JP7768570B2 - Sleep apnea syndrome treatment system, information processing device, information processing method, and program - Google Patents

Description

The present invention relates to a sleep apnea syndrome treatment system, an information processing device, an information processing method, and a program.

It is estimated that there are approximately 900 million people worldwide suffering from sleep apnea syndrome (SAS), with approximately 400 million suffering from severe SAS. In Japan, the number of SAS patients is estimated to be approximately 22 million, with approximately 9.4 million suffering from severe SAS. Depending on the severity of their condition, SAS patients are treated with at least one of the following: medication, mouthpiece therapy, CPAP (Continuous Positive Airway Pressure), or surgery. CPAP is a treatment method in which air is continuously delivered to the user's airway through a mask worn by the user.

Mouthpiece treatments and CPAP involve attaching treatment devices to areas that are likely to cause discomfort to the user, so some users may end up removing the devices.

To alleviate such discomfort, for example, Patent Document 1 discloses a sleep apnea treatment device that includes a stimulation device configured to provide stimulation to a subject, and a controller having a circuit configured to receive multiple sounds produced by the subject, convert the sounds into multiple received sound signals, obtain snoring sound information from the received sound signals, calculate the impact of the snoring sound produced by the subject based on the snoring sound information, and cause the stimulation device to provide the stimulation to the subject when the impact is higher than a threshold value.

Patent Document 2 also discloses a biological information processing device that includes a biological information acquisition unit that acquires biological information from a subject, a prediction unit that predicts the occurrence of symptoms while the subject is asleep by inputting the biological information from the subject while asleep into a trained model that predicts the occurrence of the symptoms while the subject is asleep based on the biological information from the subject, and an intervention unit that performs preventive intervention on the subject when the occurrence of the symptoms is predicted by the prediction unit.

Special Publication No. 2022-509989 Japanese Patent Application Laid-Open No. 2023-3299

However, the technology described in Patent Document 1 basically determines a patient's condition based on the sound of snoring, and requires an ultra-wideband Doppler radar system to detect the patient's apnea. Therefore, the system configuration is large-scale.

Patent Document 2 also discloses applying various biological stimuli to a subject and adjusting the intensity of the stimuli, but does not disclose which types of stimuli are effective for the subject.

The present invention was made in consideration of the above circumstances, and aims to provide a sleep apnea syndrome treatment system, information processing device, information processing method, and program that can propose appropriate sleep apnea syndrome treatment methods for each patient without requiring a large-scale system.

[1] A sleep apnea syndrome treatment system according to one aspect of the present invention includes an information processing device and a stimulus applying device. The information processing device includes a biometric information acquisition unit that acquires biometric information including at least one of a user's oxygen saturation and respiratory rate, a determination unit that determines the user's respiratory state based on the biometric information, and a decision unit that determines a stimulus to be applied to the user based on the biometric information and the user's respiratory state through machine learning. The decision unit determines the type, timing, and strength of the stimulus, and the stimulus applying device applies the stimulus to the user based on the type, timing, and strength of the stimulus.
[2] The sleep apnea syndrome treatment system described in [1] above may further include a medical support device connected to a plurality of the information processing devices, and the medical support device may include a determination unit that determines the type, timing, and strength of the stimulation to be applied to each user based on a plurality of pieces of the biological information, information regarding the respiratory condition, and the type, timing, and strength of the stimulation acquired for each of the information processing devices.

[3] Another aspect of the present invention provides an information processing device used in the treatment of sleep apnea syndrome, comprising: a biometric information acquisition unit that acquires biometric information including at least one of a user's oxygen saturation level and respiratory rate; a determination unit that determines the user's respiratory state based on the biometric information; and a decision unit that determines, through machine learning, a stimulus to be applied to the user in accordance with the biometric information and the user's respiratory state, and the decision unit determines the type, timing, and strength of the stimulus.

[4] Furthermore, an information processing method according to yet another aspect of the present invention is an information processing method used in the treatment of sleep apnea syndrome, and includes a biometric information acquisition step of acquiring biometric information including at least one of a user's oxygen saturation and respiratory rate, a determination step of determining the user's respiratory state based on the biometric information, and a decision step of determining, by machine learning, a stimulus to be applied to the user in accordance with the biometric information and the user's respiratory state, wherein the decision step determines the type, timing, and strength of the stimulus.

[5] Furthermore, a program according to yet another aspect of the present invention causes a computer to function as an information processing device used in the treatment of sleep apnea syndrome, the information processing device comprising: a biometric information acquisition unit that acquires biometric information including at least one of a user's oxygen saturation and respiratory rate; a determination unit that determines the user's respiratory state based on the biometric information; and a decision unit that determines, through machine learning, a stimulus to be given to the user in accordance with the biometric information and the user's respiratory state, wherein the decision unit determines the type, timing, and strength of the stimulus.

Embodiments of the present invention make it possible to propose appropriate treatment methods for sleep apnea syndrome for each patient without the need for a large-scale system.

1 is a block diagram of a sleep apnea syndrome treatment system according to an embodiment of the present invention. FIG. 2 is a block diagram showing an example of a functional configuration of the information processing device according to the embodiment. FIG. 2 is a block diagram showing an example of a functional configuration of the stimulation device according to the embodiment. 10 is a flowchart showing an example of a processing flow of the sleep apnea syndrome treatment system according to the embodiment. 1 is a block diagram of a sleep apnea syndrome treatment system according to an embodiment of the present invention. FIG. 2 is a block diagram showing an example of the functional configuration of the medical support device according to the embodiment.

Embodiments of the present invention will be described below with reference to the drawings. Note that in this specification and drawings, components having substantially the same functional configuration will be assigned the same reference numerals, and redundant description will be omitted.

<Sleep Apnea Syndrome Treatment System 1>
A sleep apnea syndrome treatment system according to one embodiment of the present invention will be described with reference to Figures 1 to 3. Figure 1 is a block diagram of a sleep apnea syndrome treatment system according to one embodiment of the present invention. Figure 2 is a block diagram showing an example of the functional configuration of an information processing device in the same embodiment. Figure 3 is a block diagram showing an example of the functional configuration of a stimulating device in the same embodiment. The sleep apnea syndrome treatment system 1 includes an information processing device 10 and a stimulating device 20.

[Information processing device 10]
The information processing device 10 according to this embodiment includes a biometric information acquisition unit 110 that acquires biometric information of a user, a determination unit 120 that determines the user's respiratory state based on the biometric information, and a decision unit 130 that determines a stimulus according to the biometric information and the user's respiratory state through machine learning. Furthermore, as shown in FIG. 2 , the information processing device 10 may include, for example, an instruction unit 140, a storage unit 150, a control unit 160, a communication unit 170, and a display unit 180. The information processing device 10 is realized, for example, by a wearable device, such as a smartwatch.

(Biometric information acquisition unit 110)
The biometric information acquisition unit 110 acquires biometric information of the user. The biometric information is information related to the user's life, and examples of the biometric information include oxygen saturation, respiratory rate, body temperature, and heart rate. The biometric information acquisition unit 110 acquires at least the user's oxygen saturation. The biometric information acquisition unit 110 can acquire the biometric information at any timing. For example, the biometric information acquisition unit 110 may acquire the biometric information at a predetermined interval or at the timing of a user operation. The biometric information acquisition unit 110 preferably acquires the biometric information at short intervals. Acquiring the biometric information at short intervals allows for more accurate understanding of the transition of the user's biometric information. Furthermore, when the user receives a stimulus, it is possible to more accurately understand the extent to which the sleep state changes depending on the type, timing, and intensity of the stimulus.

The oxygen saturation level is acquired by the oxygen saturation level acquisition unit 111. The oxygen saturation level acquisition unit 111 is realized by a known sensor that measures oxygen saturation level.

The respiratory rate is the number of breaths taken per unit time (e.g., per minute) and is acquired by the respiratory rate acquisition unit 112. The respiratory rate can be measured, for example, by detecting the user's movements using an acceleration sensor and gyroscope worn by the user.

The user's body temperature and heart rate are acquired by the body temperature acquisition unit 113 and heart rate acquisition unit 114, respectively. The body temperature and heart rate may be acquired using known methods.

The biometric information acquisition unit 110 may also acquire voice information uttered by the user, such as whether or not the user is snoring, and information regarding the user's movements (motion information), such as whether or not the user is turning over in bed. Voice information can be acquired, for example, by a sound collection device such as a microphone. Motion information can be acquired by an acceleration sensor and a gyroscope. Voice information and motion information are included in the biometric information.

(Determination unit 120)
The determination unit 120 determines the user's respiratory state based on the biological information. For example, the determination unit 120 sets a threshold for determining a hypopnea state and a threshold for determining an apnea state, and determines the user's respiratory state as normal if the oxygen saturation level exceeds a first threshold or the respiratory rate exceeds the first threshold during sleep. If the oxygen saturation level is equal to or lower than the first threshold or the respiratory rate is equal to or lower than the first threshold during sleep, the determination unit 120 determines the user's respiratory state as hypopnea. Furthermore, if the oxygen saturation level is equal to or lower than a second threshold lower than the first threshold or the respiratory rate is equal to or lower than a second threshold lower than the first threshold, the determination unit 120 determines the user's respiratory state as apnea. Hypopnea refers to a state in which shallow breathing, in which ventilation is 50% or less of normal, continues for 10 seconds or more, and apnea refers to a state in which breathing stops for 10 seconds or more.

Furthermore, the determination unit 120 can change the first and second thresholds for oxygen saturation and the first and second thresholds for respiratory rate based on biological information through machine learning.
The determination unit 120 generates, for example, a trained model that predicts a respiratory state based on the user's biological information. This trained model is trained based on the user's biological information from an untrained state. Alternatively, a trained model is generated based on multiple pieces of biological information, and this trained model is further trained based on the user's biological information. The user's biological information is then input into this trained model to predict the respiratory state.

(Determination unit 130)
The determination unit 130 determines, through machine learning, stimuli to be provided to the user according to the biometric information and the user's respiratory state. The types of stimuli include at least one of visual stimuli, auditory stimuli, olfactory stimuli, and tactile stimuli. More specifically, examples of the stimuli include light, sound, vibration, temperature, smell, and airflow.

The determination unit 130 also determines the type, timing, and intensity (stimulation information) of stimulation. Because the type of stimulation that is effective varies for each user, determining the type of stimulation appropriate for the user can shorten the duration of the hypopnea or apnea state. Also, determining the type of stimulation appropriate for the user can provide stimulation that will not wake the user.

The determination unit 130 can determine different stimuli depending on whether the user's breathing state is a hypopnea state or an apnea state. For example, the determination unit 130 can use machine learning to determine the type of stimulus that is more effective in restoring the breathing state to a normal state when the user is in an apnea state. Furthermore, even if the type of stimulus is the same, the determination unit 130 can vary at least one of the timing and intensity between the hypopnea state and the apnea state.

The determination unit 130 generates a trained model that predicts the respiratory state based on at least one of the user's biometric information and stimulation information, for example. This trained model is trained from an untrained state based on the user's biometric information and stimulation information. Alternatively, a trained model is generated based on multiple pieces of biometric information and stimulation information, and this trained model is further trained based on the user's biometric information and stimulation information. The user's biometric information and stimulation information are then input into this trained trained model to predict the respiratory state. Information related to the user's body (body-related information) may also be used in this training. Examples of body-related information include the user's date of birth, gender, height, weight, chronic illnesses, medical history, etc.

The type, timing, and intensity of stimulation are determined by machine learning, allowing for more effective improvement of hypopnea or apnea.

In the above, the determination unit 130 classifies the user's respiratory state into normal, hypopnea, and apnea and determines the stimuli to be given to the user. However, the classification of the user's respiratory state may be further subdivided, and the stimuli to be given to the user may be determined for each of these classifications. The classification of the respiratory state may be performed based on biological information.

(Instruction unit 140)
The instruction unit 140 transmits the stimulation information via the communication unit 170. In the sleep apnea syndrome treatment system 1 according to this embodiment, the instruction unit 140 transmits the stimulation information to the stimulation device 20 via the communication unit 170.

(Storage unit 150)
The storage unit 150 stores biological information, stimulation information, body-related information, respiratory state information (respiratory state information), and programs for various controls performed by the control unit 160. The storage unit 150 may also store information associated with the biological information, such as the date and time when the biological information was acquired, location information, or weather information.

(Control unit 160)
The control unit 160 has a function of controlling the overall operation of the information processing device 10. The control unit 160 is realized, for example, by causing a CPU (Central Processing Unit) provided as hardware in the information processing device 10 to execute a program.

(Communication unit 170)
The communication unit 170 has a function of transmitting and receiving various information to and from the stimulus application device 20 and an external information processing device. For example, the communication unit 170 can transmit stimulus information to the stimulus application device 20 via the network NW. The communication unit 170 can also transmit biological information, stimulus information, respiratory condition information, body-related information, and the like to other information processing devices via the network NW.

(Display section 180)
The display unit 180 has a function of displaying at least one of the biological information, stimulation information, respiratory status information, and body-related information. For example, the display unit 180 may display at least one item of the biological information and the respiratory status information for each acquisition timing, or may display a plurality of these items as a table. The display unit 180 may also display the progress of at least one item of the biological information, the respiratory status information, and the stimulation information as a graph. The display unit 180 may also display the average, maximum, and minimum values of each piece of biological information, or the time or number of times that the oxygen saturation or respiratory rate fell below a predetermined threshold. The display unit 180 is realized, for example, by a display.

[Stimulation device 20]
The stimulus imparting device 20 is a device capable of imparting a stimulus according to each type of stimulus, and is, for example, a light-emitting device, an audio output device, a vibration device, an air-conditioning device, or an aroma device. It is preferable to provide a plurality of stimulus imparting devices 20 in order to impart different types of stimuli to the user. Naturally, the stimulus imparting device 20 may be a device capable of imparting a plurality of different types of stimuli to the user. As shown in FIG. 3 , the stimulus imparting device 20 includes an output unit 210, a control unit 220, and a communication unit 230. The stimulus imparting device 20 may also include a storage unit 240 and a display unit 250.

(Output unit 210)
The output section 210 outputs a stimulus based on the stimulus information received from the information processing device 10. The output section 210 outputs the stimulus at a timing and strength controlled by the control section 220 based on the stimulus information.

(Control unit 220)
The control unit 220 has a function of controlling the overall operation of the stimulus application device 20. The control unit 220 is realized, for example, by causing a CPU provided as hardware in the stimulus application device 20 to execute a program.

(Communication unit 230)
The communication unit 230 has a function of transmitting and receiving various information to and from the information processing device 10 and an external information processing device. For example, the communication unit 230 receives stimulation information transmitted by the information processing device 10 via a network.

(Storage unit 240)
The storage unit 240 stores stimulation information and programs that the control unit 220 uses to perform various controls.

(Display section 250)
The display unit 250 has a function of displaying the intensity of the stimulus. The display unit 250 is realized by, for example, a display.

<Processing flow>
The functional configuration of the sleep apnea syndrome treatment system 1 according to this embodiment has been described above. Next, the processing flow according to this embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of the processing flow according to this embodiment.

The biometric information acquisition unit 110 acquires the user's biometric information (step S101). Next, the determination unit 120 determines whether the user's respiratory state is an apnea state based on the biometric information (step S103). If the user's respiratory state is determined to be an apnea state (step S103/YES), the decision unit 130 determines a stimulus to be given to the user and transmits the stimulus information to the instruction unit 140 (step S105). Next, the instruction unit 140 transmits the stimulus information to the stimulus application device 20 (step S107). Having received the stimulus information, the stimulus application device 20 applies a stimulus to the user based on the stimulus information. After step S107, the process is repeated from step S101.

If it is determined that the user's respiratory state is not an apnea state (step S103/NO), it is determined whether or not the user is in a hypopnea state (step S104). If it is determined that the user's respiratory state is a hypopnea state (step S104/YES), steps S105 and S107 are performed. The stimulation device 20, which has received the stimulation information, stimulates the user based on the stimulation information. After step S107, the process is repeated from step S101.

If the user's respiratory state is determined to be apnea, processing is repeated from step S101.

By repeating steps S101 to S107, appropriate stimulation is provided to each patient, enabling them to escape from hypopnea or apnea.

The sleep apnea syndrome treatment system according to this embodiment uses machine learning to determine the stimuli to be given to the user based on biometric information. These stimuli can help avoid apnea. Even if an apnea state occurs, the user can escape from the state. Since biometric information differs for each user and even for the same user, it can differ depending on the user's condition, it is possible to provide appropriate stimuli to each user to avoid and escape from apnea.

For users, the improvement in hypopnea and apnea symptoms leads to improved daytime health and fewer complications. It also reduces medical costs by reducing the need for medication, CPAP, and surgery.

Furthermore, the information processing device according to this embodiment can be implemented as a wearable device, such as a smartwatch, which means it is less uncomfortable than CPAP or mouthpieces and can be used continuously.

Second Embodiment
As shown in FIG. 5 , the sleep apnea syndrome treatment system 1A according to the present disclosure preferably includes multiple sleep apnea syndrome treatment systems 1 and medical support devices 30. The functions of the sleep apnea syndrome treatment system 1 are similar to those of the first embodiment, except that the sleep apnea syndrome treatment system 1 can communicate with the medical support device 30 via a network NW, and therefore detailed description thereof will be omitted here. However, one sleep apnea syndrome treatment system 1 is used by one user. Therefore, multiple sleep apnea syndrome treatment systems 1 can communicate with the medical support device 30 via the network NW, the number of which corresponds to the number of users. Furthermore, the biometric information, body-related information, and stimulation information for each user can be anonymized and transmitted to the medical support device 30.

The medical support device 30 is a device used by medical professionals. As shown in FIG. 6 , the medical support device 30 may include a biometric information acquisition unit 310, a determination unit 320, a decision unit 330, an instruction unit 340, a storage unit 350, a control unit 360, a communication unit 370, and a display unit 380. These functions are essentially the same as those of the information processing device 10. However, the medical support device 30 differs from the information processing device 10 in that it can receive biometric information and stimulation information from multiple information processing devices 10. Furthermore, the decision unit 330 can determine the type, timing, and intensity of stimulation to be applied to each user based on multiple pieces of biometric information, respiratory information, and the type, timing, and intensity of stimulation acquired from each information processing device 10.

The sleep apnea syndrome treatment system 1 equipped with the medical support device 30 can use machine learning to determine the stimuli to be given to each user from a large amount of combined information consisting of each user's biometric information, body-related information, stimulation information, etc., making it possible to provide more appropriate stimuli to each user.

<Hardware configuration>
The information processing device 10, the stimulation device 20, and the medical support device 30 may include a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), an internal bus, an input/output interface, a display device, an input device, an audio output unit, a storage device, a drive, a network interface, and an external interface.

The CPU functions as an arithmetic processing device and control device, and controls the overall operation of the information processing device 10, stimulation device 20, and medical support device 30 in accordance with various programs. The CPU works in conjunction with the ROM, RAM, and software described below to realize the functions of the control units 160, 220, and 360.

The ROM stores the programs and calculation parameters used by the CPU. The RAM temporarily stores the programs used by the CPU and parameters that change as needed during execution.

The CPU, ROM, and RAM are interconnected by an internal bus, and are further connected to the display device, input device, audio output unit, storage device, drive, network interface, and external interface (described below) via an input/output interface.

The display device is an example of the display unit 180, 250, 380 according to this embodiment, and is a display device such as a CRT display device, a liquid crystal display (LCD), or an OLED device, which converts video data into video and outputs it. The input device may be composed of a mouse, keyboard, touch panel, buttons, microphone, sensors, switches, control circuits, etc. The audio output unit is an audio output device such as a speaker or headphones, which converts audio data and the like into audio and outputs it.

The storage device is a data storage device configured as an example of the storage units 150, 240, and 350 according to this embodiment. The storage device may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, and a deletion device that deletes data recorded on the storage medium. The storage device may be configured, for example, as an HDD (Hard Disk Drive) or SSD (Solid Storage Drive), or memory with equivalent functionality. This storage device drives the storage and stores programs executed by the CPU or various data.

A drive is a reader/writer for storage media and can be built-in or external. The drive reads information stored on removable storage media such as an attached magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs it to RAM. The drive can also write information to removable storage media.

A network interface is a communication interface composed of devices for connecting to a communication network such as the Internet. The network interface may also be a communication device compatible with a wired LAN (Local Area Network) or wireless LAN, or a wired communication device that performs wired communication.

The external interface is a connection interface consisting of connection ports for connecting external devices, such as a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface) port, an RS-232C port, or an optical audio terminal.

So far, we have described the information processing system according to this embodiment. However, the technical scope of the present invention is not limited to the above embodiment, and various modifications can be made without departing from the spirit of the present invention.

For example, while three stimulating devices 20A, 20B, and 20C are shown in FIG. 1, the number of stimulating devices may be one or two, or four or more. When each stimulating device outputs one type of stimulus, it is preferable for the sleep apnea syndrome treatment system to include multiple stimulating devices, since different types of stimuli can be provided to the user.

In addition, in the above embodiment, as shown in FIG. 2, the instruction unit 140 included in the information processing device 10 transmits stimulus information to the stimulus application device 20. However, a different information processing device from the information processing device 10, which is connected to the same network NW as the information processing device 10 and the stimulus application device 20, may also transmit stimulus information to the stimulus application device 20. Examples of the different information processing device include a smart remote control for operating the stimulus application device, a smart speaker, etc.

In addition, in the above embodiment, as shown in Figure 4, the respiratory state is determined in the order of whether or not the patient is in an apnea state, and whether or not the patient is in a hypopnea state. However, this order is not limited to this, and the respiratory state may be determined in the order of whether or not the patient is in a hypopnea state, and whether or not the patient is in an apnea state.

The above describes an embodiment of the present invention. Note that part or all of the sleep apnea syndrome treatment system 1 in the above-described embodiment may be implemented by a computer. Furthermore, when part or all of the sleep apnea syndrome treatment system 1 is implemented by a computer, the system may be implemented by recording a program for implementing this function on a computer-readable recording medium, and reading and executing the program recorded on this recording medium into a computer system.

1 Sleep apnea syndrome treatment system 10 Information processing device 20 Stimulation device 30 Medical support device

Claims (5)

A treatment system for sleep apnea syndrome, comprising:
An information processing device and a stimulus providing device are provided,
The information processing device includes:
a biological information acquisition unit that acquires biological information including an oxygen saturation level and a respiratory rate of a user;
a determination unit that determines a respiratory state of the user based on the biological information;
a determination unit that determines a stimulus to be given to the user according to the biological information and a respiratory state of the user by machine learning,
The determination unit determines the type, timing, and intensity of the stimulation;
the stimulus applying device applies a stimulus to the user based on the type, timing, and intensity of the stimulus;
the determination unit determines that the respiratory state of the user is a hypopnea state but not an apnea state when at least one of the following conditions is met: the oxygen saturation level during sleep of the user is equal to or less than a first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state; and the respiratory rate is equal to or less than the first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state.
The stimulation device provides the stimulation to the user when the user's respiratory state is determined to be a hypopnea state that is not an apnea state. further comprising a medical support device connected to the plurality of information processing devices;
2. The sleep apnea syndrome treatment system of claim 1, wherein the medical support device includes a determination unit that determines the type, timing, and strength of the stimulation to be applied to each user based on multiple pieces of biometric information, information regarding the respiratory condition, and the type, timing, and strength of the stimulation acquired for each information processing device. An information processing device used in the treatment of sleep apnea syndrome,
a biological information acquisition unit that acquires biological information including an oxygen saturation level and a respiratory rate of a user;
a determination unit that determines a respiratory state of the user based on the biological information;
a determination unit that determines a stimulus to be given to the user according to the biological information and a respiratory state of the user by machine learning,
The determination unit determines the type, timing, and intensity of the stimulation;
The determination unit determines that the user's respiratory state is a hypopnea state but not an apnea state when at least one of the following conditions is met: the oxygen saturation level during sleep is equal to or less than a first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state; and the respiratory rate is equal to or less than a first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state. An information processing method used in the treatment of sleep apnea syndrome, comprising:
a biological information acquiring step of acquiring biological information including an oxygen saturation level and a respiratory rate of a user;
a determination step in which a determination unit determines a respiratory state of the user based on the biological information;
a determining step of determining a stimulus to be given to the user according to the biological information and the respiratory state of the user by machine learning;
In the determining step, a type, timing, and intensity of the stimulation are determined;
In the determination step, the user's respiratory state is determined to be a hypopnea state but not an apnea state when at least one of the following conditions is met: the oxygen saturation level during sleep is equal to or less than a first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state; and the respiratory rate is equal to or less than a first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state. Computer,
An information processing device used in the treatment of sleep apnea syndrome,
a biological information acquisition unit that acquires biological information including an oxygen saturation level and a respiratory rate of a user;
a determination unit that determines a respiratory state of the user based on the biological information;
a determination unit that determines a stimulus to be given to the user according to the biological information and a respiratory state of the user by machine learning,
The determination unit determines the type, timing, and intensity of the stimulation;
The determination unit determines that the user's respiratory state is a hypopnea state but not an apnea state when at least one of the following conditions is met: the oxygen saturation level during sleep is equal to or less than a first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state; and the respiratory rate is equal to or less than a first threshold for determining a hypopnea state and exceeds a second threshold smaller than the first threshold for determining an apnea state.