AHI estimation system and AHI estimation method

Abstract

Provided is a novel mechanism for estimating apnea hypopnea index (AHI). This AHI estimation system comprises: an AH information acquisition unit that acquires temporal pulse wave information from a subject, and acquires, on the basis of the pulse wave information, AH information indicating the time ratio in which the subject experiences apnea (A) and hypopnea (H) during sleep; and an AHI estimation unit that estimates an apnea hypopnea index (AHI) on the basis of the AH information. The AH information acquisition unit: acquires acceleration sensor information; evaluates, on the basis of the acceleration sensor information, whether the subject is in a sleeping state or a wakeful state; and if it is evaluated that the subject is in a sleeping state, acquires the AH information on the basis of the pulse wave information for when it is evaluated that the subject is in the sleeping state.

Description

AHI estimation system and AHI estimation method

[0001] [Related Application] This application claims priority to Japanese Patent Application No. 2024-208457, filed on 29 November 2024, entitled “AHI Estimation System and AHI Estimation Method,” the disclosure thereof is incorporated herein by reference in its entirety. The present invention relates to an AHI estimation system and an AHI estimation method.

[0002] As background technology for this field, Japanese Patent No. 7158641 (Patent Document 1) can be cited. This publication states that "biometric vibration signals of a subject during sleep are acquired without contact or restraint, and four parameters are extracted from them: respiratory rate, heart rate, phase coherence calculated from the instantaneous phase difference between the instantaneous phase of fluctuations in heart rate interval and the instantaneous phase of the respiratory pattern, and body movement ratio. Histograms of these parameters are created, feature images are generated from the histograms, and AHI is estimated by inputting these feature images into a pre-trained AHI estimation model" (see abstract).

[0003] Japanese Patent No. 7158641

[0004] Patent Document 1 describes a method for estimating AHI (Abdominal Hypothesis Intake) in a non-contact and non-restraint manner by using a sheet-shaped piezoelectric sensor to detect bio-vibration signals based on body movement, heart rate (cardiac pulsation), respiration, and vocalization. However, one aspect of this method is that it requires a bulky sheet-shaped piezoelectric sensor for AHI estimation, which lacks versatility and ease of use. Another aspect is that while the sheet-shaped piezoelectric sensor can detect a relatively large volume of bio-vibration signals, enabling accurate AHI estimation, it also presents challenges in terms of requiring greater processing power, power consumption, and memory capacity for detecting and transmitting these bio-vibration signals to the AHI estimation device.

[0005] This technology provides a new mechanism for estimating AHI.

[0006] To solve the above problems, for example, the configuration described in the claims is adopted. The present application includes multiple means for solving the above problems, but to give one example, it provides an AHI estimation system comprising: an AH information acquisition unit that acquires pulse wave information over time from a living organism and acquires AH information indicating the proportion of time during which the living organism experiences apnea (A) and hypopnea (H) during sleep based on the pulse wave information; and an AHI estimation unit that estimates the apnea-hypopnea index (AHI) based on the AH information.

[0007] This technology provides a new mechanism for estimating AHI. Other issues, configurations, and effects will be clarified by the following description of the embodiments.

[0008] Figure 1 shows an example configuration of the AHI estimation system 100 according to one embodiment. Figure 2 shows an example of the hardware configuration of the wearable device 101. Figure 3 shows an example of the hardware configuration of the user terminal 102. Figure 4 shows an example of the hardware configuration of the management server 103. Figure 5 shows an example of health management information according to one embodiment. Figure 6 shows an example of other health management information according to one embodiment. Figure 7 is an overall control flow diagram of the sleep health evaluation method according to one embodiment. Figure 8 is a sleep-wake evaluation flow diagram according to one embodiment. Figure 9 is an AH event information acquisition flow diagram according to one embodiment. Figure 10 is an AH information acquisition flow diagram according to one embodiment. Figure 11 is a health evaluation flow diagram according to one embodiment. Figure 12 is a diagram showing the method for acquiring AH event information according to one embodiment. Figure 13 is a graph showing the relationship between AH information acquired based on pulse wave information according to one embodiment and manual AHI acquired based on overnight polysomnography information. Figure 14 is a graph showing the relationship between estimated AHI according to one embodiment and manual AHI acquired based on overnight polysomnography information. Figure 15 shows an example of a health management display screen (partial) according to one embodiment.

[0009] The following description of this technology will be based on an AHI estimation system and AHI estimation method according to one embodiment, with reference to the drawings as appropriate. In each drawing, components having the same function may not be denoted by reference numerals or described again.

[0010] [AHI Estimation System and AHI Estimation Method] Figure 1 shows an example configuration of an AHI estimation system 100 according to one embodiment. The AHI estimation system 100 and AHI estimation method according to this technology are typically a system and method for monitoring a user's biometric information using a wearable device 101 and estimating AHI. The AHI estimation system 100 includes one or more wearable devices 101, one or more user terminals 102, and one or more management servers 103. The AHI estimation system 100 may also include one or more chargers 104.

[0011] In one embodiment, the wearable device 101, user terminal 102, management server 103, and charger 104 are configured to send and receive information from each other via a network, for example. Furthermore, the wearable device 101, user terminal 102, and charger 104 are configured to connect via short-range wireless communication such as Bluetooth®. These wearable devices 101, user terminal 102, management server 103, and charger 104 may be configured to send and receive information from each other via a network, for example, but only among themselves. Also, any two or more of the functional elements of the wearable device 101, user terminal 102, management server 103, and charger 104 may be integrated, or any of them may be separated into two or more units.

[0012] The wearable device 101 is a terminal that a user (an example of a living organism) wears on their own body. The user terminal 102 is a terminal used by the user of the wearable device 101 or the AHI estimation system 100. The management server 103 is a terminal used by the administrator who manages the AHI estimation system 100.

[0013] Each terminal and management server 103 in the AHI estimation system 100 may be a mobile device such as a smartphone, tablet, mobile phone, or personal digital assistant (PDA), or it may be a wearable device such as glasses (including goggles), a wristwatch, or clothing. The management server and terminals may also be a stationary or portable computer, or a server located in the cloud or on a network. From a functional standpoint, they may also be VR (Virtual Reality) terminals, AR (Augmented Reality) terminals, or MR (Mixed Reality) terminals. Alternatively, the management server and terminals may be a combination of multiple such terminals. For example, a combination of one smartphone and one wearable device can logically function as a single terminal. Each terminal may also be an information processing terminal other than those mentioned above.

[0014] Each terminal and management server 103 of the AHI estimation system 100 may optionally be equipped with a processor that executes an operating system, applications, and programs; a main memory such as RAM (Random Access Memory); an auxiliary memory such as an IC card, hard disk drive, SSD (Solid State Drive), and flash memory; a communication control unit such as a network card, wireless communication module, or mobile communication module; an input device such as a touch panel, keyboard, mouse, voice input device, motion controller, or motion detection device using image capture from a camera; an output device such as a monitor, display, printer, audio output device, or oscillator; and a timing device. The input device may also be equipped with sensors such as GPS, gyro sensors, and acceleration sensors. The output device may be a device or terminal that transmits information for output to an external monitor, display, printer, or other device.

[0015] The main memory stores various programs and applications (software modules), and the processor executes these programs and applications to realize each functional element of the overall system. These modules may be implemented by one or more programs or applications. Furthermore, each module may be implemented by an independent program or application, or as a subprogram or function within a single integrated program or application. These modules may also be implemented in hardware (hardware modules) by integrating circuits or employing a microcomputer.

[0016] Furthermore, each module may be implemented by a single processor or by multiple processors. Also, each module may be installed in a single terminal (including a management server) or divided among two or more terminals (including management servers) interconnected via a network. Furthermore, each module may be installed in each, or one or more, of the two or more terminals (including management servers) interconnected via a network. Consideration is also given to cases where some modules are implemented in different countries from others.

[0017] In this specification, each module is described as the entity (subject) that performs the processing; however, in reality, processing is carried out by the processor executing various programs and applications.

[0018] The auxiliary storage device stores various databases (DBs). A "database" is a collection of data organized and gathered to accommodate arbitrary data operations (e.g., extraction, addition, deletion, overwriting, etc.) from a processor or external computer. The auxiliary storage device is a functional element (storage unit) that stores one or more data collections. The implementation method of a database is not limited; for example, it may be a database management system, spreadsheet software, or text files such as XML or JSON. The database may be independently provided and connectable to a processor, etc. The database is intended, but not limited to, storing some or all of the information constituting the data collection in JSON format files. The database may be configured to store various types of information as a relational database or a non-relational database.

[0019] [Management Server] Figure 4 shows an example of the hardware configuration of the management server 103. The management server 103 is composed of a computer server located, for example, on the cloud. The management server 103 includes a main memory 401 and an auxiliary memory 402. The management server 103 also includes the processor 403 as described above, an input device 404, an output device 405, and a communication control unit 406.

[0020] The main memory 401 stores programs and applications such as the execution module 411, health management module 412, health information evaluation module 413, pre-processing module 414, post-processing module 415, and model adjustment module 416. The processor 403 executes these programs and applications to realize each functional element of the management server 103.

[0021] The execution module 411 controls the basic operation of the management server 103 for providing services by the AHI estimation system 100. For example, the execution module 411 works in conjunction with the execution module 311 of the user terminal 102 to control the basic operation for causing the user terminal 102 to execute the AHI estimation service. The execution module 411 can also support the operation of each module, as described later, and the coordination between each module. The execution module 411 may also be configured to work in conjunction with the execution module 211 of the wearable device 101, for example.

[0022] The health management module 412 acquires the user's biometric information. The health management module 412 also provides health management information to the user terminal 102. For example, the health management module 412 acquires the user's biometric information using a wearable device 101, and outputs the results of the user's health evaluation, which is evaluated by the health information evaluation module 413 based on the acquired biometric detection information of the user, to the user terminal 102. The health management module 412 is an example of an acquisition unit in this technology.

[0023] The health information evaluation module 413 evaluates the user's health status. The health information evaluation module 413 estimates and evaluates the user's health status based on various biometric detection information of the user acquired by the wearable device 101, for example. In this embodiment, the health information evaluation module 413 estimates the user's AHI using, for example, an AHI estimation model. The health information evaluation module 413 is an example of the AHI estimation unit in this technology. Hereinafter, the AHI estimated by the health information evaluation module 413 may simply be referred to as "estimated AHI".

[0024] The AHI estimation model M is a machine learning model trained to take features related to apnea and hypopnea (excluding AHI) obtained from the organism's overnight polysomnography (PSG) data as input, and to output the AHI obtained from the same overnight polysomnography data (hereinafter referred to as "manual AHI"). In this technology, a polynomial regression model is used as the machine learning model. Furthermore, as features related to apnea and hypopnea, AH information, which indicates the proportion of time during sleep in the organism that is apnea (A) and hypopnea (H), obtained from the organism's overnight polysomnography data, is adopted. AH information will be described later.

[0025] The preprocessing module 414 is an element that processes (preprocesses) various biometric detection information of the user prior to inputting it to the health information evaluation module 413. For example, the preprocessing module 414 preprocesses various biometric detection information of the user, which is the input, so that the health information evaluation module 413 can perform a more appropriate evaluation (including estimation). For example, the preprocessing module 414 acquires AH information, which indicates the percentage of time the user experiences apnea (A) and hypopnea (H) during sleep, based on the user's pulse wave information, as input information for the health information evaluation module 413. The preprocessing module 414 is an example of an AH information acquisition unit in this technology.

[0026] The post-processing module 415 is an element that performs additional processing (post-processing) on ​​the output of the health information evaluation module 413. For example, the post-processing module 415 performs post-processing on the estimated AHI output of the health information evaluation module 413 so that the user can better understand it. For example, the post-processing module 415 obtains the severity of sleep apnea syndrome based on the estimated AHI. The post-processing module 415 is an example of a symptom evaluation unit in this technology.

[0027] The model adjustment module 416 is an element that trains and further trains the AHI estimation model M. The model adjustment module 416 acquires overnight polysomnography information and manual AHI based on this overnight polysomnography information, acquires AH information based on the overnight polysomnography information, and trains the machine learning model to take the acquired polysomnography-derived AH information as input and output manual AHI. In addition, the model adjustment module 416 acquires new overnight polysomnography information at a predetermined timing, for example, and further trains the AHI estimation model M based on the acquired overnight polysomnography information. The model adjustment module 416 is an example of a model adjustment unit in this technology.

[0028] The auxiliary storage device 402 stores various types of information necessary for realizing the above-mentioned functions of the management server 103. For example, the auxiliary storage device 402 stores user information 410, health management information 420, AHI estimation model information 430, etc. The implementation method of each type of information stored in the auxiliary storage device 402 is not limited to this embodiment, and each type of information may be implemented in a distributed manner across multiple database servers or cloud applications.

[0029] User information 410 is, for example, information about a user of the AHI estimation system 100. Typically, user information 410 is a user of the wearable device 101. User information 410 is not limited to this, but may include, for example, user identification information, information about the user's attributes such as gender and age, and information from a health questionnaire about the user. Each piece of information is stored, for example, linked to user identification information.

[0030] Figures 5 and 6 show an example of health management information 420 according to one embodiment. Health management information 420 is information acquired, calculated, or estimated by the AHI estimation system 100. The figures illustrate, for example, information of the health management information 420 that is stored in an auxiliary storage device. Health management information 420 may include, for example, sleep / wake flag information (sleep / wake information) shown in (A), PPG sensor information and SpO2 information shown in (B), threshold (Th) information and event count information (AH event information) shown in (C), AH information (TRAH) shown in (D), and estimated AHI information. Each of these pieces of information is associated with time (time) information. The contents of each piece of information will be described later. The auxiliary storage device can store information other than the information shown in the figures.

[0031] The AHI estimation model information 430 is information necessary for using the AHI estimation model M in the AHI estimation system 100. The AHI estimation model information 430 may include, for example, the entire AHI estimation model M, i.e., the model function and parameters and the program for operating it, or it may include parameters for operating a machine learning model stored on an external server or the like.

[0032] [User Terminal] Figure 3 shows an example of the hardware configuration of the user terminal 102. The user terminal 102 is composed of a terminal such as a smartphone, tablet, notebook PC, or desktop PC. The user terminal 102 includes a main memory 301 and an auxiliary memory 302. The user terminal 102 also includes a processor 303 as described above, an input device 304, an output device 305, a camera 306, and a communication control unit 307.

[0033] The main memory 301 of the user terminal 102 stores programs and applications such as the execution module 311, health management module 312, health information evaluation module 313, pre-processing module 314, post-processing module 315, and model adjustment module 316. The processor 303 executes these programs and applications to realize each functional element of the user terminal 102. In other words, the main memory 301 of the user terminal 102 stores the same functional modules as the main memory 401 of the management server 103, and the user terminal 102 can perform the same processing as the management server 103.

[0034] As will be described later, the main memory 301 of the user terminal 102 stores a health management application program that manages the user's health based on sensor data acquired from the ring-shaped wearable device 101. This health management application program includes, for example, a sleep detection program that detects the sleep state and an application program for performing sleep analysis.

[0035] The functions of each of these modules are the same as those described above, so their explanation will be omitted. Note that the main memory 301 does not necessarily have to store all of the same functional modules as the management server 103; it may store only some of the functional modules (for example, the execution module 311 and the health management module 312).

[0036] The auxiliary storage device 302 stores various types of information necessary for realizing the above-mentioned functions of the user terminal 102. The auxiliary storage device 302 can store, for example, user information 310, health management information 320, AHI estimation model information 330, etc. Each of these pieces of information may be, for example, a part of the information stored in the management server 103 (for example, AH event information, health management information including AHI severity information, etc.).

[0037] [Wearable Device] The wearable device 101 is a device that can non-invasively acquire biological information of a living body such as a human as digital information by being worn on the living body. The wearable device 101 according to the present embodiment is, for example, a ring-shaped device worn on a human finger as shown in FIG. 1. FIG. 2 is an example of the hardware configuration of the wearable device 101 according to an embodiment.

[0038] The wearable device 101 includes a main storage device 201 and an auxiliary storage device 202. The management server 103 also includes a processor 203, a sensor module 204, a gyro sensor / accelerometer module 205, a charge management module 206, and a communication control unit 207 as described above. The sensor module 204 and the gyro sensor / accelerometer module 205 are examples of input devices.

[0039] The processor 203 is, for example, a digital signal processing device that controls the operations of the sensor module 204, the gyro sensor / accelerometer module 205, the charge management module 206, and the communication control unit 207. As the processor 203, for example, an MCU (Micro Controller Unit), an MPU (Micro Processor Unit), or the like can be provided. As the storage device, for example, a flash memory or an EEP-ROM (Electrically Erasable Programmable Read-Only Memory) can be provided. The wearable device 101 may include an output device not shown.

[0040] The sensor module 204 controls, for example, the operation of various sensors provided in the wearable device 101 and the sensor signals. The sensor module 204 also controls, for example, the operating conditions of the sensors. The sensor module 204 may also include digital processing functions such as a Digital Signal Controller (DSC), Digital Signal Processor (DSP), or FPGA (Field Programmable Gate Array) that process sensor data acquired by the sensors in real time. The sensor module 204 includes, for example, any combination of resistors, capacitors, coils, diodes, transistors, etc., and can optionally include circuits such as amplifiers, clocks, bandgap references, digital isolators, RC filters (e.g., low-pass filters, high-pass filters), band-pass filters, band-elimination filters, and analog-to-digital converters. Furthermore, the sensor module 204 may include analog circuit blocks such as an RMS-DC converter circuit, an average value detection circuit, an RMS detection circuit, a signal monitoring circuit, and an adaptive threshold setting circuit that process signals acquired via the sensors. Furthermore, the sensor module 204 can be configured to perform various signal processing operations using any combination of analog circuits and / or digital processing functions.

[0041] The wearable device 101 includes, for example, a pulse wave sensor S1, a temperature sensor S2, a microwave sensor S3, an electrocardiogram sensor S4, etc., and the sensor module 204 is connected to these sensors S1 to S4. These sensors S1 to S4 are, for example, examples of signal detection devices (sensors) for detecting various kinds of biological information, and are examples of input devices for the wearable device 101. Each sensor S1 to S4 may also be equipped with a digital signal controller (DSC) that processes sensor data in real time.

[0042] The pulse wave sensor S1 is a Photoplethysmogram (PPG) sensor that detects volume changes in blood vessels (e.g., arteries) of a living body. In the ring-type wearable device 101, the pulse wave sensor S1 can typically be a reflection-type pulse wave sensor including a light-emitting element that emits light of a predetermined wavelength toward the living body and a light-receiving element that detects the light reflected in the living body. The light-emitting element can be constituted by, for example, various Light-emitting diodes (LEDs), and the light-receiving element can be constituted by, for example, various Photo Diodes (PDs).

[0043] By analyzing the PPG signal acquired by the PPG sensor, various biological information can be obtained. Specifically, for example, the light-emitting element can include a green LED that generates light with a central wavelength of 500 nm or more and 600 nm or less. Since green light has a high absorption rate by hemoglobin in blood and is less affected by ambient light such as sunlight, a relatively stable volume pulse wave can be measured. Based on the pulsation of the volume pulse wave by this green light, for example, highly reliable heart rate and heart rate variability information can be obtained.

[0044] In addition, oxyhemoglobin, deoxyhemoglobin (also referred to as reduced hemoglobin), and glycated hemoglobin can have different absorption coefficients (typically, absorption spectra) with respect to the wavelengths of red light or near-infrared light. Thus, as a preferred example, for example, the light-emitting element can include a combination of a red LED with a central wavelength of 630 nm or more and 690 nm or less and an infrared LED with a central wavelength of 810 nm or more and 990 nm or less. Based on the difference in the absorption coefficients of these two lights for oxyhemoglobin and deoxyhemoglobin, SpO2 (Peripheral Blood Oxygen Saturation), blood oxygen concentration, and heart rate can be obtained.

[0045] As another preferred example, the light-emitting element may include, for example, a combination of LEDs that generate three or more (e.g., three or four) different lights with central wavelengths of 600 nm to 990 nm. Based on the difference in the extinction coefficients of oxyhemoglobin, deoxyhemoglobin, and glycated hemoglobin, blood hemoglobin concentration, blood glycated hemoglobin concentration, etc., can be calculated.

[0046] Furthermore, the light-emitting element may include LEDs that generate light of different wavelengths than those mentioned above. Since hemodynamic information is convolved into the shape of the pulse wave, blood pressure can be estimated by analyzing the shape of the volume pulse wave. Also, by analyzing the shape of the volume pulse wave, blood viscosity can be estimated, and blood glucose levels can be detected from the blood viscosity. For blood glucose measurement, spectroscopic methods (e.g., near-infrared spectroscopy, Raman spectroscopy, infrared spectroscopy, etc.) may be used. For example, the light-emitting element may include a combination of two or more (e.g., two or three) LEDs that generate near-infrared light with a central wavelength of approximately 1200 nm to 1600 nm. This allows blood glucose levels to be calculated based on the light absorption spectrum derived from glucose.

[0047] The pulse wave sensor S1 of this embodiment is, for example, a multi-wavelength PPG sensor capable of emitting and receiving (detecting) at least infrared and red light, and capable of calculating SpO2.

[0048] The temperature sensor S2 is an optional sensor capable of detecting the temperature (body temperature) of a living organism. Typically, the temperature sensor S2 can detect information regarding the skin temperature or core body temperature of a living organism. The temperature sensor S2 is not limited to this, but for example, a thermopile-type infrared sensor can be used.

[0049] The microwave sensor S3 is an optional sensor that can be installed and, for example, detect the frequency characteristics around the resonant frequency by radiating microwaves onto a living organism. By analyzing these frequency characteristics, information such as skin moisture content, sweat volume, and blood glucose levels can be obtained.

[0050] The electrocardiogram sensor S4 is an optional sensor capable of detecting electrical activity associated with the movement of the heart. The electrocardiogram sensor S4 can be used as one of the measurement electrodes in various lead methods. Therefore, for example, the electrocardiogram sensor S4 may be configured to obtain electrocardiogram information in cooperation with other electrocardiogram sensors S4 provided on other wearable devices 101. As an example, electrocardiogram information can be obtained using the bipolar lead method with two ring-shaped wearable devices 101 worn on the fingers of both the left and right hands. Alternatively, electrocardiogram information may be obtained by a combination of a ring-shaped wearable device 101 worn on the finger of one hand, a wristwatch-shaped wearable device 101 worn on the wrist of the other hand, a user terminal 102 (smartphone, etc.), or a medical device, etc.

[0051] The gyro sensor / accelerometer module 205 is equipped with a gyro sensor and an accelerometer. The gyro sensor / accelerometer module 205 can detect the angular velocity and acceleration of the wearable device 101 and can detect changes in the position of the wearable device 101 (displacement, tilt, movement, etc.). In addition, the gyro sensor / accelerometer module 205 can acquire information regarding the posture, activity level, activity intensity, calories burned, steps taken, and behavioral discrimination of the person wearing the wearable device 101.

[0052] Furthermore, the gyro sensor / accelerometer module 205, like the sensor module 204 described above, can optionally be equipped with digital processing functions such as a DSC, DSP, FPGA, etc., for processing the sensor data acquired by the sensor in real time, as well as various analog circuits.

[0053] The charge management module 206 is an element that manages charging in the charging system provided in the wearable device 101. Figure 2 shows an example of a wireless charging system that charges the secondary battery 208 from the charger 104 without physical contact via a wireless charging receiver 209. However, the wearable device 101 may be configured to include, in place of and / or in addition to the wireless charging receiver 209, contact electrodes (not shown) for contact charging with the charger 104.

[0054] The wireless charging system includes, for example, a charge management module 206, a secondary battery 208, and a wireless charging receiver 209 provided in a wearable device 101, and an external charger 104. The charge management module 206 manages the charging process to prevent overcurrent, overvoltage, overheating, etc., of the secondary battery 208. The secondary battery 208 is not particularly limited, but examples include lithium-ion batteries, lithium polymer batteries, and all-solid-state lithium-ion batteries.

[0055] Furthermore, various charging systems can be employed as wireless charging systems, such as electromagnetic induction, magnetic field resonance, electric field coupling, and radio wave reception. For example, a wireless charging system compatible with Near Field Communication (NFC) standards or Qi standards can be preferably adopted in this embodiment. Among these, a system compatible with NFC standards is particularly preferable because it allows for miniaturization and cost reduction.

[0056] The communication control unit 207 is configured to connect to other terminals (for example, user terminal 102) via a network. The network can be wired or wireless, and each terminal can send and receive information from each other via the network. In the case of wireless communication, communication devices conforming to standards such as Bluetooth®, Wi-Fi®, or LTE® can be used. In this embodiment, the communication control unit 207 connects to the user terminal 102 via BLE (Bluetooth Low Energy) communication.

[0057] The wearable device 101 stores programs and applications such as an execution module 211, a health management module 212, a health information evaluation module 213, a pre-processing module 214, a post-processing module 215, and a model adjustment module 216 in its main memory 201. The processor 203 then executes these programs and applications to realize each functional element of the wearable device 101. In other words, by storing the same functional modules in the main memory 201 of the wearable device 101 as in the main memory 401 of the management server 103, the wearable device 101 can perform the same processing as the management server 103.

[0058] The functions of each of these modules are the same as described above, and their explanation will be omitted. Note that the main memory 201 does not necessarily have to store all of the same functional modules as the management server 103. Alternatively, it may store only some of the same functional modules as the management server 103 (for example, the pre-processing module 214). Furthermore, each functional module may be composed of analog circuits, either partially or entirely. As will be described later, as an example, the main memory 201 stores the pre-processing module 214.

[0059] The auxiliary storage device 202 stores various types of information necessary for realizing the above-mentioned functions of the wearable device 101. The auxiliary storage device 202 can store, for example, user information, health management information, AHI estimation model information, etc. In this embodiment, the auxiliary storage device 202 stores, for example, a portion of the information stored in the management server 103 (for example, health management information including AH event information and sleep-wake information).

[0060] [Sleep Health Assessment Method] Next, a sleep health assessment method according to one embodiment will be described. The AHI estimation system 100 can assess the sleep health status of a user wearing the wearable device 101 by operating the wearable device 101 in "sleep health assessment mode".

[0061] In sleep health assessment mode, the following items related to "breathing status during sleep" are evaluated, for example: • Estimation of AHI • Assessment of the severity of sleep apnea syndrome • Time data of sleep apnea-hypopnea events

[0062] Figure 7 is an overall control flow diagram of a sleep health evaluation method according to one embodiment. When the user terminal 102 receives a selection (i.e., an operation instruction) to turn "Sleep Health Evaluation Mode" "ON" through user operation, the execution module 311 of the user terminal 102 sends an instruction to the wearable device 101 to operate in Sleep Health Evaluation Mode. The execution module 311 of the user terminal 102 may also send information to the management server 103 indicating that it has received an instruction from the user to turn on Sleep Health Evaluation Mode.

[0063] Furthermore, the execution module 311 may, when the "sleep health evaluation mode" is ON, send an instruction to the wearable device 101 to operate in sleep health evaluation mode at a predetermined time (for example, the scheduled bedtime of 9 PM) or during a predetermined time period (for example, from the scheduled bedtime of 9 PM to 6 AM the next day). Alternatively, the execution module 311 may send an instruction to the wearable device 101 to operate in sleep health evaluation mode at a predetermined time (for example, the scheduled bedtime of 9 PM) or during a predetermined time period (for example, from the scheduled bedtime of 9 PM to 6 AM the next day).

[0064] In sleep health assessment mode, the wearable device 101 (ring) generally performs (1) sleep / wake assessment and (2) acquires AH event information. Then, for example, when the user wakes up, it transmits the acquired information to the management server 103 via the user terminal 102. Based on this information, the management server 103, for example, (3) acquires AH information and (4) estimates AHI based on the acquired AH information. The management server 103 also performs (5) a health assessment related to sleep. The management server 103 adjusts the (6) AHI estimation model. The management server 103 then transmits the health assessment related to sleep to the user terminal 102, and the user terminal 102 provides the health assessment results to the user. The following describes each process. However, this technology does not require all of the above processes (1) to (6) to be performed.

[0065] (1) Sleep-Wake Evaluation Figure 8 is a sleep-wake evaluation flowchart according to one embodiment. The execution module 211 of the wearable device 101 operates each module in sleep health evaluation mode based on instructions from, for example, the user terminal 102. In sleep health evaluation mode, the health management module 212 and the pre-processing module 214 of the wearable device 101 execute the sleep-wake evaluation flow 800.

[0066] The sleep-wake evaluation flow 800 includes, for example, the following steps: acquiring acceleration sensor information (S810), evaluating sleep or wakefulness per unit time (S820), and assigning sleep flags or wakefulness flags (S830, 840, 850).

[0067] The health management module 212 first acquires acceleration information from the gyro sensor / accelerometer module 205 (step S810). Here, acceleration information is an example of user activity level information. The health management module 212, for example, sends an instruction to the gyro sensor / accelerometer module 205 to operate the acceleration sensor and acquire acceleration information over time at a predetermined sampling rate. Although the conditions for acquiring acceleration information are not strictly limited, for example, the sampling rate can be approximately 10 to 30 Hz (for example, approximately 12.5 Hz). Also, the acceleration information can be, for example, three-axis acceleration information in the x, y, and z axis directions.

[0068] The preprocessing module 214 evaluates whether the user wearing the wearable device 101 is in a sleep or wakeful state based on the acquired acceleration information (step S820). For sleep / wake determination based on acceleration information (an example of activity level information), a sleep determination algorithm can be used, for example. Examples of sleep determination algorithms include the Cole-Kripke algorithm and the Sadeh algorithm.

[0069] In this embodiment, the Cole-Kripke algorithm is employed. The preprocessing module 214 obtains, for example, representative values ​​of activity intensity data within a predetermined time interval (window) from the acquired acceleration information. Examples of representative values ​​of activity intensity data for a predetermined time include the mean, median, and peak values ​​of the vector norm (which may be a simplified norm with the square root omitted) for 0.5 to 5 minutes (for example, 1 minute). The preprocessing module 214 may, as an optional step, take a moving average of the representative values ​​of the activity intensity data within a 1-minute window and average them. Next, the preprocessing module 214 calculates a weighted score for the representative values ​​of the activity intensity data according to the Cole-Kripke algorithm. The weighted score can be calculated, for example, by applying the weights of the Cole-Kripke algorithm to the data in the preceding and succeeding windows (for example, 3 minutes before and after) and summing them with the data in the window of the time to be evaluated. The weights are not limited to these examples, but one example is to set the weight of the time being evaluated to "1", then the weights of times within ±1 minute to "0.20", and the weights of times within ±2 minutes to "0.04".

[0070] The preprocessing module 214 then determines, for example, that the user is "sleeping" if the weighted score for the time period being evaluated is less than a predetermined threshold, and that the user is "awake" if the weighted score is greater than the predetermined threshold. The threshold for the weighted score cannot be generalized as it depends on the configuration of the acceleration sensor and how the weights are assigned, but it can be set based on pre-acquired weighted scores and the user's actual activity status. Furthermore, the threshold for the weighted score can be empirically set and updated, for example, according to the characteristics of the user's activity intensity.

[0071] Then, if the preprocessing module 214 evaluates the state as "sleep" (Y in S830), it associates a "sleep flag" indicating sleep with the evaluation time (S840). Also, if the preprocessing module 214 evaluates the state as "awake" (N in S830), it associates an "awake flag" indicating wakefulness with the evaluation time (S850). The preprocessing module 214 stores (outputs) sleep-wake information, which associates the evaluation time with sleep or wakefulness flags (sleep / wakefulness flag information), in the auxiliary storage device 202.

[0072] The processing steps S810 to S850 described above may be performed by the gyro sensor / accelerometer module 205, and the processing results (for example, sleep-wake information) may be acquired by the pre-processing module 214.

[0073] (2) Acquisition of AH event information If the sleep-wake evaluation flow 800 described above is evaluated as "sleep", the health management module 212 executes the AH event information acquisition flow 900 in parallel with the sleep-wake evaluation flow 800. Figure 9 is an AH event information acquisition flow diagram according to one embodiment.

[0074] The AH event information acquisition flow 900 includes, for example, the following steps: pulse wave sensor information acquisition step (S910), SpO2 information acquisition step (S920), threshold setting step (S930), second average SpO2 value calculation step (S940), average SpO2 value evaluation step (S950), AH event addition step (S960), confirmation step (S970), confirmation step (S980), and AH event information output step (S990).

[0075] First, the health management module 212 acquires pulse wave sensor information from the sensor module 204 (step S910). The health management module 212, for example, sends an instruction to the sensor module 204 to operate the pulse wave sensor S1 and acquire a photoelectric volume pulse wave (PPG) signal over time at a predetermined sampling rate. Here, as described above, the pulse wave sensor S1 is equipped with a red LED and an infrared (IR) LED, and is capable of detecting reflected red and infrared light from the living body. The PPG signal includes the intensity signal of the reflected red light from the living body and the intensity signal of the reflected infrared light from the living body. Although the conditions for acquiring the PPG signal are not strictly limited, for example, the sampling rate can be approximately 10 to 50 Hz (for example, approximately 25 Hz).

[0076] The preprocessing module 214 then acquires SpO2 information based on the acquired PPG signal (S920). The preprocessing module 214 may, for example, cause the DSC of the sensor module 204 or pulse wave sensor S1 to perform part or all of the process of calculating SpO2 from the acquired PPG signal. In this embodiment, the preprocessing module 214 causes the DSC to perform the following process and acquires the calculated SpO2.

[0077] Of the PPG signal, the direct current (DC) component originates from the absorption of light by venous blood and tissues and hardly changes with the heartbeat (pulsation). On the other hand, the alternating current (AC) component fluctuates in accordance with the periodic increase and decrease in blood (arterial blood) volume due to the heartbeat. From this, the oxygenation state of arterial blood can be calculated through the ratio of the AC and DC components of red light and infrared light. Therefore, the DSC, for example, converts the PPG signal from red LED and infrared LED into an ADC signal through a ΔΣ A / D converter, divides this ADC signal into pulses corresponding to the heartbeat, and calculates SpO2 for each pulse. SpO2 can be calculated, for example, by the following formula.

[0078]

[0079] Here, in the formula, AC_ir: maximum value of infrared LED - minimum value of infrared LED AC_red: maximum value of red LED after HPF - minimum value of red LED DC_ir: peak value of infrared LED DC_red: peak value of red LED. A, B, and C are calibration coefficients that change depending on the sensor and installation conditions, etc., and can be set based on an empirical calibration formula by conducting tests in advance. Note that the values ​​after passing through a high-pass filter or moving average filter may be used for AC_ir, AC_red, DC_ir, and DC_red.

[0080] In the following steps S930 to S970, AH event information is acquired based on the sequentially acquired SpO2. Figure 12 is a diagram showing a method for acquiring AH event information according to one embodiment. In the following description, Figure 12 will be referred to as appropriate. In the graph of Figure 12, the solid line shows the measurement results of SpO2.

[0081] Here, AH event information refers to information indicating the number of times an apnea-hypopnea event (AH event), in which the living organism is in an apnea (A) state and a hypopnea (H) state, occurs per unit time. For example, it can be defined by the number of times SpO2 falls below a predetermined threshold per unit time. In this embodiment, the number of AH events is counted for each first time window. Whether or not an AH event has occurred is evaluated for each second time window, by further dividing the first time window into a plurality of second time windows.

[0082] Although the processing in steps S930 to S970 is described as being performed by the pre-processing module 214, it is also possible that the sensor module 204 (or sensor S1) performs some or all of the processing, and the pre-processing module 214 acquires the processing results (for example, AH event information).

[0083] First, the preprocessing module 214 sets a threshold for acquiring AH event information (S930). As a predetermined threshold, SpO2 can be used to distinguish between a normal breathing state during sleep and apnea (A) and hypopnea (H) states. In a healthy body, the resting SpO2 is 100% throughout sleep and wakefulness. For example, if the SpO2 is in the range of approximately 95% to 100%, it can be determined that it is a normal breathing state in which no apnea or hypopnea is occurring. Also, for example, if the SpO2 is in the range of approximately 85% to 90%, it can be determined that it is a hypopnea state, and if the SpO2 is approximately 70% or less, it can be determined that it is an apnea state.

[0084] Therefore, the pre-treatment module 214 can adopt an index that can distinguish between a normal respiratory state and an AH state as a predetermined threshold. In this embodiment, for example, the pre-treatment module 214 sets the threshold to a value 3% lower than the average value of SpO2 at the first time (i.e., 97% of the average value). In Figure 12, the dotted line indicated by BL shows the average value of SpO2 (first average value) at the first time (in this case, 5 minutes), and the dotted line indicated by Th shows the threshold for the first time.

[0085] The unit time (first time) used as the basis for counting the number of AH events can be set within a range that balances data reliability and load, for example, 1 to 10 minutes (for example, 5 minutes) can be used as a guideline. The first average value and threshold are calculated for each of the first time windows.

[0086] Next, the preprocessing module 214 calculates a second average SpO2 value, which is the average of SpO2 values ​​over a second time period that is shorter than the first time period, during the first time period (S940). For example, the second time period can be approximately 1 / 10 to 1 / 100 of the first time period. Figure 12 shows the case where the second time window is 10 seconds. Within the first time period of 5 minutes, 30 second windows of 10 seconds each are formed.

[0087] The preprocessing module 214 then evaluates whether the second mean SpO2 value falls below the predetermined threshold (second mean SpO2 < threshold?) (S950). In other words, it evaluates whether an apnea-hypopnea event (AH event) has occurred in the second time window. If the second mean SpO2 value is less than the predetermined threshold (Y in S950), the preprocessing module 214 assumes that an AH event has occurred and adds 1 to the AH event count (+1) (S960). The preprocessing module 214 stores the AH event count in the auxiliary storage device 202 each time, for example, linked to time information (for example, the start time of the first time window). If the second mean SpO2 value is greater than or equal to the predetermined threshold (N in S950), the preprocessing module 214 assumes that no AH event has occurred and proceeds to the next step without adding to the AH event count.

[0088] The preprocessing module 214 checks, for example, whether it has evaluated whether an AH event occurred for all second time windows within the first time window (S940-S960) (S970). If it has evaluated whether an AH event occurred for all second time windows (30 second windows in Figure 12) (Y in S970), the preprocessing module 214 moves on to the next step S980. If it has not evaluated whether an AH event occurred for all second time windows (N in S970), the preprocessing module 214 returns to step S940 and evaluates whether an AH event occurred for the remaining second time windows.

[0089] The preprocessing module 214 checks whether the user is evaluated as "awake" in the sleep-wake evaluation flow 800 (S980). If the user is evaluated as "awake" (Y in S980), the preprocessing module 214 proceeds to the next step S990. If the user is not evaluated as "awake" (N in S980), the preprocessing module 214 returns to step S930 and obtains the number of AH events for the next first time window. In other words, the preprocessing module 214 repeatedly executes steps S910 to S980 in the sleep-wake evaluation flow 800 from the time the user is evaluated as "sleeping" until the time they are evaluated as "awake".

[0090] When the user is evaluated as "awake," the preprocessing module 214 stores (outputs) the number of AH events acquired for each first time window, for example, as shown in Figure 5(C), in the auxiliary storage device 202 as AH event information (for example, the start time) (S990).

[0091] In the sleep-wake evaluation flow 800, if the user is evaluated as "sleeping", the pre-processing module 214, in cooperation with the pre-processing module 314 of the user terminal 102, transmits the AH event information and sleep-wake information stored in the auxiliary storage device 202 to the user terminal 102. The pre-processing module 314 of the user terminal 102, in cooperation with the pre-processing module 414 of the management server 103, transmits the AH event information and sleep-wake information acquired from the wearable device 101 to the management server 103. The pre-processing module 414 of the management server 103 stores the acquired AH event information and sleep-wake information in the auxiliary storage device 402. Here, the information transmitted and received between the wearable device 101, the user terminal 102, and the management server 103 is flag information (sleep-wake information) associated with time information related to a predetermined time window, and event count information (AH event information) associated with time information related to a first time window, and the amount of information is reduced compared to raw data (or simply digitized data).

[0092] (3) Acquisition of AH information Next, the preprocessing module 414 in the management server 103 acquires AH information for estimating AHI. Here, AH information is information that indicates the proportion of time during sleep when the body experiences apnea (A) and hypopnea (H).

[0093] Figure 10 is a flowchart illustrating an event information acquisition according to one embodiment. The event information acquisition flow 1000 includes, for example, the following steps: acquiring AH event information (S1010), acquiring the total duration of AH events (S1020), acquiring sleep-wake information (S1030), acquiring the total duration of sleep (S1040), acquiring AH information (S1050), and outputting AH information (S1060). Here, steps S1010 to S1020 and steps S1030 to S1040 are in no particular order.

[0094] The preprocessing module 414, for example, obtains AH event information from the auxiliary storage device 402 (S1010) and obtains the total duration of AH events during the evaluation period (S1020). Total duration of AH events T AH For example, it can be calculated from the following formula: T AH = Σ (Number of AH events in each first time) × (Second time) If the second time is the same for all first times, the preprocessing module 414 multiplies the total number of AH events in all first times by the second time to obtain the total duration T of the AH events. AH It is possible to calculate this.

[0095] Furthermore, the preprocessing module 414 acquires sleep-wake information from the auxiliary storage device 402 (S1030), for example, and obtains the total sleep time during the evaluation period (S1040). Total sleep time T SL For example, it can be calculated from the following formula: T SL = (Total number of sleep flags) × (Determined time in the sleep-wake evaluation flow 800) Note that depending on how the flags are recorded, the total sleep time T SL This can be calculated by subtracting the end time of sleep (the start time of wakefulness) from the start time of sleep.

[0096] And the preprocessing module 414 obtains the AH information from the total time T AH of the obtained AH events and the total time T SL of sleep (S1050). The AH information Trah can be calculated, for example, from the following formula. Trah = T AH / T SL The preprocessing module 414 records (outputs) the obtained AH information in the auxiliary storage device 402 (S1060).

[0097] FIG. 11 is a health assessment flowchart according to an embodiment. The health assessment flow 1100 includes, for example, the following steps: an estimated AHI acquisition step (S1110), a severity acquisition step (S1120), and an output step (S1130).

[0098] (4) The health information evaluation module 413 of the AHI estimation management server 103 estimates the AHI using the AHI estimation model (S1110). The health information evaluation module 413 acquires the AH information from the auxiliary storage device 402 and inputs this AH information into the AHI estimation model M to obtain the estimated AHI as an output.

[0099] FIG. 13 is a graph showing the relationship between the AH information obtained based on the pulse wave information according to an embodiment and the manual AHI obtained based on the all-night sleep polygraph information. The curve in the figure is the result of regression analysis (polynomial regression) for each data. Although the relationship between the AH information and the manual AHI can be fitted by a quadratic function, the variation becomes larger in the region where the manual AHI is higher, and it can be said that there is a limit to regressing the complex pattern of the manual AHI.

[0100] FIG. 14 is a graph showing the relationship between the estimated AHI according to an embodiment and the manual AHI obtained based on the all-night sleep polygraph information. As shown in FIG. 14, a high linear relationship is observed between the estimated AHI and the manual AHI. Therefore, it can be confirmed that an estimated AHI having a high correlation with the manual AHI can be obtained even when using the AH event information obtained and simply processed and simplified in the wearable device 101.

[0101] (5) Severity Acquisition Process Next, the post-processing module 415 of the management server 103 acquires the severity of AHI based on the estimated AHI according to the pre-set conditions (S1120). In other words, the severity of AHI is the result of evaluating the respiratory state during sleep and is an example of the sleep health evaluation result. The post-processing module 415 can acquire, for example, four types of AHI severity, a to d, based on the following conditions: a. Estimated AHI < 5: Normal breathing b. 5 ≤ Estimated AHI < 15: Mild obstructive sleep apnea c. 15 ≤ Estimated AHI < 30: Moderate obstructive sleep apnea d. 30 ≤ Estimated AHI: Severe obstructive sleep apnea

[0102] The health management module 412 of the management server 103 stores (outputs) acquired information regarding the severity of AHI (sleep health assessment results) in the auxiliary storage device 402 (S1130). The health management module 412 of the management server 103 also works in cooperation with the health management module 312 of the user terminal 102 to display a screen on the user terminal 102's display showing the severity of AHI (sleep health assessment results) (S1130).

[0103] Specifically, the health management module 412 transmits information regarding the severity of AHI (for example, any of the information a to d representing the severity of AHI) to the user terminal 102 as a result of a sleep health assessment. The health management module 312 of the user terminal 102 records the received information regarding the severity of AHI in the auxiliary storage device 302. The health management module 312 also displays a health management display screen representing the severity of AHI on the user terminal 102's display based on the received information regarding the severity of AHI.

[0104] Figure 15 shows an example of a health management display screen (partial) according to one embodiment. The health management module 312 displays, for example, one of four pre-prepared health management display screens corresponding to the severity of AHI, on the display, which corresponds to the severity of the user's AHI. Figure 15(A) is an example screen showing that the sleep health evaluation result is "normal breathing", (B) is an example screen showing that the sleep health evaluation result is "mild obstructive sleep apnea", and (C) is an example screen showing that the sleep health evaluation result is "severe obstructive sleep apnea".

[0105] The health management module 312 displays a message 1510 representing the results of the sleep health assessment on each health management display screen. In addition, the health management module 312 also displays blood oxygen concentration fluctuation information 1520 on screens indicating that the sleep health assessment result is "mild" to "severe" obstructive sleep apnea. Specifically, the health management module 312 obtains AH event information for the corresponding date and time from the auxiliary storage device 402 and displays the number of AH events that occurred during sleep in chronological order based on this AH event information.

[0106] The health management module 312 can, for example, associate AH event information with a pre-set format, and display the number of AH events as a bar graph for each first time period. The health management module 312 can, for example, change the display format of the bars according to the number of AH events per first time period. The health management module 312 displays the bars in the graph in a way that emphasizes them as the number of AH events per first time period increases. For example, bars can be displayed in a brighter color or a darker color as the number of AH events increases. In addition, although AH event information is recorded every first time period (for example, every 5 minutes), the health management module 312 may also display the number of AH events during sleep every third time period (for example, every 10 minutes), which is longer than the first time period.

[0107] In this technology, AH event information consists of approximately 96 time-event occurrence counts, for example, if the first time period is 5 minutes and the sleep time is 8 hours. Similarly, sleep-wake information consists of approximately 480 time-flag information, for example, if the predetermined period is 1 minute and the sleep time is 8 hours. Therefore, even when AH event information is sent from the wearable device 101 to the user terminal 102 in conjunction with the user's awakening, a smaller amount of data can be transmitted in a shorter time, while reducing power consumption. As a result, even a small wearable device 101, such as a ring, with limited battery capacity, can monitor the user's health status during sleep at high frequencies of 25 Hz or 12.5 Hz, enabling health management and highly accurate health assessment during sleep.

[0108] (6) Adjust the AHI estimation model. The model adjustment module 416 of the management server 103 can adjust the AHI estimation model M in a timely manner. The adjustment of the AHI estimation model M may be called additional learning, fine tuning, transfer learning, etc.

[0109] The model adjustment module 416 acquires polysomnography (PSG) information for use in additional learning and manual AHI based on this PSG information. The PSG information is typically precise PSG information based on a precise PSG examination, but may also be simplified PSG information from a simplified PSG examination. The PSG information includes manual AHI, pulse wave information, and respiratory pattern information.

[0110] This information may be obtained, for example, by the administrator of the management server 103, or by obtaining it from a medical institution or a data bank. • If the administrator obtains the information, for example, they can attach a polysomnography device and a ring-shaped wearable device 101 to the subject and acquire biological information from each device. • An example of a data bank is PhysioNet (https: / / physionet.org / about / ).

[0111] The model adjustment module 416, for example, works in cooperation with the preprocessing module 414 to perform steps (1) to (3) above based on the pulse wave information and respiratory pattern information from the acquired PSG information, and obtains adjustment AH information. Then, using the adjustment AH information as input and the corresponding manual AHI as output, the AHI estimation model M is further trained. This enables AHI estimation and health assessment during sleep with higher accuracy.

[0112] The health management module 412 may be configured to manage information related to the user's health in addition to the sleep health management related to AHI described above. Specifically, the health management module 412 may, for example, work in conjunction with the health management module 312 of the user terminal 102 to acquire biometric information obtained from the user terminal 102 by the wearable device 101. The health management module 412 also analyzes the acquired biometric information using volume plethysmography and calculates at least one piece of health management information, such as heart rate, heart rate variability, blood oxygen saturation, blood pressure, and blood glucose level. The health management module 412 may also be configured to calculate the user's posture and displacement, activity level, calories burned, steps taken, behavioral discrimination, body temperature (skin temperature and core temperature), skin moisture content and sweating, blood glucose level, electrocardiogram, heart rate, heart rate variability, respiratory rate, and other health management information based on the acquired biometric information. The health management information may include management indicators for disease prevention, defined as necessary, such as a vascular health index, activity level, stress level, depression level, and lifestyle-related disease risk. Furthermore, the health management module 412 may use data obtained from various biological signals such as displacement, body temperature, heart rate, heart rate variability, and respiratory rate to perform analysis, evaluation, etc., on any health item. The health management module 412 outputs (stores) the calculated health management information to, for example, the health management information 420 in the auxiliary storage device 402 for management.

[0113] Furthermore, the health management module 412, for example, works in conjunction with the health management module 312 of the user terminal 102 to output (display) the calculated health management information on the display of the user terminal 102 (an example of an output device 305).

[0114] The health management module 412 may also be configured to notify the health management module if it finds any of the specified characteristics in the calculated health management information. The notification method is not particularly limited and may be, for example, displayed on the display of the user terminal 102, or sent via email or message to a designated recipient.

[0115] The above describes specific examples of the present technology, but these are merely illustrative and do not limit the scope of the claims. The technology described in the claims includes various modifications and changes to the specific examples described above. For example, the above-described examples are described in detail to make the present technology easy to understand and are not necessarily limited to those having all the described configurations. Furthermore, it is possible to replace parts of the configuration of one embodiment with other configurations, and it is also possible to add other configurations to the configuration of one embodiment. In addition, it is possible to add, delete, or replace parts of the configuration of each embodiment with other configurations.

[0116] This technology provides a program for executing each step of the sleep health evaluation method in the wearable device 101, the user terminal 102, and the management server 103. This program is stored, for example, in the main memory of the wearable device 101, the user terminal 102, and the management server 103. By executing this program, the processors of the wearable device 101, the user terminal 102, and the management server 103 can utilize the services of the AHI estimation system 100.

[0117] In this embodiment, the above preprocessing is performed by the preprocessing module 214 of the wearable device 101. That is, the preprocessing module is not an essential component in the user terminal 102 or the management server 103. However, the processing performed by the preprocessing module 214 of the wearable device 101 may be provided by the preprocessing module of the user terminal 102 or the management server 103. Similarly, the main entity performing the processing in the above embodiment is not limited to that shown in the embodiment, and may be performed by the wearable device 101, the user terminal 102, or the management server 103.

[0118] Furthermore, in the above embodiment, the processing performed by one module may be performed by other modules. Alternatively, the processing performed by one module may be performed by multiple different modules.

[0119] Furthermore, each of the above configurations, functions, processing units, processing means, etc., may be implemented in hardware, in whole or in part, for example, by designing them as integrated circuits. Alternatively, each of the above configurations, functions, etc., may be implemented in software by having the processor interpret and execute programs that realize each function. Information such as programs, tables, and files that realize each function can be stored in memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD (which may be a non-temporary computer-readable medium).

[0120] Furthermore, in the diagrams showing the hardware configuration, control lines and information lines are shown only if deemed necessary for explanation, and not all control lines and information lines are necessarily shown in the actual product. In reality, it can be assumed that almost all components are interconnected. Note that the above-described embodiment discloses at least the configuration described in the claims. The claims include at least the following configurations.

[0121] 100...AHI estimation system, 101...wearable device, 102...user terminal, 211...executor module, 212...health management module, 213...health information evaluation module, 214...preprocessing module, 411...executor module, 412...health management module, 413...health information evaluation module, 414...preprocessing module, 415...postprocessing module, 416...model adjustment module

Claims

1. An AHI estimation system comprising: an AH information acquisition unit that acquires pulse wave information over time from a living organism and acquires AH information indicating the proportion of time the living organism spends apnea (A) and hypopnea (H) during sleep based on the pulse wave information; and an AHI estimation unit that estimates the apnea-hypopnea index (AHI) based on the AH information.

2. The AHI estimation system according to claim 1, wherein the AH information acquisition unit acquires acceleration sensor information, evaluates whether the living organism is in a sleep state or a wakeful state based on the acceleration sensor information, and, if the living organism is evaluated to be in a sleep state, acquires the AH information based on the pulse wave information at the time the living organism was evaluated to be in a sleep state.

3. The AHI estimation system according to claim 1, wherein the AH information acquisition unit acquires SpO2 information indicating the transcutaneous arterial oxygen saturation (SpO2) of the living body based on the pulse wave information, acquires AH event information indicating the number of times an apnea-hypopnea event occurs per unit time in which SpO2 falls below a predetermined threshold based on the SpO2 information, and acquires AH information based on the AH event information.

4. The AHI estimation system according to claim 3, wherein the AH information acquisition unit sets a predetermined threshold for the first time based on a first average SpO2 value which is the average of SpO2 over a first time calculated from the SpO2 information, evaluates whether the second average SpO2 value which is the average of SpO2 over a second time shorter than the first time is smaller than the predetermined threshold, measures the number of event occurrences as an apnea-hypopnea event occurring if the second average SpO2 value is smaller than the predetermined threshold, and outputs the measured number of event occurrences per unit time as AH event information.

5. The AHI estimation system according to claim 1, wherein the AHI estimation unit is configured to take as input the AH information, which indicates the proportion of time during sleep when the organism experiences apnea (A) and hypopnea (H) based on the organism's overnight polysomnography information, and to use a machine learning model trained to output a manual AHI obtained by an overnight polysomnography examination based on the overnight polysomnography information, and to estimate the AHI based on the AH information acquired by the AH information acquisition unit.

6. The AHI estimation system according to claim 5, further comprising: a model adjustment unit configured to acquire a second overnight polysomnography information and a second manual AHI obtained by an overnight polysomnography examination based on the second overnight polysomnography information; acquire the AH information based on the second overnight polysomnography information; and to further learn the machine learning model so that the AH information obtained based on the second overnight polysomnography information is input and the second manual AHI is output.

7. The AHI estimation system according to claim 1, further comprising a symptom evaluation unit that evaluates the severity of sleep apnea syndrome in the living organism based on the estimated AHI and outputs information indicating the evaluated severity.

8. An AHI estimation method comprising: acquiring pulse wave information over time from a living organism; acquiring AH information indicating the proportion of time during which the living organism experiences apnea (A) and hypopnea (H) during sleep based on the pulse wave information; and estimating the Apnea-Hypopnea Index (AHI) based on the AH information.

9. A program for causing a computer to perform each step of the AHI estimation method described in claim 8.

10. A wearable device comprising a pulse wave sensor and a control unit, wherein the control unit is configured to acquire pulse wave information over time from a living organism and to acquire AH information indicating the proportion of time during which the living organism experiences apnea (A) and hypopnea (H) during sleep, based on the pulse wave information.

11. The wearable device according to claim 10, wherein the wearable device is a ring device that can be worn on a person's finger.

12. A method for controlling a wearable device comprising a pulse wave sensor and a control unit, the method comprising: acquiring temporal pulse wave information from a living organism using the pulse wave sensor; and acquiring AH information indicating the proportion of time during which the living organism experiences apnea (A) and hypopnea (H) during sleep, based on the pulse wave information.

13. A program for causing a computer to perform each step of the method for controlling the wearable device described in claim 12.

Images