Sleep apnea syndrome detection device, sleep apnea syndrome detection method, and sleep apnea syndrome detection program

Abstract

To enable determination of sleep apnea syndrome.SOLUTION: It is determined that a subject has sleep apnea syndrome on the basis of a change in the sleep stage as a result of determining the sleep stage of the subject at regular time intervals. For example, a sleep apnea syndrome is determined to be present when the number of times a change in sleep stage appears at regular intervals in the order of stage 2 non-REM sleep, wakefulness, and stage 1 non-REM sleep is greater than the number of times wakefulness appears in three consecutive regular hours. Alternatively, when the change from non-REM sleep to wakefulness occurs in Stage 3 or Stage 4, the subject is determined to have sleep apnea.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to a sleep apnea syndrome determination device, a sleep apnea syndrome determination method, and a sleep apnea syndrome determination program for determining a subject's sleep apnea syndrome.

Background Art

[0002] In the medical field, in order to diagnose sleep disorders and sleep apnea syndrome, the sleep state of the measured person is measured. The sleep stages of humans are known to be classified into six stages from the perspective of the depth of sleep. These six sleep stages are, in order from the stage of light sleep, wakefulness, REM sleep, and non-REM sleep (stages 1 to 4). Conventionally, the determination of these six sleep stages has been performed, for example, by attaching a large number of electrodes to the face and head of the measured person, measuring electroencephalogram, eye movement, and masseter muscle potential from the large number of electrodes, and analyzing the measurement results.

[0003] In addition, patients with sleep apnea syndrome often experience apnea during sleep, making it difficult to breathe and resulting in light sleep, and the sleep stage often reverts to a wakeful state. Therefore, it is also necessary to measure the sleep stage when diagnosing apnea syndrome. However, in order to determine sleep apnea syndrome, in addition to measuring the sleep stage, it is necessary to simultaneously perform various measurements such as measuring the flow of air associated with breathing, such as the airflow through the mouth and nose, and the ventilation movements of the chest and abdomen. Based on the analysis results of the sleep stage and the measurement results of the respiratory state, a doctor diagnoses whether it is apnea syndrome.

[0004] The sleep examination in a state where a large number of electrodes are attached to the face and head, which is necessary for such a diagnosis, is usually an examination that requires staying at a medical institution and continuously attaching the electrodes to the body for a long time, imposing a mental burden and a physical burden on the measured person (patient). In addition, the acquired data needs to be analyzed and determined by a doctor with specialized knowledge and experience. Therefore, it has been difficult to determine sleep apnea syndrome easily.

[0005] To address the problems associated with measuring sleep stages, numerous sleep stage estimation methods that do not require a diagnosis by a specialist physician have been proposed. For example, Patent Document 1 describes a method called Database-based Compact Genetic Algorithm, which is an improved learning method using a genetic algorithm, and describes a technique for estimating sleep stages from detection data of a mattress-type pressure sensor. The technique described in Patent Document 1 estimates sleep stages based on the body movements and heart rate of the subject detected by the mattress-type pressure sensor. According to the technique described in Patent Document 1, by estimating sleep stages using a mattress-type pressure sensor, the sleep state of the subject can be estimated without imposing any burden on the subject. [Prior art documents] [Patent Documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2014-239789 [Overview of the project] [Problems that the invention aims to solve]

[0007] As mentioned above, patients with sleep apnea often experience shortness of breath during sleep, leading to shallow sleep and frequently transitioning to an awakened state. Therefore, detecting sleep stages using data from mattress-type pressure sensors, i.e., body movement detection data, can serve as one indicator for diagnosing sleep apnea.

[0008] The fact that frequent awakenings during sleep can increase the risk of sleep apnea can be seen, for example, by comparing the example of changes in sleep stages in a healthy person (a) and a patient with sleep apnea (b) in Figure 4, which will be discussed later. In other words, as can be seen from Figure 4, patients with sleep apnea experience more awakenings during sleep compared to healthy individuals. However, even healthy individuals often experience difficulty achieving deep sleep depending on the circumstances, and a high frequency of awakenings during sleep does not automatically diagnose sleep apnea. Therefore, there has been an urgent need to develop a more accurate diagnostic method for sleep apnea.

[0009] The present invention aims to provide a sleep apnea syndrome diagnosis device, a sleep apnea syndrome diagnosis method, and a sleep apnea syndrome diagnosis program capable of determining whether or not a person has sleep apnea syndrome. [Means for solving the problem]

[0010] The sleep apnea syndrome detection device of the present invention includes a sleep apnea syndrome detection unit that determines whether a subject has sleep apnea syndrome based on changes in the subject's sleep stage, determined at regular intervals, and the sleep apnea syndrome detection unit determines whether a subject has sleep apnea syndrome based on the detection of specific changes in the subject's sleep stage during sleep, including changes from non-REM sleep to wakefulness. I did that. Here, the sleep apnea syndrome determination unit performs at least one of the first determination process and the second determination process as part of its determination. The first determination process involves comparing the number of times a subject experiences a first specific change in sleep stage during sleep, including a change from a non-REM sleep stage to a wakeful sleep stage, with the number of times a second specific change occurs, which relates to the number of times wakefulness occurs. If the number of times the first specific change occurs is greater, the subject is determined to have sleep apnea syndrome. The second determination process involves detecting a change in the sleep stage determined during the subject's sleep that corresponds to a third specific change, which is a change from non-REM sleep to wakefulness. In this process, the subject is determined to have sleep apnea syndrome.

[0011] Furthermore, the sleep apnea syndrome determination method of the present invention includes a sleep apnea syndrome determination process in which the subject is determined to have sleep apnea syndrome based on changes in the subject's sleep stage, which are determined at regular intervals. In the sleep apnea syndrome determination process, the subject is determined to have sleep apnea syndrome based on the detection of specific changes in the subject's sleep stage during sleep, including changes from non-REM sleep to wakefulness. I did that. In this sleep apnea syndrome diagnosis process, at least one of the first diagnosis process and the second diagnosis process is performed. The first determination process compares the number of times the subject experiences a first specific change in sleep stage during sleep, including a change from a non-REM sleep stage to a wakeful sleep stage, with the number of times the subject experiences a second specific change related to the number of times wakefulness occurs. If the number of times the first specific change occurs is greater, the subject is determined to have sleep apnea syndrome. The second determination process determines that the subject has sleep apnea syndrome when it detects that the change in sleep stage determined during the subject's sleep is a third specific change, which is a change from a non-REM sleep stage to wakefulness.

[0012] In addition, the sleep apnea syndrome determination program of the present invention causes a computer to execute each process performed by the above-described sleep apnea syndrome determination method as a procedure.

Advantages of the Invention

[0013] According to the present invention, by utilizing the changes in the sleep stages that are peculiar to patients with sleep apnea syndrome, it becomes possible to accurately determine sleep apnea syndrome. Therefore, it becomes possible to easily determine sleep apnea syndrome using the data obtained by measuring the sleep stages during sleep.

Brief Description of the Drawings

[0014] [Figure 1] It is a block diagram showing a configuration example of a sleep apnea syndrome determination device according to an embodiment of the present invention. [Figure 2] It is a diagram showing an example of the determination state of sleep apnea syndrome according to an embodiment of the present invention. [Figure 3] It is a block diagram showing a hardware configuration example of a sleep apnea syndrome determination device according to an embodiment of the present invention. [Figure 4] It is a diagram showing an example of a process for obtaining a power spectrum during sleep at regular intervals according to an embodiment of the present invention. [Figure 5] It is a diagram comparing examples of changes in sleep stages during sleep between a healthy person (a) and a patient with sleep apnea syndrome (b). [Figure 6] It is a flowchart showing the flow of a process for determining sleep apnea syndrome according to an embodiment of the present invention. [Figure 7] It is a diagram showing an example of changes in sleep stages for 90 seconds during sleep of patients (9 people) with sleep apnea syndrome, counting the changes that occur frequently for each patient. [Figure 8] It is a diagram showing an example of changes in sleep stages for 90 seconds during sleep of healthy people (9 people), counting the changes that occur frequently for each healthy person. [Figure 9]This is a diagram comparing the cases where, among the changes in the sleep stages of 9 patients with sleep apnea syndrome in Fig. 7, the stages changed to non-REM sleep in stage 2 (2), wakefulness (w), and non-REM sleep in stage 1 (1), and the case where wakefulness (w) continued for 3 times. [Figure 10] This is a diagram comparing the cases where, among the changes in the sleep stages of 9 healthy individuals in Fig. 8, the stages changed to non-REM sleep in stage 2 (2), wakefulness (w), and non-REM sleep in stage 1 (1), and the case where wakefulness (w) continued for 3 times. [Figure 11] This is a diagram showing the case where, among the changes in the sleep stages of 9 patients with sleep apnea syndrome in Fig. 7, the stage changed from non-REM sleep in stage 2 or 3 (2 / 3) to wakefulness (w). [Figure 12] This is a diagram showing the number of occurrences when, among the changes in the sleep stages of 9 healthy individuals in Fig. 8, the stage changed from non-REM sleep in stage 2 or 3 (2 / 3) to wakefulness (w). [Figure 13] This is a diagram showing the case where, among the changes in the sleep stages of 9 patients with sleep apnea syndrome in Fig. 7, either the condition of the comparison of the changes in the example of Fig. 9 or the occurrence of the changes in the example of Fig. 11 is satisfied. [Figure 14] This is a diagram showing the case where, among the changes in the sleep stages of 9 healthy individuals in Fig. 8, either the condition of the comparison of the changes in the example of Fig. 10 or the occurrence of the changes in the example of Fig. 12 is satisfied. [Figure 15] This is a diagram showing examples that can be discriminated by other combinations among the changes in the sleep stages of 9 patients with sleep apnea syndrome in Fig. 7. [Figure 16] This is a diagram showing examples that can be discriminated by other combinations among the changes in the sleep stages of 9 healthy individuals in Fig. 8.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an exemplary embodiment of the present invention (hereinafter referred to as "this example") will be described with reference to the drawings. In the following description and drawings, sleep apnea syndrome is referred to as SAS, and patients with sleep apnea syndrome are referred to as SAS patients. Also, when a healthy individual is mentioned in the following description, it indicates a person who is not an SAS patient. [1. Configuration of the sleep apnea syndrome detection device] Figure 1 is a block diagram showing the configuration of the sleep apnea syndrome detection device 10 in this example. Figure 2 shows an example of a situation in which sleep apnea syndrome is diagnosed using the sleep apnea syndrome diagnosis device 10 of this example.

[0016] The sleep apnea syndrome detection device 10 in this embodiment acquires the subject's biological vibrations as pressure data using a mattress sensor 2. These biological vibrations include vibration components due to the subject's body movements, as well as vibration components due to heart rate and respiration. The mattress sensor 2 detects the biological vibrations of the subject A's upper body during sleep as a change in pressure. The mattress sensor 2 is used by placing it on or under the mattress of the bed 1 where the subject A sleeps, for example, as shown in Figure 2. Placing the mattress sensor 2 on the mattress below the subject A is just one example; for example, the mattress sensor 2 may be embedded inside the mattress.

[0017] Figure 2 shows an example where the sleep apnea syndrome detection device 10 is installed next to the bed 1 and the mattress sensor 2 and the sleep apnea syndrome detection device 10 are connected by a cable. However, for example, the pressure data (biometric vibration data) acquired by the mattress sensor 2 may be transmitted wirelessly to the sleep apnea syndrome detection device 10 in another room. In the following explanation, the pressure data output by mattress sensor 2 will be referred to as bio-vibration data. Obtaining bio-vibration data from a pressure sensor is just one example; other sensors may also be used. For example, infrared sensors or lasers may be used to measure the vibrations of a subject during sleep in a non-contact manner.

[0018] As shown in Figure 1, the sleep apnea syndrome detection device 10 comprises a biological data acquisition unit 11, a biological data processing unit 12, a sleep stage determination unit 13, a sleep apnea syndrome detection unit (hereinafter referred to as the "SAS detection unit") 14, and an output unit 15. The biological data acquisition unit 11 performs biological data acquisition processing to acquire biological vibration data output by the mattress sensor 2. The biological vibration data acquired by the biological data acquisition unit 11 is supplied to the biological data processing unit 12.

[0019] The bio-data processing unit 12 samples the supplied bio-vibration data, converts it into digitized data, and calculates the power spectrum of the frequency of the digitized bio-vibration data. This process of calculating the power spectrum of the frequency of the bio-vibration data is performed in 30-second cycles. However, in this example, one calculation is actually performed for 32 seconds, and these 32-second calculations are repeated in 30-second cycles, meaning they overlap by only 2 seconds.

[0020] Note that the calculation of the power spectrum by the biological data processing unit 12 at a 30-second cycle is just one example; the power spectrum may be calculated at a shorter or longer cycle. For example, the biological data processing unit 12 may calculate the power spectrum at a 60-second cycle. The 2-second overlap in each calculation is also just one example; there may be no overlapping period. The biological data processing unit 12 then supplies the calculated power spectrum results for each period of time during sleep to the sleep stage determination unit 13 and the SAS determination unit 14.

[0021] The sleep stage determination unit 13 determines the sleep stage of the subject during a given period based on the calculation results of the power spectrum for each period. When determining the sleep stage, various features obtained by calculating bio-vibration data may be used in addition to the power spectrum. Alternatively, the sleep stage may be determined from the feature data using a random forest, which is a type of machine learning.

[0022] Sleep stages, from lightest to heaviest, are WAKE (W), REM sleep (R), and non-REM sleep (NR). Non-REM sleep is further divided into four stages (NR1-NR4). Therefore, there are a total of six sleep stages. Of these six stages, stage 4, non-REM sleep (NR4), is the deepest. However, it is rare for people to actually experience such a deep sleep stage as stage 4 non-REM sleep. In the diagrams, non-REM sleep stages 1-4 are sometimes referred to as "N1" to "N4" or "1" to "4," omitting "NR." In this example, the sleep stage determination unit 13 determines the sleep stage from biological vibration data, but the sleep stage determination unit 13 may also determine the sleep stage from other biological data such as electroencephalograms (EEGs).

[0023] The SAS determination unit 14 determines whether or not a subject A has sleep apnea syndrome (SAS) based on the occurrence of specific changes in sleep stages at regular intervals (every 30 seconds) during a single sleep cycle (from falling asleep to waking up). Examples of sleep stage changes that the SAS determination unit 14 specifically determines will be described later.

[0024] The output unit 15 outputs the result of whether or not the SAS determination unit 14 has sleep apnea syndrome. The output unit 15 is configured as, for example, a display device and displays the sleep apnea syndrome determination result. Alternatively, the output unit 15 may be configured as a recording device to record the sleep apnea syndrome determination result along with the sleep state for the night. Furthermore, when the output unit 15 displays or records, it may simultaneously display or record not only the sleep apnea syndrome determination result but also the sleep stage determination result.

[0025] Furthermore, the output unit 15 may be configured to transmit the judgment result via a network, acting as an external terminal. For example, the output unit 15 may be configured to transmit the judgment result as a pre-registered smartphone. In this example, the sleep apnea syndrome detection device 10 may perform data acquisition and detection during sleep in real time. Alternatively, the sleep apnea syndrome detection device 10 may have a biological data acquisition unit 11 that only acquires biological vibration data during sleep, records the acquired data, and then performs the detection process using the recorded data at a later date.

[0026] [2. Example Hardware Configuration of a Sleep Apnea Syndrome Detection Device] Figure 3 shows an example of the hardware configuration when the sleep apnea syndrome diagnosis device 10 is configured as a computer device. Computer device C comprises a CPU (Central Processing Unit) C1, ROM (Read Only Memory) C2, and RAM (Random Access Memory) C3 connected to bus C8. Furthermore, computer device C includes non-volatile storage C4, a network interface C5, an input device C6, and a display device C7.

[0027] CPU C1 reads and executes the program code for the software that implements the functions of the biological data processing unit 12, sleep stage determination unit 13, and SAS determination unit 14 of the sleep apnea syndrome detection device 10 from ROM C2. For the processes of determining sleep stages and determining sleep apnea syndrome, CPU C1 reads the program that executes the corresponding process from ROM C2 and executes it. Variables and parameters that occur during the calculation process are temporarily written to RAM C3.

[0028] Non-volatile storage C4 can include, for example, an HDD (Hard disk drive), SSD (Solid State Drive), flexible disk, optical disk, magneto-optical disk, CD-ROM, or non-volatile memory. This non-volatile storage C4 stores the OS (Operating System), various parameters, and a program to enable the computer device C to function as a sleep apnea syndrome detection device 10. In addition, data on the sleep stage determined by the sleep stage determination unit 13 and the presence or absence of sleep apnea syndrome determined by the SAS determination unit 14 are also recorded in the non-volatile storage C4.

[0029] Network interface C5, for example, uses a NIC (Network Interface Card) and can send and receive various types of data via a LAN (Local Area Network), dedicated line, etc., to which its terminals are connected. For example, computer device C acquires pressure data output by mattress sensor 2 via network interface C5. Input device C6 consists of a device such as a keyboard, and this input device C6 is used to set the period for determining sleep apnea syndrome in the sleep apnea syndrome determination device 10, and to instruct the display format of the determination results. Display device C7 displays the sleep apnea syndrome determination results from the sleep apnea syndrome determination device 10. It should be noted that configuring the sleep apnea syndrome detection device 10 as a computer device that functions as a detection device by executing a program (software) is just one example; dedicated hardware that performs some or all of the processing of the sleep apnea syndrome detection device 10 may also be provided.

[0030] [3. Example of calculation status of frequency power spectrum and determination of sleep stage] Next, we will explain the processes performed in each part of the sleep apnea syndrome detection device 10 in this example. First, referring to Figure 4, we will explain an example in which the biodata processing unit 12 calculates the power spectrum of the frequency of bio-vibrations during sleep over a certain period of time. As already explained, in this example, the biodata processing unit 12 processes 32 seconds of data at 30-second intervals. Specifically, as shown in Figure 4, the bio-data acquisition unit 11 first acquires sensor values ​​from the mattress sensor 2 from the time of falling asleep (0 seconds) to 32 seconds, and then acquires sensor values ​​for 32 seconds at 30-second intervals. The bio-data acquisition unit 11 continuously acquires this bio-vibration data from the time of falling asleep to waking up, and supplies the acquired bio-vibration data to the bio-data processing unit 12.

[0031] The biological data processing unit 12 then calculates the power spectrum of the frequency over a 32-second period, as shown in the lower right of Figure 4. This frequency analysis to calculate the power spectrum is performed, for example, by the Fast Fourier Transform (FFT). When calculating the power spectrum of bio-vibrations during sleep, as in this example, the frequencies showing high density are the components of bio-vibrations due to heartbeat and respiration. Normally, the frequency of heartbeat is around 1 Hz, and the component of bio-vibrations due to respiration is around 2 Hz. However, in the case of sleep apnea patients, there are periods when no bio-vibrations occur due to respiration. Also, in periods with large body movements such as turning over in bed, a component of bio-vibration due to body movement is generated that is much larger than that of heartbeat or respiration.

[0032] The sleep stage determination unit 13 determines the dominant sleep stage over a 30-second period from the power spectrum of bio-vibrations, as shown in Figure 4. The method for determining the sleep stage from the power spectrum of bio-vibrations is applicable to methods already proposed by the inventors of this application. While not explained here, this method allows for the determination of the sleep stage from the occurrence of different feature quantities for each sleep stage. In the example in Figure 4, the first 30 seconds after falling asleep are determined to be wakeful (W), and the next 30 seconds are determined to be stage 2 non-REM (N2).

[0033] Figure 5 compares an example of measuring the sleep stages of a healthy individual during a certain sleep period (a) with an example of measuring the sleep stages of a patient with sleep apnea syndrome (SAS patient) (b).

[0034] In Figure 5, the horizontal axis represents sleep duration, and the vertical axis represents sleep stages. The vertical axis of sleep stages shows that the uppermost part represents wakefulness, the lightest sleep stage, and as you move downwards, the sleep stages progress sequentially to deeper sleep stages: REM sleep, Stage 1 non-REM sleep (NREM1), Stage 2 non-REM sleep (NREM2), Stage 3 non-REM sleep (NREM3), and Stage 4 non-REM sleep (NREM4).

[0035] In the example in Figure 5, in both the healthy individual shown in (a) and the sleep apnea patient shown in (b), the deepest sleep stage is Stage 3 non-REM sleep (NREM3), and Stage 4 non-REM sleep (NREM4) is not reached. As can be seen by comparing a healthy person (a) and a sleep apnea patient (b) in Figure 5, sleep apnea patients experience frequent awakenings (WAKE) due to apnea. In patients with sleep apnea (SAS), the tongue obstructs the airway during wakefulness, causing apnea, which manifests as changes in heart rate. Therefore, when the sleep stage determination unit 13 determines the sleep stage, it is preferable to perform determination processing that also takes into account the characteristics that appear when sleep apnea patients are awake.

[0036] In this example, the sleep apnea syndrome detection device 10 makes a determination of SAS based on the state in which these six sleep stages change, according to the processing procedure described below.

[0037] [4. Flowchart for determining sleep apnea syndrome (SAS)] Figure 6 is a flowchart showing the process flow for determining SAS using the sleep apnea syndrome detection device 10 in this example. First, the SAS determination unit 14 compares the number of occurrences of a specific change state during a 90-second sleep period with the ratio of the number of consecutive 90-second periods of wakefulness (step S11). Here, the specific change state during a 90-second period refers to a state in which the first 30 seconds are stage 2 non-REM sleep (NR2), the next 30 seconds are wakefulness (WAKE), and the last 30 seconds are stage 1 non-REM sleep (NR1).

[0038] Furthermore, the SAS determination unit 14 determines whether or not there is a change in sleep stage during a single sleep cycle, specifically whether or not the patient transitions from non-REM sleep (NR3 or NR4) in stage 3 or stage 4 to wakefulness (step S12).

[0039] Then, in the comparison in step S11, the SAS determination unit 14 determines whether the number of specific state changes—stage 2 non-REM sleep (NR2), wakefulness (WAKE), and stage 1 non-REM sleep (NR1)—is equal to or greater than the number of times wakefulness lasts for 90 seconds. If, in this determination, the number of specific state changes is equal to or greater than the number of times wakefulness lasts for 90 seconds, the SAS determination unit 14 determines that the person being measured is a patient with sleep apnea syndrome (SAS).

[0040] Furthermore, the SAS determination unit 14 determines in step S12 that the subject is a sleep apnea patient if there is at least one instance of the subject transitioning from stage 3 or stage 4 non-REM sleep (NR3 or NR4) to wake (WAKE) (step S13). If the subject is not found to be a sleep apnea patient based on these determinations, the SAS determination unit 14 determines that the subject is not a sleep apnea patient. This determination result is output from the output unit 15.

[0041] [5. Verification using actual measurement data] Next, we will explain how the determination in step S13 of Figure 6 can correctly identify SAS using an example of sleep stage changes obtained from actual measurement data. Figure 7 shows a list of changes observed during three consecutive measurement periods (90 seconds each) in nine sleep apnea patients (D11-D19), along with the number of occurrences of each change. Figure 8 shows a list of changes observed during three consecutive measurement periods (90 seconds each) in nine healthy individuals (D21-D29) during a single sleep cycle, along with the number of occurrences of each change. In the data for each SAS patient (D11-D19) and healthy control group (D21-D29) shown in Figures 7 and 8, the leftmost data represents the most frequently occurring change.

[0042] To explain how to interpret Figures 7 and 8, for example, in the top row of Figure 7, the change at the leftmost end of each SAS patient D11, "WWW," indicates that three consecutive wakes (90 seconds each) occurred. The "14" below it indicates that the number of times three consecutive wakes occurred during a single sleep cycle was 14. The number "0.285714" below "14" represents the percentage of cases where three consecutive wakes occur. In other words, in this example, the percentage of cases where three consecutive wakes occur is approximately 28.5%.

[0043] Below are representative examples of the symbols shown in Figures 7 and 8, and the meanings of the three sleep stages that occur sequentially within a 90-second period they represent. WWW: Awakening → Awakening → Awakening 2WW: Stage 2 non-REM sleep → awakening → awakening • 2W2: Stage 2 non-REM sleep → wakefulness → Stage 2 non-REM sleep • 2W1: Stage 2 non-REM sleep → wakefulness → Stage 1 non-REM sleep • 1WW: Stage 1 non-REM sleep → awakening → awakening • 1W1: Stage 1 non-REM sleep → wakefulness → Stage 1 non-REM sleep WW1: Awakening → Awakening → Stage 1 Non-REM Sleep • 3W1: Stage 3 non-REM sleep → wakefulness → Stage 1 non-REM sleep 3WW: Stage 3 non-REM sleep → awakening → awakening • 4W3: Stage 4 non-REM sleep → wakefulness → Stage 3 non-REM sleep • RWW: REM sleep → wakefulness → wakefulness RW1: REM sleep → Awakening → Stage 1 non-REM sleep • RWR: REM sleep → wakefulness → REM sleep

[0044] Examples of analyzing the data shown in Figures 7 and 8 will be explained sequentially from Figure 9 onwards. Figure 9 compares the number of times sleep stages changed in the sequence of Stage 2 non-REM sleep → wakefulness → Stage 1 non-REM sleep (hereinafter referred to as the "2W1" sequence) with the number of times three consecutive awakenings occurred (referred to as the "WWW" sequence) for each data set of SAS patients D11-D19 in Figure 7. Similarly, Figure 10 compares the number of times sleep stages changed in the order "2W1" with the number of times three consecutive awakenings occurred in the order "WWW" for each of the healthy control data points D21-D29 in Figure 8.

[0045] In Figure 9, for SAS patients D11-D19, if the number of times the sleep stage changed in the order "2W1" is equal to or greater than the number of times the sleep stage changed in the order "WWW", then six of the nine patients, D12, D13, D14, D17, D18, and D19, qualify as SAS patients. However, in the case of SAS patient D19, the sleep stage change in the order "WWW" did not occur. In other words, a state of wakefulness lasting 90 seconds did not occur.

[0046] On the other hand, in the case of healthy individuals D21-D29 in Figure 10, all nine individuals experienced sleep stage changes in the order "WWW" more times than in the order "2W1". Therefore, by determining that a person has sleep apnea syndrome (SAS) when the number of times their sleep stages change in the order "2W1" is equal to or greater than the number of times their sleep stages change in the order "WWW," it becomes possible to identify SAS patients with relatively high accuracy. For example, in the case of Figure 9, the accuracy rate for identifying a person as having SAS is a high 66.7%. In the case of Figure 10, the accuracy rate for determining that a person does not have SAS is 100%.

[0047] Furthermore, the state in which the sequence changes to "2W1" within 90 seconds is a state in which the person is temporarily awake for about 30 seconds in the middle of the 90 seconds. In patients with sleep apnea, this temporary awakening is likely to occur due to the onset of apnea. Conversely, in healthy individuals, such short-lived awakenings occur very infrequently, and the state in which awakenings occur consecutively within 90 seconds in the sequence "WWW" occurs relatively frequently.

[0048] Figure 11 shows the number of times, for each data set of SAS patients D11-D19 in Figure 7, that the sleep stage changed from stage 3 non-REM sleep or stage 4 non-REM sleep to wakefulness (hereinafter referred to as "3W / 4W occurrences"). Similarly, Figure 12 shows the number of times "3W / 4W" occurred for each of the data points for healthy individuals D21-D29 in Figure 8.

[0049] This "3W / 4W" occurred in 7 of the 9 SAS patients D11-D19 shown in Figure 11: D11, D12, D13, D15, D16, D17, and D19. On the other hand, in the case of healthy individuals D21-D29 in Figure 12, only one of the nine, D21, experienced "3W / 4W". Therefore, by identifying a patient as having SAS when "3W / 4W" occurs, it becomes possible to diagnose SAS patients with high accuracy. For example, in the case of Figure 11, the accuracy rate for identifying a patient as having SAS is 100%. In the case of Figure 12, the accuracy rate for identifying a patient as not having SAS is 89%.

[0050] Furthermore, the occurrence of "3W / 4W," that is, a sudden shift from non-REM sleep in stage 3 or stage 4 to a state of wakefulness, is a change from a deep sleep stage to the lightest sleep stage. While this change from deep to lightest sleep stage rarely occurs in healthy individuals, in patients with sleep apnea, it can occur due to apnea during deep sleep.

[0051] Figure 13 shows an example of determining whether a patient had SAS based on the data of nine SAS patients D11-D19 from Figure 7. The criteria were: either the number of times sleep stages changed in the order "2W1" was equal to or greater than the number of times sleep stages changed in the order "WWW", or there was an occurrence of "3W / 4W". This determination in Figure 13 corresponds to the determination made in step S13 of the flowchart in Figure 6. In the example shown in Figure 13, the accuracy rate for identifying a patient with sleep apnea syndrome (SAS) is 100%.

[0052] Figure 14 shows an example of how, for the data of the nine healthy individuals D21-D29 in Figure 8, a person was determined not to be a sleep apnea patient if either of the following conditions was met: the number of times the sleep stage changed in the order of "2W1" was less than the number of times the sleep stage changed in the order of "WWW", or there were no occurrences of "3W / 4W". In the example shown in Figure 14, the accuracy rate for determining that the person is not a sleep apnea patient is 89%.

[0053] Therefore, the sleep apnea syndrome detection device 10 in this example makes it possible to identify patients with sleep apnea syndrome with very high accuracy based on changes in sleep stages. In the embodiments described so far, sleep stages are obtained from measurement data of the non-restraining mattress sensor 2, but the acquisition of sleep stages is not limited to this example. For example, in a polysomnography (PGS) test, electrodes may be attached to the subject to acquire sleep stages, and the sleep apnea syndrome detection device 10 in this example may identify patients with sleep apnea syndrome based on the changes in the acquired sleep stages. Alternatively, sleep stages may be acquired from measurement data of a restraining wearable device such as a smartwatch, and the sleep apnea syndrome detection device 10 in this example may identify patients with sleep apnea syndrome based on the changes in the acquired sleep stages.

[0054] [6. Variant] The processes described in the above-mentioned embodiment examples are merely preferred examples and are not limited to those described in the embodiment examples. For example, in the embodiment described above, the sleep apnea syndrome detection device 10 determines the sleep stage every 30 seconds and determines whether or not the person is a SAS patient based on the changes in the sleep stage every 30 seconds. Alternatively, the sleep apnea syndrome detection device 10 may determine whether or not the person is a SAS patient based on the results of determining the sleep stage at relatively longer intervals, such as every 60 seconds or every 90 seconds. In the sleep apnea syndrome detection device 10 of this embodiment, if the sleep stage is determined at least every 30 seconds or more, it is possible to capture changes specific to SAS patients.

[0055] Furthermore, in the above-described embodiment, the number of times the sleep stage changed in the order of Stage 2 non-REM sleep → wakefulness → Stage 1 non-REM sleep, the number of times there were three consecutive awakenings, and whether or not there was a state of wakefulness from Stage 3 non-REM sleep or Stage 4 non-REM sleep were combined. However, it is possible to determine whether or not a person has SAS based on any one of these criteria alone.

[0056] Furthermore, in the above-described embodiment, the number of times the sleep stage changed in the order of Stage 2 non-REM sleep → wakefulness → Stage 1 non-REM sleep, the number of times there were three consecutive awakenings, and the presence or absence of Stage 3 non-REM sleep or Stage 4 non-REM sleep were used to determine whether or not the patient is a sleep apnea patient based on changes in other sleep stages.

[0057] Figures 15 and 16 show possible combinations other than those explained in Figures 9 to 14. Figure 15 shows the number of occurrences of the REM sleep → wakefulness → REM sleep state ("RWR" state) and the stage 1 non-REM sleep → wakefulness → stage 1 non-REM sleep state ("1W1" state) in a 90-second period for data D11 to D19 from the nine SAS patients shown in Figure 7. Thus, in the case of SAS patients, a considerable number of times they temporarily wake up from REM sleep or stage 1 non-REM sleep and then return to their original sleep stage.

[0058] Figure 16 shows the number of occurrences of the state of wakefulness → wakefulness → stage 1 non-REM sleep ("WW1" state) and the number of occurrences of the state of stage 2 non-REM sleep → wakefulness → wakefulness ("2WW" state) in a 90-second period for data D21-D29 from the nine healthy individuals shown in Figure 8. Thus, in patients with sleep apnea syndrome (SAS), it is quite common for them to experience periods of wakefulness lasting 60 seconds or more followed by a return to Stage 1 non-REM sleep, or to transition from Stage 2 non-REM sleep to a state of wakefulness lasting 60 seconds or more.

[0059] Therefore, it is possible to determine whether or not a person has sleep apnea syndrome (SAS) by detecting instances where a person temporarily wakes up from REM sleep or Stage 1 non-REM sleep and then returns to their original sleep stage, or where they remain awake for 60 seconds or more before returning to Stage 1 non-REM sleep, or where they remain awake for 60 seconds or more after Stage 2 non-REM sleep. The assessments shown in Figures 15 and 16 can be performed independently, but combining them with the assessments shown in Figures 9 to 14, as explained earlier, is expected to further improve the accuracy of determining whether or not a patient has sleep apnea syndrome (SAS).

[0060] Furthermore, as explained in one embodiment, determining sleep stages from biological vibrations obtained using the mattress sensor 2 is just one example; the present invention may also determine whether or not a person is a sleep apnea patient by similarly judging changes in sleep stages based on the results of determining sleep stages by various methods. [Explanation of Symbols]

[0061] 1...Bed, 2...Mattress sensor, 10...Sleep apnea syndrome detection device, 11...Biometric data acquisition unit, 12...Biometric data processing unit, 13...Sleep stage determination unit, 14...Sleep apnea syndrome detection unit (SAS determination unit), 15...Output unit, A...Subject, C...Computer device, C1...CPU, C2...ROM, C3...RAM, C4...Non-volatile storage, C5...Network interface display unit, C6...Input device, C7...Display device, C8...Bus

Claims

1. The system includes a sleep apnea syndrome determination unit that determines the subject has sleep apnea syndrome based on changes in the subject's sleep stage, determined at regular intervals. The sleep apnea syndrome detection unit determines that the subject has sleep apnea syndrome based on the detection of specific changes in the subject's sleep stage, including a change from a non-REM sleep stage to a wakeful sleep stage. The sleep apnea syndrome diagnosis unit performs at least one of the following: the first diagnosis process and the second diagnosis process. The first determination process involves comparing the number of times the sleep stage changes during the subject's sleep are a first specific change, including a change from a non-REM sleep stage to a wakeful sleep stage, with the number of times the sleep stage changes are a second specific change, and determining that the subject has sleep apnea syndrome if the number of times the sleep stage changes are a second specific change, with the first specific change being greater. The second determination process determines that the subject has sleep apnea syndrome when it detects that the change in sleep stage determined during the subject's sleep is a third specific change, which is a change from a non-REM sleep stage to wakefulness. Sleep apnea syndrome determination device.

2. The first specific change described above is a change that occurs in the following order: Stage 2 non-REM sleep, wakefulness, and Stage 1 non-REM sleep. The second specific change described above is a change in which arousal occurs in three consecutive periods of time. A sleep apnea syndrome detection device according to claim 1.

3. The third specific change is the transition from stage 3 or stage 4 non-REM sleep to wakefulness. A sleep apnea syndrome detection device according to claim 1.

4. The sleep apnea syndrome determination unit compares the number of times the changes in sleep stages determined during the subject's sleep are a first specific change, including a change from a non-REM sleep stage to a wakeful sleep stage, with the number of times the changes are a second specific change, which relates to the number of times wakefulness occurs. The unit determines that the subject has sleep apnea syndrome if either of the following conditions is met: the number of times the changes are a first specific change is greater, or the changes in sleep stages determined during the subject's sleep are a third specific change, which is a change from a non-REM sleep stage to wakefulness. A sleep apnea syndrome detection device according to claim 1.

5. The time required to determine a sleep stage is at least 30 seconds. A sleep apnea syndrome detection device according to any one of claims 1 to 4.

6. This is a method for diagnosing sleep apnea syndrome that uses computer calculations to determine if a person has sleep apnea syndrome. The process to be performed by the aforementioned computer is: The process includes a sleep apnea syndrome determination process that determines the subject has sleep apnea syndrome based on changes in the subject's sleep stage, determined at regular intervals. The sleep apnea syndrome determination process described above involves performing at least one of the first determination process and the second determination process. The first determination process compares the number of times the sleep stage changes during the subject's sleep are a first specific change, including a change from a non-REM sleep stage to a wakeful sleep stage, with the number of times the sleep stage changes are a second specific change, and if the number of times the sleep stage changes are a second specific change, the first determination process determines that the subject has sleep apnea syndrome. The second determination process determines that the subject has sleep apnea syndrome when it detects that the change in sleep stage determined during the subject's sleep is a third specific change, which is a change from a non-REM sleep stage to wakefulness. How to determine sleep apnea syndrome.

7. This is a sleep apnea syndrome diagnosis program that causes a computer to execute a sleep apnea syndrome diagnosis procedure, which determines that a subject has sleep apnea syndrome based on changes in their sleep stages, determined at regular intervals. The aforementioned sleep apnea syndrome diagnosis procedure involves performing at least one of the first diagnosis procedure and the second diagnosis procedure. The first determination procedure involves comparing the number of times the sleep stage changes during the subject's sleep are a first specific change, including a change from a non-REM sleep stage to a wakeful sleep stage, with the number of times the sleep stage changes are a second specific change, and determining that the subject has sleep apnea syndrome if the number of times the sleep stage changes are a second specific change, the first specific change is determined to be greater. The second determination procedure determines that the subject has sleep apnea syndrome when it detects that the change in sleep stage determined during the subject's sleep is a third specific change, which is a change from a non-REM sleep stage to wakefulness. Sleep apnea syndrome diagnosis program.

Images