Wearable physiological signal sensing system
The wearable physiological signal sensing system addresses the limitations of traditional equipment by integrating sensors for continuous health monitoring, enabling real-time vital sign tracking and AI-driven blood pressure estimation, suitable for home healthcare and telemedicine.
Patent Information
- Application Number
- JP2025085264
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-12-25
- Filing Date
- 2025-05-22
- Publication Date
- 2025-12-05
AI Technical Summary
Traditional physiological parameter detection equipment is large, single-function, and unable to meet the demands for long-term and real-time monitoring, especially in applications like home healthcare and telemedicine, where integrated and intelligent sensor systems are needed for continuous health monitoring.
A wearable physiological signal sensing system integrating a stethoscope, electrocardiogram electrodes, and a blood oximeter on a circuit board, utilizing AI to estimate continuous blood pressure through pulse wave transit time and multi-variable linear modeling, with sensors for heart sound, electrocardiogram, and blood oxygen level monitoring.
Enables real-time, continuous monitoring of vital signs like heart sounds, electrocardiogram, and blood oxygen levels, facilitating health prediction and care solutions, and connecting to mobile devices for data processing and analysis.
Smart Images

Figure 2025178191000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to the technical field related to physiological signal sensing, and more particularly to a wearable physiological signal sensing system. [Background technology]
[0002]
[0003] As people become more and more concerned about their own health, physiological monitoring systems are becoming more and more sophisticated. For patients with chronic diseases, long-term and accurate physiological parameter detection can effectively reduce the risk of disease and provide useful reference data for treatment. Traditional physiological parameter detection equipment includes simple medical and healthcare instruments that measure heart rate, respiratory rate, blood pressure, blood oxygen saturation, body temperature, etc., providing a basis for evaluating the health status of the blood circulation system and respiratory system, etc., and has wide application prospects in areas such as home healthcare, telemedicine, and clinical medicine.
[0003] While the development of medical detection equipment technology is moving towards portability and networking, traditional physiological parameter detection equipment has the problem of being single-function and large in volume, which cannot meet the ever-increasing demands for long-term and real-time detection. Meanwhile, with the continuous improvement of the integration and intelligence of sensor technology, it has become possible to integrate various sensors into one unit for medical detection at low cost.
[0004] Heart failure is a global public health problem that poses a huge burden on overall medical costs. In recent years, with increasing public interest in health, health management methods that monitor the physical and mental conditions of patients in daily life by recording and analyzing physiological information over long periods of time, from several hours to several months, have become widespread.
[0005] With the aging of the population, health prediction and care products are becoming a current development trend. To detect diseases early, especially in cardiac diseases with a very high sudden death rate, wearable physiological signal sensing systems can provide real-time and effective detection and recording of abnormal heart rate signals, and provide important physiological signals such as blood oxygen levels and blood pressure. Doctors can use these real-time recorded physiological signals for analysis and provide health prediction and care solutions. Summary of the Invention [Problem to be solved by the invention]
[0006] Therefore, it is necessary and has important practical value to provide a wearable physiological signal sensing system that can be applied to application scenarios such as home care, outpatient care, occupational safety and health management, and self-health prediction. [Means for solving the problem]
[0007] In accordance with the above objectives, the present invention discloses a wearable physiological signal sensing system including a system circuit board having an upper surface and a lower surface, a stethoscope mounted on the lower surface for sensing a user's heart sound signal, a plurality of electrocardiogram electrodes mounted on the lower surface and adjacent to the stethoscope for sensing the user's electrocardiogram signal, and a blood oximeter mounted on the upper surface for sensing the user's blood oxygen level and pulse wave signal. The system circuit board is electrically connected to the stethoscope, the plurality of electrocardiogram electrodes, and the blood oximeter, and the system circuit board obtains the user's pulse wave transit time by comparing the electrocardiogram signal with the pulse wave signal or the heart sound signal with the pulse wave signal, and estimates the user's continuous blood pressure based on the obtained pulse wave transit time.
[0008] In one embodiment, the estimation of the user's continuous blood pressure is performed through an artificial intelligence (AI) algorithm, which jointly constructs a multi-variable linear model using the time domain features of the pulse wave signal, the pulse wave transit time, and the user's height parameters.
[0009] In one embodiment, the stethoscope includes a vibrating membrane, a piezoelectric sensor, and a sound-insulating ring. The vibrating membrane is mounted on the underside of a circuit board, and the sound-insulating ring is mounted on the underside, surrounding the vibrating membrane and sealing it with the circuit board to form a resonant cavity. The piezoelectric sensor is mounted on one side of the sound-insulating ring that does not contact the circuit board and is attached to the user's skin.
[0010] In one embodiment, the blood oxygen meter includes an infrared light source, a red light source, and a photodetector, and is used to sense a user's fingertip pulse wave. The circuit board includes at least a signal pre-processing circuit for filtering, amplifying, and converting the heart sound signal, electrocardiogram signal, and pulse wave signal into analog-to-digital data. The microprocessor receives the digitized heart sound signal, electrocardiogram signal, and pulse wave signal and processes them to obtain pre-processed digitized heart sound signal, electrocardiogram signal, and pulse wave signal.
[0011] In one embodiment, the wearable physiological signal sensing system is attached to the chest of a user and is used to continuously monitor the heart sound signal and electrocardiogram signal, and acquires the blood oxygen level and pulse wave signal while the user presses the blood oxygen level meter.
[0012] In one embodiment, the wearable physiological signal sensing system connects to an external mobile device to enable transmission of physiological signals, and the external mobile device can connect to a cloud server or an edge device to enable processing and analysis of the physiological signals, and the physiological signals include any one or any combination of an electrocardiogram signal, a pulse wave signal, a heart sound signal, and a blood oxygen level. In another embodiment, the wearable physiological signal sensing system includes an embedded SIM card installed on a system circuit board, and in one embodiment, the wearable physiological signal sensing system connects to any one of the external mobile device, the cloud server, or the edge computing device through the embedded SIM card to enable transmission of the physiological signals.
[0013] In one embodiment, the system circuit board performs the following steps to measure blood pressure, including sensing a user's heart sound signal, an electrocardiogram signal, and a blood oxygen level; obtaining a pulse transit time (PTT) by comparing the electrocardiogram signal with a pulse wave signal or comparing the heart sound signal with a pulse wave signal; and obtaining the user's blood pressure by an AI algorithm.
[0014] In one embodiment, the wearable physiological signal sensing system includes a system circuit board having an upper surface and a lower surface, a stethoscope mounted on the lower surface and electrically connected to the system circuit board, the stethoscope being used to sense a user's heart sound signal, and at least one patch mounted on the lower surface and attached to the user's skin. A plurality of electrocardiogram electrodes are mounted on the lower surface and used to sense the user's electrocardiogram signal. A blood oximeter is mounted on the upper surface and used to sense the user's blood oxygen level and pulse wave signal. In one embodiment, the system includes comparing the electrocardiogram signal with a pulse wave signal or comparing the heart sound signal with a pulse wave signal to obtain a user's pulse wave transit time, and estimating the user's continuous blood pressure. The continuous blood pressure is used to perform blood pressure prediction through an artificial intelligence (AI) algorithm, which uses time-domain features of the pulse wave signal, the pulse wave transit time, and the user's height to construct a multi-dimensional linear model. [Effects of the Invention]
[0015] The wearable physiological signal sensing system of the present invention can be applied to applications such as home care, outpatient care, occupational safety and health management, and self-health prediction. [Brief explanation of the drawings]
[0016] [Figure 1] 1 is a diagram showing a system configuration provided by the present invention. [Figure 2(a)] 1 is a side view of a voltage sensor structure provided by the present invention; [Figure 2(b)] FIG. 1 is a diagram showing a voltage patch structure provided by the present invention. [Figure 3(a)] 1A-1C illustrate different design embodiments of the piezoelectric patch structure. [Figure 3(b)] 1A-1C illustrate different design embodiments of the piezoelectric patch structure. [Figure 3(c)] 1A-1C illustrate different design embodiments of the piezoelectric patch structure. [Figure 4(a)] FIG. 10 is a diagram showing a method for testing the attachment of a piezoelectric patch structure. [Figure 4(b)] FIG. 10 is a diagram showing a method for testing the attachment of a piezoelectric patch structure. [Figure 4(c)] FIG. 10 is a diagram showing a method for testing the attachment of a piezoelectric patch structure. [Figure 5(a)] FIG. 10 shows an embodiment in which a pressure sensor is positioned. [Figure 5(b)] FIG. 10 shows an embodiment in which a pressure sensor is positioned. [Figure 5(c)] FIG. 10 shows an embodiment in which a pressure sensor is positioned. [Figure 6(a)] FIG. 1 illustrates a stethoscope according to one embodiment of the present invention. [Figure 6(b)] FIG. 10 illustrates a stethoscope according to another embodiment of the present invention. [Figure 7] FIG. 1 is a functional block diagram of a stethoscope according to an embodiment of the present invention. [Figure 8] 1 is a flowchart of a heart sound detection system according to one embodiment of the present invention. [Figure 9] FIG. 2 is an explanatory diagram of an embodiment of the charging state of the present invention. [Figure 10] FIG. 2 is an explanatory diagram of an embodiment of the charging state of the present invention. [Figure 11] FIG. 1 illustrates a method for obtaining the pulse transit time (PTT) of the present invention. [Figure 12] 1 is a diagram illustrating a method for measuring blood pressure according to the present invention. [Figure 13(a)] 1 is a cross-sectional illustration of a wearable physiological signal sensing system according to one embodiment of the present invention; [Figure 13(b)] FIG. 10 is a cross-sectional illustration of a wearable physiological signal sensing system according to another embodiment of the present invention. [Figure 13(c)]FIG. 10 is a cross-sectional illustration of a wearable physiological signal sensing system according to yet another embodiment of the present invention. [Figure 13(d)] FIG. 10 is a cross-sectional illustration of a wearable physiological signal sensing system according to yet another embodiment of the present invention. [Figure 14] 1 is a functional block diagram of a wearable physiological signal sensing system according to an embodiment of the present invention. [Figure 15(a)] 1 is a system configuration diagram according to an embodiment of the present invention. [Figure 15(b)] FIG. 10 is a system configuration diagram according to another embodiment of the present invention. [Figure 16] FIG. 1 illustrates an exemplary processing system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION
[0017] Here, the present invention will be described in detail with respect to specific embodiments and aspects thereof. Such descriptions are intended to explain the structure or step flow of the present invention and are provided for illustrative purposes only and do not limit the scope of the claims of the present invention. Therefore, in addition to the specific and preferred embodiments described in the specification, the present invention can be broadly implemented in other different embodiments. Hereinafter, the implementation of the present invention will be described using specific specific embodiments, so that those skilled in the art can easily understand the effectiveness and advantages of the present invention based on the content disclosed herein. Furthermore, the present invention can be operated and implemented in other specific embodiments, and the details of each item described herein can be adapted to different requirements, and various modifications or changes can be made within the scope of the present invention.
[0018] The wearable heart sound detection system provided by the present invention mainly utilizes heart sound detection equipment worn on the human body, and combines an acoustic sensing device and wireless transmission to form a portable heart sound collection device that can be connected to IoT. The collected physiological data (e.g., personal heart sounds) are processed by a portable electronic computing device (mobile device), and then transmitted and stored in a cloud server via a cloud network.
[0019] 1 shows a wearable heart sound detection system 100, the main structure of which includes a heart sound acquisition device 101 attached to the body of a user 10 in the form of a monitoring patch. The heart sound acquisition device 101 is communicatively connected to a mobile device 103 (e.g., an external computing electronic device such as a smartphone or tablet). Heart sound data collected by the wearable heart sound acquisition device 101 is uploaded by the mobile device 103 to a cloud server 107 via a cloud network 105 through wireless transmission (e.g., wireless communication methods such as Bluetooth or WiFi). In the cloud server, the data is stored in a cloud data database. The above system further includes an application program installed in the mobile device, which includes instructions for receiving and transmitting data between the wearable heart sound acquisition device 101, the mobile device 103, and the cloud server 107. The above-mentioned application program can run on Android, Windows 10 or iOS operating system platforms, and uploads and stores the collected relevant data / signals, such as heart sound signals and their waveforms, to the cloud server 107, analyzes and processes the data using data analysis and feature extraction algorithms, and then generates an evaluation report and provides medical advice based on the same.
[0020] For ease of wearing, the stethoscope (heart sound acquisition device) 101 can be attached to the chest of the user 10 in the form of a monitoring patch. Its built-in acoustic sensor detects human body sound signals. The acoustic sensor mainly consists of a piezoelectric sensor and a microphone. The piezoelectric sensor mainly consists of a piezoelectric material layer (e.g., polyvinylidene fluoride (PVDF) polymer piezoelectric thin film, lead zirconate titanate (PZT), etc.), with conductive metal (e.g., aluminum (Al), copper (Cu), etc.) plated on its upper and lower surfaces. Each of the upper and lower metal layers has a lead wire connected to a circuit board, which can be used to measure voltage signals generated by vibration. The microphone mainly consists of a typical capacitive sensor, using an ultrathin material (e.g., 30 μm thick glass) as a diaphragm plated with a conductive material. The diaphragm is then sealed to the circuit board using a frame adhesive to form a resonant cavity. The purpose is to vibrate the diaphragm with the sound vibrations emitted by the heartbeat, causing a change in capacitance between the diaphragm and the circuit board, and the heart sound acquisition device acquires this change to record the heartbeat.
[0021] FIG. 2(a) shows a side view of a piezoelectric sensor structure 19 provided by the present invention. As shown in the upper part of the figure, the main component of the piezoelectric sensor is a piezoelectric material layer 201 (e.g., a material such as polyvinylidene fluoride (PVDF) piezoelectric thin film or lead zirconate titanate (PZT)), the upper and lower surfaces of which are plated with a conductive metal (e.g., aluminum (Al), copper (Cu), etc.). The lower part of the figure shows a top view of the above-mentioned piezoelectric sensor structure 19, in which the upper and lower metal electrodes (203a, 203b) each have a lead wire leading out and connected to a circuit board 205, which can be used to measure voltage signals generated by vibration. In one embodiment, the thickness of the above-mentioned piezoelectric sensor is less than 50 μm.
[0022] 2(b) shows a piezoelectric patch structure 20 according to the present invention. The top part of the figure is a side view of the piezoelectric patch structure, including a substrate 207, a layer of anti-allergy gel 209 applied to the substrate and capable of contacting the skin, a plurality of bottom electrodes (211a, 211b, 211c) positioned below the substrate 207 and exposed outside the gel layer 209, which are used to determine whether the piezoelectric patch structure 20 has been attached, an insulating layer 213 positioned on the substrate 207 as a planarizing layer and also serving a planarizing function, a piezoelectric material layer 201 attached to the insulating layer 213, metal leads 203 extending to connect to a nearby circuit board 205 (electrical connection portion 204 may be a conductive adhesive, a snap connector, or the like), a cover plate 215, and a sealing adhesive 217. The sealing adhesive 217 is used to bond and seal the cover plate 215 to the substrate 207 using heat and pressure or roll pressure to form a protective layer. The bottom part of the figure is a front view of the piezoelectric patch structure 20 according to the present invention. Here, the insulating layer 213, the substrate 207, and the gel layer 209 are stacked from bottom to top to form the base 220.
[0023] In one embodiment, the material of the substrate 207 may be glass, or a plastic such as polyimide (PI) or polyethylene terephthalate (PET), or a woven fabric. In one embodiment, the sealing adhesive 217 is ethylene / vinyl acetate copolymer (EVA). In one embodiment, the material of the cover plate 215 may be glass, or a plastic such as polyimide (PI) or polyethylene terephthalate (PET), or a woven fabric.
[0024] In one embodiment, the thickness of the above-mentioned piezoelectric patch structure 20 is less than 2000 μm, wherein the thickness of the gel layer 209 is less than 700 μm, the thickness of the substrate 207 is less than 300 μm, the thickness of the insulating layer 213 is less than 50 μm, the thickness of the piezoelectric material layer 201 is less than 50 μm, the thickness of the circuit board 205 is less than 200 μm, and the thickness of the sealing adhesive 217 is less than 300 μm. In one embodiment, the above-mentioned piezoelectric sensor can be replaced with an acceleration sensor, a gyroscope, or other sensors.
[0025] 3(a) to 3(c) show different designs of the piezoelectric patch structure 20. In FIG. 3(a), the piezoelectric patch structure 20 has a circuit board 205 placed above a piezoelectric material layer 201. The piezoelectric material layer 201 is attached to an insulating layer 213. The circuit board 205 is attached to the piezoelectric material layer 201 via a paste 206. An electrical connection 204 between the circuit board 205 and metal leads 203 plated on the piezoelectric material layer 201 is made using conductive adhesive or a snap connector. FIG. 3(b) shows that the piezoelectric material layer 201 is directly attached to the circuit board 205, and the metal leads 203 of the piezoelectric sensor structure 19 are electrically connected to a system board 230. FIG. 3(c) shows that the piezoelectric material layer 201 is directly attached to the circuit board 205, and the circuit board 205 is a flexible circuit board that can be bent directly above the piezoelectric sensor structure 19.
[0026] 4(a) to 4(c) illustrate a method for performing an attachment test on a piezoelectric patch structure 20. Taking the piezoelectric patch structure 20 shown in FIG. 4(a) as an example, its lamination method is similar to that shown in FIG. 2(b). For details of the structure, please refer to the above description. The structure includes a plurality of bottom electrodes (211a, 211b, 211c) disposed below the substrate 207 and exposed outside the gel layer 209. The bottom electrodes (211a, 211b, 211c) can be referred to as the first electrode P1, the second electrode P2, and the third electrode P3, respectively. As shown in FIG. 4(b), a switch arrangement circuit is designed between the bottom electrodes to perform an attachment test on the piezoelectric patch structure 20 and the skin resistance 231 of human skin. Here, the above-mentioned switch arrangement circuit is arranged so that the first switch SW1 (switch 1) and the second switch SW2 (switch 2) are connected in series in the circuit connecting the first electrode P1 and the third electrode P3, the first switch SW1 (switch 1) and the third switch SW3 (switch 3) are connected in series in the circuit between the first electrode P1 and the second electrode P2, and the second switch SW2 (switch 2) and the third switch SW3 (switch 3) are connected in series in the circuit between the third electrode P3 and the second electrode P2. When the above-mentioned switch arrangement circuit is installed in the manner shown in Figure 4(b), the method of attaching the piezoelectric patch structure 20 to the test is as follows. First, in step S401, the first switch SW1 (switch 1) and the second switch SW2 (switch 2) are connected, and the third switch SW3 (switch 3) is opened to check whether resistance is measured; if not, it means that the tape is not completely attached; if it is measured, step S403 is executed, the first switch SW1 (switch 1) and the third switch SW3 (switch 3) are connected, and the second switch SW2 (switch 2) is opened to check whether resistance is measured; if not, it means that the tape is not completely attached; if it is measured, step S405 is executed, the second switch SW2 (switch 2) and the third switch SW3 (switch 3) are connected, and the first switch SW1 (switch 1) is opened to check whether resistance is measured; if not, it means that the tape is not completely attached; if it is measured, it means that the tape is completely attached.
[0027] Another implementation of the stethoscope (heart sound acquisition device) 101 is a microphone composed of a capacitive sensor. The microphone is primarily composed of a common capacitive sensor, which uses an ultra-thin material as a vibrating membrane (e.g., 30 μm thick glass), on which a conductive material is deposited, and then seals the vibrating membrane with a frame adhesive to form a resonant cavity. The purpose is to vibrate the vibrating membrane with the sound vibrations emitted by the heartbeat, causing a change in capacitance between the vibrating membrane and the circuit board, and the heart sound acquisition device captures this change to record the heartbeat.
[0028] Because wearable capacitive sensors need to be able to detect contact with the user's body due to environmental noise and other issues, the present invention proposes placing a pressure sensor on the sound-insulating ring of the capacitive sensor. This pressure sensor can be piezoelectric, capacitive, resistive, or other technologies, and can be located between the sound-insulating ring and the circuit board or below the circuit board. The pressure sensor can generate a corresponding pressure signal depending on the degree to which it is pressed, and the pressure sensor can determine the degree of contact between the wearable capacitive sensor and the user based on the detected pressure signal.
[0029] The capacitive sensor provided by the present invention is shown in Figures 5(a) to 5(c), which respectively show several possible embodiments of pressure sensor arrangement, with the left side view and the right side view being a bird's-eye view. Referring to Figures 5(a) to 5(b), a pressure sensor 503 is installed between a circuit board 505 of a capacitive sensor 501 and a sound-insulating ring 507. Alternatively, as shown in Figure 5(c), the pressure sensor 503 may be installed below the sound-insulating ring 507.
[0030] Based on the above-mentioned problems that the wearable capacitive sensor may face, namely, technical difficulties such as poor response at low frequencies and large environmental noise, the present invention provides a wearable heart sound acquisition device that integrates the piezoelectric sensor structure disclosed in Figures 3(a) to 4(c) and the capacitive sensor disclosed in Figures 5(a) to 5(c), and the integrated wearable heart sound acquisition device will be described in the following paragraphs.
[0031] 6(a) shows a stethoscope (heart sound acquisition device) 601 provided according to one embodiment of the present invention. The stethoscope (heart sound acquisition device) 601 includes a vibrating membrane 601a, which is plated with a conductive material and sealed with a rubber frame (sound-insulating ring) 607 and a circuit board 605. (The resonant cavity formed by the sound-insulating ring 607 and the circuit board 605, combined with the vibrating membrane 601a, forms a microphone structure.) A piezoelectric sensor 603 is installed below the sound-insulating ring 607 and electrically connected to the circuit board 605 via wiring 604. It can be used to measure voltage signals generated by vibrations through contact with human skin 631. That is, the piezoelectric sensor 603 functions as a vibrating membrane and can be used to compensate for the drawback of conventional capacitive sensors, which have poor response to low-frequency signals, such as the third and fourth heart sounds at frequencies around 20 Hz.
[0032] In one embodiment, the piezoelectric sensor 603 is formed on a flexible base (see FIGS. 2(a) and 2(b)) and can be manufactured in a patch format. Here, multiple electrodes are installed at the bottom of the flexible base, which can be used to determine whether the attachment is complete. In one embodiment, the stethoscope (heart sound acquisition device) 601 can be directly attached to the human skin 631 above the user's heart via the patch and used to measure heart sound signals.
[0033] 6(b) shows a stethoscope (heart sound acquisition device) 601 provided according to another embodiment of the present invention, which includes a vibrating membrane 601a, on which a conductive material is plated, and which is sealed with a rubber frame (sound-insulating ring) 607 and a circuit board 605. A piezoelectric sensor 603 designed with multiple holes 640 is installed under the sound-insulating ring 607 and electrically connected to the circuit board 605 via wiring 604, and can be used to measure voltage signals generated by vibration. This design allows sound to enter through the holes, making it possible to perform measurements without necessarily having to make contact with the human body.
[0034] In one embodiment, the size of the hole provided in the piezoelectric sensor 603 ranges from 10 μm to 1000 μm. In one embodiment, in the integrated wearable heart sound acquisition device 601 in which the hole is designed in the piezoelectric sensor 603, the distance d between the piezoelectric sensor 603 and the human skin 631 ranges from 0 μm to 1000 μm. <d<5cmである。
[0035] The design of the above-mentioned sensor is mainly for receiving signals, and the received signals are heartbeat signals. The integrated wearable heart sound acquisition device provided by the present invention can receive heartbeat signals using a capacitive sensor and a piezoelectric sensor, respectively. In the integrated wearable heart sound acquisition device, the circuit board includes multiple amplifiers, filters, a power management system, an identification system, Bluetooth, a processor, etc.
[0036] 7 shows a functional block diagram of a stethoscope (heart sound acquisition device) 601, which is a wearable heart sound acquisition device that can acquire heart sound signals from a human body through a capacitive sensor 701 and a piezoelectric sensor 703. The wearable heart sound acquisition device 601 can receive and transmit data and run software applications, and includes a microprocessor, a storage unit, and a wireless transmission module.
[0037] Microprocessor 725 may be a microcontroller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic circuit, or other digital data processing device that executes instructions to perform processing operations in accordance with the present invention. Microprocessor 725 can execute various application programs stored in a storage unit, including executing firmware algorithms.
[0038] The storage unit 727 may include read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM (EEPROM), flash memory, or any memory commonly used in computers.
[0039] The wireless transmitting module 729 is connected to an antenna 729a, which is configured to transmit output data and receive input data through a wireless communication channel, which may be a digital wireless communication channel, such as WiFi, Bluetooth, RFID, NFC, 3G / 4G / 5G, or any other future wireless communication interface.
[0040] The capacitive sensor 701 and the piezoelectric sensor 703 individually acquire heart sound signals from the human body, amplify the signals through a first amplifier 731 and a second amplifier 731a, and then remove noise through a first low-pass filter 733 and a second low-pass filter 733a. The filtered heart sound signals are converted from analog to digital through a first analog-to-digital converter (ADC) 735 and a second analog-to-digital converter (ADC) 735a, and then processed by a microprocessor 725 to obtain a de-noised, stable heart sound signal. The microprocessor 725 can store the de-noised, stable electrocardiogram signal and body sound in a storage unit through instructions or programs, or can transmit the signals to a mobile device, such as a smartphone, via a wireless transmission module 729 for further analysis.
[0041] A battery pack 737 provides power to the wearable heart sound acquisition device 601 and can be combined with a power management unit 739 to optimize power usage. Additionally, the battery pack 737 can be wirelessly charged via a charging coil 741.
[0042] In one embodiment, the above-mentioned microprocessor 725, storage unit 727, wireless transmission module 729, amplifiers 731, 731a, low-pass filters 733, 733a, analog-to-digital converters (ADCs) 735, 735a, and power management unit 739, etc., can be integrated into a single circuit module.
[0043] Based on Figures 2(a) to 7 and related embodiments, the present invention constructs a wearable heart sound detection system as shown in Figure 1, which is mainly divided into a heart sound acquisition device 601 and a mobile device (such as a smartphone or tablet PC) 103, which provides continuous monitoring of the heart health status under normal circumstances, and in the event of an emergency, issues an alarm through the mobile device 103 so that rescue can be called in a timely manner. The execution flow of the system is as shown in Figure 8.
[0044] First, in step S801, the stethoscope (heart sound acquisition device) 601 is confirmed to be attached to the body of the user 10. If it is not attached completely, the mobile device 103 continuously notifies the user (step S802). Once attachment is confirmed, the process proceeds to the next step. Next, in step S803, biometric features are collected from the user. Then, in step S804, the user's identity is confirmed using the collected biometric features. After identity confirmation, the process proceeds to the next step S805, in which heartbeat signal acquisition, including heart sound signal collection, is performed on the user using the wearable stethoscope (heart sound acquisition device) 601. Next, in step S806, the heart sound signal is filtered and amplified. In step S807, an initial heartbeat analysis is performed. After the heartbeat analysis, step S808 first checks for an emergency. If there is a problem (e.g., the heartbeat is not measured), the mobile device 103 is immediately connected to the mobile device 103 for comparison with other sensors (step S809). If a critical situation is confirmed, the mobile device 103 immediately issues an alarm (step S810). If the heartbeat is normal, the mobile device 103 passes the heartbeat signal to the mobile device 103 for further signal processing and continues signal collection (step S811). After the mobile device 103 receives a normal heartbeat signal, it performs signal processing such as filtering, wavelet analysis, and Fourier transform to obtain feature points of the heartbeat signal (step S812). Next, in step S813, an artificial intelligence (AI) comparison and situation classification are performed between the feature points and previous data in a database to determine whether there are any abnormalities. Then, in step S813, the results of the comparison and situation classification are sent to the database and filed for subsequent comparison, and are used by medical units to interpret the signal and provide medical advice. In one embodiment, the database may be a cloud database built on a cloud server.
[0045] In one embodiment, the above-mentioned AI comparison and situation classification performs initial classification of normal and abnormal heart sound signals through an AI algorithm installed in the mobile device 103. The AI algorithm may include the following series of steps: pre-filtering and normalization processes are performed on the input heart sound signals, time domain and frequency domain features are extracted, and a classification result is output using a convolutional neural network (CNN) model. In one embodiment, the above-mentioned pre-filtering and normalization processes on the heart sound signals are performed using a software calculation method.
[0046] 9 is a schematic diagram of a wireless charging device according to the present invention. The stethoscope (heart sound acquisition device) charging device 900 includes a battery 904 and multiple wireless transmitting coils 902, and multiple stethoscopes (heart sound acquisition devices) 601 can be paired therewith. Wireless charging (also called inductive charging) utilizes electromagnetic inductive coupling to transmit energy from the stethoscope charging device 900 to the heart sound acquisition device 601, and the battery pack 737 of the heart sound acquisition device 601 is charged via the charging coil 741. Energy is transmitted between the stethoscope charging device 900 and the stethoscope (heart sound acquisition device) 601 via electromagnetic inductive coupling, eliminating the need for a wired connection between them. The Qi standard of the Wireless Power Consortium (WPC) or the AirFuel Resonant (A4WP) and AirFuel Inductive (PMA) standards of the AirFuel Alliance (AFA) can be used. The non-current-carrying contact design avoids the risk of electric shock, allowing implanted medical devices to be charged without damaging body tissue, eliminating the need for wires to penetrate the skin or other tissues, and reducing the risk of infection. Charging does not require wire connections; it can simply be placed near the charger. The stethoscope charging device 900 of the present invention can charge multiple heart sound acquisition devices 601 simultaneously, eliminating the need for multiple chargers when multiple power-consuming devices are present, eliminating the need to occupy multiple power outlets, and eliminating the hassle of tangled wires.
[0047] The stethoscope charging device 900 incorporates the control circuitry required for power transmission and reception, eliminating the need for an external microcontroller, making it suitable for wearable devices that can be worn for extended periods of time and have large battery capacities. In one embodiment, the device uses a high-frequency band of 13.56 MHz, and therefore also supports Near Field Communication (NFC), a short-range wireless communication standard that uses the same frequency for contactless communication.
[0048] In another embodiment, the above-mentioned multiple wireless transmitting coils 902 can be arranged to partially overlap, which is advantageous for preventing misalignment errors when the stethoscope (heart sound acquisition device) 601 is placed on the charging plate. Even if there is a slight position error when the stethoscope (heart sound acquisition device) 601 is placed on the charging plate, it can still be effectively charged. See FIG. 10.
[0049] The present invention mainly discloses a wearable physiological parameter sensing system, which is used for real-time monitoring of important physiological signals of the human body, including one or any combination of heart sound, electrocardiogram, blood oxygen level, and blood pressure.
[0050] Among the above important physiological signals, heart sounds, electrocardiograms, and blood oxygen levels can all be measured directly by sensors, while blood pressure requires obtaining the pulse transit time (PTT) via electrocardiogram (ECG), pulse pulse gram (PPG), and blood oxygen level signals.
[0051] Cardiac activity can reveal a wealth of valuable information about the human body. In typical medical settings, monitoring heart rate and cardiac activity is accomplished by measuring electrophysiological signals and electrocardiograms (ECGs), which connect electrodes to the body to measure the electrical activity signals induced in cardiac tissue. Furthermore, as the heart beats, pressure waves pass through blood vessels, causing slight changes in their diameter. In addition to ECGs, pulse waves can also be obtained by measuring the photoplethysmography (PPG) signal of blood flow using a light source and a photoelectric sensor. Therefore, pulse waves measured using this technology are also called PPG signals, an optical technique that can obtain cardiac function information without measuring bioelectric signals. While PPG technology is primarily used to measure blood oxygen saturation (SpO2), it can also provide cardiac function information without measuring bioelectric signals. Using PPG technology, heart rate monitoring devices can be integrated into wearable devices, achieving continuous detection applications.
[0052] 11, a pulse transit time (PTT) 1106 can be obtained by comparing a pulse wave signal (PPG) 1102 and an electrocardiogram (ECG) 1104. Based on the respective physiological features of the pulse wave signal (PPG) 1102 and the electrocardiogram (ECG) 1104, the peak value of the electrocardiogram signal (ECG) 1102 is caused by ventricular contraction, and the peak value of the pulse wave signal (PPG) 1104 is caused by vasoconstriction. Therefore, the transit time for blood to arrive at a measurement site after being pumped out of the heart, i.e., the pulse transit time (PTT) 1106, can be obtained. Specifically, a widely used method for obtaining the pulse transit time (PTT) includes measuring the time delay between the R peak value (indicated by the dashed line) of the electrocardiogram signal (ECG) 1102 and a feature point of the pulse wave signal (PPG) 1104, such as the peak value of the pulse wave signal (PPG) (indicated by the dashed line), and utilizing the time delay required for a pressure pulse to travel from a proximal point to a distal point. Similarly, the pulse transit time (PTT) can be obtained by comparing the pulse wave signal (PPG) 1102 with the heart sound signal.
[0053] The pulse wave transmission speed and blood pressure are directly correlated, and when blood pressure is high, the pulse wave transmission speed is fast, and vice versa. Therefore, the pulse wave transmission time (PTT) 1106 can be obtained through the electrocardiogram signal (ECG) 1102 and the pulse wave signal (PPG) 1104, and by adding normal body parameters (height, weight, etc.), the pulse wave transmission speed can be obtained. The systolic blood pressure and diastolic blood pressure of the human pulse can be estimated through the established characteristic equation, thereby realizing non-invasive continuous blood pressure measurement.
[0054] FIG. 2 illustrates a blood pressure measurement method 1200 according to the present invention, which includes performing the following steps: First, in step S1201, the wearable physiological signal sensing system 1300 (see FIG. 13A) uses the heart sound sensing device 1302, the electrocardiogram sensing device 1304 (e.g., an electrocardiogram patch (ECG+, ECG-)) and the blood oxygen concentration meter 306 (i.e., a pulse wave signal sensing device) to sense the user's heart sound signal, electrocardiogram signal and blood oxygen signal, respectively, where the blood oxygen signal includes a blood oxygen concentration and a pulse wave signal (e.g., a fingertip pulse wave signal); next, in step S1202, the electrocardiogram signal and the blood oxygen signal (pulse wave signal) are compared, or the heart sound signal and the blood oxygen signal (pulse wave signal) are compared to perform calculations to obtain the pulse transit time (PTT); subsequently, in step S1203, the user's blood pressure is determined using an artificial intelligence (AI) algorithm; and then in step S1204, the blood pressure value is obtained based on the result of the AI algorithm.
[0055] According to an embodiment of the present invention, the blood pressure prediction using the above-mentioned artificial intelligence (AI) algorithm is a blood pressure prediction method based on pulse wave conduction time and pulse wave velocity, which mainly uses the time domain features of the accelerated pulse wave, pulse wave transit time (PTT), and user height parameters to jointly construct a multi-dimensional linear model.
[0056] 13(a) shows a cross-sectional schematic diagram of a wearable physiological signal sensing system 1300 disclosed according to an example of the present invention. The wearable physiological signal sensing system 1300 includes a circuit board 1301 having a first surface (lower surface) 1301a on which a stethoscope 1302 and multiple electrocardiogram patches 1304 are mounted, and a blood oxygen saturation meter 1306 on a second surface (i.e., upper surface opposite to the first surface) 1301b on which a blood oxygen saturation meter 1306 is mounted. For ease of wearing, the wearable physiological signal sensing system 1300 can be attached to the chest of a user 10 in the form of a patch. Here, when using the wearable physiological signal sensing system 1300, multiple electrocardiogram patches 1304 (e.g., a pair of ECG+ and ECG- electrodes) are attached to the chest skin of the user 10.
[0057] In one embodiment, the stethoscope 1302 includes a vibrating membrane 1302a, plated with a conductive material, and sealed to the circuit board 1301 by a rubber frame (sound-insulating ring) 1302b (wherein the resonant cavity formed by the sound-insulating ring 1302b and the circuit board 1301 combines with the vibrating membrane 1302a to form a microphone structure). A piezoelectric sensor 1302c is installed below the sound-insulating ring and electrically connected to the circuit board (not shown) via wiring. This sensor can be used to measure voltage signals generated by vibrations through contact with the user's skin. In other words, the piezoelectric sensor 1302c can be used as a separate vibrating membrane to address the problem of conventional capacitive sensors, which have poor response to low-frequency signals, such as the frequencies of the third and fourth heart sounds (around 20 Hz).
[0058] The main component of the microphone structure described above is a common capacitive sensor, using an ultra-thin material as the diaphragm 1302a (for example, 30 μm thick glass) plated with a conductive material, and sealing this diaphragm 1302a with the circuit board 1301 using a rubber frame 1302b to form a resonant cavity. The purpose is to vibrate the diaphragm 1302a with the vibration of the sound emitted by the heartbeat, causing a change in capacitance between the diaphragm 1302a and the circuit board 1301, and the stethoscope 1302 (heart sound acquisition device) detects this change and records the heart sound signal.
[0059] The main component of the piezoelectric sensor 1302c is a piezoelectric material layer (e.g., a material such as polyvinylidene fluoride (PVDF) thin polymer piezoelectric film or lead zirconate titanate (PZT)), the upper and lower surfaces of which are plated with a conductive metal (e.g., aluminum (Al), copper (Cu), etc.). A metal lead can be drawn out from each of the upper and lower metal layers and connected to a circuit board, which can be used to measure voltage signals generated by vibration. In one embodiment, the thickness of the piezoelectric sensor is less than 50 μm.
[0060] In one embodiment, the stethoscope 1302 is used to measure the heart sound signals of the user 10. In one embodiment, the multiple electrocardiogram patches 1304 include at least two electrodes, i.e., ECG+ and ECG-, and are used to measure the electrocardiogram signals of the user. In one embodiment, the blood oximeter 1306 is used to measure the PPG signals and blood oxygen saturation (SpO2) of the user 10. According to an embodiment of the present invention, the blood oximeter 1306 includes an infrared light source (infrared LED), a red light source (red LED), and a photosensitive element, and is used to sense the fingertip PPG signals, i.e., fingertip pulse waves, of the user 10.
[0061] As shown in FIG. 13(a), a stethoscope 1302 and multiple electrocardiogram patches 1304 in a wearable physiological signal sensing system 1300 are attached to the chest of a user 10, in which the stethoscope and multiple electrocardiogram patches 1304 are used to acquire heart sound signals and electrocardiogram signals, respectively. The operation method of the above-mentioned wearable physiological signal sensing system 1300 includes the following: (1) the wearable physiological signal sensing system 1300 is attached to the chest of the user 10 and used to acquire the user's 10 heart sound and electrocardiogram information, and continuously monitor the user's 10 heart sound signals (PCG signals) and electrocardiogram signals (ECG signals); (2) the user 10 presses the blood oxygen meter with his / her finger to acquire the pulse wave signal (PPG) and blood oxygen concentration (discontinuous monitoring, in which the PPG signal and blood oxygen saturation (SpO2) are monitored only when information needs to be acquired); (3) the pulse wave transit time (PTT) from the user's 10 heart to the fingertip is acquired, and the user's 10 blood pressure is obtained after calculation by an artificial intelligence (AI) algorithm (discontinuous monitoring).
[0062] 13(b) shows a cross-sectional schematic view of a wearable physiological signal sensing system 1300a according to another embodiment of the present invention. The wearable physiological signal sensing system 1300a includes a circuit board 1301, a first surface (lower surface) 1301a of which a stethoscope 1302 and a first electrocardiogram patch 1304a are mounted, and a second surface 1301b (i.e., the upper surface opposite the first surface) of the circuit board 1301 is mounted with a blood oxygen saturation meter 1306 and a second electrocardiogram patch 1304b (both integrated). In one embodiment, the structure of the stethoscope 1302 is the same as that shown in FIG. 13A and will not be described in detail here. In one embodiment, the stethoscope 1302 is used to measure the heart sound signals of a user 110. In one embodiment, the first electrocardiogram patch 1304a and the second electrocardiogram patch 1304b are one of two positive and negative electrodes (i.e., ECG+ and ECG-), respectively, installed on opposite sides of the circuit board 1301, and used to measure the electrocardiogram signals of the user 10. In one embodiment, the blood oximeter 1306 is used to measure the PPG signal and blood oxygen saturation (SpO2) of the user 10.
[0063] 13(b), a stethoscope and a first electrocardiogram patch 1304a in a wearable physiological signal sensing system 1300a are attached to the chest of a user 10, and a second electrocardiogram patch 1304b and a blood oxygen saturation meter 1306 are integrated and placed on the opposite side of the stethoscope 1302. Here, the stethoscope 1302 is used to acquire a cardiac signal. The first and second electrocardiogram patches (1304a, 1304b) are used to acquire an electrocardiogram signal, and the blood oxygen saturation meter 1306 is used to acquire a PPG signal and blood oxygen saturation (SpO2). The operation method of the above-mentioned wearable physiological signal sensing system 1300a includes the following: (1) attaching the wearable physiological signal sensing system 1300a to the user's chest, acquiring the user's 10 heart sound information, and continuously monitoring the user's 10 heart sound signals (PCG signals); (2) the user 10 presses his / her finger on one of the blood oxygen meter and ECG electrodes (i.e., one of the first electrocardiogram patch or the second electrocardiogram patch) to acquire the blood oxygen concentration, the user's fingertip pulse wave (PPG) signal, and the electrocardiogram signal (discontinuous monitoring, in which the ECG signal, PPG signal, and blood oxygen saturation (SpO2) are monitored only when information needs to be acquired); (3) acquiring the PTT from the user's 10 heart to the finger, and acquiring the user's 10 blood pressure after calculation by an artificial intelligence (AI) algorithm (discontinuous monitoring).
[0064] 13(c) shows a cross-sectional schematic diagram of a wearable physiological signal sensing system 1300 disclosed in accordance with a further embodiment of the present invention, in which a blood oxygen saturation meter 1306 and an electrocardiogram auscultation device 1303 are separated from each other and electrically connected by a coaxial cable or metal wiring. Here, the electrocardiogram auscultation device 1303 is configured by combining a plurality of electrocardiogram patches 1304, a stethoscope 1302, and a circuit board 1301. In this embodiment, the plurality of electrocardiogram patches 1304 and the stethoscope 1302 of the electrocardiogram auscultation device 1303 are mounted on the same side of the circuit board 1301. The structure of the above-mentioned stethoscope 1302 is the same as that of the stethoscope described above in FIG. 13(a), and will not be described in detail here.
[0065] In this embodiment, the above-mentioned stethoscope 1302 is used to measure the heart sound signals of the user 10, the multiple electrocardiogram patches 1304, which include two positive and negative electrodes (i.e., ECG+ and ECG-), are used to measure the electrocardiogram signals (ECG signals) of the user 10, and the blood oxygen meter 1306 is used to measure the PPG signals and blood oxygen saturation (SpO2) of the user 10.
[0066] Referring to FIG. 13(c), the electrocardiogram auscultation device 1303 is attached to the chest of the user 10 during use, and the blood oxygen concentration meter 1306 can be placed on the user's fingertips, palms, wrists, upper arms, thighs, lower legs, ankles, toes, ears, foreheads, or cheeks, etc., based on actual needs, but is not limited to these.
[0067] 13(d) shows a cross-sectional schematic diagram of a wearable physiological signal sensing system 300 disclosed in accordance with yet another embodiment of the present invention, in which a blood oxygen saturation meter 1306 and an electrocardiogram auscultation device 1303 are designed separately and connected wirelessly (including Bluetooth, Wi-Fi, etc.). The structure and usage of the blood oxygen saturation meter 1306 and the electrocardiogram auscultation device 303 are the same as those in the embodiment of FIG. 3(c), and will not be described again in detail here.
[0068] According to an embodiment of the present invention, a blood oxygen saturation meter 1306 shown in FIGS. 13(a) to 13(d) includes an infrared light source (infrared LED), a red light source (red LED), and a photodetector, and is used to sense the fingertip PPG signal, i.e., fingertip pulse wave, of a user 10.
[0069] According to an embodiment of the present invention, the above-mentioned circuit board 1301 can be placed on a flexible base, which can be fabric, polyimide (PI), or polyethylene terephthalate (PET).
[0070] 14 is a functional block diagram of a wearable physiological signal sensing system 1400, in which a stethoscope 1302 can detect a heart sound signal from a user's body, a pair of electrocardiogram electrodes (ECG electrodes), i.e., an electrocardiogram patch 1304, can detect an electrocardiogram signal from the user's body, and a blood oximeter 1306 can detect a PPG signal and blood oxygen saturation (SpO2). The heart sound signal, the electrocardiogram signal, and the PPG signal are individually filtered, amplified, and analog-to-digital converted through corresponding signal pre-processing channels 1411a, 1411b, and 1411c in a signal pre-processing circuit 411 to obtain pre-processed digitized heart sound signal, the electrocardiogram signal, and the PPG signal. In one embodiment, each pre-processing channel includes a filter, a signal amplifier, and an analog-to-digital (A / D) converter.
[0071] The microprocessor 1415 can store the stable and background noise-removed heart sound signal, electrocardiogram signal, and PPG signal in the storage unit 417 through instructions or programs, or can transmit the signals to an external mobile device via the wireless transmission module 1419 for further analysis. The mobile device can be a smartphone. The microprocessor 1415 can compare the electrocardiogram signal with the PPG signal or the heart sound signal with the PPG signal to calculate the pulse transit time (PTT) between the two, and estimate and obtain continuous blood pressure from the PTT, thereby achieving the function of continuous blood pressure measurement. According to an embodiment of the present invention, the microprocessor 1415 can perform blood pressure prediction through the aforementioned artificial intelligence (AI) algorithm.
[0072] The battery pack 1421 supplies power to the integrated heart sound and electrocardiogram signal sensing device 1400 and can optimize power usage in combination with the power management module 1423. The battery pack 1421 can also be wirelessly charged using a charging coil 1425.
[0073] In one embodiment, the above-mentioned components such as the microprocessor 1415, storage unit 1417, wireless transmission module, signal pre-processing circuit 1411 and power management module 1421 can be integrated into a single system circuit board, for example, the circuit board 1301 shown in Figures 3(a) and 3(b).
[0074] In one embodiment, a user can view the collected electrocardiogram (ECG), phonocardiogram (PCG), and PPG for further analysis and comparison of the data through an externally connected computing electronic device, which may be a smartphone, tablet computer, or cloud server.
[0075] As shown in FIG. 15(a), according to one embodiment of the present invention, a wearable physiological signal sensing system 1500 includes a circuit board 1301 (see FIG. 3(a)), a first surface (lower surface) 1301a of which a stethoscope 1302 and a plurality of electrocardiogram patches 1304 are mounted, and a second surface (i.e., the upper surface opposite the first surface) 1301b of which a blood oxygen saturation meter 1306 is mounted. The circuit board 1301 is worn on the body of a user 10 and communicatively connected to a mobile device (e.g., an external computing electronic device such as a smartphone or tablet computer) 1503. Physiological data collected by the wearable physiological signal sensing system 1500 (including heart sound signals, electrocardiogram signals, blood oxygen signals, and blood pressure signals) can be uploaded by the mobile device 1503 to a cloud server 1507 via a cloud network 1505 via wireless transmission (e.g., wireless communication methods such as Bluetooth and WiFi). In the cloud server, the data is stored in a cloud data database. The above-mentioned system further includes an application program installed in the mobile device, which includes instructions for receiving and transmitting data between the wearable physiological signal sensing system 1500, the mobile device 1503, and the cloud server 1507. The above-mentioned application program can run on Android, Windows 10, or iOS operating system platforms, and uploads the collected related data / signals, such as electrocardiogram signals, heart sound signals, blood oxygen signals, and their waveforms, to the cloud server 1507 for storage, and then analyzes and processes the data using data analysis and feature extraction algorithms to generate an evaluation report, and provides medical advice based on the report.
[0076] Considering that elderly people are not familiar with using external electronic devices such as mobile devices, e.g., smartphones / tablet computers, etc. Referring to FIG. 5(b), according to another embodiment of the present invention, an embedded SIM card (eSIM) is installed on the circuit board 1301 (see FIG. 3(a)) of the wearable physiological signal sensing system 1500 and is integrated into the device (i.e., the wearable physiological signal sensing system 1500). Physiological data collected by the wearable physiological signal sensing system 1500 (including heart sound signals, electrocardiogram signals, blood oxygen signals, and blood pressure signals) can be directly uploaded from the cloud network 1505 to the cloud server 1507 through wireless transmission of the eSIM card. In the cloud server 1507, the data is stored in a cloud data database. Here, the eSIM card can be configured in the form of hardware, firmware, or software.
[0077] FIG. 16 illustrates a functional block diagram of a processing system 1650 operating on a computing system implemented as a cloud server 1507 or a mobile device 1503. Specifically, the processing system 1650 represents a processing system within the mobile device 1503 or a computing system implemented as a cloud server 1507 (FIGS. 15(a) and 15(b)), where the cloud server 1507 (or the mobile device 1503) executes instructions to perform computational processes in accordance with embodiments of the present invention, such as executing algorithms for detecting cardiac abnormalities as described above, extracting ECG signal features, etc. Those skilled in the art should understand that the instructions described above can be stored and / or executed as hardware, software, or firmware without departing from the spirit of the present invention. Furthermore, those skilled in the art should understand that the exact configuration of each processing system may vary, and the processing system 650 illustrated in FIGS. 6(a) and 6(b) is exemplary only.
[0078] In one embodiment, the mobile device 1503 is connected to an edge computing facility instead of a cloud server 1507. The goal is to minimize long-distance communication between the client and the server by reducing the amount of computation performed remotely. Edge computing allows enterprise application programs to be closer to data sources, such as IoT devices, and this architecture offers powerful advantages, including shorter response times and better bandwidth availability. Edge computing over 5G networks and mobile edge computing enable faster and more comprehensive data analysis. Therefore, in a preferred embodiment, data such as heart sounds, electrocardiograms, and pulse waves are processed by the edge computing facility using a 5G or 6G network, and tasks that cannot be processed by the edge computing facility are sent to an external cloud computing facility. The edge computing architecture can be divided into a "device layer" for data acquisition, an "edge layer" for real-time data processing, and a "cloud layer" responsible for secure storage and in-depth analysis. In this embodiment, each sensing device acquires physiological data through its built-in sensors. In one embodiment, the collected relevant data / signals, such as electrocardiogram signals, heart sound signals, blood oxygen level signals, and their waveforms, are uploaded to edge computing equipment, where the data is analyzed through data analysis and feature extraction algorithms. The "edge layer" is closest to the location where the data is generated, and its distribution range is wider than that of traditional cloud servers. Data can be processed and analyzed in real time, significantly reducing latency.
[0079] If the data requires deeper analysis, the information is uploaded to the cloud server 1507 for further analysis. Edge computing solves the bottleneck and latency issues of cloud computing, but if the "edge tier" determines that certain data requires more detailed analysis, it sends the data to the "cloud tier" for deeper computing and storage.
[0080] The processing system 1650 includes a processor 1601, a main memory 1602, a wireless transceiver 1603 (including a Bluetooth® module, a near field communication (NFC) module, etc., and a wireless network interface), a control device 1605 (e.g., a keyboard and pointing device), a video display 1607, an input / output (I / O) device 1609, and a signal generating device 1613 communicatively connected to the bus 6011.
[0081] A main memory 1602, a wireless transceiver 1603, a video display 1607, an input / output (I / O) device 1609, and any number of other peripheral devices are connected to the processor 1601 and exchange data with the processor 1601 over a bus (BUS) 6011 for use in application programs executed by the processor. The wireless transceiver 1603 is connected to an antenna and configured to transmit output voice and data signals and receive voice and data signals over a wireless communication channel. In one embodiment, the wireless communication channel may be a digital wireless communication channel such as WiFi, Bluetooth, RFID, NFC, 3G / 4G / 5G, eSIM, or any other future wireless communication interface.
[0082] Video display 1607 receives display data from processor 1601 and displays images on a screen for viewing by a user. Video display 1607 may be a liquid crystal display (LCD) or an organic light emitting diode (OLED) display.
[0083] Main memory 1602 is a device that transmits data to, receives data from, and stores data on processor 1601. Main memory 1602 may include non-volatile memory, such as read-only memory (ROM), which stores instructions and data necessary to operate the individual subsystems of the processing system and to start the system at startup. Those skilled in the art should understand that any number of memories can be used to perform this function. Main memory 1602 may also include volatile memory, such as random access memory (RAM), which stores instructions and data necessary for processor 1601 to execute software instructions to provide computing, such as the computing required for a system in accordance with the present invention. Those skilled in the art should understand that any type of memory can be used as volatile memory, and the specific type used is left to the design choice of the artisan.
[0084] The Bluetooth module is a module that enables the processing system 1650 to establish communication with similar devices, such as the wearable stethoscope device 1101, based on the Bluetooth technology standard. The near field communication (NFC) module is a module that enables the integrated heart sound and electrocardiogram signal sensing device 1500 to establish wireless communication with another similar device by bringing them into close proximity or contact. Other peripheral devices that can be connected to the processor 1601 include global positioning systems (GPS) and other positioning transceivers.
[0085] The processor 1601 is a processor, a microprocessor, or any combination of a processor and a microprocessor, and executes processing instructions according to the present invention. The processor 1601 can execute various application programs stored in a storage unit. These application programs can receive user input via a display having a touch screen or directly from a keyboard area. Some application programs stored in the main memory 1602 and executable by the processor 1601 may be application programs developed for UNIX, Android, iOS, Windows, Blackberry, or other platforms.
[0086] The present invention utilizes a patch-type wearable physiological signal sensing system that is attached to the human skin, allowing for direct measurement of desired physiological signals, such as heart sounds, electrocardiograms, and blood oxygen levels. While this method eliminates the need to attach the sensing system to clothing, it requires measuring signals through the clothing, which can result in noise interference caused by friction from the clothing, affecting the accuracy of the received signals. To eliminate the noise, noise reduction technology must be applied, which increases costs.
[0087] Preferably, the stethoscope can also be used to receive lung sounds, so the present invention can be used to monitor lung sounds, perform respiratory sound analysis, and perform respiratory health assessment. Similarly, if the device is attached around the intestinal tract, the stethoscope can also monitor intestinal peristalsis sounds. Obviously, the present invention can provide movement frequency monitoring, intensity analysis, and gastrointestinal function status assessment.
[0088] The present invention provides multimodal data integration, for example, the system can simultaneously acquire a user's body temperature, cardiac rhythm signal (PCG), electrocardiogram signal (ECG), pulse wave signal (PPG), and blood oxygen saturation (SpO2). The body temperature sensor 1306a acquires the user's body temperature (see Figures 13(a), 13(b), 13(c), 13(d), and 14). Multimodal features such as ECG RR interval, cardiac rhythm S1-S2 interval, pulse rise time, and blood oxygen saturation change are fusion-analyzed to build an artificial intelligence (AI) prediction model.
[0089] The multimodal data acquired by the present invention improves the accuracy and stability of blood pressure estimation and is advantageous for cardiovascular health risk assessment (e.g., detecting early signs of arrhythmia and valvular disease), respiratory health monitoring (e.g., using blood oxygen saturation and heart sound changes as indicators of respiratory abnormalities), and physiological stress load analysis (e.g., estimating physical fatigue state from heart sound fatigue state and electrocardiogram changes).
[0090] Based on the above features, the present invention provides novel heart sound analysis functions, such as delay time analysis: the time interval between S1 and S2 can be used to perform early detection of valvular diseases and arrhythmias; heart sound variability analysis: statistics on changes in the time intervals between multiple heart sounds are collected and used for stress response analysis; trend change monitoring: long-term S1 and S2 change trends are used as cardiovascular health indicators.
[0091] In addition to the advantages mentioned above, the present invention has the following technical features that make it superior to existing technologies. In terms of equipment and applications: (1) The blood oximeter module of the present invention has the ability to operate independently. As an independent device, the blood oximeter module (including PPG sensing) can record, store, and upload data on heart rate and blood oxygen level. The independent blood oximeter device can be placed on any part of the human body where PPG can be measured, including the fingertip, wrist, arm, etc., and is equipped with wireless transmission capabilities, allowing it to perform monitoring tasks independently without relying on a host device. (2) Telemedicine Applications: The present invention can be applied to remote care-related applications, such as home physiological monitoring of patients with chronic diseases (such as hypertension and cardiopulmonary disease). Medical institutions can remotely receive data such as heart sounds, blood pressure, SpO2, and HR to perform health tracking, abnormality warnings, and remote interventions, highlighting the value of the present invention in telemedicine and long-term care applications.
[0092] In terms of signal processing and AI algorithms: (1) Expandable application of multimodal models for disease detection: The multimodal signal model of the present invention (combining PCG, ECG, PPG, SpO2, etc.) can be applied to the detection and risk analysis of various diseases, such as cardiac arrhythmias, heart failure, valvular disease, abnormal lung sounds, and sleep-disordered breathing, thereby improving the accuracy of model predictions. (2) Effect of multimodal data signal denoising: The present invention performs dynamic filtering and denoising through cross-comparison of multimodal signals (e.g., ECG and PCG time series, PPG and SpO2 trends), reducing noise caused by movement, poor contact, or external interference, improving signal stability and data reliability, and improving the accuracy of subsequent analysis and diagnosis. The multimodal AI model of the present invention can be applied to disease detection and risk prediction by combining PCG, ECG, PPG, SpO2, etc., and the algorithms and architecture of the multimodal AI model can be applied to cardiac arrhythmias, abnormal lung sounds, sleep-disordered breathing, etc., improving the analysis capabilities of various physiological conditions.
[0093] The above is a preferred embodiment of the present invention, and those skilled in the art should understand that it is for the purpose of illustrating the present invention and does not limit the scope of the patent rights claimed by the present invention. The scope of patent protection is defined by the following claims and their equivalents. Any changes or modifications made by those skilled in the art without departing from the spirit or scope of this patent should be considered as equivalent changes or designs completed under the spirit of the disclosure of the present invention and should be included in the scope of the following claims. [Explanation of symbols]
[0094] 10 users 100 Heart Sound Detection System 101 Heart sound acquisition device (stethoscope) 103 Mobile Devices 107 Cloud Server 19 Voltage sensor structure 201 Piezoelectric material layer 203a Metal electrode 203b Metal electrode 205 Circuit Board 20 Piezoelectric patch structure 207 Substrate 209 Anti-allergy gel 211a Bottom electrode 211b Bottom electrode 211c bottom electrode 213 Insulating Layer 203 Metal Lead 204 Electrical Connections 215 Lid plate 217 Packaging Adhesives 220 base 206 Paste S401 Step S403 Step S405 Step 231 Skin resistance 503 Pressure Sensor 501 Capacitive Sensor 505 Circuit Board 507 Soundproof ring 601 Heart sound acquisition device (stethoscope) 601a Vibration membrane 607 Rubber frame (sound insulation ring) 605 Circuit Board 603 Piezoelectric Sensor 604 Line 631 Human skin 640 Multiple Holes 701 Capacitive Sensor 703 Piezoelectric Sensor 725 microprocessor 727 Storage Unit 729 Wireless Transmission Module 729a Antenna 731 Amplifier 731a Amplifier 733 Low-pass filter 733a low pass filter 737 battery pack 739 Power Management Unit 741 Charging Coil S801, S802, S803, S804, S805, S806, S807, S808, S809, S810, S811, S812, S813, S814 steps 900 Stethoscope Charging Device 902 Wireless Transmitting Coil 904 battery 1102 Pulse wave signal (PPG) 1104 Electrocardiographic signal (ECG) 1106 Pulse Transmit Time (PTT) 1200 methods S1201, S1202, S1203, S1204 steps 1300 Wearable Physiological Signal Sensing System 1300a Wearable physiological signal sensing system 1400 Wearable Physiological Signal Sensing System 1500 Wearable Physiological Signal Sensing System 1301 Circuit Board 1301a 1st surface 1301b 2nd surface 1302 stethoscope 1302a Vibration membrane 1302b Rubber frame (sound insulation ring) 1302c Piezoelectric Sensor 1303 Electrocardiogram stethoscope equipment 1304 Multiple ECG Patches 1304a 1st ECG patch 1304b Second ECG patch 1306 Oximeter 1306a Body Temperature Sensor 1411 Signal pre-processing circuit 1411a Signal Pre-processing Channel 1411b Signal Pre-processing Channel 1411c signal pre-processing channel 1415 microprocessor 1417 Storage Unit 1419 Wireless Transmission Module 1421 Battery Pack 1423 Power Management Module 1425 Charging Coil 1503 Mobile Devices 1505 Cloud Network 1507 Cloud Server 1601 processor 1602 main memory 1603 Wireless Transceiver 1605 Control device 1607 Video Display 1609 Input / Output (I / O) Devices 6011 communication connection bus 1613 Signal Generator 1650 Processing System
Claims
1. a system circuit board having an upper surface and a lower surface; a stethoscope disposed on the underside and electrically connected to the system circuit board, the stethoscope being used to sense the user's heart, lung, and bowel sound signals; an electrocardiogram electrode disposed on the lower surface and used to sense the electrocardiogram signal of the user; a blood oxygen meter disposed on the upper surface and used for sensing the blood oxygen concentration and pulse wave signal of the user; A wearable physiological signal sensing system comprising:
2. The wearable physiological signal sensing system of claim 1 , further comprising comparing the electrocardiogram signal with the pulse wave signal, or comparing the heart sound signal with the pulse wave signal, obtaining the user's pulse wave transit time, and estimating the user's continuous blood pressure.
3. 3. The wearable physiological signal sensing system of claim 2, wherein the continuous blood pressure is predicted by an artificial intelligence (AI) algorithm, which constructs a multivariate linear model using time-domain features of the pulse wave signal, the pulse wave transit time, and the user's height.
4. The stethoscope comprises: a vibration membrane disposed on the lower surface of the system circuit board; a sound-insulating ring that surrounds the diaphragm and forms a resonant cavity with the system circuit board; a piezoelectric sensor mounted on the system circuit board and attached to the user's skin; The wearable physiological signal sensing system of claim 1 , comprising:
5. 2. The wearable physiological signal sensing system of claim 1, further comprising an e-SIM installed on the system circuit board, wherein the wearable physiological signal sensing system is connected to an external mobile device, a cloud server, or an edge computing device via the e-SIM to facilitate transmission of the physiological signals, and the stethoscope collects biometric features and performs heart rate analysis to determine whether an emergency situation exists.