Blood pressure measurement based on sensor fusion

Abstract

Various arrangements for measuring blood pressure using sensor fusion are presented herein. A radio frequency (RF) signal is transmitted, and a radar sensor of the fixture receives the RF reflected signal. The RF reflected signal at the first range of distances is analyzed to identify a first pulse pressure waveform (PPW) at the aortic valve of the user. A stationary device receives vital sign data measured by a mobile device at a limb of a user. The vital sign data is analyzed to identify a second PPW at the limb of the user. A pulse transit time from the aortic valve to the limb is determined using the first PPW and the second PPW. Using the PTT, a blood pressure (BP) of the user is determined and an indication of BP is output.

Description

Background Technology

[0001] Blood pressure (BP) is an important vital sign statistic used to measure health. People may want to measure their BP occasionally or regularly to ensure it is within healthy limits. A sudden drop or rise in BP can serve as a warning that people should seek medical help. Often, home BP measuring devices are inconvenient and uncomfortable. Some devices require a cuff to apply a high level of pressure to the arm. Others require a special device to be clipped to the finger or other limb. In yet another arrangement, a hybrid approach combining multiple specialized sensors, such as an electrocardiogram (ECG) sensor with a photoplethysmography (PPG) sensor, can lead to unreliable BP measurements.

[0002] Such an arrangement is not conducive to convenient and consistent individual BP monitoring. First, it requires a dedicated device that needs to be stored and retrieved each time a person wants to measure their BP. Second, such a device is susceptible to user error, leading to inaccurate BP measurements. The embodiments described herein address these and other problems. Summary of the Invention

[0003] In some embodiments, a blood pressure measurement system is provided. The system may include: a mobile device wearable by a user and configured to collect vital sign data at the user's limb; and a fixed device communicating with the mobile device. The fixed device may include: a radio frequency (RF) transmitter that transmits RF signals; an RF receiver that receives reflected RF signals based on the reflected transmitted RF signals; and one or more processors. The one or more processors may be configured to analyze the reflected RF signals over a first distance range to identify a first pulse pressure waveform at the user's aortic valve. The one or more processors may be further configured to analyze the vital sign data to identify a second pulse pressure waveform at the user's limb. The one or more processors may be further configured to use the first pulse pressure waveform and the second pulse pressure waveform to determine the pulse conduction time (PTT) of the pulse pressure wave from the user's aortic valve to the user's limb. The one or more processors may be further configured to determine the user's blood pressure based on the determined PTT. The one or more processors may be further configured to output an indication of the determined blood pressure.

[0004] In some embodiments, the vital signs data includes photoplethysmography (PPG) data, and the mobile device includes an optical sensor that measures PPG data at the user's limb. In some embodiments, the fixation device further includes a microphone, a speaker, and an electronic display, wherein the indication of the determined blood pressure is output via the electronic display. In some embodiments, the mobile device is a smartwatch, and the user's limb is the user's wrist. The smartwatch may further include a microphone, a speaker, and an electronic display, wherein the indication of the determined blood pressure is output via the electronic display.

[0005] In some embodiments, the RF reflected signal is associated with a first set of timestamps generated by a first clock of the fixed device, the vital signs data is associated with a second set of timestamps generated by a second clock of the mobile device, and the one or more processors are further configured to synchronize the first set of timestamps with the second set of timestamps and adjust the first set of timestamps, the second set of timestamps, or both, based on processing latency differences between the fixed device and the mobile device. In some embodiments, the one or more processors are further configured to receive an external blood pressure measurement using a blood pressure device separate from the fixed device and the mobile device, compare the external blood pressure measurement with a determined blood pressure measurement, and create a calibration curve for modifying future determined blood pressure measurements. In some embodiments, the one or more processors are further configured to use the RF reflected signal and the vital signs data as input to a machine learning model trained to derive the user's blood pressure based on the PTT (Personal Tolerance Request).

[0006] In some embodiments, a method for measuring blood pressure is provided. The method may include transmitting a radio frequency (RF) signal by a radar sensor of a fixed device. The method may further include receiving a reflected RF signal by the radar sensor of the fixed device based on the reflection of the transmitted RF signal. The method may further include analyzing the reflected RF signal at a first distance range by a processing system of the fixed device to identify a first pulse pressure waveform at the aortic valve of the user. The method may further include receiving vital sign data measured by a mobile device at the user's limb by the processing system of the fixed device. The method may further include analyzing the vital sign data by the processing system of the fixed device to identify a second pulse pressure waveform at the user's limb. The method may further include determining the pulse conduction time (PTT) of the pulse pressure wave from the user's aortic valve to the user's limb by the processing system of the fixed device using the first and second pulse pressure waveforms. The method may further include determining the user's blood pressure by the processing system of the fixed device based on the determined PTT. The method may further include outputting an indication of the determined blood pressure by the processing system of the fixed device.

[0007] In some embodiments, the vital signs data includes photoplethysmography (PPG) data, and the method further includes measuring PPG data at the user's limb using an optical sensor of the mobile device. In some embodiments, the RF reflected signal is associated with a first set of timestamps generated by a first clock of the fixed device, the vital signs data is associated with a second set of timestamps generated by a second clock of the mobile device, and the method further includes synchronizing the first set of timestamps with the second set of timestamps. Embodiments of such methods may further include adjusting the first set of timestamps, the second set of timestamps, or both, based on processing delay differences between the fixed device and the mobile device.

[0008] The method may further include determining a phase difference between the first pulse pressure waveform and the second pulse pressure waveform, wherein the PTT is determined using this phase difference. In some embodiments, the user's limb is the user's wrist. In some embodiments, the method further includes determining a heart rate based on analysis of the RF reflected signal, the second pulse pressure waveform, or both, wherein determining the user's blood pressure is further based on the heart rate. In some embodiments, a derived pulse waveform amplitude (DPWA) is determined based on analysis of the RF reflected signal, wherein determining the user's blood pressure is further based on the DPWA. In some embodiments, a respiratory rate is determined based on analysis of the RF reflected signal, the second pulse pressure waveform, or both, wherein determining the user's blood pressure is further based on the respiratory rate.

[0009] In some embodiments, analyzing the RF reflected signal within the first distance range includes analyzing data from the RF reflected signal using a trained machine learning model. In some embodiments, the method further includes receiving an external blood pressure measurement using a blood pressure device separate from the fixed device and the mobile device by the processing system of the fixed device, comparing the external blood pressure measurement with a determined blood pressure measurement by the processing system, and creating a calibration curve by the processing system to modify future determined blood pressure measurements.

[0010] In some embodiments, a stationary blood pressure measurement device is provided. The device may include a radar subsystem. The radar subsystem may include: a radio frequency (RF) transmitter that transmits an RF signal; an RF receiver that receives a reflected RF signal based on the reflection of the transmitted RF signal; and a processing system. The processing system may include one or more processors communicating with the radar subsystem. The processing system may be configured to analyze the reflected RF signal at a first distance range to identify a first pulse pressure waveform at the user's aortic valve. The processing system may be further configured to receive vital sign data measured by a mobile device at the user's limb. The processing system may be further configured to analyze the vital sign data to identify a second pulse pressure waveform at the user's limb. The processing system may be further configured to use the first pulse pressure waveform and the second pulse pressure waveform to determine the pulse conduction time (PTT) of the pulse pressure wave from the user's aortic valve to the user's limb. The processing system may be further configured to determine the user's blood pressure based on the determined PTT. The processing system may be further configured to output an indication of the determined blood pressure. Attached Figure Description

[0011] The nature and advantages of the various embodiments can be further understood by referring to the following figures. In the figures, similar parts or features may have the same reference numerals. Furthermore, various parts of the same type can be distinguished by adding a dash after the reference numerals and a second reference numeral to differentiate similar parts. If only the first reference numeral is used in the specification, the description applies to any similar part having the same first reference numeral, regardless of the second reference numerals.

[0012] Figure 1 An embodiment of a distributed BP measurement system that can be used to perform BP measurements based on sensor fusion is shown.

[0013] Figure 2 A block diagram of an embodiment of a BP measurement system based on sensor fusion is shown.

[0014] Figure 3 A block diagram of another embodiment of a BP measurement system based on sensor fusion is shown.

[0015] Figure 4 An embodiment of frequency-modulated continuous wave radar radio waves output by a radar subsystem is shown.

[0016] Figure 5 An example of a pulse wave measured by a distributed BP measurement system is shown.

[0017] Figure 6 An embodiment of the BP measuring device is shown.

[0018] Figure 7 An exploded view of an embodiment of the BP measuring device is shown.

[0019] Figure 8 An example of a user measuring their BP using a distributed BP measurement system is shown.

[0020] Figure 9 Another example of a user measuring their BP using a distributed BP measurement system is shown.

[0021] Figure 10 An embodiment of a method for measuring BP is shown.

[0022] Figure 11 Another embodiment of the method for measuring BP is shown.

[0023] Figure 12 An embodiment of a method for calibrating a distributed BP measurement system is shown. Detailed Implementation

[0024] Pulse conduction time (PTT) refers to the amount of time it takes for a pulse pressure wave (PPW) to travel between two arterial sites, such as from the aortic valve to a limb (e.g., wrist, fingers, foot). The speed at which the PPW travels through the vascular system, and therefore PTT, is proportional to blood pressure (BP). As a person's BP increases, the speed decreases, and therefore PTT decreases. Therefore, by determining a person's PTT—and possibly in conjunction with other measurements—one can determine a person's BP.

[0025] The embodiments detailed herein focus on embodiments of a BP measurement system based on sensor fusion and associated methods that allow for BP measurement using distributed sensing devices. A BP measurement system based on sensor fusion may include a stationary device equipped with a radar sensor capable of detecting small movements at discrete distances. Thus, movement at the aortic valve corresponding to the PPW generated by the human heart can be distinguished from other movements in the surrounding environment. A BP measurement system based on sensor fusion may also include a mobile device equipped with an optical sensor capable of detecting PPG data from the user. When placed on a limb, the PPG data can be used to detect them after the same PPW has propagated from the aortic valve to the limb. Using the PPW from each device, the PTT from the aortic valve to the user's limb can be determined. The user's BP can then be determined using the PTT from the aortic valve to the limb.

[0026] As detailed herein, additional measurements can be performed using data from either device to determine a user's more accurate blood pressure, such as PPW amplitude (PPWA), heart rate (HR), respiratory rate (RR), etc. In some embodiments, as described herein, trained machine learning models are used to partially or fully analyze data obtained from radar and optical sensors.

[0027] Components of such distributed BP measurement systems can be incorporated as part of devices including radar sensors (such as home assistant devices). The home assistant device can present users with information about their measured BP and can be physically positioned to facilitate BP measurement. Using this type of device can be highly beneficial because it can typically be placed in a prominent location in people's homes, such as on a table or bedside table, and provides users with easy access to BP measurements. Furthermore, components of such systems can be incorporated as part of devices including optical sensors (such as smart wearable devices). As long as the user wears a smart wearable device (such as a smartwatch), the device can provide additional convenience due to its easy accessibility.

[0028] As detailed herein, BP measurements can only be performed with explicit user approval. To perform a BP measurement, the user may need to remain in a specific physical location and relatively still. During this time, visual and / or auditory messages indicating that the user's BP is being measured may be output. Furthermore, the user may be required to provide consent allowing the measurement of their BP. The user retains the ability to delete any BP measurements performed using such a system.

[0029] Further details regarding these and other embodiments are provided in the accompanying drawings. Figure 1An embodiment of a distributed BP measurement system 100 (“System 100”) for performing BP measurements is illustrated. System 100 may include: a BP measurement device 105; a remote sensing device 160; a network 180; and a cloud-based server system 190. The BP measurement device 105 may typically be a smart home assistant device, a smartphone, a smartwatch, a laptop computer, a gaming device, or a smart home hub device for interacting with various smart home devices present in the home. The BP measurement device 105 may include: a processing system 110; a BP data storage 118; a radar subsystem 120; an environmental sensor suite 130; a display 140; a wireless network interface 145; and a speaker 150. Typically, the BP measurement device 105 may include a housing that houses all the components of the BP measurement device 105.

[0030] Processing system 110 may include one or more processors configured to perform various functions—such as radar processing module 112; remote sensor module 113; and BP measurement engine 114. As further described herein, radar processing module 112 and remote sensor module 113 may analyze raw or otherwise unprocessed radar data and remote sensor data, respectively, to provide input to BP measurement engine 114. For example, radar processing module 112 may receive data from radar subsystem 120. Radar subsystem 120 (also referred to as a radar sensor) may be a single integrated circuit (IC) that transmits, receives, and outputs data indicating the received reflected waveform. Radar processing module 112 may then process the reflected waveform to identify micro-motion at different distances from BP measurement device 105. As another example, remote sensor module 113 may process vital sign data from remote sensing device 160. BP measurement engine 114 may then receive processed data from radar processing module 112 and / or remote sensor module 113 to derive measurements indicating the user's BP. Figures 2 to 4 Further details are provided regarding radar subsystem 120, radar processing module 112, remote sensor module 113, and BP measurement engine 114.

[0031] Processing system 110 may include one or more dedicated or general-purpose processors. Such dedicated processors may include processors specifically designed to perform the functions detailed herein. Such dedicated processors may be ASICs or FPGAs, which are general-purpose components physically and electrically configured to perform the functions detailed herein. Such general-purpose processors may execute dedicated software stored using one or more non-transitory processor-readable media, such as random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD) media.

[0032] BP measurement device 105 may include one or more environmental sensors, such as all or a combination of environmental sensors provided as part of environmental sensor kit 130. Environmental sensor kit 130 may include: a light sensor 132; a microphone 134; a temperature sensor 136; and a passive infrared (PIR) sensor 138. In some embodiments, multiple instances of some or all of these sensors may be present. For example, in some embodiments, multiple microphones may be present. Light sensor 132 may be used to measure the amount of ambient light present in the general environment of BP measurement device 105. Microphone 134 may be used to measure the level of ambient noise present in the general environment of BP measurement device 105. Temperature sensor 136 may be used to measure the ambient temperature of the general environment of BP measurement device 105. PIR sensor 138 may be used to detect moving organisms (e.g., humans, pets) within the general environment of BP measurement device 105.

[0033] Other types of environmental sensors are also possible. For example, a camera and / or humidity sensor can be incorporated as part of the environmental sensor suite 130. As another example, an active infrared sensor may be included. In some embodiments, some data, such as humidity data, may be obtained via the Internet from a nearby weather station with available data. In some embodiments, active acoustic sensing methods, including but not limited to sonar and ultrasound, may be implemented and include a single or array of sound sources and / or receivers. Such arrangements may be used as one or more auxiliary sensing modes in conjunction with other sensors and methods described herein.

[0034] In some embodiments, one, some, or all of the sensors in the environmental sensor suite 130 may be located outside the BP measurement device 105. For example, one or more remote environmental sensors may communicate directly with the BP measurement device 105 (e.g., via a direct wireless communication method, via a low-power mesh network) or indirectly (e.g., via a low-power mesh network through one or more other devices, via a network access point, via a remote server).

[0035] The BP measurement device 105 may include various interfaces, such as a display 140, a wireless network interface 145, and a speaker 150. The wireless network interface 145 may allow communication with various wireless networks and / or wireless devices using one or more communication protocols. For example, the wireless network interface 145 may allow communication using a wireless local area network (WLAN) (such as a WiFi-based network). In some embodiments, the wireless network interface 145 allows direct communication with other devices via Bluetooth, Bluetooth Low Energy (BLE), or some other device-to-device communication protocol. For example, the wireless network interface 145 may allow communication between the BP measurement device 105 and a remote sensing device 160.

[0036] Alternatively, other forms of wireless communication are possible. For example, the BP measurement device 105 can communicate with various smart home devices using low-power wireless mesh network radios and protocols (e.g., Thread). In some embodiments, a wired network interface (such as an Ethernet connection) can be used to communicate with a network. Furthermore, the evolution of wireless communication towards fifth-generation (5G) and sixth-generation (6G) standards and technologies offers higher throughput and lower latency, enhancing mobile broadband services. 5G and 6G technologies also provide new service categories for vehicle-to-everything (V2X), fixed wireless broadband, and the Internet of Things (IoT) through control and data channels. Such standards and technologies can be used for the communication of the BP measurement device 105.

[0037] Low-power wireless mesh network radios and protocols can be used to communicate with power-constrained devices. Power-constrained devices can be purely battery-powered. Such devices can rely on only one or more batteries for power, and therefore, the power used for communication can be kept low to reduce the frequency of needing to replace one or more batteries. In some embodiments, power-constrained devices may have the ability to communicate via relatively high-power networks (e.g., WiFi) and low-power mesh networks. Power-constrained devices can use relatively high-power networks infrequently to conserve power. Examples of such power-constrained devices include environmental sensors (e.g., temperature sensors, carbon monoxide sensors, smoke sensors, motion sensors, presence detectors) and other forms of remote sensors.

[0038] Display 140 allows processing system 110 to present information for viewing by one or more users. Speaker 150 allows for the output of sound, such as synthesized speech. For example, a response to a verbal command received via microphone 134 can be output via speaker 150 and / or display 140. The verbal command can be analyzed locally by BP measurement device 105, or it can be sent to cloud-based server system 190 for analysis via wireless network interface 145. A response based on the analysis of the verbal command can be sent back to BP measurement device 105 via wireless network interface 145 for output via speaker 150 and / or display 140. Alternatively, speaker 150 and microphone 134 can be jointly configured for active acoustic sensing, including ultrasonic acoustic sensing.

[0039] It is worth noting that some embodiments of the BP measuring device 105 do not have any still camera or video camera. By not incorporating an onboard camera, nearby users can be assured of their privacy. For example, the BP measuring device 105 can typically be installed in a user's bedroom. For many reasons, users do not want a camera placed in such a private space or facing them while they are sleeping or performing some other private activity. In other embodiments, the BP measuring device 105 may have a camera, but the camera lens may be obstructed by a mechanical lens shutter. To use the camera, the user may need to physically open the shutter to allow the camera to have a view of the environment surrounding the BP measuring device 105. When the shutter is closed, the user can ensure that their privacy is not captured by the camera.

[0040] The remote sensing device 160 can typically be a smartwatch, a fitness device, or other smart health device capable of measuring and / or monitoring one or more vital signs of a user, such as body temperature, pulse, respiration, blood pressure, and other types of health data. The remote sensing device 160 can measure vital signs by sensing and / or collecting low-level data, such as changes in blood oxygen saturation over time, electrical activity of the heart or brain, etc. For sensing and / or collecting data, the remote sensing device 160 can be worn on the user's limbs for extended periods, such as as a watch or ring. Alternatively, the remote sensing device 160 can be fitted to the user for a limited amount of time during or when performing vital sign measurements.

[0041] The remote sensing device 160 may include: a remote processing system 165; an electronic display 162; a wireless interface 164; one or more speakers 166; one or more microphones 168; and a sensor suite 170. The remote processing system 165 may include one or more processors, which may include dedicated or general-purpose processors that execute instructions stored using one or more non-transitory processor-readable media. These instructions may configure the one or more processors of the remote processing system 165 to perform various functions. For example, the remote processing system 165 may be configured to control the operation of the sensor suite 170 to collect sensor measurements from a user of the remote sensing device 160. The remote processing system 165 may be further configured to analyze the sensor measurements to provide vital sign data, as discussed further below. Alternatively or additionally, the remote processing system 165 may be configured to receive vital sign data directly from the sensor suite 170 for subsequent processing, transmission, and / or output to a user.

[0042] Remote sensing device 160 may include one or more sensors and / or sensor subsystems configured to collect measurements associated with a user's health and / or vital signs. For example, remote sensing device 160 may include all, one, or a combination of sensors provided as part of sensor suite 170. Sensor suite 170 may include: an optical subsystem 172; an inertial measurement unit (IMU) 174; a temperature sensor 176; and an electrical sensor 178. IMU 174 may allow remote sensing device 160 and / or remote processing system 165 to monitor the movement and orientation of remote sensing device 160. Monitoring the movement and orientation of remote sensing device 160 may allow remote processing system 165 to perform various functions, such as step counting, activity recognition, posture control, etc. Alternatively or additionally, IMU 174 may allow remote processing system 165 to determine the relative position and orientation of remote sensing device 160 relative to one or more external devices, such as BP measurement device 105.

[0043] IMU 174 may include multiple sensors, such as an accelerometer, a gyroscope, and a magnetometer. The accelerometer can measure linear acceleration, such as the up-down, left-right, or forward-backward movement of the remote sensing device 160. Alternatively, the accelerometer can measure directional acceleration due to Earth's gravity. The gyroscope can measure the angular velocity of the remote sensing device 160, such as rotation about a specific axis. The magnetometer can measure the magnetic field strength and can be used to determine the orientation of the remote sensing device 160 relative to the Earth's magnetic field.

[0044] Temperature sensor 176 allows remote sensing device 160 and / or remote processing system 165 to measure the ambient temperature of the environment surrounding remote sensing device 160 and / or the temperature of a user's skin near remote sensing device 160. Temperature sensor 176 may include one or more electrical sensors, such as thermistors, thermocouples, resistance temperature detectors, or other similar components configured to detect temperature changes and convert those changes into electrical signals. Alternatively, temperature sensor 176 may include one or more optical sensors and / or use data from optical subsystem 172 to measure the user's temperature. For example, temperature sensor 176 may use one or more infrared emitters and receivers to measure the amount of infrared radiation emitted by the user's skin.

[0045] Electrical sensor 178 may allow remote sensing device 160 and / or remote processing system 165 to measure electrical signals and / or characteristics related to a user's body or environment, such as the electrical activity of the user's heart. Electrical sensor 178 may be or otherwise include an electrocardiogram (ECG) sensor. Electrical sensor 178 may use two or more electrodes in contact with the user's skin to detect electrical signals generated by the user's heart as it beats. The voltage difference between the two or more electrodes may be measured to generate a waveform representing the electrical activity of the user's heart. The waveform may then be analyzed to determine the user's heart rate, heart rhythm, and other cardiac parameters. Alternatively or additionally, the two or more electrodes may be used to detect moisture (e.g., sweat) on the user's skin by measuring the electrical conductivity difference of the user's skin.

[0046] Optical subsystem 172 allows remote sensing device 160 to optically measure a person's pulse, respiration, and / or oxygen levels by detecting changes in blood volume within the person's microvascular system. Optical subsystem 172 may be or include a photoplethysmography (PPG) sensor. Typically, when blood flows through the microvascular system of a tissue, it causes subtle fluctuations in the tissue's blood volume. As the blood volume of the tissue changes, the amount of light absorbed by that tissue also changes. The amount of light absorbed by the tissue can also change with variations in the oxygen content of the blood. Therefore, by detecting the amount of light reflected by and thus absorbed by the tissue, optical subsystem 172 can be used to measure a user's pulse, respiration, and / or blood oxygen levels.

[0047] As further described below, the optical subsystem 172 may include a light source or emitter (such as an LED) and a light receiver or photodetector (such as a photodiode or phototransistor). The light emitter may be configured to illuminate a user's skin, and the light receiver may be configured to measure changes in the intensity of the light as it travels through user tissue adjacent to the emitter and / or receiver. The remote sensing device 160 may be configured such that the light emitter and receiver are in contact with the user's skin during use. For example, in the case of a wrist-worn device (such as a smartwatch), the light emitter and receiver may be located on the outer surface of the housing of the remote sensing device 160, inside the loop formed by the remote sensing device 160 and the wristband. When worn by a user, the light emitter and receiver can maintain contact with the skin of the user's wrist through pressure applied from the wristband.

[0048] Although described herein as a wrist-worn device, other types of devices (such as rings, finger clips, armbands, etc.) may also be used in conjunction with the optical subsystem 172. Alternatively, the remote sensing device 160 and one or more components of the optical subsystem 172 may be physically separate from each other. For example, the remote sensing device 160 may be a smartphone, tablet, or laptop computer configured to receive wired and / or wireless communications from the optical subsystem 172. Alternatively, the remote sensing device 160 may be configured to operate the remote light emitter and receiver components of the optical subsystem 172 via a wired and / or wireless connection to measure light reflected / absorbed by the user's tissue based on the light intensity detected by the receiver.

[0049] The optical subsystem 172 may further include an optical processing circuitry configured to analyze changes in reflected light and determine one or more pulse wave measurements, such as pulse rate, pulse waveform, pulse pressure amplitude, and other vital sign data related to a person's cardiovascular health. Alternatively, the remote processing system 165 may be configured to receive reflected light signals from the optical subsystem 172 to derive vital sign data related to a person's cardiovascular health. The remote processing system 165 may then transmit the reflected light signals and / or vital sign data to an external device (such as a BP measuring device 105) for further processing. For example, the BP measuring device 105 may perform various fusion analyses on the reflected light signals, pulse waveforms, pulse rate, and / or other vital sign data from the remote sensing device 160, along with other vital sign data, to determine other health-related indicators, such as the user's blood pressure.

[0050] In some embodiments, one or more additional sensors provided as part of the sensor kit 170 can be used to compensate for variations in environmental conditions that may affect the accuracy of pulse wave measurements. For example, user body temperature determined using temperature sensor 176 or perspiration determined using electrical sensor 178 can be used to improve the accuracy of pulse wave measurements. Alternatively, ambient temperature and / or humidity measurements collected by the BP measurement device 105 can further supplement the accuracy of pulse wave measurements.

[0051] The remote sensing device 160 may include interfaces such as an electronic display 162, a wireless interface 164, one or more speakers 166, and one or more microphones 168. The wireless interface 164 may allow communication with wireless networks and / or wired devices using the same or similar communication protocols described above with respect to the wireless network interface 145. For example, the wireless interface 164 may allow the remote sensing device 160 to communicate with other devices, computer systems, etc., via WiFi, 5G, 6G, wireless mesh network protocols, etc. As another example, the wireless interface 164 may allow direct communication with other electronic devices, such as the BP measuring device 105, via Bluetooth, Bluetooth Low Energy (BLE), or some other device-to-device communication protocol.

[0052] The remote sensing device 160 can be configured to communicate with other devices, such as the BP measuring device 105, via a wireless interface 164 to perform various health-related measurements and procedures. For example, the remote sensing device 160 can receive signals, instructions, or requests from the BP measuring device 105 to begin collecting and transmitting vital sign data related to the user's cardiovascular health, such as the user's pulse waveform measured at the location of the remote sensing device 160 on the user's body. Alternatively, the remote sensing device 160 can send instructions or requests to the BP measuring device 105 instructing the user to perform a blood pressure measurement. In response, the remote sensing device 160 and / or the BP measuring device 160 can perform initial synchronization between the clocks of each respective device, as further described below. Once synchronized, the remote sensing device 160 can begin collecting vital sign data and transmitting it to the BP measuring device 105, while the BP measuring device 105 begins collecting radar data from the radar processing module 112. Using the synchronized data, the BP measurement engine 114 can derive the user's BP measurement and subsequently send it to the remote sensing device 160 for output to the user.

[0053] The electronic display 162, one or more speakers 166, and one or more microphones 168 allow the teleprocessing system 165 to provide various user interface functionalities. For example, the electronic display 162 can allow the teleprocessing system 165 to present various graphical user interfaces (GUIs). The GUI can allow the teleprocessing system 165 to present information to the user and / or receive input from the user. For example, the GUI can display one or more optional options that, when selected by the user, can configure the teleprocessing system 165 and / or the processing system 110 to begin collecting vital sign data from the user. The GUI can be further used to display information to the user, such as instructions for performing accurate collection of vital sign data. For example, the teleprocessing system 165 can display instructions to the user regarding the appropriate positioning, posture, activity level, etc., of the user or the remote sensing device 160 that can lead to improved measurement readings.

[0054] One or more microphones 168 may allow the remote processing system 165 to present various voice user interfaces (VUIs). Using speech recognition technology, the remote processing system 165 may be configured to monitor one or more verbal commands detectable in the audio captured by the one or more microphones. For example, the VUI may allow a user to speak a command corresponding to an instruction to begin collecting vital signs data. In response, one or more speakers 166 may output audio that confirms the user's instruction and / or provides further instructions for performing vital signs data collection. As described above with reference to the BP measurement device 105, the remote sensing device 160 may perform speech recognition locally and / or send the detected audio to a remote processing system (such as the BP measurement device 105 and / or a cloud-based server system 190) for analysis and response generation.

[0055] As described above, wireless network interface 145 and / or wireless interface 164 may allow wireless communication with network 180. Network 180 may include one or more public and / or private networks. Network 180 may include a private local wired or wireless network, such as a home wireless LAN. Network 180 may also include a public network, such as the Internet. Network 180 may allow communication between BP measuring device 105 and remote sensing device 160. Alternatively or additionally, network 180 may allow BP measuring device 105 and / or remote sensing device 160 to communicate with a remotely located cloud-based server system 190.

[0056] The cloud-based server system 190 can provide various services to the BP measurement device 105 and / or the remote sensing device 160. Regarding BP data, the cloud-based server system 190 may include processing and storage services for BP-related data. Although Figure 1 The embodiments involve processing system 110 performing BP measurements, but such functionality can be performed by cloud-based server system 190. Furthermore, as a supplement or alternative to using BP data storage 118 to store BP data, BP-related data can be stored by cloud-based server system 190, such as data mapped to a public user account linked to BP measurement device 105. If multiple users are associated with BP measurement device 105, BP data can be stored and mapped to individual user accounts, such as user accounts associated with remote sensing device 160.

[0057] Whether a single user or multiple users use the BP measurement device 105 to measure BP, each user may be required to provide their informed consent. Such informed consent may involve each user agreeing to an end-user agreement that addresses data use in accordance with HIPAA and / or other generally accepted health information security and privacy standards. Users may be required to periodically (e.g., annually) renew their consent to the collection of BP data. In some embodiments, each end-user may receive periodic notifications, such as via a mobile device (e.g., a smartphone), reminding each user that their BP data is being collected and analyzed, and providing each user with the option to disable such data collection.

[0058] The cloud-based server system 190 can additionally or alternatively provide other cloud-based services. For example, the BP measuring device 105 can additionally act as a home assistant device. The home assistant device can respond to verbal queries from the user. In response to detecting a spoken trigger phrase, the BP measuring device 105 can record audio via microphone 134. The audio stream can be sent to the cloud-based server system 190 for analysis. The cloud-based server system 190 can perform a speech recognition process, using a natural language processing engine to understand queries from the user, and provide responses to be output by the BP measuring device 105 as synthesized speech, outputs to be displayed on display 140, and / or commands to be executed by the BP measuring device 105 (e.g., increasing the volume of the BP measuring device 105) or sent to another device (such as remote sensing device 160). Furthermore, queries or commands can be submitted to the cloud-based server system 190 via display 140 (which may be a touchscreen). For example, the BP measuring device 105 can be used to control various smart home devices or home automation devices. Such commands can be sent directly from the BP measurement device 105 to the device to be controlled, or they can be sent via a cloud-based server system 190.

[0059] Figure 2 A block diagram of an embodiment of a BP measurement system 200 (“System 200”) based on sensor fusion is shown. System 200 may include a radar subsystem 205 (which may represent an embodiment of radar subsystem 120); a radar processing module 210 (which may represent an embodiment of radar processing module 112); an optical subsystem 220 (which may represent an embodiment of optical subsystem 172); a remote sensor module 225 (which may represent an embodiment of remote sensor module 113); and a BP measurement engine 230 (which may represent an embodiment of BP measurement engine 114).

[0060] Radar subsystem 205 may include an RF transmitter 206, an RF receiver 207, and radar processing circuitry 208. The RF transmitter 206 may transmit radio waves, for example, in the form of a continuous wave (CW) radar. The RF transmitter 206 may use a frequency modulated continuous wave (FMCW) radar. The FMCW radar may operate in burst mode or continuous sparse sampling mode. In burst mode, the RF transmitter 206 may output frames or bursts with multiple chirps, where the chirps are spaced apart by relatively short time intervals. Each frame may be followed by a relatively long time until the next frame. In continuous sparse sampling mode, chirped frames or bursts are not output; instead, chirps are output periodically. The duration of the chirp interval in continuous sparse sampling mode may be greater than the interval between chirps within a frame in burst mode. In some embodiments, radar subsystem 205 may operate in burst mode, but the raw chirped waterfall data output from each burst may be combined (e.g., averaged) to create simulated continuously sparsely sampled chirped waterfall data. In some embodiments, raw waterfall data collected in burst mode may be preferred for posture detection, while raw waterfall data collected in continuously sparsely sampled mode may be preferred for certain functions such as BP measurement, sleep tracking, vital sign detection, and general health monitoring. Posture detection may be performed by other hardware or software components (not shown) using the output of radar subsystem 205.

[0061] RF transmitter 206 may include one or more antennas and can transmit at or around 60 GHz. The transmitted radio waves can be scanned repeatedly from low to high frequencies (or vice versa). The power level used for transmission can be very low, making the effective range of radar subsystem 205 a few meters or even shorter. About Figure 4 Further details are provided regarding the radio waves generated and transmitted by radar subsystem 205.

[0062] RF receiver 207 includes one or more antennas different from the transmitting antenna and can receive radio waves reflected from nearby objects by radio waves emitted by RF transmitter 206. Radar processing circuitry 208 can interpret reflected radio waves by mixing the transmitted radio waves with the received reflected radio waves, thereby generating a mixed signal that can be analyzed for distance. Based on this mixed signal, radar processing circuitry 208 can output raw waveform data, also known as waterfall data, for analysis by a separate processing entity. Radar subsystem 205 can be implemented as a single integrated circuit (IC), or radar processing circuitry 208 can be a component separate from RF transmitter 206 and RF receiver 207. In some embodiments, radar subsystem 205 is integrated as part of device 105 such that RF transmitter 206 and RF receiver 207 are pointed in the same direction as display 140. In other embodiments, external devices including radar subsystem 205 can be connected to device 105 via wired or wireless communication. For example, radar subsystem 205 can be an add-on to a home assistant device.

[0063] Raw waveform data can be transferred from radar subsystem 205 to radar processing module 210. The raw waveform data transferred to radar processing module 210 may include waveform data indicating continuous sparse reflection chirps generated due to radar subsystem 205 operating in continuous sparse sampling mode or due to radar subsystem 205 operating in burst mode and a conversion process simulating the raw waveform data generated by radar subsystem 205 operating in continuous sparse sampling mode is being performed. Processing can be performed to convert the burst-sampled waveform data into continuous sparse samples using an averaging process, such as each burst group of reflected radio waves being represented by a single averaged sample. Radar processing module 210 may include one or more processors. Radar processing module 210 may include one or more dedicated or general-purpose processors. Dedicated processors may include processors specifically designed to perform the functions detailed herein. Such dedicated processors may be ASICs or FPGAs, which are general-purpose components physically and electrically configured to perform the functions detailed herein. A general-purpose processor can execute dedicated software stored using one or more non-transitory processor-readable media, such as random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD). Radar processing module 210 may include: a motion filter 211; a frequency emphasis unit 212; a range-vital sign conversion engine 213; a range gating filter 214; a spectrum summing engine 215; and a radar timing engine 216. Each of the components of radar processing module 210 can be implemented using software, firmware, or as dedicated hardware.

[0064] The raw waveform data output by radar subsystem 205 can be received by radar processing module 210 and processed first using motion filter 211. In some embodiments, it is important that motion filter 211 is the initial component used to perform filtering. That is, in some embodiments, the processing performed by radar processing module 210 is non-interchangeable. Typically, vital signs determination (including BP measurement) may occur when the monitored user is in a low-motion environment. In such an environment, there may typically be a small amount of movement. The movement present can be attributed to the user's vital signs, including movement due to breathing and movement due to the monitored user's heartbeat. In such an environment, most of the radio waves emitted from RF transmitter 206 can be reflected by static objects near the monitored user, such as furniture, bedding, walls, etc. Therefore, most of the raw waveform data received from radar subsystem 205 may be unrelated to user movement and the user's vital sign measurements.

[0065] Motion filter 211 may include a waveform buffer that buffers "chirps" or segments of the received raw waveform data. For example, sampling may occur at a rate of 10 Hz. In other embodiments, sampling may be slower or faster. In some embodiments, motion filter 211 may buffer 20 seconds of received raw waveform chirps. In other embodiments, buffered raw waveform data may be buffered for shorter or longer durations. The buffered raw waveform data may be filtered to remove raw waveform data indicating stationary objects. That is, for a moving object, such as the chest of a monitored user, the user's heart rate and respiratory rate will affect the distance and velocity measurements performed by radar subsystem 205 and output to motion filter 211. This movement of the user will cause the received raw waveform data to "jitter" during the buffered time period. More specifically, jitter refers to the phase shift caused by radio waves emitted by a moving object. As detailed in this article, instead of using the reflected FMCW radio waves to determine the speed of a moving object, vital signs statistics, including heart rate and respiratory rate, can be measured using the phase shift caused by motion in the reflected radio waves.

[0066] For stationary objects such as furniture, the raw waveform data will contain zero phase shift (i.e., no jitter) during the buffered time period. The motion filter 211 can subtract this type of raw waveform data corresponding to the stationary object, allowing the motion-indicating raw waveform data to be passed to the frequency enhancement unit 212 for further analysis. The raw waveform data corresponding to the stationary object can be discarded or ignored for further processing by the radar processing module 210.

[0067] In some embodiments, an infinite impulse response (IIR) filter is incorporated as part of the motion filter 211. Specifically, a unipolar IIR filter can be implemented to filter out raw waveform data that does not indicate motion. Thus, the unipolar IIR filter can be implemented as a high-pass, low-impedance filter that prevents raw waveform data indicating motion below a certain frequency from being passed to the frequency accentuator 212. The cutoff frequency can be set based on known limits of human vital signs. For example, a respiratory rate between 10 and 60 breaths per minute is expected. The filter can exclude motion data indicating a frequency below 10 breaths per minute. In some embodiments, a bandpass filter can be implemented to exclude raw waveform data indicating motion at high frequencies that are unlikely or improbable for human vital signs. For example, for a person at rest or near rest, a heart rate above the respiratory rate is unlikely to exceed 150 beats per minute. Raw waveform data indicating higher frequencies can be filtered out by the bandpass filter.

[0068] The vital signs of the monitored user being measured are periodic pulse events: the user's heart rate may vary over time, but the user's heart can be expected to continue beating periodically. This beating is not a sinusoidal function, but can be understood as a pulse event, more akin to a square wave with a relatively low duty cycle, causing movement in the user's body. Frequency components resulting from this spectral leakage should be minimized.

[0069] The frequency emphasis unit 212 can work in conjunction with the range-vital signs transformation engine 213 to determine the frequency components of the raw waveform data attributable to vital sign statistics, such as the user's pulse. The frequency emphasis unit 212 can use frequency windowing, such as a 2D Hamming window (other forms of windowing are also possible, such as Hann windows), to emphasize important frequency components of the raw waveform data and weaken or remove waveform data attributable to spectral leakage outside the defined frequency window. Such frequency windowing can reduce the amplitude of the raw waveform data—which may be due to processing artifacts. Using frequency windowing can help reduce the impact of data-related processing artifacts while preserving data that can be individually determined for heart rate and respiratory rate.

[0070] For fixed desktop or bedside FMCW radar-based monitoring devices that can be positioned within 1 to 2 meters of one or more monitored users to detect heart rate, a 2D Hamming window emphasizing the frequency range (0.5 Hz to 2.5 Hz) of 30 bpm to 150 bpm of heart rate provides a sufficiently good signal for reliable measurement without prior knowledge of the subject's age or medical history.

[0071] Since heart rate and respiratory rate are periodic pulse events, they can be represented by different fundamental frequencies in the frequency domain, but each may have many harmonic components at higher frequencies. One of the primary purposes of the frequency emphasis unit 212 is to prevent harmonic frequency ripple from the monitored user's heart rate from affecting any other vital sign statistics being measured, such as respiratory rate. While the frequency emphasis unit 212 can use a 2D Hamming window, it should be understood that other windowing functions or isolation functions can be used to help isolate the frequency ripple of the monitored user's respiratory rate from the frequency ripple of the monitored user's heart rate.

[0072] The range-vital signs transformation engine 213 analyzes the received motion-filtered waveform data to identify and quantify the magnitude of movement at a specific frequency. More specifically, the range-vital signs transformation engine 213 analyzes time-varying phase jitter to detect relatively small movements caused by the user's vital signs, which have relatively low frequencies (such as respiratory rate and heart rate). The analysis by the range-vital signs transformation engine 213 can assume that the frequency components of the motion waveform data are sinusoidal. Furthermore, the transformation used by the range-vital signs transformation engine 213 can also identify the distance at which the frequency is observed. Frequency, amplitude, and distance can all be determined at least partially because the radar subsystem 205 uses an FMCW radar system.

[0073] The range-vitality transformation engine 213 can perform a series of Fourier transforms (FTs) to determine the frequency components of the received raw waveform data output by the frequency accentuator 212. Specifically, the range-vitality transformation engine 213 can perform a series of fast Fourier transforms (FFTs) to determine specific frequencies and the amplitude of the waveform data at such frequencies.

[0074] Waveform data acquired over a period of time can be represented using multiple dimensions. A first dimension (e.g., along the y-axis) can be associated with multiple samples of waveform data from a specific chirp, and a second dimension (e.g., along the x-axis) can be associated with a specific sample index of waveform data collected across multiple chirs. A third dimension of the data exists (e.g., along the z-axis), which indicates the intensity of the waveform data.

[0075] Multiple FFTs can be performed based on the first and second dimensions of the waveform data. An FFT can be performed along each of the first and second dimensions: an FFT can be performed for each chirp, and an FFT can be performed for each specific sample index across multiple chirs occurring over a period of time. An FFT performed on waveform data for a specific reflected chirp can indicate one or more frequencies, which, in FMCW radar, indicate the distance to the location of an object reflecting the emitted radio waves. An FFT performed for a specific sample index across multiple chirs can measure the phase jitter frequency across multiple chirs. Therefore, an FFT in the first dimension can provide the distance to the location of vital sign statistics, and an FFT in the second dimension can provide the frequency of vital sign statistics. The output of an FFT performed across both dimensions indicates: 1) the frequency of the vital sign statistics; 2) the range of the measured vital sign statistics; and 3) the amplitude of the measured frequencies. In addition to the values ​​resulting from the vital sign statistics present in the data, there may be noise, such as that filtered using the spectral summation engine 215. This noise may be partly due to the fact that heart rate and respiration are not perfect sine waves.

[0076] It is important to clarify that the transformation performed by the range-vital signs transformation engine 213 differs from the range-Doppler transformation. Instead of analyzing velocity changes (as in the range-Doppler transformation), it analyzes the periodic changes in phase shift over time as part of the range-vital signs transformation. By tracking phase changes (referred to as phase jitter), the range-vital signs transformation is modulated to identify small movements (e.g., respiration, vascular and valvular dilation) occurring over relatively long time periods.

[0077] Range gating filter 214 is used to monitor a defined area of ​​interest and exclude waveform data resulting from movement outside the defined area of ​​interest. For the arrangement detailed herein, the defined area of ​​interest can be 0 to 1 meter. In some embodiments, the defined area of ​​interest may vary or may be set by the user (e.g., via a training or setup process) or by a service provider. In some embodiments, the goal of this arrangement may be to monitor the person closest to the device (and exclude or isolate data from any other person at a greater distance—such as someone sleeping next to the monitored person). Therefore, the range-vitality transformation engine 213 and range gating filter 214 are used to separate, exclude, or remove movement data attributed to objects outside the defined area of ​​interest and to sum the energy of movement data attributed to objects within the defined area of ​​interest. The output of range gating filter 214 may include data having a defined range within the allowable range of range gating filter 214. This data may further have a frequency dimension and an amplitude dimension. Therefore, the data may have three dimensions.

[0078] As part of the range-vital sign transformation engine 213 and / or range gating filter 214, data collected at specific distances can be binned together. For example, a number of range bins, such as 256, can be created. Motion detected within a specific distance range corresponding to a bin can be grouped together for analysis. As will be detailed herein, a first distance bin can be identified where the user's pulse is detected at or near the user's aortic valve; a second distance bin can be identified where the user's pulse is detected at the user's limbs (e.g., hand, foot).

[0079] The spectrum summing engine 215 can receive the output from the range gating filter 214. The spectrum summing engine 215 can be used to transmit the measured harmonic frequency energy of the user's heart rate and add the harmonic frequency energy to the fundamental frequency energy of each distance partition. This function may be referred to as the Harmonic Sum Spectrum (HSS). As previously mentioned, vital sign statistics such as heart rate and respiratory rate are not sinusoidal; therefore, in the frequency domain, harmonics will exist at frequencies higher than the fundamental frequency of the user's respiratory rate and the fundamental frequency of the user's heart rate. One of the primary purposes of the spectrum summing engine 215 may be to prevent harmonics of the monitored user's respiratory rate from affecting the frequency measurement of the monitored user's heart rate (and vice versa). The HSS can be performed in second order by adding the original spectrum to a downsampled instance of the spectrum (multiplied by two). This process can also be applied to higher-order harmonics, such that their corresponding spectra are added to the spectrum below the fundamental frequency. The HSS can be applied to some or all of the distance partitions in which a pulse (and / or respiration) is detected.

[0080] The radar timing engine 216 can operate in conjunction with the clock synchronization engine 226 and / or the optical timing engine 227, as further described below, to synchronize the output of the radar processing module 210 with other inputs of the BP measurement engine 230. From the perspective of the clock associated with the electronic device, there may be a delay between the time when a real-world event (such as a heartbeat) occurs and the time when data from the sensor observing the event is finally processed and assigned a timestamp. This delay may be due to physical constraints associated with electronic sensors, processing power, algorithm complexity, etc. To account for this delay, the radar timing engine 216 can adjust the timestamps associated with the output of the radar processing module 210. For example, the radar timing engine 216 can apply a static adjustment amount to each timestamp based on predefined specifications associated with a particular device and / or its components (such as the model of the processor or sensor, the version of the software, etc.). Alternatively, the radar timing engine 216 can monitor one or more operating characteristics of the electronic device (such as the current processor load) and / or characteristics of the underlying data (such as the distance between the electronic device and the user) to dynamically calculate the adjustment amount.

[0081] Optical subsystem 220 may include a light emitter 221, a light receiver 222, and optical processing circuitry 223. As described above with respect to optical subsystem 172, light emitter 221 may include one or more light sources configured to illuminate a user's skin, such as LEDs, laser diodes, organic LEDs (OLEDs), etc. Light emitter 221 may be configured to emit light of one or more specific wavelengths, such as red or infrared light, which may be absorbed and / or reflected differently by oxygenated and deoxygenated blood. As further described above, light receiver 222 may include one or more photodetectors, such as photodiodes and / or phototransistors, configured to convert incident light of wavelengths emitted by light emitter 221 into electrical signals. Optical processing circuitry 223 may process the electrical signals from light receiver 222 to detect the amount of light reflected or absorbed by the user's tissue from light emitter 221. Optical processing circuitry 223 may represent the amount of light reflected or absorbed by the user's tissue in its raw waveform. Alternatively, the optical processing circuit 223 can further analyze the amount of light reflected or absorbed over time to derive the pulse waveform.

[0082] The optical subsystem 220 may be implemented as a single integrated circuit (IC), or the optical processing circuitry 223 may be a component separate from the light emitter 221 and the light receiver 222. In some embodiments, the optical subsystem 205 is integrated as part of the remote sensing device 160, such that the light emitter 221 and the light receiver 222 are pointed in the opposite direction to the display 162. In other embodiments, an external device including one or more components of the optical subsystem 220 may be connected to the remote sensing device 160 and / or the BP measurement device 105 via wired or wireless communication.

[0083] Pulse waveform data can be transmitted from optical subsystem 220 to remote sensor module 225. The pulse waveform data transmitted to remote sensor module 225 may include waveform data indicating light intensity (e.g., light absorption) measured at the user's limb. Alternatively, the pulse waveform data may include a processed pulse waveform measured at the user's limb. As described above with respect to radar processing module 210, remote sensor module 225 may include one or more general-purpose or dedicated processors. Alternatively, remote sensor module 225 and radar processing module 210 may share a processing system. For example, remote sensor module 226 and radar processing module 210 may be separate firmware or software components executing on the same device (such as BP measurement device 105). Alternatively, one or more components or functions of remote sensor module 226 may be executed on or facilitated by the same device as optical subsystem 220 (such as remote sensing device 160).

[0084] The remote sensor module 225 may include a clock synchronization engine 226 and an optical timing engine 227. As described above with reference to radar timing engine 216, the optical timing engine 227 may adjust the timestamp associated with the output of optical subsystem 220 to account for the delay between the time when the optical subsystem 220 can detect the pulse wave and the time when the pulse wave is actually recorded in the data associated with the timestamp. For example, the optical timing engine 227 may adjust the timestamp based on the model, version, or manufacturer of the electronic device and / or optical subsystem 220.

[0085] In addition to the processing delay between the time when real-world events occur and the time when data representing those events is recorded, the accuracy of measurements derived from data collected by distributed systems can be further reduced due to differences in the time reference frame of each system. As described herein, it is assumed that the time reference frame of each system is relative to the clock of that system. Such differences can arise from each clock being calibrated to different reference sources (such as Global Positioning System (GPS) time, Coordinated Universal Time (UTC), etc.), inaccurate initial time calibration (e.g., relative to the time reference source), and / or subsequent clock drift.

[0086] Clock synchronization engine 226 can account for differences in time reference systems used by radar subsystem 205, radar processing module 210, and / or optical subsystem 220 by synchronizing the clocks of each reference system to a common time reference. For example, in the case of two electronic devices (e.g., BP measurement device 105 and remote sensing device 160), clock synchronization engine 226 can synchronize the first clock of remote sensing device 160 to the second clock of BP measurement device 105, and vice versa. Alternatively, clock synchronization engine 226 can synchronize the clocks to a standard time reference source, such as UTC or GPS time. Based on the common time reference, clock synchronization engine 226 can use one or more technologies (such as Network Time Protocol (NTP), Precision Time Protocol (PTP), etc.) to synchronize the clocks.

[0087] The time-adjusted outputs of the radar processing module 210 and the remote sensor module 225 can be transmitted to the BP measurement engine 230. The BP measurement engine 230, which can be implemented using the same or different processing systems as the radar processing module 210 and / or the remote sensor module 225, may include: a radar analysis engine 231, an optical analysis engine 232, a PTT determination engine 233; and a BP determination engine 234.

[0088] The radar analysis engine 231 can be used to detect pulse waveforms at the user's chest caused by the user's heartbeat using the output from the radar processing module 210. More specifically, the radar analysis engine 231 can detect pulse waveforms at or near the user's aortic valve. The radar analysis engine 231 can analyze range partition data received from the spectral summation engine 215. Since the heartbeat causes a significant amount of movement at and around the aortic valve, the range partition with the largest amount of movement attributable to the pulse waveform can be the range partition selected and analyzed by the radar analysis engine 231. The radar analysis engine 231 can be a trained machine learning model, such as a trained neural network, that can recognize the user's heartbeat (e.g., pulse waveform) and can assign timestamps to the heartbeat based on time-adjusted and synchronized output from the radar processing module 210.

[0089] In some embodiments, the radar analysis engine 231 further detects pulse waveforms at the user's limbs (such as the user's hand or foot) caused by the user's heartbeat. For example, the user may be asked to position their hand or foot at a defined distance from the radar subsystem 205, allowing the determination of the distance partition corresponding to the user's limb. Based on the request for the user to maintain the position of their hand or foot, the distance partition determined for the user's limb may be the closest distance partition to the radar subsystem 205 where a pulse can be detected. Based on the data in the distance partition corresponding to the user's limb, the radar analysis engine 231 can identify the pulse waveform at the user's limb and assign a timestamp to it.

[0090] The optical analysis engine 232 can be used to detect pulse waveforms at locations on the user's body adjacent to the light emitter 221 and / or light receiver 222, caused by the user's pulse. As described herein, this location is assumed to be a limb of the user, such as the user's wrist, fingers, hand, foot, or arm. The optical analysis engine 232 can analyze time-adjusted and synchronized output from the remote sensor module 225 to identify the pulse waveform at the user's limb and assign it a timestamp. For example, the optical analysis engine 232 can apply one or more signal processing algorithms to the light absorption / reflection waveform to derive the pulse waveform. Such algorithms may include filters, noise reduction techniques, peak detection algorithms, etc. Alternatively or additionally, the optical analysis engine 232 can be configured to receive pulse waveforms provided by the optical subsystem 220.

[0091] The PTT determination engine 233 can at least determine the PTT by calculating the time difference between the pulse waveform measured by the radar analysis engine 231 at the user's chest and the pulse waveform measured by the optical analysis engine 232 and / or the radar analysis engine 231 at the user's limbs (attributed to the same heartbeat). Alternatively or additionally, the PTT determination engine 233 can first calculate the phase difference between the pulse waveform measured by the radar analysis engine 231 and the pulse waveform measured by the optical analysis engine 232, from which the PTT can be determined. In some embodiments, additional data based on the pulse waveform measured by the radar analysis engine 231 and / or the optical analysis engine 232 can be determined. This data may include a derived pulse waveform amplitude (DPWA), which indicates the amplitude of the pulse measured at the user's limbs and / or chest. In some embodiments, separate DPWA values ​​are calculated for the limbs and chest. This data may additionally or additionally include heart rate (HR) data by determining the number of pulse waveforms over a period of time. In some embodiments, separate HR values ​​are calculated for the limbs and chest. Alternatively, respiratory rate (RR) can be derived by identifying periodic increases and matched decreases in HR and / or pulse waveform frequency. PTT, HR, DPWA, RR, or some combination thereof can be output to the BP determination engine 234.

[0092] The BP determination engine 234 may be an algorithm or lookup arrangement for calculating BP using PTT, HR, DPWA, and / or RR, which may include systolic and diastolic blood pressure. In some embodiments, a trained machine learning model may receive these values ​​as input and may output systolic and diastolic blood pressure. In some embodiments, a calibration curve is applied to adjust the determined BP based on one or more measurements of the user's BP obtained via another form of BP measurement device. The output of the BP determination engine 234 may be presented via display 140, display 162, speaker 150, one or more speakers 166, and / or stored by BP data storage 118 and / or cloud-based server system 190.

[0093] Figure 3A block diagram of an embodiment of a BP measurement system 300 (“System 300”) based on sensor fusion is shown. System 300 may include a radar subsystem 205 (which may represent an embodiment of radar subsystem 120); a radar processing module 210 (which may represent an embodiment of radar processing module 112); an optical subsystem 220 (which may represent an embodiment of optical subsystem 172); a remote sensor module 225 (which may represent an embodiment of remote sensor module 113); and a BP measurement engine 310 (which may represent an embodiment of BP measurement engine 114). Except for the BP measurement engine 310, System 300 may function similarly to System 200. The BP measurement engine 310 may include only an analysis engine 311. The analysis engine 311 may be a trained machine learning model, such as a neural network, which receives time-adjusted and synchronized outputs from radar processing module 210 and remote sensor module 225 as its input. The analysis engine 311 can be trained to output BP measurements, such as systolic and diastolic blood pressure values, by directly analyzing the outputs of the radar processing module 210 and the remote sensor module 225.

[0094] To train the analysis engine 311, a distributed system similar to the radar processing module 210 and the remote sensor module 225 can be used to perform numerous measurements on the user. The output data can be mapped to the user's blood pressure collected using an accurate BP measurement device. This training data can then be used to build a machine learning model that can determine blood pressure based on the output of the radar processing module 210 and the remote sensor module 225.

[0095] In some embodiments, a calibration curve is applied to adjust the determined BP based on one or more measurements of the user's BP obtained via another form of BP measurement device. In system 300, a layer of analysis engine 311 can be created or modified to take into account the user's calibration curve.

[0096] Figure 4An embodiment of a chirp timing diagram 400 for frequency-modulated continuous wave (FMCW) radar radio waves output by a radar subsystem is shown. Chirp timing diagram 400 is not drawn to scale. Radar subsystem 205 can typically output radar according to the pattern of chirp timing diagram 400. Chirp 450 represents a continuous radio wave pulse scanning upwards from a low frequency to a high frequency. In other embodiments, individual chirps may continuously scan downwards from a high frequency to a low frequency, scan from a low frequency to a high frequency and back to a low frequency, or scan from a high frequency to a low frequency and back to a high frequency. In some embodiments, the low frequency is 58 GHz and the high frequency is 63.5 GHz. (For such frequencies, the radio waves may be referred to as millimeter waves). In some embodiments, the frequencies are between 57 GHz and 64 GHz. The low and high frequencies can vary depending on the embodiment. For example, the low and high frequencies may be between 45 GHz and 80 GHz. The frequencies may be selected at least partially to comply with government regulations. In some embodiments, each chirp comprises a linear scan from low frequency to high frequency (or vice versa). In other embodiments, an exponential or other pattern may be used to scan frequencies from low to high or from high to low.

[0097] Chirp 450, representing all chirps in chirp timing diagram 400, can have a chirp duration 452 of 128 μs. In other embodiments, the chirp duration 452 can be longer or shorter, such as between 50 μs and 1 ms. In some embodiments, a period of time may elapse before the emission of a subsequent chirp. The inter-chirp pause 456 can be 405.33 µs. In other embodiments, the inter-chirp pause 456 can be longer or shorter, such as between 10 μs and 1 ms. In the illustrated embodiment, the chirp period 454, including chirp 450 and inter-chirp pause 456, can be 333.33 μs. This duration varies based on the selected chirp duration 452 and inter-chirp pause 456.

[0098] The output of multiple chirps separated by chirp pauses can be referred to as frame 458 or frame 458. Frame 458 may include twenty chirps. In other embodiments, the number of chirps in frame 458 may be more or less, such as between 1 and 100. The number of chirps present within frame 458 can be determined based on the amount of maximum power expected to be output within a given time period. The FCC or other regulatory agencies may set the maximum amount of power that can be allowed to radiate into the environment. For example, there may be a duty cycle requirement that limits the duty cycle for any 33ms time period to less than 10%. In a particular example where there are twenty chirps per frame, each chirp may have a duration of 128 μs, and the duration of each frame may be 33.33 ms. The corresponding duty cycle is (20 frames) * (128 ms) / (33.33 ms), which is approximately 8.8%. By limiting the number of chirps within frame 458 before the inter-frame pause, the total power output can be limited. In some embodiments, the peak effective isotropic radiated power (EIRP) may be 13 dBm (20 mW) or less, such as 12.86 dBm (19.05 mW). In other embodiments, the peak EIRP is 15 dBm or less, and the duty cycle is 15% or less. In some embodiments, the peak EIRP is 40 dBm or less. That is, at any given time, the amount of power radiated by the radar subsystem may never exceed such values. Furthermore, the total power radiated over a period of time may be limited.

[0099] Frames can be transmitted at a frequency of 30 Hz (33.33 ms), as shown in time period 460. In other embodiments, this frequency can be higher or lower. The frame frequency can depend on the number of chirps within the frame and the duration of the inter-frame pause 462. For example, the frequency can be between 1 Hz and 50 Hz. In some embodiments, chirps can be transmitted continuously, such that the radar subsystem output is a continuous chirp stream interspersed with chirp pauses. Trade-offs can be made to save the average power consumed by the device due to transmitting chirps and processing received chirp reflections. Inter-frame pause 462 represents the time period when no chirps are output. In some embodiments, inter-frame pause 462 is significantly longer than the duration of frame 458. For example, the duration of frame 458 can be 6.66 ms (where the chirp period 454 is 333.33 µs and there are 40 chirs per frame). If a 33.33 ms interval occurs between frames, then the inter-frame pause 462 can be 46.66 ms. In other embodiments, the duration of the inter-frame pause 462 can be longer or shorter, such as between 15 ms and 40 ms.

[0100] exist Figure 4In the illustrated embodiment, a single frame 458 and the beginning of subsequent frames are shown. It should be understood that each subsequent frame can be structured similarly to frame 458. Furthermore, the transmission mode of the radar subsystem can be fixed. That is, the chirp can be transmitted according to the chirp timing diagram 400 regardless of the presence of a user, the time of day, or other factors. Therefore, in some embodiments, the radar subsystem always operates in a single transmission mode, regardless of environmental conditions or the activity being monitored. When the BP measurement device 105 is powered on, a continuous sequence of frames similar to frame 458 can be transmitted.

[0101] Figure 5 A simplified graphic 500 of a pulse wave measured by a distributed BP measurement system is shown. As described above, components of the distributed BP measurement system (such as radar subsystem 205 and optical subsystem 220) can be used to detect pulse waveforms at different locations on the user's body. For example, radar analysis engine 231 can use the output from radar processing module 210 to detect an aortic pulse wave 505 at the user's chest. As another example, optical analysis engine 232 can detect a peripheral pulse wave 520 at the user's limbs (such as the user's wrist or fingers). For simplicity, aortic pulse wave 505 and peripheral pulse wave 520 are shown as single pulse waves corresponding to the same heartbeat. However, it should be clear that each pulse wave can be part of a continuous waveform measured separately at the user's chest and limbs. Furthermore, for illustrative purposes, aortic pulse wave 505 and peripheral pulse wave 520 are substantially separated from each other such that they do not overlap. However, in most instances, there is considerable overlap in the time domain (e.g., along the x-axis) between the pulse wave detected at the chest and the same pulse wave detected at the limb.

[0102] As further shown in Figure 500, an aortic pulse wave 505 can be detected at a first time 510, and a peripheral pulse wave 525 can be detected at a second time 525. The first time 510 and the second time 525 can each correspond to the time at which the system detects the peak or maximum value of each corresponding pulse wave. Although described with reference to the peak or maximum value of each corresponding pulse wave, other points within the pulse wave can also be used alternatively as reference points from which subsequent determinations and / or measurements can be made, such as the start of each pulse wave corresponding to the ascending limb of systole, dicrotic notch, etc.

[0103] As further described above with reference to radar timing engine 216 and / or optical timing engine 227, there may be a delay between the time when the pulse wave occurs or is otherwise observable at the user's chest and limbs and the time when the pulse wave is detected. Therefore, and as shown in Figure 500, a first adjustment amount 512 can be subtracted from a first time 510 to produce an aortic pulse time 515, and a second adjustment amount 527 can be subtracted from a second time 525 to produce a peripheral pulse time 530. As further shown, the first adjustment amount 512 and the second adjustment amount 527 can be different time amounts to account for the different delays associated with each respective measurement system. Although shown and described as subtracting time from the detection time of the pulse wave, the embodiments described herein can alternatively perform a similar time adjustment on the underlying measurements (such as optical absorption data and / or radar data) before detecting the pulse wave, thereby producing an accurate detection time.

[0104] As further explained above, each pulse wave takes time to travel from the heart to the limb. The amount of time it takes for a pulse wave to travel from the heart to the limb can be referred to as the PTT. For example, as shown in Figure 500, the time difference 540 measured from the aortic pulse time 515 to the peripheral pulse time 530 can represent the PTT of a pulse wave from the user's chest where the aortic pulse wave 505 is detected to the user's limb where the peripheral pulse wave 520 is detected. The time difference 540 can also represent the phase difference between the continuous pulse waveform detected at the user's chest and the continuous pulse waveform detected at the user's limb. In some embodiments, the phase difference between the pulse waveform detected at the user's chest and the pulse waveform detected at the user's limb can be measured at a specific time point, and this phase difference can be used to derive the PTT.

[0105] Figure 6 An embodiment of a BP measurement device 600 (“Device 600”) is illustrated. Device 600 can be a smart home hub device capable of receiving voice-based commands and providing users with interfaces to interact with various other smart home devices, view images, interact with media, and perform various other tasks. Device 600 may have a front surface including a front transparent screen 640, making the display visible. Such a display may be a touchscreen. Surrounding the front transparent screen 640 may be an optically opaque area, referred to as a bezel 630, through which the radar subsystem 205 can have a field of view of the environment in front of Device 600.

[0106] For the purposes of the following description, the terms "vertical" and "horizontal" generally describe directions relative to the real-world environment, where vertical refers to a direction aligned with acceleration due to gravity, and horizontal refers to a direction perpendicular to vertical. Since the radar subsystem (which may be an Infineon® BGT60 radar chip) is generally planar and mounted generally parallel to the bezel 630 for the sake of overall device compactness, and since the antenna within the radar chip is located in the plane of the chip, the receiving beam of the radar subsystem 120 can be pointed in a direction 650 generally perpendicular to the bezel 630 when not beam-aiming. Because the bezel 630 is offset from a purely vertical direction (in some embodiments, this offset is set to approximately 25 degrees to facilitate easy user interaction with the touchscreen functionality of the transparent screen 640), direction 650 can be pointed upwards from horizontal to an offset angle 651. Assuming that device 600 will typically be mounted on a surface at approximately the same height as or higher than the user who will be sitting or lying down (e.g., a table, counter, or bedside table), it may be advantageous to aim the receiving beam of radar subsystem 120 in a horizontal or near-horizontal direction (e.g., between -5° and 5° from the horizontal). Therefore, vertical beam aiming can be used to compensate for the offset angle 651 of the portion of device 600 where radar subsystem 120 is located.

[0107] Figure 7 An exploded view of an embodiment of the BP measurement device 600 is shown. The device 600 may include: a display assembly 601; a display housing 602; a main circuit board 603; a neck assembly 604; a speaker assembly 605; a base plate 606; a mesh network communication interface 607; a top sub-plate 608; a button assembly 609; a radar assembly 610; a microphone assembly 611; a rocker switch bracket 612; a rocker switch plate 613; a rocker switch button 614; a Wi-Fi assembly 615; a power board 616; and a power support assembly 617. The device 600 can illustrate embodiments of how the BP measurement device 105 can be implemented.

[0108] The display assembly 601, display housing 602, neck assembly 604, and base plate 606 can collectively form a housing that accommodates all the remaining components of the device 600. The display assembly 601 may include an electronic display, which may be a touchscreen, to present information to a user. Therefore, the display assembly 601 may include a display screen, which may include a display metal plate that can serve as a ground plane. The display assembly 601 may include a transparent portion away from the metal plate, which allows various sensors to have a field of view in the general direction in which the display assembly 601 is oriented. The display assembly 601 may include an outer surface made of glass or transparent plastic, which serves as part of the housing of the device 600.

[0109] The display housing 602 can be made of plastic or other rigid or semi-rigid materials that serve as the housing for the display assembly 601. Various components (such as the main circuit board 603; the mesh network communication interface 607; the top daughter board 608; the button assembly 609; the radar assembly 610; and the microphone assembly 611) can be mounted on the display housing 602. The mesh network communication interface 607; the top daughter board 608; the radar assembly 610; and the microphone assembly 611 can be connected to the main circuit board 603 using a flat cable assembly. Adhesive can be used to attach the display housing to the display assembly 601.

[0110] The mesh network communication interface 607 may include one or more antennas and can enable communication with a mesh network (such as a Thread-based mesh network). The Wi-Fi assembly 615 may be located at a distance from the mesh network communication interface 607 to reduce the possibility of interference. The Wi-Fi assembly 615 can enable communication with Wi-Fi-based networks.

[0111] The radar assembly 610 may include radar subsystem 120 or radar subsystem 205, which may be positioned such that its RF transmitter and RF receiver are remote from the metal plate of the display assembly 601 and located at a significant distance from the mesh network communication interface 607 and the Wi-Fi assembly 615. These three components may be arranged in an approximately triangular configuration to increase the distance between components and reduce interference. For example, in device 600, a distance of at least 74 mm may be maintained between the Wi-Fi assembly 615 and the radar assembly 610. A distance of at least 98 mm may be maintained between the mesh network communication interface 607 and the radar assembly 610. Additionally, it is desirable that the distance between the radar assembly 610 and the speaker 618 minimizes the impact of vibrations generated by the speaker 618 on the radar assembly 610. For example, in device 600, a distance of at least 79 mm may be maintained between the radar assembly 610 and the speaker 618. Additionally, it is expected that the distance between the microphone and the radar assembly 610 will minimize any potential interference from the microphone to the received radar signal. The top sub-plate 608 may include multiple microphones. For example, the nearest microphone on the top sub-plate 608 may maintain a distance of at least 12 mm from the radar assembly 610.

[0112] Other components may also be present. A third microphone assembly, namely microphone assembly 611, may be present, which may face rearward. Microphone assembly 611 may work in conjunction with the microphone of top sub-board 608 to isolate spoken commands from background noise. Power board 616 may convert power received from AC power supply to DC to power the components of device 600. Power board 616 may be mounted within device 600 using power bracket assembly 617. Rocker switch bracket 612, rocker switch plate 613, and rocker switch button 614 may collectively be used to receive user input, such as up / down input. For example, such input may be used to adjust the volume of sound output through speaker 618. As another user input, button assembly 609 may include a toggle button that can be actuated by the user. Such user input may be used to activate and deactivate all microphones, such as when the user desires privacy and / or does not want device 600 to respond to voice commands.

[0113] Figure 8 An embodiment 800 of a user measuring their blood pressure (BP) using a distributed BP measurement system is illustrated. As shown, the distributed BP measurement system may include a BP measurement device 600 and a remote sensing device 822. The BP measurement device 600 (which may represent an embodiment of BP measurement device 105) may be fixed to a surface such as a table 830. The remote sensing device 822 (which may represent an embodiment of remote sensing device 160) may be worn by the user 820 at or near a limb 826 (such as a wrist, finger, ear, toe, ankle, etc.) or otherwise in contact with the user. As further described above, the remote sensing device 822 may include a suite of sensors and / or sensor subsystems, such as an optical subsystem 172, configured to detect and collect vital sign data from the user 820, such as PPG data from the limb 826.

[0114] The BP measuring device 600 and the remote sensing device 822 can communicate with each other via one or more wired or wireless communication protocols. For example, user 820 can pair with remote sensing device 822 via Bluetooth® or a mesh network connection such as Thread®. Alternatively, the BP measuring device 600 and remote sensing device 822 can communicate via a LAN such as a Wi-Fi network. In some embodiments, the BP measuring device 600 and / or remote sensing device 822 perform an authentication process before initiating communication with each other. For example, after detecting the presence of the BP measuring device 600, the remote sensing device 822 can request authentication from a cloud-based server system such as a cloud-based server system 190. The authentication request may include credentials for the BP measuring device 600 and / or user account credentials for user 820. Based on the credentials for the BP measuring device 600, the cloud-based server system 190 can determine whether one or more preferences or permissions associated with user 820's user account allow the transmission of vital signs data between the remote sensing device 822 and the BP measuring device 600. After authenticating the BP measurement device 600 according to one or more preferences associated with the user account, the BP measurement device 600 and / or the remote sensing device 822 can continue to initiate the transmission and sharing of vital sign data between each other.

[0115] Alternatively, the BP measurement device 600 may receive credentials from the remote sensing device 822. Using the credentials from the remote sensing device 822, the BP measurement device 600 may further identify the user account associated with the remote sensing device 822 and / or verify whether the user account is associated with the BP measurement device 600. Based on the identified and / or verified user account, the BP measurement device 600 may determine whether the user 820 consents to the measurement of their BP and / or the collection of other health and vital signs data. After determining the user 820's BP and / or the collection of other health and vital signs data, the BP measurement device may store the data in association with the user account (e.g., on the BP measurement device 600 and / or on the cloud-based server system 190).

[0116] After determining that user 820 wishes to measure their blood pressure (BP), BP measuring device 600 and / or remote sensing device 822 may (e.g., via an electronic display or speaker) provide user 820 with one or more instructions. For example, user 820 may be instructed to sit in a relaxed posture with their legs and arms uncrossed. As another example, user 820 may be instructed to ensure that the distance 802 between BP measuring device 600 and its aortic valve 824 meets predefined threshold distance and / or angle criteria, such as minimum and / or maximum distances. In some embodiments, the predefined distance and / or angle criteria are based on the radar sensor capabilities of BP measuring device 600, as described above. In yet another example, user 820 may be instructed to ensure that remote sensing device 822 is in firm contact with user 820's skin, located on limb 826 at a predefined location, and / or at a predefined distance from aortic valve 824.

[0117] The BP measurement device 600 and / or the remote sensing device 822 can use data from one or more sensors to verify whether the user 820's environment, state, and / or location meet one or more predefined criteria before continuing to measure the user 820's BP. For example, radar-based object and / or motion detection can be used to determine whether the user 820 is within the range of the radar subsystem, whether the detected coarse motion associated with the user 820 is less than a predefined threshold, and whether there are no other living beings near the user 820. As another example, IMU data from the remote sensing device 822 can be used to detect the relative location of limbs 826. In yet another example, vital sign data (such as HR and / or RR data) obtained from the remote sensing device 822 can be used to determine whether the user 820 is in a relaxed state by determining whether the vital sign data is within a threshold deviation of a baseline vital sign measurement previously obtained for the user 820.

[0118] Based on the determination that one or more predefined criteria are not met, the BP measurement device 600 and / or the remote sensing device 822 can provide additional instructions to the user 820 to resolve the failure condition. For example, the user 820 can be instructed to move closer to the BP measurement device 600. As another example, the user 820 can be instructed to perform controlled breathing exercises until (e.g., based on subsequent HR and / or RR measurements) it is determined that they are at rest.

[0119] As further described above, before initiating BP measurement, the BP measurement device 600 and the remote sensing device 822 can synchronize their respective clocks to ensure accurate BP measurement. Alternatively, the BP measurement device 600 can adjust the timestamps associated with either set of data based on a determined time difference (e.g., drift) between the clocks of the BP measurement device 600 and the remote sensing device 822. Once synchronized, the BP measurement device 600 can begin collecting and / or analyzing radar data from its radar subsystem while simultaneously receiving vital signs data (e.g., PPG data) from the remote sensing device 822.

[0120] Once the BP measurement process is initiated, the BP measurement device 600 can begin analyzing the collected and received data. The BP measurement device 600 can continuously collect and analyze data until a predefined accuracy or confidence level is determined for the BP measurement. Alternatively, the BP measurement device 600 can collect and store data for a predefined time period before batch processing the collected data to determine the BP of user 820. For example, based on the amount of data required to generate a BP determination with accuracy or confidence level that meets predefined threshold criteria, the BP measurement device 600 can collect data for 15 seconds, 30 seconds, 1 minute, or similar suitable time. Based on the data collected by the BP measurement device 600 and the remote sensing device 822, the BP measurement engine (such as BP measurement engine 230 and / or BP measurement engine 310) can continue to determine the BP measurement of user 820.

[0121] After determining the BP measurement of user 820, BP measurement device 600 can output the BP measurement to user 820. For example, BP measurement device 600 can display the BP measurement on its own display and / or cause the display of remote sensing device 822 to display the BP measurement. Alternatively, BP measurement device 600 and / or remote sensing device 822 can store the BP measurement along with previous BP measurements of user 820. BP measurements can be stored locally (e.g., on BP measurement device 600) and / or remotely (e.g., within cloud-based server system 190) in association with user 820's account and / or remote sensing device 822's device credentials.

[0122] The BP measuring device 600 and / or the remote sensing device 822 can continue to make additional determinations about the health of user 820 by analyzing the current BP measurement in the context of the user 820's previous BP measurements and / or analyzing anonymous BP measurement statistics of other users with matching demographics to user 820. For example, based on determining that the current BP measurement is higher or lower than user 820's previous BP measurements, the BP measuring device 600 can determine that user 820 may have high blood pressure or low blood pressure. As another example, by analyzing trends associated with user 820's current and previous BP measurements, the BP measuring device 600 can determine whether user 820's BP is higher or lower at different times of the day. Based on this determination, the BP measuring device 600 and / or the remote sensing device 822 can provide suggestions to user 820 to address the condition or seek further medical advice. Alternatively, the BP measurement device 600 may detect a recent trend in the BP measurements of the user 820, which indicates that the BP calibration curve may need to be updated by acquiring the user 820's BP using a conventional BP measurement device (e.g., a wristband or armband) when the time is close to when subsequent BP measurements are performed by the distributed BP measurement system.

[0123] Although the above describes measuring user 820's BP while seated, other orientations, orientations, and environments are equally suitable for measuring user 820's BP. Figure 9 Another embodiment 900 of a user 820 measuring their blood pressure (BP) using a distributed BP measurement system is shown. As shown, the BP measuring device 600 can be fixed to a surface such as a bedside table 930, while the user 820 lies on a surface (e.g., bed 932) such that the user 820's aortic valve 824 is a distance 902 from the BP measuring device 600. Although the BP measuring device 600 is shown as being adjacent to the foot of the bed 932, other positioning and / or locations of the BP measuring device 600 relative to the user 820 are also possible. For example, the bedside table 930 and the BP measuring device 600 could be located at the head of the bed 932. Since the blanket 935 remains stationary or nearly stationary during BP measurement and allows RF travel through it with little loss, its influence on the BP measurement is negligible.

[0124] Measuring blood pressure (BP) at night when the user is most relaxed may be beneficial for obtaining an accurate baseline BP measurement. Accurate and consistent baseline measurements can improve the accuracy of other BP measurements taken throughout the day and / or aid in subsequent determinations. For example, accurate baseline BP measured at night can improve determinations related to conditions such as hypertension or hypotension. Alternatively, BP measurements obtained during sleep can be combined with other vital signs data (such as heart rate, respiratory rate, and respiratory rate) to make various determinations about the user's health, such as the occurrence of sleep apnea.

[0125] Before measuring user 820's BP at night, BP measuring device 600 and / or remote sensing device 822 may first verify that user 820 has consented to such a measurement. For example, BP measuring device 600 may determine that preferences associated with user 820's account indicate that user 820 has consented to have their BP measured at night, without prompting from user 820. As another example, BP measuring device 600 and / or remote sensing device 822 may display a notification to user 820 before user 820 goes to sleep, requesting user consent to perform a BP measurement. After measuring user 820's BP, BP measuring device 600 and / or remote sensing device 822 may wait until it has been determined that user 820 is awake before presenting the results of the BP measurement. For example, remote sensing device 822 may wait until one or more predefined mobility criteria have been met before displaying a notification to user 820.

[0126] Usable Figures 1 to 9 Systems, devices, and arrangements are used to perform various methods. Figure 10 It shows how to use things like about Figure 1 An embodiment of a distributed BP measurement system 1000 for measuring blood pressure is described in detail. The distributed BP measurement system for performing method 1000 may include system 200. At block 1005, consent to measure a user's blood pressure can be obtained. Block 1005 may include a verbal command from the user requesting blood pressure measurement, or such a command may be entered into the BP measuring device and / or remote sensing device via a touchscreen. This consent may inform the user that their BP will be measured, and the resulting measurement may be stored in association with the user's user account. For the first BP measurement, the user may need to review and agree to a detailed end-user agreement. Method 1000 can only proceed if the user provides consent. Furthermore, since method 1000 requires the user to remain in a specific physical location, consent can be inferred from the user adopting that physical location and remaining stationary in that location to allow BP measurement.

[0127] Method 1000 may optionally include outputting instructions using synthesized speech, via messages presented on a display of the BP measuring device, or both, instructing the user to be in a specific physical position. Such positioning may involve the user's chest being at a set distance from the radar sensor of the BP measuring device. For example, the user may be instructed to sit or lie down at a distance of approximately 1 to 4 feet from the radar sensor. Additional or alternative instructions may instruct the user to ensure that the optical sensor of the remote sensing device is in firm contact with the user's skin. For example, the user may be instructed to tighten the strap of the remote sensing device worn on the wrist or arm. Additionally or alternatively, method 1000 may include synchronizing the clocks associated with the BP measuring device and the remote sensing device to a common time reference, as further described above.

[0128] At box 1010, an RF signal can be transmitted into the environment by a BP measurement device such as radar subsystem 205. The RF signal can be from an FMCW radar, as per [reference needed]. Figure 4 Detailed description. The reflection of the transmitted RF signal can be received at box 1015. After receiving the reflected RF signal, preliminary processing can be performed on it. For example, the timestamp associated with the reflected RF signal can be adjusted to reflect processing delays. As another example, the reflected RF signal can be analyzed to obtain frequency measurements of range zones, as detailed with respect to radar processing module 210. Figure 2 Find further details about the processing of the received RF signals.

[0129] At box 1020, radar data within a first distance range can be analyzed by a BP measurement device. This first distance range may correspond to a distance zone where the user's aortic valve is located. Since the aortic valve moves a significant distance with each heartbeat compared to the blood vessel, a distance zone containing the highest amplitude-frequency component corresponding to a resting heart rate (e.g., between 40 BPM and 150 BPM) can be selected. Based on motion detected within the first distance range, a first pulse pressure waveform can be identified and stored. In some embodiments, box 1020 involves applying a trained machine learning model, such as a trained neural network, to the radar data to determine the first distance range and / or detect the first pulse pressure waveform.

[0130] At box 1025, vital sign data measured by a mobile device can be received. The mobile device can be a remote sensing device, such as... Figure 1 As described above. For example, the mobile device may include an optical subsystem, such as optical subsystem 172, configured to measure vital sign data such as PPG data. Vital sign data can be measured at a user's limbs (such as wrists, fingers, feet, ankles, or arms) via the mobile device.

[0131] At block 1030, vital sign data can be analyzed to identify a second pulse pressure waveform. For example, a BP measurement device can apply one or more signal processing algorithms to PPG data, such as light absorption waveforms, to identify a second pulse pressure waveform at the user's limb. In some embodiments, vital sign data is preprocessed by a mobile device to identify the second pulse pressure waveform. In such instances, block 1030 may include extracting the pulse pressure waveform from vital sign data received from the mobile device. Before identifying the second pulse pressure waveform, the vital sign data may be time-adjusted to account for delays in the collection, processing, and / or transmission of the vital sign data. Alternatively, such time adjustment may be performed on the second pulse pressure waveform after identification. In some embodiments, block 1030 relates to applying a trained machine learning model, such as a trained neural network, to the vital sign data to identify the second pulse pressure waveform.

[0132] In boxes 1020 and 1030, in addition to analyzing radar data and vital sign data to identify the first pulse pressure waveform at or near the user's aortic valve and the second pulse pressure waveform at the user's limb, the user's HR, RR and / or DPWA can also be measured based on the first pulse pressure waveform, the second pulse pressure waveform or both.

[0133] At box 1035, the first pulse pressure waveform and the second pulse pressure waveform can be used to determine the PTT between the aortic valve and the limb. For example, the amount of time elapsed from the detection of the first pulse wave at the aortic valve (e.g., from the first pulse pressure waveform) to the detection of the first pulse wave at the limb (e.g., from the second pulse pressure waveform) can be determined. Alternatively or additionally, the phase difference between the first and second pulse pressure waveforms can be calculated, from which the PTT can be determined.

[0134] At box 1040, PPT (possibly along with DPWA, RR, and / or HR) can be used to determine the user's BP (systolic and diastolic blood pressure). In some embodiments, a lookup table or algorithm is used that takes PPT, DPWA, RR, and / or HR as input and outputs BP. In other embodiments, a trained machine learning model can take PPT, DPWA, RR, and / or HR as input and output BP values. At box 1050, an indication of the determined blood pressure is output. The indication of the determined BP may be output via synthesized speech, via a display of the BP measuring device and / or mobile device, and / or output to a cloud-based server system (e.g., for storage or for access by the user from another computerized device).

[0135] Figure 11 It shows how to use things like about Figure 1 Detailed embodiments of a method 1100 for measuring BP using a distributed BP measurement system. The distributed BP measurement system for performing method 1100 may include... Figure 3 System 300. At box 1105, consent to measure the user's blood pressure can be obtained. Box 1105 may include a verbal command from the user requesting a blood pressure measurement, or such a command may be entered into the BP measuring device or remote sensing device via a touchscreen. This consent may inform the user that their BP will be measured, and the resulting measurement may be stored in association with the user's user account. For the first BP measurement, the user may need to review and agree to a detailed end-user agreement. Method 1100 can only proceed if the user provides consent. Furthermore, since method 1100 requires the user to remain in a specific physical location, consent can be inferred from the user adopting that physical location and remaining stationary in that location to allow the BP measurement to be performed.

[0136] Method 1100 may optionally include outputting instructions using synthesized speech, via messages presented on a display of the BP measuring device, or both, instructing the user to be in a specific physical position. Such positioning may involve the user's chest being at a set distance from the radar sensor of the BP measuring device. For example, the user may be instructed to sit or lie down at a distance of approximately 1 to 4 feet from the radar sensor. Additional or alternative instructions may instruct the user to ensure that the optical sensor of the remote sensing device is in firm contact with the user's skin. For example, the user may be instructed to tighten the strap of the remote sensing device worn on the wrist or arm. Additionally or alternatively, method 1100 may include synchronizing the clocks associated with the BP measuring device and the remote sensing device to a common time reference, as further described above.

[0137] At box 1110, an RF signal can be emitted into the environment by a BP measurement device such as radar subsystem 205. The RF signal can be from an FMCW radar, as per [reference needed]. Figure 4 Detailed description. The reflected RF signal can be received at box 1115. At box 1120, initial processing can be performed on the received RF signal to obtain frequency measurements of the range zone and / or adjust various processing delays, as detailed regarding radar processing module 210. (Details regarding...) Figure 2 Find further details about the processing of the received RF signals.

[0138] At box 1125, vital sign data measured by a mobile device can be received. The mobile device can be a remote sensing device, such as... Figure 1As described above. For example, the mobile device may include an optical subsystem, such as optical subsystem 172, configured to measure vital sign data such as PPG data. Alternatively or additionally, the vital sign data may include pulse pressure waveform data recognizable by the mobile device. Vital sign data can be measured at a user's limb (such as wrist, finger, foot, ankle, or arm) via the mobile device. In some embodiments, after receiving the vital sign data, the data is preprocessed to account for collection and / or processing delays, as detailed with respect to the remote sensor module 225. [Further details may be needed regarding...] Figure 2 Find further details about the processing of the received vital signs data.

[0139] At box 1130, radar data and vital sign data can be analyzed using a machine learning model. The machine learning model can be trained to take radar data from the radar subsystem and vital sign data from the optical subsystem as input and output the user's blood pressure (systolic and diastolic). Therefore, the trained machine learning model directly analyzes radar data and vital sign data to determine BP. In some embodiments, the trained machine learning model is further trained to use the user's HR, RR, and / or DPWA as input to determine BP. Alternatively or additionally, the trained machine learning model can automatically detect such features from radar data and / or vital sign data, thereby reducing additional processing of the radar data and / or vital sign data before executing the trained machine learning model. The machine learning model can be a trained neural network. In some embodiments, additional layers can be added or modified at the BP measurement device to take into account information about... Figure 12 Detailed calibration curves.

[0140] At box 1135, the determined blood pressure indication is output. The determined BP indication may be output via synthesized speech, via the display of the BP measuring device and / or mobile device, and / or output to a cloud-based server system (e.g., for storage or for access by the user from another computerized device).

[0141] To accurately determine BP using PTT, HR, RR, and / or DPWA, a calibration process can be performed for the individual user. The calibration process can take into account the user's specific physical location and / or user-specific characteristics when performing BP measurements using a distributed BP measurement system. Figure 12An embodiment of method 1200 for calibrating a distributed BP measurement system is illustrated. In method 1200, prior to determining accurate BP using method 1000 or 1100, at block 1205, the user can be instructed to determine their BP using a separate blood pressure measuring device (expected to be accurate). The separate blood pressure device can be a mercury gravimeter, a liquid-free manometer, or an electronic device. Such devices can measure blood pressure using a cuff placed around the arm or wrist, or using a sensor placed on the finger. In other embodiments, a combination of electrocardiogram (ECG) and a finger or wrist PPG sensor can be used to determine PTT. At block 1210, the determined BP and / or PTT measurements can be input to the BP measuring device or to a cloud-based server system communicating with the BP measuring device via a computerized device (e.g., a smartphone).

[0142] Before or after box 1205 or box 1210, the user can measure their BP according to method 1000 or method 1100. Ideally, two BP measurements are performed within a short time interval between each other. For example, the user can potentially perform one BP measurement while sitting or lying down and immediately perform another BP measurement. Regardless of the physical positioning used by the user, the user can be instructed to continue using the same positioning for future BP measurements taken by the BP measuring device.

[0143] At box 1215, the BP measured by the BP measuring device can be compared with the BP measurement received from box 1210. In some embodiments, the user is required or requested to perform multiple rounds of BP measurements using both the BP measuring device and a separate BP measuring device to allow for more comparisons. One or more comparisons performed at box 1215 are used to create a calibration curve at box 1220. In some embodiments, blood pressure measurements and use via a separate blood pressure device... Figure 1 The corresponding BP measurement of the BP measurement device is used to create a training dataset, which can be used to optimize the machine learning model used in systems 200 and 300 or methods 1000 and 1100.

[0144] In some embodiments, the calibration curve may be a simple offset value, an offset algorithm, or a created offset lookup. In other embodiments, a calibration model may be created using methods such as shot or few-trial learning, maximum likelihood estimation, or least squares estimation.

[0145] The created calibration curves or calibration training datasets can be used, for example, in Method 1000 or Method 1100, to adjust BP measurements performed using a distributed BP measurement system. In Method 1000, the calibration curves or calibration training datasets can be used as part of box 1040 to adjust the user's BP measurements. Referring to system 200, this calibration can be performed by the BP determination engine 234. In Method 1100, the calibration training datasets can be used to create or adjust the layers of the machine learning model used at box 1130. Referring to system 300, the analysis engine 311 can be modified based on the calibration curves.

[0146] It should be noted that the methods, systems, and apparatus discussed above are merely illustrative. It must be emphasized that various embodiments may omit, substitute, or add various procedures or components as needed. For example, it should be understood that in alternative embodiments, the methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, in various other embodiments, features described with respect to certain embodiments may be combined. Different aspects and elements of the embodiments may be combined in a similar manner. Moreover, it should be emphasized that technology is constantly evolving, and therefore many elements are illustrative and should not be construed as limiting the scope of the invention.

[0147] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, those skilled in the art will understand that embodiments can be practiced without these specific details. For example, well-known processes, structures, and techniques have been shown without unnecessary detail to avoid obscuring the embodiments. This description provides only exemplary embodiments and is not intended to limit the scope, applicability, or configuration of the invention. Rather, the foregoing description of the embodiments will provide those skilled in the art with an enabling description for implementing embodiments of the invention. Various changes can be made to the function and arrangement of the elements without departing from the spirit and scope of the invention.

[0148] Furthermore, it is worth noting that embodiments can be described as processes depicted in flowcharts or block diagrams. Although each flowchart or block diagram can describe operations as a sequential process, many operations can be performed in parallel or simultaneously. Moreover, the order of operations can be rearranged. Processes may have additional steps not included in the diagrams.

[0149] Several embodiments have been described, and those skilled in the art will recognize that various modifications, alternative constructions, and equivalents can be used without departing from the spirit of the invention. For example, the foregoing elements may simply be components of a larger system, where other rules may take precedence over or otherwise modify the application of the invention. Furthermore, steps may be taken before, during, or after considering the foregoing elements. Therefore, the foregoing description should not be considered as limiting the scope of the invention.

Claims

1. A blood pressure measurement system, comprising: A mobile device that can be worn by a user and configured to collect vital sign data from the user's limbs; as well as A fixed device communicating with the mobile device, the fixed device comprising: An RF transmitter that transmits RF signals; An RF receiver that receives a reflected RF signal based on the reflection of a transmitted RF signal; and One or more processors, said one or more processors being configured to: Analyze the RF reflected signal at a first distance range to identify the first pulse pressure waveform at the user's aortic valve; Analyze the vital signs data to identify the second pulse pressure waveform at the user's limb; The pulse pressure waveform and the second pulse pressure waveform are used to determine the pulse conduction time (PTT) from the user's aortic valve to the user's limb; The user's blood pressure is determined based on the determined PTT; and Output the determined blood pressure reading.

2. The blood pressure measurement system of claim 1, wherein the vital signs data includes photoplethysmography (PPG) data, and the mobile device includes an optical sensor that measures the PPG data at the user's limb.

3. The blood pressure measurement system according to claim 1, wherein the fixing device further comprises: A microphone, a loudspeaker, and an electronic display, wherein the indication of the determined blood pressure is output via the electronic display.

4. The blood pressure measurement system according to claim 1, wherein the mobile device is a smartwatch, and the user's limb is the user's wrist.

5. The blood pressure measurement system according to claim 4, wherein the smartwatch further comprises: A microphone, a loudspeaker, and an electronic display, wherein the indication of the determined blood pressure is output via the electronic display.

6. The blood pressure measurement system of claim 1, wherein the RF reflected signal is associated with a first set of timestamps generated by a first clock of the stationary device, the vital signs data is associated with a second set of timestamps generated by a second clock of the mobile device, and the one or more processors are further configured to: Synchronize the first set of timestamps with the second set of timestamps; and The first set of timestamps, the second set of timestamps, or both are adjusted based on the processing delay difference between the fixed device and the mobile device.

7. The blood pressure measurement system of claim 1, wherein the one or more processors are further configured to: Receive external blood pressure measurements using a blood pressure device that is separate from the fixed device and the mobile device; Compare the external blood pressure measurement with the determined blood pressure measurement; and Create calibration curves to modify future blood pressure measurements.

8. The blood pressure measurement system of claim 1, wherein the one or more processors are further configured to use the RF reflected signal and the vital signs data as input to a machine learning model trained to derive the user's blood pressure based on the PTT.

9. A method for measuring blood pressure, comprising: Radio frequency (RF) signals are emitted by radar sensors mounted on fixed devices; The RF signal is received by the radar sensor of the fixed device based on the reflection of the emitted RF signal; The processing system of the fixation device analyzes the RF reflected signal at a first distance range to identify the first pulse pressure waveform at the user's aortic valve; The processing system of the fixed device receives vital sign data measured by the mobile device at the user's limb; The processing system of the fixation device analyzes the vital signs data to identify the second pulse pressure waveform at the user's limb; The processing system of the fixation device uses the first pulse pressure waveform and the second pulse pressure waveform to determine the pulse conduction time (PTT) of the pulse pressure wave from the user's aortic valve to the user's limb; The processing system of the fixed device determines the user's blood pressure based on the determined PTT; as well as The processing system of the fixed device outputs a determined blood pressure indication.

10. The method for measuring blood pressure according to claim 9, wherein the vital signs data includes photoplethysmography (PPG) data, and the method further comprises: The PPG data at the user's limb is measured by the optical sensor of the mobile device.

11. The method for measuring blood pressure according to claim 9, wherein the RF reflected signal is associated with a first set of timestamps generated by a first clock of the fixed device, the vital signs data are associated with a second set of timestamps generated by a second clock of the mobile device, and the method further comprises: Synchronize the first set of timestamps with the second set of timestamps.

12. The method for measuring blood pressure according to claim 11, further comprising: The first set of timestamps, the second set of timestamps, or both are adjusted based on the processing delay difference between the fixed device and the mobile device.

13. The method for measuring blood pressure according to claim 9, further comprising: The phase difference between the first pulse pressure waveform and the second pulse pressure waveform is determined, wherein the PTT is determined using the phase difference.

14. The method for measuring blood pressure according to claim 9, wherein the user's limb is the user's wrist.

15. The method for measuring blood pressure according to claim 9, further comprising determining a heart rate based on analyzing the RF reflected signal, the second pulse pressure waveform, or both, wherein determining the user's blood pressure is further based on the heart rate.

16. The method for measuring blood pressure according to claim 9, further comprising determining a derived pulse waveform amplitude (DPWA) based on analysis of the RF reflected signal, wherein determining the user's blood pressure is further based on the DPWA.

17. The method for measuring blood pressure according to claim 9, further comprising determining a respiratory rate based on analysis of the RF reflected signal, the second pulse pressure waveform, or both, wherein determining the user's blood pressure is further based on the respiratory rate.

18. The method for measuring blood pressure according to claim 9, wherein analyzing the RF reflected signal at the first distance range comprises analyzing data from the RF reflected signal using a trained machine learning model.

19. The method for measuring blood pressure according to claim 9, further comprising: The processing system of the fixed device receives external blood pressure measurements using a blood pressure device that is separate from the fixed device and the mobile device; The processing system compares the external blood pressure measurement with the determined blood pressure measurement; and The processing system creates calibration curves to modify future blood pressure measurements.

20. A fixed blood pressure measuring device, comprising: Radar subsystem, the radar subsystem comprising: An RF transmitter that transmits RF signals; An RF receiver that receives a reflected RF signal based on the reflection of a transmitted RF signal; and A processing system, comprising one or more processors communicating with the radar subsystem, wherein the processing system is configured to: Analyze the RF reflected signal at a first distance range to identify the first pulse pressure waveform at the user's aortic valve; Receive vital sign data measured by the mobile device at the user's limb; Analyze the vital signs data to identify the second pulse pressure waveform at the user's limb; The pulse pressure waveform and the second pulse pressure waveform are used to determine the pulse conduction time (PTT) from the user's aortic valve to the user's limb; The user's blood pressure is determined based on the determined PTT; and Output the determined blood pressure reading.

Images