shift analysis, (v) determining right atrial pressure (RAP) from variations in optical pulse transit time and venous waveform changes, (vii) performing cardiac wall motion mapping through speckle tracking and phase-based optical analysis to estimate left ventricular pressure variation, (viii) employing hemodynamic modeling to correlate the extracted optical motion parameters with intraventricular pressure dynamics to determine the atrium and ventricle blood pressure, (ix) analyzing morphological features in the JVP waveform, including a-wave, c-wave, and v-wave, and correlating these with myocardial strain patterns to detect arrhythmias, valvular dysfunction, or conduction abnormalities (x) synchronizing optical data acquisition with an ECG or respiratory gating signal, when available, to improve the timing accuracy of PTT-based metrics and capture intrathoracic pressure variations that influence atrial and ventricular pressures, (xi) implementing a continuous or adaptive calibration model that refines the correlation between measured optical parameters and reference intraventricular pressures from known invasive or clinical standards, thus enhancing accuracy over time and across varying patient profiles, and (xii) providing real-time or near-real-time alerts or trend analyses to identify acute hemodynamic changes including fluid overload, increased right atrial pressure, or left ventricular dysfunction, facilitating early intervention in conditions including heart failure or valvular disease.23 The method as claimed in claim 17, wherein the method determines the cerebral blood pressure from the dynamically changing speckle pattern by (i) processing the dynamically changing speckle pattern using motion description modelling and speckle contrast analysis to derive arterial pulsatility and flow resistance in middle cerebral artery (MCA), (ii) utilizing phase-based optical pulse timing to evaluate cerebrovascular resistance (CVR) by measuring pressure-dependent flow variations across brain regions, (iii) estimating intracranial pressure (ICP) fluctuations by analyzing arterial waveform shifts detected through motion description modelling algorithms, and (iv) determining cerebral blood pressure based on the derived CPP,MCA pulsatility, CVR, and ICP estimations using an Al-driven cerebral blood pressure estimation model.

Images