Mobile Device-Based Oscillometric Blood Pressure Measurement

Abstract

Systems, devices, and methods for performing mobile device-based oscillometric blood pressure measurements are disclosed. In some embodiments, the mobile device includes a vibration motor, an inertial motion unit (IMU), a camera, a processor, and a non-transitory computer-readable memory, and the processor is configured to at least: vibrate the vibration motor; acquire, via the inertial measurement unit of the mobile device, IMU data indicative of vibration damping caused by a user's body part applying a force to the camera; determine the applied force based on a force model and the IMU data; capture, via the camera of the mobile device, photoplethysmography (PPG) data of blood vessels in the body part simultaneously with the application of the force; and determine the user's blood pressure using oscillometric techniques based on the PPG data and the applied force.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This patent document claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 385,383, entitled "SMARTPHONE-BASED BLOOD PRESSURE MEASUREMENT," filed November 29, 2022. The entire contents of the aforementioned patent application are incorporated by reference as part of the present disclosure of this patent document.

[0002] This patent document relates to mobile device-based oscillometric blood pressure measurement. [Background technology]

[0003] The American Heart Association (AHA) and the American Medical Association (AMA) issued a joint statement outlining the importance of integrating home self-monitoring of blood pressure and clearly stating that the oscillometric method of calculating blood pressure is preferred, which is the standard calculation performed by most FDA-approved blood pressure cuffs. Summary of the Invention

[0004] This document discloses a method, device, and system for performing blood pressure measurements based on oscillometric techniques using sensor data acquired by built-in sensors in a mobile device without additional accessories.

[0005] Aspects of the present document relate to a mobile device configured to measure blood pressure based on oscillometric techniques using sensor data acquired by an integrated sensor in the mobile device without accessories. The mobile device may include a vibration motor, an inertial motion unit (IMU), a camera, a processor, and non-transitory computer-readable memory storing instructions that, when executed by the processor, cause the processor to at least: vibrate the vibration motor; acquire, via the inertial measurement unit of the mobile device, IMU data indicative of vibration damping caused by a user's body part applying a force to the camera; determine the applied force based on a force model and the IMU data; capture, via the camera of the mobile device, photoplethysmography (PPG) data of blood vessels in the body part simultaneously with the application of the force; and determine the user's blood pressure using oscillometric techniques based on the PPG data and the applied force.

[0006] An aspect of this document relates to a method for measuring blood pressure based on oscillometric techniques using sensor data acquired by a built-in sensor of a mobile device without accessories. The method may include vibrating a vibration motor of the mobile device, using an inertial measurement unit (IMU) of the mobile device to acquire IMU data indicative of vibration damping caused by a body part of a user applying a force to a camera of the mobile device, determining the applied force based on a force model and the IMU data, using the camera of the mobile device to capture photoplethysmography (PPG) data of blood vessels in the body part simultaneously with the application of the force, and determining the user's blood pressure using oscillometric techniques based on the PPG data and the applied force.

[0007] A further aspect of this document relates to one or more non-transitory computer-readable media storing instructions that, when executed by one or more processors of a mobile device, cause the mobile device to perform any one or more of the solutions described herein.

[0008] These and other aspects of this document, as well as their implementations and applications, are explained in more detail in the drawings, description, and claims. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram of an exemplary system implementing the disclosed technology in accordance with the disclosed technology;

[0010] [Figure 2] FIG. 1 is an exemplary block diagram of various components of a mobile device in accordance with some embodiments of the present document.

[0011] [Figure 3] FIG. 1 illustrates an example application for mobile device-based blood pressure measurement according to some embodiments of the present disclosure.

[0012] [Figure 4] 1 is a flowchart of a process for mobile device-based blood pressure measurement according to some embodiments of the present document.

[0013] [Figure 5] 10A-10C are regression and Bland-Altman plots for force measurements of three different smartphones in accordance with some embodiments of the present document.

[0014] [Figure 6] FIG. 1(a) shows typical PPG and applied force data measured by a mobile device and corresponding oscillograms generated according to some embodiments of the present document.

[0015] [Figure 6] (b) Average oscillograms corresponding to different blood pressure ranges according to some embodiments of the present document.

[0016] [Figure 7] FIG. 6( a) shows a confusion matrix and ROC analysis of the results of FIG. 6( a) and FIG. 6(b) according to some embodiments of the present document. DETAILED DESCRIPTION OF THE INVENTION

[0017] This document describes systems, devices, and methods for measuring blood pressure using oscillometric methods in substantially the same way that a blood pressure cuff functions. This method can be applied to any mobile device equipped with a camera, vibration motor, and inertial measurement unit (IMU). Determining blood pressure using oscillometric methods requires the device to 1) apply a known force to a blood vessel and simultaneously 2) measure local blood volume. In the case of a blood pressure cuff, an inflatable cuff applies pressure to the blood vessels, while an integrated sensor measures changes in blood volume within the vessels. In the case of a mobile phone application disclosed herein, a user applies force by pressing a body part (e.g., the user's finger) against the mobile device's camera, while the camera can utilize photoplethysmography (PPG) to measure blood volume within the body part simultaneously with the application of force. Quantifying the applied force can be achieved by inducing vibrations within the mobile device via its internal vibration motor and using the mobile device's IMU to monitor the decay of these vibrations resulting from the applied force. The mobile device can determine a user's blood pressure based on the applied force and PPG data acquired using sensors already built into the mobile device, without requiring hardware modifications, physical accessories, or any prior blood pressure measurements for calibration; this can be enabled solely through software by downloading an application to any mobile device, as described in more detail below. This technology can therefore provide an opportunity for large-scale screening for hypertension. Because the software enables measurements on any mobile device equipped with a camera, IMU, and vibration motor, this technology can be rapidly disseminated to communities lacking adequate blood pressure monitoring.

[0018] Widespread blood pressure screening is an important step toward improving healthcare worldwide. Hypertension (defined here as systolic and / or diastolic blood pressure greater than 130 / 80 mmHg) has long been considered a major risk factor for heart disease, stroke, and chronic kidney disease. Recently, hypertension has been demonstrated to accelerate cognitive decline in middle-aged and older adults, and there is growing evidence that hypertension is associated with a higher risk of all-cause mild cognitive impairment (MCI) and non-amnestic MCI. Given that the World Health Organization estimates that nearly half (46%) of adults with hypertension are unaware of their symptoms, BP screening is essential to reaching the United Nations goal of reducing the prevalence of hypertension by 30% between 2010 and 2030. Furthermore, enabling large-scale screening could significantly improve health literacy and enable at-risk communities to address hypertension in non-traditional healthcare settings. Mobile device-based blood pressure monitoring could offer a scalable and cost-effective screening solution due to the widespread availability of mobile devices.

[0019] Most previous studies on smartphone and smartwatch blood pressure measurements have performed relative blood pressure measurements using optical methods that require only PPG measurements (e.g., pulse transit time (PTT) or pulse wave analysis (PWA)). However, these techniques are fundamentally different from the mobile device-based oscillometric blood pressure measurement technology disclosed herein. PTT and PWA only provide relative changes in blood pressure and cannot provide the valuable systolic and diastolic blood pressure measurements commonly used by physicians. Instead, blood pressure cuff measurements must be performed daily or weekly to calibrate the measurements. These measurements of relative change assume that the individual has access to a blood pressure cuff (or another absolute blood pressure measurement). Otherwise, the relative measurements cannot be meaningfully interpreted. Existing smartphone-based absolute blood pressure measurements often use custom accessories (e.g., additional force sensors) to measure force.

[0020] The mobile device-based oscillometric blood pressure measurement disclosed herein requires no accessories and works on any model of mobile device equipped with a vibration motor, camera, and IMU. Oscillometric blood pressure measurement is not an "optical" blood pressure measurement that relies on pulse transit time (PTT), pulse arrival time (PAT), pulse wave analysis (PWA), or any other technique to estimate relative changes in blood pressure. This application can perform absolute blood pressure measurements based on the oscillometric method used in clinical blood pressure cuffs. The oscillometric method is recommended by the American Medical Association (AMA) and the American Heart Association (AHA). As explained elsewhere in this document, blood pressure measurement based on oscillometric technology requires measuring two key indices: applied force and local blood volume. Local arterial blood volume can be accurately estimated using photoplethysmography (PPG) with a smartphone camera. Measuring applied force without accessories is a key finding that enables the blood pressure measurement disclosed herein. By relying on components common to different types of mobile devices, the oscillometric blood pressure measurement disclosed herein can function across different types of mobile devices (eg, type may correspond to model by manufacturer).

[0021] Some embodiments of this document disclose a force damping technique that uses only a mobile device's vibration motor and IMU to measure applied forces. Most mobile devices already include an IMU with an accelerometer and gyroscope for other purposes, such as measuring linear acceleration and angular velocity, which allows mobile devices to estimate their position, which is widely used for rotating screens, playing games, counting steps, gesture recognition, and many more. Similarly, most mobile devices already include a vibration motor to provide haptic feedback for messages, calls, and screen interactions. To measure forces, a mobile device may be set to vibrate (e.g., at full vibration), and the IMU measures the movement of the device when it vibrates (due to vibration). If a force is applied during vibration, the IMU signal changes because the vibration changes or damps. According to embodiments of this document, vibration damping is measured and, based on that, the applied force is modeled as a damping force for the vibration.

[0022] According to some embodiments of the present document, IMU data, including multi-axis accelerometer data and multi-axis gyroscope data that collectively represent vibration damping, is used to determine the corresponding forces that cause vibration damping. The method recognizes the coupling between the accelerometer data and different axes of the gyroscope that respond differently to the applied force. Due to conservation of energy, an applied force will not only cause vibration damping or a decrease in amplitude along all IMU axes. Rather, some axes may even increase because a force applied to damp vibration motion in one axis may transfer vibration energy to another axis. The disclosed method takes multiple inputs from both the accelerometer and the gyroscope as inputs and examines the frequency, amplitude, and relationship between the different axes.

[0023] The applied force that causes vibration damping of a mobile device may be quantified based on a force model trained to correlate (1) IMU data measured by the mobile device and indicative of the mobile device's vibration damping, and (2) the force applied to the mobile device that causes the corresponding vibration damping. The force model may include a machine learning algorithm (e.g., a multivariate linear regression algorithm). The correlation may vary depending on the configuration of the mobile device. Vibration damping may depend on one or more factors that contribute to how the mobile device absorbs and dissipates vibration energy. Examples of such factors include the intensity of the vibration, the load distribution within the mobile device (e.g., including how the weight and components are distributed within the mobile device), the materials used within the mobile device (e.g., including density, elasticity, and internal friction), the overall design (e.g., including features such as shape and structural integrity, ribs, gussets, etc.), the interactions between components within the device, etc., or a combination thereof. Additionally, the damping measured by a mobile device's IMU may depend on one or more factors, such as the location of the IMU relative to the vibration motor(s), sensor parameters such as sensitivity, resolution, noise level, etc., or a combination thereof. The cross-device reliability study disclosed herein demonstrates that the techniques disclosed herein provide similar force estimation performance across all smartphone models tested, indicating that the techniques are versatile and transferable between mobile devices. Force models may be determined for a mobile device type (e.g., model by manufacturer) and may be used to calibrate mobile devices of the same type.

[0024] The calibration step can enable standardized measurements across different types of mobile devices. Calibration can ensure that various mobile devices of the same type or of different types are configured to measure force consistently. In this way, the same blood pressure estimation model can be used across various mobile devices of the same type or of different types, even though the force models (also referred to as force estimation algorithms) may differ. This is useful because force model development is an automatic or at least partially automatic process, can be completed within a short period of time (e.g., one day), and does not require large-scale participant recruitment or clinical measurements. However, blood pressure model development may require many participants with different demographic data to undergo clinical blood pressure measurements, which can take several months or longer.

[0025] FIG. 1 illustrates an exemplary system implementing the disclosed technology for mobile-device-based oscillometric blood pressure measurement. The system 100 includes a mobile device 102, which may include at least one of a camera 104, a vibration motor 105, an IMU 106, a processor 108, a wireless transmitter 110, and a display 112. The processor 108 can control the operation of the mobile device 102 (e.g., vibrate the vibration motor 105, cause the camera 104 and / or the IMU 106 to acquire data), receive and process sensor data (e.g., image data acquired by the camera 104, IMU data acquired by the IMU 106), run algorithms (e.g., force models) on the sensor data, and generate results (e.g., applied force to provide vibration damping, force plots, PPG plots, blood pressure, diagnoses based on the determined blood pressure, etc.). As shown in FIG. 1, the mobile device 102 can communicate with a user 114 or an external device or system (e.g., a cloud server 116). For example, the mobile device 102 may transmit a report of the status of the system to the cloud server 116, e.g., using the wireless transmitter 110. As another example, the mobile device 102 may communicate with the user 114 via the display 112. The display 112 may be a touchscreen configured as a graphical user interface, and the mobile device 102 may display data or results to the user 114 via the display 112 and receive user input via the display 112. In some embodiments, the mobile device 102 may be a smartphone, a tablet, or the like.

[0026] FIG. 2 illustrates an exemplary block diagram of various components of a mobile device according to some embodiments of the present document. The mobile device 200 is an example of the mobile device 102 illustrated in FIG. 1. In some embodiments, the mobile device 200 may be a smartphone, a tablet, or the like. In some embodiments, the mobile device 200 may vibrate driven by a built-in vibration motor 203, measure vibration damping caused by a user applying force to the mobile device 200, capture PPG data recordings of changes in blood volume in blood vessels caused by the applied force, and estimate blood pressure using a force model based on the PPG data and the applied force. The mobile device 200 includes one or more sensors 202 capable of collecting data, a processing unit 204 coupled to the one or more sensors 202 and capable of running a force model on the collected data, a wireless transceiver 206 coupled to the processing unit 204, and a display 208 coupled to the processing unit 204. The one or more sensors 202 may include one or more of a camera or an IMU. The IMU of the mobile device 200 may include an accelerometer and a gyroscope.

[0027] 3 illustrates an exemplary application for mobile device-based blood pressure measurement according to some embodiments of the present disclosure. For purposes of illustration only and not limitation, a smartphone application is shown. It is understood that the mobile device-based blood pressure measurement disclosed herein may also be implemented on other mobile devices (including, for example, tablets).

[0028] Figure 3(a) shows a schematic diagram of smartphone force damping. The smartphone includes a vibration motor, a camera, an IMU, and a display. The vibration motor drives the vibration motion. The user applies a damping force by pressing their finger against the camera. The smartphone's IMU records the movement (vibration), and the smartphone's camera simultaneously records the PPG. When the opposite side or base of the fingernail presses against the smartphone's camera, the smartphone's camera can measure the real-time blood volume in the finger while the finger applies force by pressing against the camera.

[0029] Figure 3(b) shows vertical plots of (I) the vibration motor motion along the Z-axis (perpendicular to the smartphone display), (II) the finger force applied along the Z-axis, and (III) the linear Z-axis acceleration of the smartphone IMU. As illustrated, increasing the applied force decreases the Z-axis vibration acceleration or vibration amplitude. The raw PPG signal in (IV) is also plotted vertically, showing how increasing the applied force affects blood volume (V).

[0030] The smartphone IMU may include an accelerometer and a gyroscope. While only linear acceleration along the Z axis is shown ((III)), the smartphone IMU measures acceleration in multiple directions (e.g., three perpendicular directions, including a direction along the Z axis and two directions in a plane perpendicular to the Z axis) and also measures gyroscope data in multiple directions (e.g., the same three directions as the accelerometer). Vibration and its damping of the smartphone may be monitored based on IMU data that includes a combination of multi-axis accelerometer data and multi-axis gyroscope data. Depending on how vibration energy dissipates, the IMU's linear acceleration along various axes (indicating smartphone motion) may change in various patterns. For example, as shown in (II) and (III), as the applied force increases, the linear acceleration along the Z axis decreases. However, during a portion or portions of the time during which the damping force is applied, the linear acceleration along different directions may decrease at different rates or even increase. Similarly, the IMU's angular velocity along various directions (indicating smartphone motion) may change in various patterns in response to the damping force applied by the user. Thus, IMU data including a combination of multi-axis accelerometer data and multi-axis gyroscope data may be used in determining the applied forces. See elsewhere in this document for further discussion in this regard.

[0031] Figure 3(c) shows a graphical user interface (GUI) for the smartphone application, which includes visual indicators to guide a user through performing a blood pressure measurement using the application. The first visual indicator includes an image of the fingertip near the smartphone camera, which provides intuitive guidance to the user on how to position the finger. The second visual indicator includes a real-time plot of the applied force, overlaid with force guidelines during the force decay measurement. The force guides can help the user apply the appropriate amount of force during the measurement.

[0032] The GUI may also include plots of the acquired PPG signal during data collection. The acquired PPG signal may provide useful information to the user or others (e.g., research staff) during data collection. The PPG signal may be plotted in real time before and during measurement, allowing the user and / or research staff to verify data quality. For example, if the PPG signal is not within the desired range, the user or research staff can press a button to calibrate the PPG signal before measurement to prevent the PPG signal from becoming over- or under-saturated. At the end of the measurement, the application may plot the total force and PPG signal to provide a data summary. The GUI may also display predicted results, including, for example, systolic blood pressure (sysBP), diastolic blood pressure (diaBP), heart rate (HR), etc. The GUI may further display user identification information (e.g., user ID) and the number (or count) of attempts by the user. As illustrated, the smartphone is oriented upside down, bringing the smartphone camera closer to the user, making it convenient for the user to place their finger on the camera to apply force and acquire PPG signals.

[0033] Additionally or alternatively, the application may provide guidance to the user on how to perform a blood pressure measurement using the application and the mobile device. Such guidance information may be provided in the form of text, audio, video, images, etc., or a combination thereof. For example, the GUI may remind the user that a software update or calibration is needed, that the mobile device should be placed on a particular type of surface (e.g., a flat wooden surface such as a desk or table), that surface calibration (described elsewhere in this document) is required, and that the user should follow a protocol. The protocol may be substantially the same as a standard blood pressure procedure. For example, the user should sit upright with the measurement device (mobile device) at heart level, the user's feet should be flat on the ground, the user should be calm and breathing normally during the measurement, and, in the case of a mobile device-based measurement, the user should place the mobile device flat on the surface with the screen facing up and the front-facing camera closest to the user (so that the user can conveniently press the camera and simultaneously view the application's GUI). The application may provide instructions and / or guidance on how to properly perform the measurement. For example, the instructions / guidance may include the user placing their hand flat on a surface with their index finger over the front camera of the mobile device.

[0034] Figure 3(d) shows a graph showing the correlation between the applied finger pressure and the amplitude of blood volume oscillations plotted against it, e.g., approximate points for diastolic blood pressure (DBP), mean arterial pressure (MAP), and systolic blood pressure (SBP) are shown for interpretability.

[0035] 4 shows a flowchart of a process for mobile device-based blood pressure measurement according to some embodiments of this document. The process 400 may be implemented on a mobile device (e.g., mobile device 102, mobile device 200).

[0036] At block 410, the process 400 includes vibrating a vibration motor of the mobile device. The vibration motor may be one already built into the mobile device. For example, the vibration may be driven by a vibration motor used to provide haptic feedback for messages, phone calls, screen interactions, etc. The vibration motor may vibrate at a particular level (e.g., a maximum level) of the vibration motor.

[0037] In some embodiments, considering that vibration damping is related to surface characteristics, the mobile device may be placed on a particular type of surface to perform an oscillometric blood pressure measurement. For example, process 400 may include providing information to guide or remind the user to place the mobile device on that type of surface (e.g., a flat wooden surface such as a table or desk) as part of preparation for the blood pressure measurement. Process 400 may also include providing additional information as part of preparation, including, for example, how the user should sit, how force should be applied, etc., or a combination thereof.

[0038] In some embodiments, process 400 may include performing surface calibration by measuring characteristics of a surface on which the mobile device is placed. Exemplary characteristics of a surface include flatness, level, material, etc., or a combination thereof. In some embodiments, the mobile device may determine whether a surface is level by using built-in sensors, including an IMU (including an accelerometer and / or gyroscope), to detect the direction of gravity relative to the orientation of the mobile device and / or the angle and direction of the slope of the surface. In some embodiments, the mobile device may identify the material of the surface. By way of example only, process 400 may include determining the material of the surface by driving a built-in vibration motor to vibrate a mobile phone placed on the surface in a vibration mode having a known vibration profile, measuring the vibration of the mobile device, and comparing the measured vibration profile to the known vibration profile. As another example, process 400 may include determining the material of the surface by driving a built-in vibration motor to vibrate a mobile phone placed on the surface in different vibration modes having known vibration profiles, measuring the vibration profile of the mobile device, and comparing changes in the measured vibration profile to changes in the known vibration profile. Additionally or alternatively, process 400 may include identifying characteristics of the surface based on one or more images of the surface. Process 400 may include performing a surface calibration based on the characteristics of the surface when determining the applied force, as described below.

[0039] At block 420, process 400 includes using an inertial measurement unit (IMU) of the mobile device to acquire IMU data indicative of vibration damping caused by a body part of the user applying a force to a camera of the mobile device. The body part may be a tip portion of a user's finger (e.g., the user's index finger). In some embodiments, process 400 may include providing a visual guide to be displayed on a display of the mobile device. The visual guide (also referred to as a visual indicator) may include markings that guide the user in placing the surface of the body part over the camera.

[0040] The IMU of a mobile device may include a multi-axis accelerometer and a multi-axis gyroscope. The vibration motor may already be built into the mobile device for other purposes, such as measuring linear acceleration and angular velocity to enable position estimation by mobile devices commonly used for rotating screens, playing games, counting steps, gesture recognition, etc.

[0041] The IMU data may include multi-axis accelerometer data and multi-axis gyroscope data. For example, the IMU data may include tri-axis accelerometer data and tri-axis gyroscope data. The tri-axis accelerometer data may include the linear acceleration of the IMU in various axes (indicating smartphone motion). Depending on how energy is dissipated during vibration damping, the linear acceleration of the IMU may change in various patterns. For example, during a portion or portions of the time during which a damping force is applied, linear acceleration along different directions may decrease at different rates or even follow opposite trends (e.g., linear acceleration in some directions increases while linear acceleration in other directions decreases). Similarly, the angular velocity of the IMU along various directions (indicating smartphone motion) may change in various patterns in response to a user-applied damping force. Therefore, IMU data, including multi-axis accelerometer data and multi-axis gyroscope data, may be used in combination to provide a comprehensive representation of vibration damping and, therefore, improve the accuracy of determining applied forces. As used herein, "damping" or "vibration damping" refers to the recorded change in device motion resulting from an applied force.

[0042] Each axis of the multi-axis accelerometer data and the multi-axis gyroscope data may include a time-series signal. The signal for an axis of the IMU data may include high-frequency components from the vibration motor and low-frequency components corresponding to noise. In some embodiments, raw IMU data may be sampled from the mobile device at maximum speed without on-device filtering or post-processing. In some embodiments, the raw IMU data may undergo a series of processing steps. For example, the raw IMU data may be processed using one or more of the following techniques: low-pass filtering, high-pass filtering, band-pass filtering, Savitzky-Golay (Savgol) filtering, standard deviation, or empirical mode decomposition. Filtering may also include multiple steps, such as in the case of a filter bank or multiple stages of different filtering types. Additional features can be obtained from the filtered or raw IMU data (e.g., signal power for axis combinations). One or more features may be evaluated using various metrics (e.g., including principal component analysis, recursive feature elimination, lasso regression, and correlation).

[0043] At block 430, the process 400 includes determining the applied force based on the force model and the IMU data.

[0044] In some embodiments, process 400 may include decomposing the IMU data based on an empirical mode decomposition (EMD) technique. According to the EMD technique, process 400 may include, for each axis of the multi-axis accelerometer data and the multi-axis gyroscope data, decomposing the axis's signal into multiple intrinsic mode functions (IMFs) representing different frequency components of the signal, so that the applied force may be determined based at least in part on the IMFs corresponding to the various axes of the multi-axis accelerometer data and the multi-axis gyroscope data.

[0045] Given that the high-frequency components of the various axis signals from the vibration motor are the strongest components of the corresponding signals, the first IMFs of the various axes of the IMU data primarily correspond to the vibration motor signals. The upper envelope of the first IMFs of each axis of the multi-axis accelerometer data and the multi-axis gyroscope data may be used as a feature to identify the applied force. In some embodiments, the upper envelope of the first IMFs on each IMU axis serves as a typical feature, and the first IMFs collectively may be most significantly correlated with the force data and thus may be used as input to a force model to determine the applied force, while excluding other features. Thus, by way of example only, process 400 may include, for each axis of the multi-axis accelerometer data and the multi-axis gyroscope data, identifying a first IMF corresponding to the highest frequency from the multiple IMFs of the axis signal, identifying an upper envelope of the first IMFs of the axis, and inputting the upper envelope of the first IMFs corresponding to all axes of the multi-axis accelerometer data and the multi-axis gyroscope data, respectively, into the force model.

[0046] The EMD techniques for processing IMU data are described herein for purposes of illustration and not limitation. As described elsewhere herein, the IMU data may be processed by at least one of filtering, filter banks, averaging, standard deviation, wavelet decomposition, spectral analysis, EMD, or the like before being input to the force model. In some embodiments, signals from at least two different axes of IMU data (including multi-axis accelerometer data and multi-axis gyroscope data) may be processed using various techniques. In some embodiments, raw IMU data may be input directly to the force model.

[0047] The force model may include a machine learning model trained to correlate (1) IMU data measured by a mobile device and indicative of vibration damping of the mobile device with (2) forces applied to the mobile device that cause corresponding vibration damping. The force model may be a data-driven model including parametric modeling, linear regression models, ensemble learning models (e.g., random forests, Adaboost, etc.), support vector machine models, neural networks (e.g., transformer models, convolutional neural networks (CNNs), etc.), or variations or combinations thereof. By way of example only, the force model may include a multivariate linear regression model that provides values ​​of applied force on a continuous scale.

[0048] The force model can be trained using training data including applied force measured using a force sensor (e.g., a force-sensing resistor (FSR)) and the measured attenuation caused by the applied force. An exemplary test case was performed involving five participants and three different smartphones: a Google Pixel 4, a Samsung Galaxy A53, and a Motorola Moto G Power, from various smartphone manufacturers, physical shapes, costs, and built-in components. In the exemplary test case, each group of five participants applied pressure with their index finger to a 0.3 mm thick force sensor located on the front camera of the smartphone. To account for hydrostatic pressure, participants applied force with their index finger in the same vertical positioning as blood pressure measurements. A force sensor (a calibrated linear force sensor (SingleTact 15 mm 4.5 N)) was placed on the front camera of the smartphone. Participants pressed their finger against the smartphone force sensor (and the smartphone camera) to measure the applied force of their finger. In the exemplary example, the smartphone was placed on a flat wooden table surface during measurements. During the measurements, real-time measurements from the force sensor were displayed on a screen in front of the user along with a force guide. Using real-time feedback, the user was instructed to follow the force guide as they applied various pressures. Similar to cuff-based blood pressure measurements, the force guide instructed the user to continuously increase the applied force. The study included three 40-second sessions of applying various forces. These three repetitions were performed by each participant on each of three different smartphone types, resulting in 10 minutes of raw applied force data for each phone (2 minutes per participant). The acquired IMU data was processed based on EMD in essentially the same manner as described above to obtain vibration damping data. The forces measured using the force sensor and the corresponding vibration damping data were used to train and validate the force model. The mean absolute error, correlation coefficient, and bias for each smartphone are shown in Table 1 and Figure 5.In Figure 5, black dots indicate data corresponding to the Motorola Moto G Power, crosses indicate data corresponding to the Samsung Galaxy A53, and stars indicate data corresponding to the Google Pixel 4. The average correlation coefficient for all phones is 0.86. The Google Pixel 4 smartphone used in the blood pressure validation study had the lowest mean absolute error (MAE). [Table 1]

[0049] As described elsewhere in this document, the vibration damping behavior of a mobile device may depend on its configuration. Results from exemplary test cases suggest that relevant differences in force measurements from different types of mobile devices (e.g., types may correspond to models by manufacturer) may be calibrated using different force models. Force models may be trained when new types of mobile devices (e.g., new models by manufacturer) are released, and the obtained force models may be used to calibrate mobile devices of the same type. The type of mobile device may correspond to the model and / or manufacturer of the mobile device and may be related to factors (e.g., including the mobile device's vibration motor configuration, IMU configuration, camera configuration, etc., or a combination thereof).

[0050] A model library may be built by collecting force models corresponding to different types of mobile devices, and in some embodiments, process 400 may include obtaining a force model based on the type of mobile device from such a model library in preparation for a blood pressure measurement procedure.

[0051] Process 400 may determine the applied force substantially in real time. In some embodiments, during measurement, process 400 may include providing a visual guide to be displayed on a display of the mobile device. The visual guide may include a force plot showing the applied force substantially in real time. In some embodiments, the visual guide may further include force guidelines superimposed on the applied force. The user may be instructed to follow the force guide in applying a range of forces using real-time feedback. By way of example only, the force guide may instruct the user to continuously increase the applied force within a range, similar to how cuff-based blood pressure measurements are performed.

[0052] In some embodiments, process 400 may include measuring an area of ​​a surface of the body part, where the force is applied by pressing the surface of the body part against a camera. By way of example only, process 400 may cause a camera to take a photograph of the surface of the body part as the body part is pressed against the camera and a damping force is applied, and determine the area based on the images. As another example, the mobile device may include a display including a touchscreen configured to detect contact by a user, and process 400 may determine the area by identifying an area of ​​contact between the body part and the display. Process 400 may include determining an applied pressure based on the applied force and area.

[0053] At block 440, process 400 includes capturing photoplethysmography (PPG) data of blood vessels in the body part using a camera on the mobile device simultaneously with the application of force. The user's body part may include a tip portion of a finger, and the blood vessels may include at least one blood vessel in the transverse palmar arch branch of a digital artery in the tip portion of the finger. The PPG data may relate to blood flow in the blood vessels, which varies with the amplitude of the applied force. The PPG data may record intensity in the red channel of the camera. Because the volume of blood flowing through the artery near the base of the nail varies with the amplitude of the applied force, the reflective properties of the tissue in that area also change. Thus, the camera on the mobile device can record changes in blood volume by measuring the changes in reflective properties.

[0054] By way of example only, the display (or screen) of the mobile device may be set to a pure white background with maximum brightness. The user may be instructed (e.g., with the aid of a visual indicator) to place a body part (e.g., index finger) on the camera. A bright white screen illuminates the finger, and the camera records changes in pixel intensity in the red channel as a proxy for changes in blood volume. To account for changes in skin color and lighting, the mobile device may perform a calibration by placing the user's finger on the camera and adjusting the ISO (the camera's sensor's sensitivity to light). For example, the intensity of the red channel may be between 70 and 200. This calibration may prevent under- or over-saturation of the PPG measurement.

[0055] At block 450, process 400 includes determining the user's blood pressure using oscillometric techniques based on the PPG data and the applied force. By aligning the PPG measurements with the applied force measurements, each PPG peak may be assigned an applied force value. The prominence of each PPG peak may be determined by determining the difference between the peak and the valley. During blood pressure measurement, the mobile device's camera records the PPG signal while the user applies force to the camera with a body part (e.g., index finger). The applied force causes changes in the PPG signal, forming the shape of an oscillogram. If the applied force is greater than the diastolic blood pressure, blood volume increases during the systolic pulse phase and decreases during the diastolic phase. While the total amount of blood flowing through the arteries remains approximately the same, arterial pressure causes more blood to flow during the systolic pulse phase and less during the diastolic pulse phase. This increases the prominence of the PPG signal. If the applied force exceeds the mean arterial pressure, blood volume begins to be restricted, even during the systolic phase of the pulse. As a result, the prominence of the PPG during the systolic phase begins to decrease, and the blood volume during the diastolic phase approaches zero and remains nearly constant. The prominence of the PPG continues to decrease even after the applied force exceeds the systolic blood pressure. As the pressure increases, the signal decreases to zero (or noise) as blood flow through the artery approaches zero during both the systolic and diastolic phases. For each PPG peak, plotting the prominence of the pulse over a range of applied forces (below the diastolic pressure to above the systolic pressure) creates a Gaussian or distorted Gaussian-like shape, which may be referred to as an oscillogram. Blood pressure may be determined based on the oscillogram and a blood pressure model.

[0056] As described elsewhere in this disclosure, the blood pressure model may be substantially independent of the type of mobile device, and therefore no calibration needs to be performed on the blood pressure model based on the type of mobile device.

[0057] The blood pressure model may be a data-driven model, such as a parametric model, a linear regression model, an ensemble learning model (such as a random forest or Adaboost), a support vector machine model, a neural network (e.g., a transformer model, CNN), or a variation or combination thereof.

[0058] The oscillometric method utilized in most FDA-approved blood pressure cuffs utilizes the shape of an oscillogram to estimate blood pressure. Therefore, a blood pressure model may be trained to estimate blood pressure based on an oscillogram. In training, the oscillogram may be processed to extract characteristic features, including, for example, the maximum value of the oscillogram, the applied force at the maximum value (the deflection angle of the maximum value of the oscillogram), the extreme slope of the oscillogram (e.g., maximum slope, minimum slope), the deflection angle of the extreme slope (the deflection angle of the maximum slope, the deflection angle of the minimum slope), the prominence of the extreme slope (e.g., the prominence of the maximum slope, the prominence of the minimum slope), etc., or combinations thereof. These typical characteristic features are visualized in Figures 6(a) and 6(b).

[0059] Figure 6(a) illustrates typical PPG and applied force data measured by a mobile device and corresponding oscillograms generated in accordance with some embodiments of the present document. Specifically, Figure 6(a) shows filtered PPG and applied force data captured using a smartphone. The amplitude of the filtered PPG signal is calculated, and force is converted to pressure via a fixed estimate of the fingertip surface area. The filtered amplitude of the PPG signal plotted against the applied pressure is called an oscillogram. The shape of the oscillogram resembles a skewed Gaussian distribution, with the peak representing mean arterial pressure.

[0060] Figure 6(b) shows average oscillograms corresponding to various blood pressure ranges according to some embodiments of the present document. A plot of the average oscillograms for each blood pressure range shows that the shape of the oscillogram is indicative of blood pressure. The shape of the average oscillogram is plotted as a solid line. The average skewed Gaussian fit is plotted as a dotted line. At higher blood pressures, for example, due to higher mean arterial pressure, the peak of the oscillogram is shifted to the right.

[0061] In an exemplary case of training a blood pressure model, the only inputs to the blood pressure model were characteristic features of the oscillometric method, including the oscillogram maximum, the applied force at the maximum (the deflection angle of the oscillogram maximum), the oscillogram's extreme gradients (e.g., maximum gradient, minimum gradient), the deflection angle of the extreme gradients (the deflection angle of the maximum gradient, the deflection angle of the minimum gradient), and the prominence of the extreme gradients of each training oscillogram (e.g., the prominence of the maximum gradient, the prominence of the minimum gradient). In the illustrative example, exercise-related attributes (e.g., heart rate and pulse shape) were not included in the features provided to the model. All oscillograms were interpolated to have the same number of points with the same force value, thereby avoiding indirect measurements of heart rate or pulse. A least absolute value shrinkage and selection operator (LASSO) regression model was trained to predict systolic and diastolic blood pressure measurements. The model was trained and tested using hold-one-participant-out validation. In this training regimen, the model was trained on all data except for one or more blood pressure measurements from one participant. This model was then used to predict the blood pressure of holdout participants. This process was repeated for each participant.

[0062] Based on the trained blood pressure model, a validation study was performed with N = 30 participants. Participant demographics are shown in Table 2. [Table 2]

[0063] In Table 2 of participant demographics, "skin" refers to Fitzpatrick skin type, "phone" refers to the average smartphone estimate (rounded to the nearest integer), and "cuff" refers to the cuff measurement used for ground truthing. The average phone and cuff measurements shown are based on natural (non-exercise-induced) measurements only. Of the 30 participants, each participated in multiple measurements.

[0064] In a blood pressure validation study, the smartphone device was compared with an FDA-approved cuff-based device (Omron BP7350). Participants first recorded a trial measurement using their smartphone to learn how to use the device and practice applying force. The trial measurement was not used in the analysis. Using the cuff-based device, participants' blood pressure was measured according to the standard protocol. Immediately thereafter, participants performed three blood pressure measurements using their smartphone. After completing the three blood pressure measurements on the smartphone, blood pressure was measured again using the cuff-based device. The complete measurement procedure was as follows: cuff, smartphone, smartphone, smartphone, cuff. If the difference between the two cuff systolic BP measurements was less than 3 mmHg, the first cuff measurement was used as the label for all three smartphone measurements in the analysis. If the difference between the two blood pressure measurements was more than 3 mmHg, the two measurements were averaged.

[0065] Participants were also asked to optionally complete a second phase of exercise data collection. The purpose of this exercise phase was to obtain hypertension data. Consenting participants were asked to perform a wall air chair for approximately 1 minute. During the wall air chair, participants' blood pressure was measured simultaneously using a blood pressure cuff device and a smartphone device. Both blood pressure measurements began approximately 10 seconds after the start of the wall air chair.

[0066] Of the 30 participants, N = 6 participants were completely excluded. Of these 6 excluded participants, 1 participant was unable to perform any valid force measurements, 1 participant had low salience in all measurements, and 1 participant had poor Gaussian strain fits in all measurements. For the other 3 excluded participants, the criteria for excluding each measurement were combined. Participant measurements were excluded based on the following exclusion criteria: Cuff BP > 160mmHg. If the baseline measurement exceeds 160mmHg, the measurement is excluded based on previous studies demonstrating that fingertip and brachial BP values ​​differ at extremely high exercise-induced BP values. Pulse inconsistency / missing detection or excessive noise. A fast Fourier transform (FFT) of the PPG signal between 0 Hz and 2 Hz (frequencies associated with the human pulse) should have a narrow, identifiable peak indicating the pulse rate. Insufficient applied force. The applied force measurements must have a correlation coefficient greater than 0.88. The first 0.5 seconds of the force signal must have a correlation coefficient less than 0.21N. The minimum applied force must be less than 6N and the maximum applied force value must be greater than 7N. Poor skew Gaussian fit. The mean absolute error for the best fit normalized skew Gaussian should be less than 0.18. Saturation of the PPG signal. If the PPG signal increases by more than 254 pixel intensity units, the measurement is discarded. This indicates that the finger was lifted away from the smartphone camera during the measurement. PPG saliency remains unchanged. The standard deviation of normalized PPG saliency must be greater than 0.17.

[0067] A validity study demonstrated that mobile device-based oscillometric blood pressure measurement achieved MAEs of 9.9 mmHg and 8.9 mmHg for systolic and diastolic BP, respectively, compared with an FDA-approved blood pressure cuff. The Pearson correlation coefficients were 0.67 and 0.23 for systolic and diastolic measurements, respectively. Blood pressure cuff measurements ranged from 62 to 107 mmHg for diastolic and 89 to 147 mmHg for systolic. See Figures 6(a) and 6(b). These show the regression plot and Bland-Altman plot for systolic blood pressure (systolic BP) and diastolic blood pressure (diastolic BP), respectively, for all measurements from N = 24 included participants. Each participant had multiple measurements, resulting in a total of 73 measurements. Systolic and diastolic BP values ​​were calculated using the same model.

[0068] For use in screening based on the technology disclosed herein, blood pressure (BP) values ​​can be classified based on the AMA / ACC criteria. Figure 7 shows a confusion matrix based on the results shown in Figures 6(a) and 6(b). This confusion matrix was adjusted to ensure correct labeling of elevated and hypertensive individuals. Specifically, for categorical prediction, the sensitivity and specificity were adjusted from the original prediction. The categorical prediction threshold was determined solely by the systolic BP value, based on the criteria established by the AMA / ACC. Receiver operating characteristic (ROC) analysis revealed an area under the curve (AUC) of 0.88 for detecting hypertensive individuals characterized by a systolic BP greater than 130 mmHg. The ROC curve provides information about the sensitivity and specificity of the prediction. The confusion matrix shown in Figure 7 demonstrates effective blood pressure screening using a downloadable application without the need for accessories or hardware, according to an embodiment of this document. With a false positive rate of 3 percent and a true positive rate of 88% in distinguishing high or elevated blood pressure from normal blood pressure, the technology could be used as a hypertension screening tool that can be easily downloaded to the home and used on one's own mobile device.

[0069] These results suggest the feasibility of blood pressure screening using only a downloadable smartphone software application. This technology could be used as a low-barrier hypertension screening measure suitable for widespread implementation.

[0070] Additionally, the mobile device-based oscillometric blood pressure technology disclosed herein may provide a calibration mechanism. For example, using wearable devices (e.g., smartwatches or smart glasses) to monitor relative changes in blood pressure is becoming increasingly common. These devices typically rely on pulse transit time (PTT), pulse wave analysis (PWA), or pulse arrival time (PAT) methods. A major limitation of this type of blood pressure measurement is the need for calibration using absolute blood pressure measurements. Calibration is often performed daily or weekly with a blood pressure cuff device. As disclosed herein, absolute blood pressure measurements on mobile devices may provide an effective, low-cost method for calibrating wearable or other continuous relative BP measurements.

[0071] Additionally, the mobile device-based oscillometric blood pressure technology disclosed herein may be combined with other cardiovascular measurements to analyze cardiac health. For example, the system disclosed herein may be combined with another optical system using a camera to perform PWA, heart rate variability (HRV) measurements, or pulse measurements to provide additional information to blood pressure.

[0072] Technical improvements proposed in the embodiments disclosed herein include a method for performing absolute blood pressure measurements that can be applied across different types (e.g., models) of mobile devices without hardware modifications or accessories, and instead can be implemented through a downloadable application. Generalizing sensor-based measurements across a wide variety of mobile devices is a well-established problem that significantly limits the impact of research in the mobile health field. Cross-device compatibility studies demonstrate that the force attenuation technology disclosed herein enables blood pressure measurements to function on a variety of mobile devices. Data processing and modeling indicate that many different types of mobile devices can perform oscillometric blood pressure measurements after calibration based on the mobile device type for force measurements. Because there are tens of millions of users for each common type of mobile device, a single factory calibration may enable oscillometric blood pressure measurements to be performed on millions of mobile devices. [Example]

[0073] The following examples illustrate some embodiments in accordance with the present technology. Other exemplary embodiments of the present technology may be presented before or after the examples listed below.

[0074] 1. A mobile device comprising: a vibration motor; an inertial motion unit (IMU); a camera; a processor; and a non-transitory computer-readable memory storing instructions that, when executed by the processor, cause the processor to at least: vibrate the vibration motor; acquire, with the inertial measurement unit of the mobile device, IMU data indicative of vibration damping caused by a user's body part applying a force to the camera; determine the applied force based on a force model and the IMU data; capture, with the camera of the mobile device, photoplethysmography (PPG) data of blood vessels in the body part concurrently with the application of the force; and determine the user's blood pressure using oscillometric techniques based on the PPG data and the applied force.

[0075] 2. Any one or more mobile devices of the solutions described herein, wherein the force model includes a machine learning algorithm trained to correlate (1) the IMU data measured by the mobile device and indicative of the vibration damping of the mobile device, and (2) the forces applied to the mobile device and causing the vibration damping.

[0076] 3. A mobile device of any one or more of the solutions described herein, wherein the IMU includes an accelerometer and a gyroscope, and the IMU data includes multi-axis accelerometer data and multi-axis gyroscope data.

[0077] 4. A method for measuring blood pressure using a mobile device, the method comprising: vibrating a vibration motor of the mobile device; using an inertial measurement unit (IMU) of the mobile device to acquire IMU data indicative of vibration damping caused by a body part of a user applying a force to a camera of the mobile device; determining the applied force based on a force model and the IMU data; using the camera of the mobile device to capture photoplethysmography (PPG) data of blood vessels in the body part contemporaneously with the application of the force; and determining the blood pressure of the user using oscillometric techniques based on the PPG data and the applied force.

[0078] 5. The method of any one or more of the solutions described herein, wherein the IMU data includes multi-axis accelerometer data and multi-axis gyroscope data.

[0079] 6. The method of any one or more of the solutions described herein, wherein determining the applied force from the IMU data includes processing the IMU data based on at least one of filtering, filter bank, averaging, standard deviation, wavelet decomposition, spectral analysis, and empirical mode decomposition (EMD).

[0080] 7. The method of any one or more of the solutions described herein, wherein each axis of the multi-axis accelerometer data and the multi-axis gyroscope data includes a signal, and determining the applied force from the IMU data includes, for each axis of the multi-axis accelerometer data and the multi-axis gyroscope data, decomposing the signal of the axis into a plurality of intrinsic mode functions (IMFs) corresponding to different frequency components of the signal, and the applied force is determined based at least in part on the IMFs corresponding to the various axes of the multi-axis accelerometer data and the multi-axis gyroscope data.

[0081] 8. The method of any one or more of the solutions described herein, wherein determining the applied force from the IMU data further includes, for each axis of the multi-axis accelerometer data and the multi-axis gyroscope data, identifying a first IMF corresponding to a highest frequency from the multiple IMFs of the signals for that axis, identifying an upper envelope of the first IMF for that axis, and inputting the upper envelopes of the first IMFs corresponding to all axes of the multi-axis accelerometer data and the multi-axis gyroscope data, respectively, into the force model.

[0082] 9. The method of any one or more of the solutions described herein, wherein the PPG data relates to blood flow in the blood vessels as it varies with the amplitude of the applied force.

[0083] 10. The method of any one or more of the solutions described herein, wherein the PPG data records intensity in the red channel of the camera.

[0084] 11. Any one or more of the methods of the solutions described herein, wherein the mobile device is placed on a support surface when the user applies the force, and the method further includes performing a surface calibration by characterizing a material of the support surface, and determining the applied force further based on the surface calibration.

[0085] 12. The method of any one or more of the solutions described herein, further comprising providing a visual guide to be displayed on a display of the mobile device, the visual guide comprising a force plot showing the applied force substantially in real time.

[0086] 13. The method of any one or more of the solutions described herein, wherein the visual guide further comprises force guidelines superimposed on the applied force.

[0087] 14. The method of any one or more of the solutions described herein, further comprising providing a visual guide to be displayed on a display of the mobile device, the visual guide including markings to guide the user in placing a surface of the body part over the camera.

[0088] 15. The method of any one or more of the solutions described herein, further comprising: measuring an area of ​​a surface of the body part, wherein the force is applied by pressing the surface of the body part against the camera; and determining an applied pressure based on the applied force and the area, wherein determining the blood pressure comprises generating an oscillogram based on the PPG data and the applied pressure, and deriving the blood pressure from the oscillogram.

[0089] 16. The method of any one or more of the solutions described herein, further comprising displaying the oscillogram on a display of the mobile device.

[0090] 17. The method of any one or more of the solutions described herein, wherein the body part of the user is a tip portion of a finger, and the group of blood vessels includes at least one blood vessel at a transverse palmar arch branch of a digital artery at the tip portion of the finger.

[0091] 18. The method of any one or more of the solutions described herein, wherein determining the user's blood pressure using oscillometric techniques includes generating an oscillogram based on the PPG data and the applied force; extracting characteristic features from the oscillogram including at least one of a peak in the oscillogram, the applied force corresponding to the peak, and an extremum in the slope of the oscillogram, a prominence of the extremum in the slope of the oscillogram, or an angle of deviation of the extremum in the slope; and generating the blood pressure based on the characteristic features and a blood pressure model.

[0092] 19. The method of any one or more of the solutions described herein, further comprising obtaining the force model from a model library based on a type of the mobile device, the type of the mobile device being associated with at least one of a configuration of the IMU, a configuration of the vibration motor, or a configuration of the camera.

[0093] 20. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors of a mobile device, cause the mobile device to perform any one or more of the solutions described herein.

[0094] Implementations of the subject matter and functional operations described in this patent document can be implemented in various systems, digital electronic circuits, or computer software, firmware, or hardware (including the structures disclosed herein and their structural equivalents), or one or more combinations thereof. Implementations of the subject matter described herein can be implemented as one or more computer program products, i.e., as one or more modules of computer program instructions encoded on a tangible and non-transitory computer-readable medium for execution by or controlling the operation of a data processing apparatus. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter providing a machine-readable propagated signal, or one or more combinations thereof. The term "data processing unit" or "data processing apparatus" includes all devices, devices, and machines for processing data, including, by way of example, a programmable processor, a computer, or multiple processors or computers. In addition to hardware, an apparatus can include code that creates an execution environment for a given computer program, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, or one or more combinations thereof.

[0095] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, e.g., a compiled or interpreted language, and can be deployed in any form, e.g., as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored as part of files that maintain other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple associated files (e.g., files storing one or more modules, subprograms, or portions of code). A computer program can be deployed to run on one computer or on multiple computers, either located at one site or distributed across multiple sites and interconnected by a communications network.

[0096] The processes and logic flows described herein may be performed by one or more programmable processors executing one or more computer programs that perform functions by operating on input data and generating output. The processes and logic flows may also be performed by, or apparatus implemented as, special purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0097] Processors suitable for executing a computer program include, by way of example, both general-purpose and special-purpose microprocessors, and any one or more processors of any kind of digital computer. Typically, a processor receives instructions and data from a read-only memory or a random-access memory, or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer also includes, or is operatively coupled to, one or more mass storage devices (e.g., magnetic, magneto-optical, or optical disks) for storing data, and receives and / or transfers data therefrom. However, a computer need not have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, by way of example, semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices. The processor and memory can be supplemented by, or incorporated in, special-purpose logic circuitry.

[0098] This specification, together with the drawings, are intended to be considered illustrative only, and by illustrative is meant to be exemplary. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, the use of "or" is intended to include "and / or" unless the context clearly indicates otherwise.

[0099] While this patent document contains many details, these should not be construed as limitations on the scope of any invention or what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of a particular invention. Certain features described in this patent document in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Furthermore, while features may be described above as working in a particular combination, and even initially claimed as such, one or more features from a claimed combination can, in some cases, be deleted from that combination, and the claimed combination may be directed to subcombinations or variations of subcombinations.

[0100] Similarly, although operations are shown in the figures in a particular order, this should not be understood as requiring that such operations be performed in the particular order or sequential order shown, or that all of the illustrated operations be performed, to achieve desirable results. Further, the separation of various system components in the embodiments described in this patent document should not be understood as requiring such separation in all embodiments.

[0101] Various embodiments described herein are described in the general context of a method or process, which in one embodiment may be implemented by a computer program product embodied in a computer-readable medium, e.g., computer-executable instructions, e.g., program code, executed by a computer in a network environment. Computer-readable media may include removable and non-removable storage devices, such as, but not limited to, read-only memory (ROM), random access memory (RAM), compact discs (CDs), digital versatile discs (DVDs), Blu-ray discs, etc. Accordingly, computer-readable media as described herein includes non-transitory storage media. Generally, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of program code for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps or processes.

[0102] For example, one aspect of the disclosed embodiments relates to a computer program product embodied on a non-transitory computer-readable medium, the computer program product including program code for performing any one and / or all of the operations of the disclosed embodiments.

[0103] Only some embodiments and examples have been described; other embodiments, extensions, and variations can be made based on what is described and illustrated in this patent document.

Claims

1. 1. A method for measuring blood pressure using a mobile device, the method comprising: vibrating a vibration motor of the mobile device; using an inertial measurement unit (IMU) of the mobile device to acquire IMU data indicative of vibration damping caused by a user's body part applying a force to a camera of the mobile device; determining the applied force based on a force model and the IMU data; capturing photoplethysmography (PPG) data of blood vessels in the body part simultaneously with the application of the force using the camera of the mobile device; determining the user's blood pressure using oscillometric techniques based on the PPG data and the applied force; A method comprising:

2. The method of claim 1 , wherein the IMU data includes multi-axis accelerometer data and multi-axis gyroscope data.

3. 3. The method of claim 2, wherein determining the applied force from the IMU data includes processing the IMU data based on at least one of filtering, filter bank, averaging, standard deviation, wavelet decomposition, spectral analysis, and empirical mode decomposition (EMD).

4. each axis of the multi-axis accelerometer data and the multi-axis gyroscope data includes a signal; determining the applied forces from the IMU data includes, for each axis of the multi-axis accelerometer data and the multi-axis gyroscope data, decomposing the signal for that axis into a plurality of intrinsic mode functions (IMFs) corresponding to different frequency components of the signal; the applied force is determined based at least in part on the IMFs corresponding to different axes of the multi-axis accelerometer data and the multi-axis gyroscope data. The method of claim 3.

5. Determining the applied force from the IMU data further comprises: For each axis of the multi-axis accelerometer data and the multi-axis gyroscope data, identifying a first IMF from the plurality of IMFs of the signal for the axis corresponding to a highest frequency; identifying an upper envelope of the first IMF for the axis; and inputting into the force model the upper envelope of the initial IMF corresponding to all axes of the multi-axis accelerometer data and the multi-axis gyroscope data, respectively.

6. The method of claim 1 , wherein the PPG data relates to blood flow in the blood vessels, which varies with the amplitude of the applied force.

7. The method of claim 1 , wherein the PPG data records intensity in the red channel of the camera.

8. When the user applies the force, the mobile device is placed on a support surface, and the method further comprises: performing a surface calibration by characterizing the material of the support surface; determining the applied force further based on the surface calibration; The method of claim 1 , comprising:

9. providing a visual guide to be displayed on a display of the mobile device, the visual guide including a force plot showing the applied force substantially in real time. The method of claim 1.

10. The method of claim 9 , wherein the visual guide further comprises force guidelines superimposed on the applied force.

11. providing a visual guide to be displayed on a display of the mobile device, the visual guide including markings to guide the user in placing a surface of the body part over the camera. The method of claim 1.

12. measuring an area of ​​a surface of the body part, the force being applied by pressing the surface of the body part against the camera; determining an applied pressure based on the applied force and the area, wherein determining the blood pressure includes: generating an oscillogram based on the PPG data and the applied pressure; deriving the blood pressure from the oscillogram; The method of claim 1 further comprising:

13. further comprising displaying the oscillogram on a display of the mobile device. The method of claim 12.

14. Determining the user's blood pressure using oscillometric techniques includes: generating an oscillogram based on the PPG data and the applied force; extracting characteristic features from the oscillogram including at least one of a peak in the oscillogram, an applied force corresponding to the peak, and an extremum in the slope of the oscillogram, a prominence of the extremum in the slope of the oscillogram, or an angle of the extremum in the slope of the oscillogram; generating the blood pressure based on the characteristic features and a blood pressure model; The method of claim 1 , comprising:

15. the body part of the user is a tip of a finger, The blood vessel group includes at least one blood vessel in the transverse palmar arch branch of the digital artery in the tip portion of the finger, The method of claim 1.

16. and further comprising: obtaining the force model from a model library based on a type of the mobile device, the type of the mobile device being associated with at least one of a configuration of the IMU, a configuration of the vibration motor, or a configuration of the camera. The method of claim 1.

17. 1. A mobile device comprising: a vibration motor; an inertial motion unit (IMU); a camera; a processor; and a non-transitory computer-readable memory storing instructions that, when executed by the processor, cause the processor to at least: vibrating the vibration motor; acquiring, with the IMU of the mobile device, IMU data indicative of vibration damping caused by a user's body part applying a force to the camera; determining the applied force based on a force model and the IMU data; capturing, by the camera of the mobile device, photoplethysmography (PPG) data of blood vessels in the body part simultaneously with the application of the force; determining the user's blood pressure by oscillometric techniques based on the PPG data and the applied force; Let your mobile device do this.

18. 18. The mobile device of claim 17, wherein the force model comprises a machine learning algorithm trained to correlate (1) the IMU data measured by the mobile device and indicative of the vibration damping of the mobile device, and (2) the forces applied to the mobile device and causing the vibration damping.

19. 20. The mobile device of claim 17, wherein the IMU includes an accelerometer and a gyroscope, and the IMU data includes multi-axis accelerometer data and multi-axis gyroscope data.

20. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors of a mobile device, cause the mobile device to: vibrating a vibration motor of the mobile device; using an inertial measurement unit (IMU) of the mobile device to acquire IMU data indicative of vibration damping caused by a user's body part applying a force to a camera of the mobile device; determining the applied force based on a force model and the IMU data; capturing photoplethysmography (PPG) data of blood vessels in the body part simultaneously with the application of the force using the camera of the mobile device; determining the user's blood pressure using oscillometric techniques based on the PPG data and the applied force; One or more non-transitory computer-readable media for causing operations to be performed, including:

21. The operation is and further comprising: obtaining the force model from a model library based on a type of the mobile device, the type of the mobile device being associated with at least one of a configuration of the IMU, a configuration of the vibration motor, or a configuration of the camera.

21. One or more non-transitory computer-readable media as recited in claim 20.

Images