Apparatus and method for 24-hour ambulatory blood pressure monitoring with compensation based on posture and / or activity detection

Abstract

An apparatus for monitoring a person's health condition, the apparatus comprising: one or more biometric sensors for periodically measuring biometric data of the person; one or more activity sensors for periodically measuring the person's activity; and a circuit operatively coupled to the one or more biometric sensors and the one or more activity sensors, the circuit comprising an artificial intelligence (AI) engine configured to use a trained AI model to analyze the person's health condition based on measurement data collected from the one or more biometric sensors and the one or more activity sensors.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Patent Application No. 63 / 408,887, filed September 22, 2022, which is incorporated herein by reference in its entirety.

[0002] The present disclosure relates generally to blood pressure monitoring, and more particularly to 24-hour ambulatory blood pressure monitoring with compensation based on posture and / or activity detection. [Background technology]

[0003] Blood pressure is closely related to a person's health. High blood pressure (also called "hypertension") or low blood pressure (also called "hypotension") can lead to a variety of health problems. However, a single blood pressure measurement taken in a doctor's office or clinical setting may not be sufficient to confirm hypertension or hypotension, and 24-hour ambulatory blood pressure (24-hour ABP) monitoring is often required. In this monitoring, a person's or patient's blood pressure is monitored periodically (e.g., once every 20 to 30 minutes during the day and once every hour at night) or continuously over at least a 24-hour period, and heart rate is also monitored. Summary of the Invention

[0004] According to one aspect of the present disclosure, there is provided an apparatus for monitoring a health condition of a person, the apparatus comprising: one or more biometric sensors for periodically measuring biometric data of the person; one or more activity sensors for periodically measuring activities of the person; and circuitry operatively coupled to the one or more biometric sensors and the one or more activity sensors, the circuitry including an artificial intelligence (AI) engine configured to use a trained AI model to analyze the health condition of the person based on measurement data collected from the one or more biometric sensors and the one or more activity sensors.

[0005] In some embodiments, the one or more biometric sensors and the one or more activity sensors are configured to periodically perform measurement sets to periodically measure the person's biometric data and the person's activity, and the one or more activity sensors are configured, when performing each measurement set, to measure the person's activity at least two of before, during, and after the one or more biometric sensors measure the person's biometric data.

[0006] In some embodiments, the device further comprises one or more stickable pads for sticking to a person's body, each of the one or more stickable pads including at least one of the one or more biometric sensors and the one or more activity sensors.

[0007] In some embodiments, using the trained AI model to analyze the person's health condition includes determining whether any of the one or more biometric sensors and the one or more activity sensors are erroneous based on measurement data collected by the one or more biometric sensors and the one or more activity sensors, and if the one or more biometric sensors and the one or more activity sensors are not erroneous, analyzing the person's health condition based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors.

[0008] In some embodiments, the activity of the person includes at least one of a movement of the person and a posture of the person.

[0009] In some embodiments, the one or more biometric sensors include at least one of one or more blood pressure sensors and one or more heart rate sensors, and the biometric data of the person includes blood pressure data of the person and heart rate data of the person.

[0010] In some embodiments, the one or more biometric sensors further include one or more temperature sensors for measuring the person's body temperature, one or more oxygen saturation sensors for measuring the person's oxygen level, and at least one of one or more vibration sensors or one or more microphones for measuring sounds from the person's body.

[0011] According to one aspect of the present disclosure, there is provided a computerized method for monitoring a person's health status, the method including: periodically measuring biometric data of the person using one or more biometric sensors; periodically measuring the person's activity using one or more activity sensors; and using a trained AI model to analyze the person's health status based on the measurement data collected from the one or more biometric sensors and the one or more activity sensors. Includes:

[0012] In some embodiments, periodically measuring the person's biometric data and periodically measuring the person's activity includes periodically performing a set of measurements using one or more biometric sensors and one or more activity sensors to periodically measure the person's biometric data and the person's activity, respectively, and, when performing each set of measurements, measuring the person's activity using the one or more activity sensors at least two of before, during, and after the one or more biometric sensors measure the person's biometric data.

[0013] In some embodiments, the computerized method further includes attaching one or more stickable pads to the person's body, each of the one or more stickable pads including at least one of the one or more biometric sensors and the one or more activity sensors.

[0014] In some embodiments, using the trained AI model to analyze the person's health condition includes determining whether any of the one or more biometric sensors and the one or more activity sensors are erroneous based on measurement data collected by the one or more biometric sensors and the one or more activity sensors, and if the one or more biometric sensors and the one or more activity sensors are not erroneous, analyzing the person's health condition based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors.

[0015] In some embodiments, the activity of the person includes at least one of a movement of the person and a posture of the person.

[0016] In some embodiments, the one or more biometric sensors include at least one of one or more blood pressure sensors and one or more heart rate sensors, and the biometric data of the person includes blood pressure data of the person and heart rate data of the person.

[0017] In some embodiments, the one or more biometric sensors further include one or more temperature sensors for measuring the person's body temperature, one or more oxygen saturation sensors for measuring the person's oxygen level, and at least one of one or more vibration sensors or one or more microphones for measuring sounds from the person's body.

[0018] According to one aspect of the present disclosure, one or more non-transitory computer-readable storage devices are provided that include computer-executable instructions that, when executed, cause one or more circuits to perform actions including periodically measuring biometric data of a person using one or more biometric sensors, periodically measuring activity of the person using one or more activity sensors, and using a trained AI model to analyze a health condition of the person based on measurement data collected from the one or more biometric sensors and the one or more activity sensors.

[0019] In some embodiments, periodically measuring the person's biometric data and periodically measuring the person's activity includes periodically performing a set of measurements using one or more biometric sensors and one or more activity sensors to periodically measure the person's biometric data and the person's activity, respectively, and, when performing each set of measurements, measuring the person's activity using the one or more activity sensors at least two of before, during, and after the one or more biometric sensors measure the person's biometric data.

[0020] In some embodiments, the action further includes attaching one or more stickable pads to the person's body, each of the one or more stickable pads including at least one of one or more biometric sensors and one or more activity sensors.

[0021] In some embodiments, using the trained AI model to analyze the person's health condition includes determining whether any of the one or more biometric sensors and the one or more activity sensors are erroneous based on measurement data collected by the one or more biometric sensors and the one or more activity sensors, and if the one or more biometric sensors and the one or more activity sensors are not erroneous, analyzing the person's health condition based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors.

[0022] In some embodiments, the activity of the person includes at least one of a movement of the person and a posture of the person.

[0023] In some embodiments, the one or more biometric sensors include at least one of one or more blood pressure sensors and one or more heart rate sensors, and the biometric data of the person includes blood pressure data of the person and heart rate data of the person.

[0024] In some embodiments, the one or more biometric sensors further include one or more temperature sensors for measuring the person's body temperature, one or more oxygen saturation sensors for measuring the person's oxygen level, and at least one of one or more vibration sensors or one or more microphones for measuring sounds from the person's body. [Brief explanation of the drawings]

[0025] For a more complete understanding of the present disclosure, reference is made to the following description and accompanying drawings.

[0026] [Figure 1] FIG. 1 is a schematic diagram of a health monitoring and analysis system according to some embodiments of the present disclosure. [Figure 2] FIG. 2 is a schematic diagram illustrating a simplified hardware structure of a client computing device and a server computer of the health monitoring and analysis system shown in FIG. 1, according to some embodiments of the present disclosure. [Figure 3] FIG. 2 is a schematic diagram illustrating a simplified software architecture of a client computing device and a server computer of the health monitoring and analysis system shown in FIG. 1 , according to some embodiments of the present disclosure. [Figure 4] FIG. 2 is a schematic diagram illustrating a simplified hardware structure of a health measurement device of the health monitoring and analysis system shown in FIG. 1, according to some embodiments of the present disclosure. [Figure 5]FIG. 2 is a schematic diagram illustrating the functional structure of the health monitoring and analysis system shown in FIG. 1, according to some embodiments of the present disclosure. [Figure 6] 2 is a flowchart illustrating steps of a blood pressure monitoring and analysis procedure performed by the health monitoring and analysis system shown in FIG. 1 , according to some embodiments of the present disclosure. [Figure 7] FIG. 1 is a schematic diagram of a health monitoring and analysis system according to some other embodiments of the present disclosure. [Figure 8] FIG. 10 is a schematic diagram of a health monitoring and analysis system according to some other embodiments of the present disclosure. [Figure 9] 2 is a schematic diagram illustrating a health measurement device of the health monitoring and analysis system shown in FIG. 1, according to some embodiments of the present disclosure. [Figure 10] 10 is a schematic cross-sectional view of a pad of the health measurement device shown in FIG. 9, according to some embodiments of the present disclosure. [Figure 11] FIG. 11 is a schematic diagram illustrating a blood pressure sensor coupled to the pad shown in FIG. 10, according to some embodiments of the present disclosure. [Figure 12] 2 is a schematic diagram illustrating a health measurement device of the health monitoring and analysis system shown in FIG. 1, according to some embodiments of the present disclosure. [Figure 13] 2 is a schematic diagram illustrating a health measurement device of the health monitoring and analysis system shown in FIG. 1 according to some further embodiments of the present disclosure. [Figure 14] 2 is a schematic diagram illustrating a health measurement device of the health monitoring and analysis system shown in FIG. 1 according to some further embodiments of the present disclosure. [Figure 15] 2 is a schematic diagram illustrating a health measurement device of the health monitoring and analysis system shown in FIG. 1 according to still other embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0027] FIELD OF THE INVENTION The embodiments disclosed herein relate to blood pressure monitoring, and more particularly to 24-hour ambulatory blood pressure (24-hour ABP) monitoring.

[0028] Generally, a blood pressure measurement (or simply "blood pressure") includes (1) the systolic blood pressure, which is the blood pressure when the heart is beating, and (2) the diastolic blood pressure, which is the blood pressure when the heart is resting between beats. Blood pressure is often given as "(systolic blood pressure measurement)" / "(diastolic blood pressure measurement)." For example, a blood pressure of 120 / 80 millimeters of mercury (mmHg) means that the systolic blood pressure is 120 mmHg and the diastolic blood pressure is 80 mmHg.

[0029] Normal blood pressure values ​​for a healthy person are below 120 mmHg and below 80 mmHg.

[0030] If a person's systolic blood pressure is between 120 mmHg and 129 mmHg and their diastolic blood pressure is less than 80 mmHg, they may have a health condition that puts them at high risk of elevated blood pressure.

[0031] A person may be diagnosed with stage 1 hypertension if their systolic blood pressure is between 130mmHg and 139mmHg or their diastolic blood pressure is between 80mmHg and 89mmHg.

[0032] A person may be diagnosed with stage 2 hypertension if their systolic blood pressure is higher than 140 mmHg or their diastolic blood pressure is higher than 90 mmHg.

[0033] If the systolic blood pressure is higher than 180 mmHg and / or the diastolic blood pressure is higher than 120 mmHg, the person may be diagnosed with hypertensive crisis.

[0034] Stage 1 hypertension, stage 2 hypertension, and hypertensive crisis are often collectively referred to as "hypertension" or "high blood pressure."

[0035] On the other hand, blood pressure that is too low can be diagnosed as "hypotension." This typically includes paroxysmal hypotension and orthostatic hypotension. If a person's resting blood pressure (i.e., blood pressure when the person is at rest) is below 90 / 60 mmHg, the person can be diagnosed with paroxysmal hypotension. If the person's blood pressure drops so that the systolic blood pressure drops by more than 20 mmHg and the diastolic blood pressure drops by more than 10 mmHg within three minutes after standing up from a sitting position, the person can be diagnosed with orthostatic hypotension (also called "postural hypotension").

[0036] As those skilled in the art will appreciate, blood pressure is generally related to a person's posture and activity. Furthermore, a single blood pressure measurement taken in a doctor's office or clinical setting may not be sufficient to confirm hypertension or hypotension. Therefore, 24-hour ambulatory blood pressure (24-hour ABP) monitoring is often used. In this monitoring, a person's or patient's blood pressure is monitored periodically (e.g., every 20-30 minutes during the day and once an hour at night) or continuously over at least a 24-hour period, and heart rate is simultaneously monitored.

[0037] Blood pressure data collected during 24-hour ABP allows for a person's blood pressure profile in a normal, stress-free environment that they might experience in a clinical setting. Such a blood pressure profile may enable accurate blood pressure analysis and diagnosis of blood pressure-related health problems.

[0038] As will be appreciated by those skilled in the art, a person's blood pressure may change or fluctuate depending on that person's daily activities and sleep patterns, and therefore, analysis of 24-hour ABP measurements may need to take into account the person's daily activities and sleep patterns.

[0039] According to one aspect of the present disclosure, a health monitoring and analysis system is disclosed. The health monitoring and analysis system includes a health measurement device that can be attached to a person. The health measurement device includes multiple sensors, such as one or more biometric sensors (one or more blood pressure sensors 202 and / or one or more heart rate sensors 204, oxygen saturation sensors, CO2 saturation sensors, temperature sensors, vibration sensors, other audio sensors, optical sensors, thermal sensors, pressure sensors, etc.) for periodically measuring the person's biometric data (blood pressure, heart rate, respiratory rate, pulse rate, electrocardiogram (ECG), photoplethysmography (PPG), oxygen level, CO2 level, breath sounds, body mass index (BM) / weight / height, etc.), and one or more activity sensors. The health measurement device uses the multiple sensors to collect measurement data of the person's blood pressure, heart rate, posture, and activity, and is in communication with a client computing device and / or a server computer for using an artificial intelligence (AI) engine and trained AI models to analyze the person's health status based on the collected measurement data.

[0040] In some embodiments, the health measurement device provides a user-friendly interface and device settings that allow patients and physicians to operate it with simple instructions. When the health measurement device is carried by or otherwise attached to a person (e.g., a patient), the health measurement device can measure and monitor the person's blood pressure, heart rate, and other information at regular intervals (e.g., once every 20-30 minutes during the day and once every hour at night) over an extended period of time, such as 48 hours. In some embodiments, the frequency and timing of measurements can be easily programmed.

[0041] In some embodiments, the activity sensor may collect posture and activity measurement data during the time intervals that the blood pressure sensor and heart rate sensor are collecting measurement data).

[0042] In some other embodiments, the activity sensor may collect posture and activity measurement data (such as acceleration and angular velocity) before, during, and / or after the time interval during which the blood pressure and heart rate sensors are collecting measurement data. For example, the activity sensor may collect posture and activity measurement data once before, about 10-15 times during, and once after each blood pressure and / or heart rate measurement (thus resulting in about 12-17 sensor data sets for each blood pressure and / or heart rate measurement), which may be used to identify a person's activity (e.g., standing upright, walking, running, resting, sleeping, etc.) and generate a working chart for more accurately analyzing the blood pressure and / or heart rate measurement data.

[0043] In some other embodiments, the activity sensor may continuously collect posture and activity measurement data throughout the entire 24-hour ABP monitoring period (or a longer ABP monitoring period, if desired).

[0044] The measurement data may be stored on the health measurement device, the client computing device, and / or a server computer (e.g., in the person's personal cloud account).

[0045] Thus, the collected measurement data includes the person's blood pressure data, heart rate data, posture data, and activity data throughout the person's daily activities, including sleep. More specifically, the collected measurement data can be categorized as follows: Blood pressure measurement data when a person is active, Heart rate measurement data when a person is active; Blood pressure measurement data when a person is at rest, and Heart rate measurement data when a person is at rest.

[0046] By analyzing the collected measurement data, the health monitoring and analysis system can provide accurate reports of a person's health measurements, such as the person's blood pressure status, heart rate status, posture profile, activity profile (e.g., active or resting), etc.

[0047] By using an AI engine and a trained AI model to analyze a person's health status, the health monitoring and analysis system can accurately identify activity-induced and / or posture-induced fluctuations in a person's blood pressure and / or heart rate. For example, the health monitoring and analysis system can accurately identify that a rise in blood pressure overnight was caused by the person standing up. As another example, the health monitoring and analysis system can accurately identify that high blood pressure during nighttime sleep was caused by the person's snoring. Furthermore, the health monitoring and analysis system can accurately identify that a blood pressure fluctuation was caused by the person's change in posture (e.g., from lying down to standing up).

[0048] By using an AI engine and trained AI models to analyze a person's health status, the health monitoring and analysis system can also identify sensor errors that may cause irregular data samples in the collected blood pressure and / or heart rate measurement data.

[0049] Referring now to FIG. 1, a health monitoring and analysis system according to some embodiments of the present disclosure is illustrated and generally identified by the reference numeral 100 . The health monitoring and analysis system 100 includes a health measurement device 102 that can be attached to a person. The health measurement device 102 communicates wirelessly with the client computing device 104 via any suitable wireless or wired communication technology, such as BLUETOOTH® (BLUETOOTH is a registered trademark of Bluetooth Sig, Inc., Kirkland, Washington, USA), Bluetooth Low Energy (BLE), WI-FI® (WI-FI is a registered trademark of Wi-Fi Alliance, Austin, Texas, USA), Ethernet, Z-Wave, Long Range (LoRa), ZIGBEE® (ZIGBEE is a registered trademark of ZigBee Alliance, San Ramon, California, USA), wireless broadband communication technologies, such as GSM, Code Division Multiple Access (CDMA), Universal Mobile Telecommunications System (UMTS), WiMAX (Global Interoperable Microwave Access), CDMA2000, Long Term Evolution (LTE), 3GPP, 5th Generation New Radio (5G NR), 6th Generation (6G) wireless networks, etc. The client computing devices 104 communicate with one or more server computers 106 via a network 108, either wirelessly or via wired connections.

[0050] In these embodiments, the health measurement device 102 is used to measure and monitor a person's blood pressure, such as for 24-hour ABP monitoring, and to monitor the person's daily activity and sleep patterns. The health measurement device 102 reports measurement data of the person's blood pressure, activity, and sleep patterns to the client computing device 104. The client computing device 104 can analyze the person's health status using the data received from the health measurement device 102 and display the analysis results on a screen. The client computing device 104 can use services provided by the server computer 106 to facilitate the health status analysis and / or store the data and analysis results received from the health measurement device 102 in the server computer 106.

[0051] The client computing device 104 can be a portable or non-portable computing device, such as a smartphone, a tablet, a personal digital assistant (PDA), a laptop computer, a desktop computer, or the like.

[0052] The server computer 106 can be a computing device specially designed for server purposes, or a general-purpose computing device that functions as a server computer and is used by a variety of users.

[0053] Typically, the client computing device 104 and the server computer 106 have similar hardware structures, such as the hardware structure shown in Figure 2. As shown, the computing device 104 / 106 includes a processing structure 122, a control structure 124, one or more non-transitory computer-readable memory or storage devices 126, a network interface 128, an input interface 130, and an output interface 132, which are operatively interconnected by a system bus 138. The computing device 104 / 106 may also include other components 134 coupled to the system bus 138.

[0054] The processing fabric 122 may be one or more single-core or multi-core computing processors, such as an INTEL® microprocessor (INTEL is a registered trademark of Intel Corporation, Santa Clara, Calif., USA), an AMD® microprocessor (AMD is a registered trademark of Advanced Micro Devices, Sunnyvale, Calif., USA), or an ARM® microprocessor (ARM is a registered trademark of Arm Ltd., Cambridge, UK) manufactured under the ARM® architecture by various manufacturers, such as Qualcomm (San Diego, Calif., USA). When the processing fabric 122 includes multiple processors, these processors may cooperate via specialized circuitry or a system bus 138, such as a specialized bus.

[0055] The processing circuitry 122 may also include one or more real-time processors, programmable logic controllers (PLCs), microcontroller units (MCUs), μ-controllers (UCs), specialized / custom processors and / or controllers using, for example, field programmable gate array (FPGA) or application specific integrated circuit (ASIC) technology, etc.

[0056] Generally, each processor of processing structure 122 includes the necessary circuitry, implemented using technologies such as electrical and / or optical hardware components, to execute one or more processes to perform various tasks, depending on the implementation purpose and / or use case. In many embodiments, one or more processes may be implemented as firmware and / or software stored in memory 126. Those skilled in the art will recognize that in these embodiments, one or more processors of processing structure 122 are typically useless without significant firmware and / or software.

[0057] Of course, those skilled in the art will recognize that the processor may be implemented using other technologies, such as analog technology.

[0058] Control structure 124 includes one or more control circuits, such as a graphics controller and an input / output chipset, for coordinating the operation of the various hardware components and modules of computing device 104 / 106.

[0059] Memory 126 includes one or more non-transitory computer-readable storage devices or media accessible by processing structure 122 and control structure 124 for reading and / or storing instructions executed by processing structure 122 and for reading and / or storing data, including input data and data generated by processing structure 122 and control structure 124. Memory 126 can be volatile and / or non-volatile, non-removable or removable memory, such as RAM, ROM, EEPROM, solid-state memory, hard disk, CD, DVD, flash memory, etc. In use, memory 126 is typically divided into multiple portions for different uses. For example, one portion of memory 126 (referred to herein as storage memory) can be used for long-term data storage, such as storing files or databases. Another portion of memory 126 can be used as system memory for storing data during processing (referred to herein as working memory).

[0060] Network interface 128 includes one or more network modules for connecting to other computing devices or networks via network 108 using appropriate wired and / or wireless communication technologies. In some embodiments, parallel ports, serial ports, USB connections, optical connections, etc. may also be used to connect to other computing devices or networks, which are generally considered input / output interfaces for connecting input / output devices.

[0061] Input interface 130 includes one or more input modules for one or more users to input data via, for example, a touchscreen, a touch whiteboard, a touchpad, a keyboard, a computer mouse, a trackball, a microphone, a scanner, a camera, etc. Input interface 130 can be a physically integral part of computing device 104 / 106 (e.g., a touchpad on a laptop computer or a touchscreen on a tablet) or a device that is physically separate but functionally coupled to other components of computing device 104 / 106 (e.g., a computer mouse). Input interface 130 can, in some implementations, be integrated with a display output to form a touchscreen or a touch whiteboard.

[0062] Output interface 132 includes one or more output modules for outputting data to a user. Examples of output modules include a display (monitor, LCD display, LED display, projector, etc.), speakers, a printer, a virtual reality (VR) headset, an augmented reality (AR) goggles, etc. Output interface 132 can be a physically integral part of computing device 104 / 106 (e.g., a display of a laptop computer or tablet) or can be a device that is physically separate from but functionally coupled to other components of computing device 104 / 106 (e.g., a monitor of a desktop computer).

[0063] Computing device 104 / 106 may also include other components 134, such as one or more positioning modules, temperature sensors, barometers, inertial measurement units (IMUs), etc. Examples of positioning modules are one or more Global Navigation Satellite System (GNSS) components (e.g., one or more components for operating with the United States' Global Positioning System (GPS), Russia's GLONASS, the European Union's Galileo positioning system, and / or China's Beidou system).

[0064] The system bus 138 interconnects the various components 122-134, allowing them to send and receive data and control signals to and from each other.

[0065] 3 shows a simplified software structure of computing device 104 or 106. Software structure 160 includes an application layer 162, an operating system 166, a logical input / output (I / O) interface 168, and a logical memory 172. Application layer 162, operating system 166, and logical I / O interface 168 are generally embodied as computer-executable instructions or code in the form of software or firmware programs stored in logical memory 172 that can be executed by processing fabric 122.

[0066] The application layer 162 includes one or more application programs 164 that are executed or performed by the processing fabric 122 to perform various tasks.

[0067] Operating system 166 manages the various hardware components of computing device 104 or 106 via logical I / O interface 168, manages logical memory 172, and manages and supports application programs 164. Operating system 166 is also in communication with other computing devices (not shown) via network 108, allowing application programs 164 to communicate with programs running on other computing devices. As will be appreciated by those skilled in the art, operating system 166 may be any suitable operating system, such as MICROSOFT® WINDOWS® (MICROSOFT and WINDOWS are registered trademarks of Microsoft Corporation, Redmond, Washington, USA), APPLE® OS X, APPLE® iOS (APPLE is a registered trademark of Apple Inc., Cupertino, California, USA), Linux, or ANDROID® (ANDROID is a registered trademark of Google Inc., Mountain View, California, USA). Computing devices 104 or 106 of computer network system 100 may all have the same operating system or may have different operating systems.

[0068] Logical I / O interface 168 includes one or more device drivers 170 for communicating with each input and output interface 130 and 132 to receive data from and send data to each interface 130 and 132. Received data can be sent to application layer 162 for processing by one or more application programs 164. Data generated by application programs 164 can be sent to logical I / O interface 168 for output to various output devices (via output interface 132).

[0069] Logical memory 172 is a logical mapping of physical memory 126 to facilitate access by application program 164. In this embodiment, logical memory 172 typically includes a storage memory area that can be mapped to non-volatile physical memory, such as a hard disk, solid-state disk, or flash drive, for long-term data storage. Logical memory 172 also typically includes a working memory area that can be mapped to typically fast, and in some implementations volatile, physical memory, such as RAM, for application program 164 to temporarily store data during program execution. For example, application program 164 can load data from a storage memory area into the working memory area and store data generated during execution in the working memory area. Application program 164 can also store some data in the storage memory area as needed or in response to a user command.

[0070] In a server computer 106, an application layer 162 typically includes one or more server-side application programs 164 that provide server functionality for managing network communications with client computing devices 104 (and other computing devices connected to network 108) and for facilitating collaboration between the server computer 106 and client computing devices 104. As used herein, the term "server" can refer to the server computer 106 from a hardware perspective or to a logical server from a software perspective, depending on the context.

[0071] In these embodiments, the health measurement device 102 is a small, portable machine for measuring a person's blood pressure, heart rate, or other information at regular intervals over an extended period of time, such as 48 hours. Figure 4 is a schematic diagram illustrating the hardware structure of the health measurement device 102 according to some embodiments of the present disclosure.

[0072] As shown, the health measurement device 102 includes one or more biometric sensors for physically measuring a person's biometric data (such as one or more blood pressure sensors 202 and / or one or more heart rate sensors 204 for periodically measuring the person's blood pressure and heart rate data), one or more activity sensors 206, a user input / output (I / O) interface 208, a memory 210, and a communication module 212, all connected to a control circuit or controller 214.

[0073] The blood pressure sensor 202 may take any suitable form, such as an upper arm cuff, a finger cuff, a photoplethysmography (PPG) optical sensor for positioning on the wrist, etc. The blood pressure sensor 202 may use any suitable technique for measuring blood pressure, such as auscultation, oscillometric, ultrasound, finger cuff, optical, etc.

[0074] The heart rate sensor 204 may use any suitable technology for measuring heart rate, such as an electrical sensor (e.g., an electrocardiogram (ECG) sensor) that measures heart rate by detecting electrical signals associated with the expansion and contraction of the ventricles, or an optical sensor (e.g., a PPG optical sensor) that measures heart rate by measuring fluctuations in blood volume in the blood vessels.

[0075] The activity sensor 206 may be any sensor suitable for detecting a person's posture and activity, such as an accelerometer, a gyroscope, an inertial measurement unit (IMU), an inclinometer, or the like.

[0076] User input / output (I / O) interface 208 may include any suitable I / O interface components for receiving input from a user (such as one or more buttons, a keypad, a keyboard, a computer mouse, a trackball, a touchscreen, a digital pen, a microphone, etc.) and for outputting information to a user (such as a screen, a monitor, a light-emitting diode (LED) panel, a speaker, etc.).

[0077] Memory 210 may be any suitable non-transitory, computer-readable, volatile and / or non-volatile storage device or medium, similar to memory 126 described above.

[0078] The communications module 212 may be any suitable module for communicating with the client computing device 104 or other computing devices using wireless and / or wired communications techniques. For example, in some embodiments, the communications module 212 may be a Bluetooth module.

[0079] The controller 214 may be a processing unit or circuit, such as an integrated circuit (IC) chip, operatively coupled to the modules 202-212 to control the operation of the modules 202-212, receive measurement data from the blood pressure sensor 202, the heart rate sensor 204, and the one or more activity sensors 206, receive user input from the user I / O interface 208, display information to a user via the user I / O interface 208, receive data and / or instructions from other computing devices, such as the client computing device 104, and store various received data and instructions in the memory 210. In some embodiments, the controller 214 may process received data (e.g., measurement data received from the blood pressure sensor 202, the heart rate sensor 204, and the one or more activity sensors 206), analyze the measurement data, and transmit the received data and / or the analysis results to the client computing device 104. In some other embodiments, the controller 214 does not analyze the measurement data, and analysis of the measurement data may be performed by the client computing device 104 and / or the server computer 106.

[0080] 5 is a schematic diagram illustrating the functional structure of health monitoring and analysis system 100 according to some embodiments of the present disclosure. As shown, health monitoring and analysis system 100 includes a data acquisition module 242 for acquiring measurement data, a data analysis module 244 having an artificial intelligence (AI) engine (e.g., a machine learning engine) for analyzing the acquired data using a trained AI model 246, and a reporting module 248 for reporting the analysis results. In these embodiments, AI model 246 may be any suitable AI model, such as a machine learning model, a deep neural network model, a clustering model, or a convolutional neural network, and may be trained using historical measurement data collected from multiple individuals.

[0081] As used herein, the data acquisition module 242 is generally implemented in the health measurement device 102. In some embodiments, the data analysis module 244, the AI ​​model 246, and the reporting module 248 are implemented in the client computing device 104. In some other embodiments, some of the data analysis module 244, the AI ​​model 246, and the reporting module 248 may be implemented in the server computer 106.

[0082] FIG. 6 is a flow chart illustrating the steps of a blood pressure monitoring and analysis procedure 300 performed by health monitoring and analysis system 100.

[0083] Procedure 300 begins (step 302), and health monitoring and analysis system 100 acquires (step 304) measurement data of blood pressure, heart rate, and patient posture and activity from blood pressure sensor 202, heart rate sensor 204, and one or more activity sensors 206 using data acquisition module 242. The acquired measurement data is then transmitted to data analysis module 244 for analysis.

[0084] In step 306, the data analysis module 244 identifies sensor errors using the AI ​​engine and trained AI model 246 based on the acquired measurement data. As will be appreciated by those skilled in the art, a person's blood pressure and heart rate generally have a corresponding relationship. For example, a high heart rate generally corresponds to high blood pressure. Furthermore, a person's blood pressure and heart rate also generally have a corresponding relationship with the person's posture and activity. For example, a person engaged in strenuous activity typically experiences a high heart rate and high blood pressure.

[0085] Furthermore, those skilled in the art will recognize that such relationships are generally complex, and that instantaneous measurements of a person's blood pressure and / or heart rate may not be consistent with such relationships and may appear biased from such relationships. There are various reasons that can cause such measurement bias, such as so-called "noise," data errors (e.g., caused by sensor errors), and sudden changes in a person's health status. Therefore, it is necessary to correctly identify the reasons causing the measurement bias and take corresponding measures. For example, if the measurement bias is caused by noise, the noise needs to be removed and a corrected measurement needs to be obtained. If the measurement bias is caused by a sensor error, the malfunctioning sensor needs to be replaced. If the measurement bias is caused by a sudden change in a person's health status, the person needs to be given appropriate advice (e.g., consult a doctor or go to a hospital, call an emergency number, etc.). However, due to the complexity of the relationship between a person's blood pressure / heart rate and their posture / activity, it is impossible, or at least extremely difficult, to correctly identify such reasons manually.

[0086] Using the trained AI model 246, the AI ​​engine of the data analysis module 244 can identify measurement data samples that are biased from such relationships and determine that the identified measurement data samples are erroneous data samples and are likely caused by malfunctioning sensors that collected these erroneous data samples.

[0087] For example, if the blood pressure is rising but the heart rate remains low, then either the blood pressure sensor or the heart rate sensor may not be working properly. If the activity sensor then reports that the person is very active, then the blood pressure sensor is working properly but the heart rate sensor is not working properly.

[0088] If the data analysis module 244 identifies a sensor error in step 308, the data analysis module 244 reports the sensor error using any suitable method, such as activating an alarm beep, displaying an error message on the screen of the client computing device 104, sending a message to a user (e.g., a caretaker), etc. (step 310). The procedure 300 then ends (step 318).

[0089] If the data analysis module 244 does not identify a sensor error at step 308, the data analysis module 244 then uses the AI ​​engine and trained AI model 246 to identify the person's posture and / or activity patterns (including sleep patterns) (step 312). For example, the data analysis module 244 may identify the person as active rather than sleeping if the activity sensor 206 reports the person as having an upright posture and the heart rate sensor 204 reports an increased heart rate. In some other embodiments, the data analysis module 244 may identify the person's posture and / or activity pattern as one of standing upright, walking, running, resting, and sleeping.

[0090] In step 314, the data analysis module 244 analyzes the person's health condition using the AI ​​engine and trained AI model 246 based on the identified patterns and the measurement data. As described above, the measurement data may be various biometric data such as blood pressure, heart rate, respiratory rate, pulse rate, ECG, PPG, oxygen level, CO2 level, breath sounds, BM / weight / height, etc. Some biometric data may be measured or otherwise obtained from one or more biometric sensors, some biometric data may be obtained or corrected by matching with other related biometric data, some biometric data may be pre-stored biometric data, and some biometric data may be obtained using a suitable predictive algorithm, such as a suitable AI method.

[0091] In step 316, the analysis results are sent from the data analysis module 244 to the reporting module 248 for reporting, such as storing the analysis results in a database (e.g., in the person's personal cloud account), displaying the analysis results to the user, sending the analysis results to another client computing device or another computing device such as the server 106, etc. In some other embodiments, the reported analysis results may include: Activity rating: no activity, light activity, or heavy activity Posture reporting: standing upright, lying down, sleeping, etc. Blood pressure grading: hypotension, normal, or hypertension Heart rate grading: high, normal, or low.

[0092] In some other embodiments, if the data analysis module 244 determines that the blood pressure, heart rate, posture, and activity measurement data are not adequately correlated and no sensor error is identified, the data analysis module 244 can instruct the reporting module 248 to report a risk of heart disease or heart failure and issue an alarm to the person.

[0093] After reporting, procedure 300 ends (step 318).

[0094] Those skilled in the art will recognize that various embodiments are readily available. In some other embodiments, for example, as shown in Figure 7, the health monitoring and analysis system 100 includes multiple client computing devices 104, and the health measurement devices 102 can be directly connected to the network 108 using suitable wireless and / or wired communication technology.

[0095] 8, some sensors, such as the activity sensor 206, may not be included in the health measurement device 102 and may be implemented as separate sensor devices. In these embodiments, the health measurement device 102 and the activity sensor 206 may connect to the network 108 via one or more access points 402.

[0096] In some other embodiments, the health measurement device 102 may not include a heart rate sensor 204 and thus does not monitor a person's heart rate.

[0097] In some other embodiments, the health measurement device 102 may not monitor the person's posture, and thus the activity sensor 206 is only for monitoring the person's movement.

[0098] 9 , the health measurement device 102 may include one or more attachable pads 402 for attaching to suitable locations on the user, such as the user's chest, wrist, elbow area, ankle area, etc. Each pad 402 includes a blood pressure sensor 202 connected to a central unit 404 attached to the user's belt, for example. In these embodiments, the central unit 404 may include other modules such as an activity sensor 206, a user I / O interface 208, a memory 210, a communication module 212, and a controller 214. In these embodiments, the heart rate sensor 204 may be a separate component attachable to the user (such as a separate pad suitable for attaching to the user's body).

[0099] 10 is a schematic cross-sectional view of a pad 402 according to some embodiments of the present disclosure. As shown, the pad 402 includes a sensor layer 412 having a blood pressure sensor 202, an attachment layer 414 coupled to the front side of the sensor layer 412 and having an adhesive material suitable for adhering to human skin, and a protective layer 416 coupled to the rear side of the sensor layer 412.

[0100] 11 is a schematic diagram illustrating a blood pressure sensor 202 (coupled to a pad 402), according to some embodiments of the present disclosure. As shown, the blood pressure sensor 202 includes a light emitting portion 412, such as a pulsed light emitting diode, and a light sensor 414. When the blood pressure sensor 202 is coupled to the pad 402, the mounting layer 414 may include a transparent adhesive material and / or may include an opening at a location corresponding to the blood pressure sensor 202 to allow light to pass through the mounting layer 414.

[0101] In operation, the light emitter 412 emits two light beams of two different wavelengths towards the user's skin, which are reflected off the peripheral arteries beneath the user's skin and captured by the light sensor 414. The controller 214 can then analyze the captured light beams using photoplethysmography (PPG) to obtain the user's blood pressure.

[0102] In some embodiments, each activity sensor 206 may be in the form of an attachable pad.

[0103] In some embodiments, at least one pad 402 may include two or more of a blood pressure sensor 202 , a heart rate sensor 204 , and an activity sensor 206 .

[0104] In the above embodiments, the one or more blood pressure sensors 202 and the one or more heart rate sensors 204 are used as biometric sensors for periodically measuring the person's biometric data. In some embodiments, the biometric sensors may further include one or more temperature sensors for measuring the person's temperature at one or more locations, one or more oxygen saturation sensors for measuring the person's oxygen level, one or more vibration sensors or microphones for measuring sounds from various body locations (such as the person's lungs or throat). In some embodiments, the stickable pad may include one of the above-mentioned sensors. In some other embodiments, the stickable pad may include more than one of the above-mentioned sensors.

[0105] By combining measured temperature, oxygen levels, and sound with measured blood pressure and / or heart rate and measured activity, an AI engine can be used to determine a person's health status. For example, if measured activity indicates a person is walking or running, but the measured temperature and / or oxygen levels drop, risk of heart failure can be determined. Similarly, measured sound may indicate snoring caused by sleep apnea, which alone or in combination with measured audibility may indicate risk of heart failure. Measured sound may also indicate lung conditions (e.g., fluid in the lungs, an indicator of cancer risk), which can be combined with other sensor measurements to more accurately determine a person's health status.

[0106] Those skilled in the art will recognize that the health measurement device 102 may take any suitable form. For example, Figure 12 is a schematic diagram illustrating a health measurement device 102 according to some embodiments of the present disclosure. As shown, the health measurement device 102 is in the form of an attachable pad for attachment to a person's chest and includes all components (blood pressure sensor 202, heart rate sensor 204, vibration sensor, controller 214, etc.).

[0107] In some embodiments, such as that shown in FIG. 13, the health measurement device 102 is in the form of a cuff containing all components (blood pressure sensor 202, heart rate sensor 204, controller 214, etc.) for positioning around the user's elbow.

[0108] 14, the health measuring device 102 is in the form of a cuff 422 for positioning around the user's elbow, which includes all components except the vibration sensors. The health measuring device 102 also includes a pair of vibration sensors 424 in the form of attachable pads for attaching to the chest around the left and right lungs, respectively. The pads 424 are connected to the cuff 422 using any suitable wired or wireless method.

[0109] 15, the health measurement device 102 includes a first and a second stickable pad 432 for attachment to the chest around the left and right lungs, respectively. The first stickable pad 432 includes all components (blood pressure sensor 202, heart rate sensor 204, controller 214, etc.) and may or may not include a vibration sensor. The second stickable pad 434 includes the vibration sensor and is connected to the first pad 432 using a suitable wired or wireless method.

[0110] Although embodiments have been described with reference to the accompanying drawings, those skilled in the art will appreciate that variations and modifications can be made without departing from the scope defined by the appended claims.

Claims

1. 1. A device for monitoring a person's health condition, comprising: one or more biometric sensors for periodically measuring biometric data of said person; one or more activity sensors for periodically measuring the person's activity; a circuit operatively coupled to the one or more biometric sensors and the one or more activity sensors, using a trained artificial intelligence (AI) model to analyze the person's health status based on the measurement data collected from the one or more biometric sensors and the one or more activity sensors. A circuit including an AI engine configured as described above; An apparatus comprising:

2. the one or more biometric sensors and the one or more activity sensors are configured to periodically perform a set of measurements to periodically measure the biometric data of the person and the activity of the person; The one or more activity sensors, in performing each measurement set, measuring the person's activity at least two of before, during, and after the one or more biometric sensors measure the person's biometric data; The device of claim 1 , configured to:

3. further comprising one or more attachable pads for attachment to the person's body; The device of claim 1 or 2, wherein each of the one or more stickable pads includes at least one of the one or more biometric sensors and the one or more activity sensors.

4. Using the trained AI model to analyze the health status of the person, determining whether any of the one or more biometric sensors and the one or more activity sensors are erroneous based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors; If the one or more biometric sensors and the one or more activity sensors are not erroneous, analyzing the health status of the person based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors; 4. The apparatus of claim 1, comprising:

5. The apparatus of claim 1 , wherein the activity of the person includes at least one of a movement of the person and a posture of the person.

6. the one or more biometric sensors include at least one of one or more blood pressure sensors and one or more heart rate sensors; The apparatus of claim 1 , wherein the biometric data of the person comprises blood pressure data of the person and heart rate data of the person.

7. 7. The device of claim 6, wherein the one or more biometric sensors include one or more temperature sensors for measuring the person's body temperature, one or more oxygen saturation sensors for measuring the person's oxygen level, and at least one of one or more vibration sensors or one or more microphones for measuring sounds from the person's body.

8. 1. A computerized method for monitoring a health condition of a person, comprising: periodically measuring biometric data of the person using one or more biometric sensors; periodically measuring the person's activity using one or more activity sensors; using a trained AI model to analyze the person's health status based on the measurement data collected from the one or more biometric sensors and the one or more activity sensors; A computerized method comprising:

9. Periodically measuring the biometric data of the person and periodically measuring the activity of the person may include: periodically performing a set of measurements using one or more biometric sensors and one or more activity sensors for periodically measuring biometric data of the person and activity of the person, respectively; When performing each set of measurements, measuring the person's activity with the one or more activity sensors at least two of before, during, and after the one or more biometric sensors measure the person's biometric data; 9. The computerized method of claim 8.

10. further comprising attaching one or more attachable pads to the person's body; 10. The computerized method of claim 8 or 9, wherein each of the one or more stickable pads includes at least one of the one or more biometric sensors and the one or more activity sensors.

11. Using the trained AI model to analyze the health status of the person, determining whether any of the one or more biometric sensors and the one or more activity sensors are erroneous based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors; If the one or more biometric sensors and the one or more activity sensors are not erroneous, analyzing the health status of the person based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors; 11. The computerized method of any one of claims 8 to 10, comprising:

12. 12. The computerized method of claim 8, wherein the activity of the person includes at least one of a movement of the person and a posture of the person.

13. the one or more biometric sensors include at least one of one or more blood pressure sensors and one or more heart rate sensors; 13. The computerized method of claim 8, wherein the biometric data of the person comprises blood pressure data of the person and heart rate data of the person.

14. 14. The computerized method of claim 13, wherein the one or more biometric sensors further comprise one or more temperature sensors for measuring the person's body temperature, one or more oxygen saturation sensors for measuring the person's oxygen level, and at least one of one or more vibration sensors or one or more microphones for measuring sounds from the person's body.

15. One or more non-transitory computer-readable storage devices containing computer-executable instructions that, when executed, periodically measuring biometric data of the person using one or more biometric sensors; periodically measuring the person's activity using one or more activity sensors; using a trained AI model to analyze the person's health status based on the measurement data collected from the one or more biometric sensors and the one or more activity sensors; and one or more non-transitory computer-readable storage devices that cause one or more circuits to perform actions including:

16. Periodically measuring the biometric data of the person and periodically measuring the activity of the person may include: periodically performing a set of measurements using one or more biometric sensors and one or more activity sensors for periodically measuring biometric data of the person and activity of the person, respectively; When performing each set of measurements, measuring the person's activity with the one or more activity sensors at least two of before, during, and after the one or more biometric sensors measure the person's biometric data; 16. One or more non-transitory computer-readable storage devices according to claim 15.

17. The action is further comprising attaching one or more attachable pads to the person's body; 17. The one or more non-transitory computer-readable storage devices of claim 15 or 16, wherein each of the one or more stickable pads includes at least one of the one or more biometric sensors and the one or more activity sensors.

18. Using the trained AI model to analyze the health status of the person, determining whether any of the one or more biometric sensors and the one or more activity sensors are erroneous based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors; If the one or more biometric sensors and the one or more activity sensors are not erroneous, analyzing the health status of the person based on the measurement data collected by the one or more biometric sensors and the one or more activity sensors; 18. One or more non-transitory computer-readable storage devices according to any one of claims 15 to 17, comprising:

19. 19. The one or more non-transitory computer-readable storage devices of claim 15, wherein the activity of the person includes at least one of a movement of the person and a posture of the person.

20. the one or more biometric sensors include at least one of one or more blood pressure sensors and one or more heart rate sensors; 20. The one or more non-transitory computer-readable storage devices of claim 15, wherein the biometric data of the person comprises blood pressure data of the person and heart rate data of the person.

21. 14. The one or more non-transitory computer-readable storage devices of claim 13, wherein the one or more biometric sensors further comprise one or more temperature sensors for measuring the person's body temperature, one or more oxygen saturation sensors for measuring the person's oxygen level, and at least one of one or more vibration sensors or one or more microphones for measuring sounds from the person's body.

Images