JP2019187970A - Evaluation device and program - Google Patents

Abstract

To provide a sleep evaluation device which can estimate what causes a patient to leave the bed as one of evaluations for sleep state.SOLUTION: A sleep evaluation device includes a control unit and a storage unit. The storage unit stores biological information values of a patient. The control unit acquires the number of times of bed-leaving during sleeping of the patient. The sleep evaluation device estimates what causes the patient to leave the bed on the basis of the number of times of bed-leaving and the biological information values.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an evaluation apparatus and the like.

  Conventionally, various methods for determining a sleep state of a person to be measured are known for the health management of a sleeping person (a person to be measured). As typical methods, sleep polysomnography (PSG), actigraph, and the like are known.

  As an example, Patent Document 1 is disclosed as a method for determining the sleep state of the measurement subject in real time, for example. That is, the body movement (body movement) of the measurement subject is detected, and when the body movement level exceeds the determination threshold during the predetermined detection time, the sleep state is determined as “wakefulness”, and the case below that Is determined as “sleep”.

  An apparatus for evaluating sleep of a sleeper by using such a technique is known. For example, a technique for advising health management related to sleep based on sleep state and life rhythm information input by the person is known (for example, see Patent Document 2).

JP 2008-142238 A JP 2013-45336 A

  This invention is providing the evaluation apparatus etc. which can estimate the cause which the patient left bed as one of the evaluation of a sleep state, for example.

The evaluation apparatus of the present invention is
A storage unit capable of storing the biological information of the user;
The said user is provided with the control part which estimates the user's bed leaving cause based on the frequency | count of bed leaving in a 1st area, and the said biometric information.

The program of the present invention is
In a computer having a storage unit capable of storing user biometric information,
The user realizes a function of estimating the cause of getting out of the user based on the number of times of getting out in the first section and the biological information.

  ADVANTAGE OF THE INVENTION According to this invention, the evaluation apparatus etc. which can estimate the cause from which the patient got out of bed as one of the sleep state evaluations can be provided, for example.

It is a figure which shows the whole system in this embodiment. It is a figure which shows an example of a structure of the sleep evaluation apparatus in this embodiment. It is a figure which shows an example of a structure of the parameter table in this embodiment. It is a figure which shows an example of a structure of the sleep evaluation table in this embodiment. It is a figure for demonstrating an example of the sleep diary in this embodiment. It is a figure which shows an example of a structure of the bed leaving evaluation table in this embodiment. It is an operation | movement flow for demonstrating operation | movement of the main process in this embodiment. It is an operation | movement flow for demonstrating the operation | movement of the bed leaving cause estimation process in this embodiment. It is a figure for demonstrating the variable in this embodiment. It is an operation | movement flow for demonstrating the operation | movement of the bed leaving cause estimation process in this embodiment. It is an operation | movement flow for demonstrating the operation | movement of the bed leaving cause estimation process in this embodiment. It is the figure which showed an example of the evaluation report in this embodiment. It is the figure which showed an example of the evaluation report in this embodiment. It is the figure which showed an example of the evaluation report in this embodiment.

Hereinafter, an embodiment for carrying out the present invention will be described with reference to the drawings.
An evaluation apparatus determines a patient's sleep state based on biological information values such as a patient's heart rate and respiratory rate, and performs sleep evaluation according to the determined sleep state.

  At this time, the items to be evaluated are roughly classified into five categories such as “amount of sleep, quality of sleep, habit, sleep abnormality, and vitality of user (eg, patient)”. A combination of a plurality of these items to evaluate sleep using an evaluation device has not been performed.

  In particular, when there is a disorder in sleep, nothing that identifies the cause of the disorder or outputs advice by combining sleep and lifestyle habits, sleep abnormalities, vitals, sleep quality is not done It was.

  “Leaving the bed”, which is one of the sleep disorders, is a very important obstacle because it not only inhibits the sleep of the patient, for example, but also increases the risk of falling. Therefore, it is important to pay attention to getting out of bed and to evaluate the content that leads to the cause of getting out of bed based on sleep data and to give advice based on the evaluation.

  Therefore, according to the sleep evaluation apparatus of the present embodiment, it is possible to output advice on an appropriate patient abnormality based on the acquired biological information value and the calculated sleep index. Preferably, by estimating the cause of getting out of bed as a patient abnormality, it is possible to provide useful information at a medical site or a nursing site.

  In this specification, a patient means a person who uses a bed apparatus (mattress), and is not limited to a person who receives treatment due to illness, and is a person who receives care at a facility or sleeps on a bed apparatus. It is applicable as a person.

[1. Entire system]
FIG. 1 shows that the evaluation apparatus of the present invention is applied to a sleep evaluation apparatus capable of evaluating a patient's sleep and a bed leaving cause evaluation apparatus capable of estimating or evaluating the cause of the patient getting out of the sleep state. 1 is a diagram for describing an overall outline of a system 1. FIG. As illustrated in FIG. 1, the system 1 includes a patient's floor from a floor portion of the bed device 10, a detection device 3 placed between the mattress 20, and a value (biological information value) output from the detection device 3. In order to evaluate sleep, the sleep evaluation device 5 is provided.

  In addition, the sleep evaluation apparatus in this embodiment means the apparatus which performs evaluation based on a patient's sleep. Therefore, the sleep evaluation device is a concept that includes a device that evaluates sleep itself and a device that does not evaluate sleep itself such as simply estimating the cause of getting out of the patient (for example, estimating and evaluating the cause of getting out of bed). is there.

  When an object person (hereinafter referred to as “patient P” as an example) is present on the mattress 20, the detection device 3 detects body vibration (vibration emitted from the human body) as a biological signal of the patient P who is the object person. Further, based on the detected vibration, the biological information value of the patient P can be calculated.

  The calculated biological information value (for example, respiratory rate, heart rate, amount of activity) may be output / displayed as the biological information value of the patient P.

  The biological information value calculated by the detection device 3 is transmitted to the sleep evaluation device 5. Here, the biometric information value may be transmitted by wireless communication such as a wireless LAN or Bluetooth (registered trademark), or may be transmitted via a storage medium such as an SD card (registered trademark). Moreover, you may transmit to the sleep evaluation apparatus 5 from the detection apparatus 3 via a server apparatus.

  In addition, the information transmitted from the detection device 3 to the sleep evaluation device 5 may be a signal (for example, a biological signal or vibration data) acquired by the detection device 3, or based on the acquired signal. Thus, it is possible to transmit various information such as the biological information value calculated by the detection device 3, the patient's sleep index, the bed leaving state, and the patient's position.

  Such information may be calculated by the detection device 3 or may be calculated by the sleep evaluation device 5. In addition, only some biological information values such as heart rate, respiratory rate, and activity amount may be calculated by the detection device 3, and other sleep indexes and information indicating the patient's state may be calculated by the sleep evaluation device 5. Various values may be calculated on the server side.

  Further, the detection device 3 may be formed integrally with the sleep evaluation device 5 by providing a storage unit, a display unit, and the like. Moreover, since the sleep evaluation apparatus 5 may be a general-purpose apparatus, the sleep evaluation apparatus 5 is not limited to an information processing apparatus such as a computer, and may be configured by an apparatus such as a tablet or a smartphone. Moreover, when the detection apparatus 3 has a communication function, you may connect to a server apparatus instead of the sleep evaluation apparatus 5. FIG.

  Further, the target person may be a person who is undergoing medical treatment or needs care. Moreover, even if it is a healthy person who does not require care, it may be an elderly person, a child, a disabled person, a person, and an animal.

  Here, the detection device 3 is configured in a sheet shape so as to be thin. Thereby, even if it is placed between the bed apparatus 10 and the mattress 20, it can be used without making the patient P feel uncomfortable, so that the patient's condition in the bed can be detected for a long period of time.

  In addition, the detection apparatus 3 should just detect the vibration of the patient P. For example, a load cell for measuring a load arranged on an actuator with a strain gauge or a leg of a bed may be used. Moreover, you may implement | achieve, for example with the smart phone mounted on the bed apparatus 10, a tablet, etc. by utilizing the built-in acceleration sensor.

  In FIG. 1, the H side is the longitudinal head side of the bed apparatus 10 (mattress 20), and the F side is the foot side. In FIG. 1, the L side is the left side when the patient P is in the supine position, and the R side is the right side.

[2. Configuration of sleep evaluation device]
It continues and demonstrates the structure of the sleep evaluation apparatus 5 using FIG. The sleep evaluation apparatus 5 in the present embodiment includes a control unit 100, a storage unit 130, a communication unit 150, an input unit 160, and an output unit 170.

[2.1 Control unit and storage unit]
The control unit 100 controls the operation of the system 1. For example, it is a control device such as one or a plurality of CPUs (Central Processing Units). The control unit 100 implements various processes by reading and executing various programs stored in the storage unit 130.

  The storage unit 130 is a functional unit that stores various programs and various data necessary for the operation of the sleep evaluation device 5. The storage unit 130 includes, for example, a solid state drive (SSD) that is a semiconductor memory, a hard disk drive (HDD), or the like.

  That is, in this embodiment, by executing the software stored in the storage unit 130, the control unit 100 causes the biological information acquisition unit 102, the sleep state determination unit 104, the index output unit 106, the index evaluation unit 108, and diary creation. Functions as a unit 110, a bed leaving cause estimation unit 112, and an evaluation report output unit 114.

[2.1.1 Biometric information acquisition unit]
The biological information acquisition unit 102 acquires a patient's biological information value. For example, a biological information value is received from the detection device 3 via the communication unit 150 and acquired. Similarly, when a biological signal is received from the detection device 3 via the communication unit 150, the biological information value is obtained by calculating the biological information value from the received biological signal.

  When calculating a biological information value from a biological signal, a respiratory component and a heartbeat component are extracted from the received biological signal (body motion), and a respiratory rate and a heart rate are calculated based on the respiratory interval and the heartbeat interval. Alternatively, the periodicity of body motion may be analyzed (Fourier transform or the like), and the respiration rate and heart rate may be calculated from the peak frequency.

  The acquired biological information value is stored in the biological information value data 132. Here, the biometric information value is stored in the biometric information value data 132 every predetermined time. For example, as shown in FIG. 3A, the biometric information value data 132 includes a biometric information value (in this figure, a heart rate (in this figure, “2018/02/01 02:10:00”). For example, “56”), respiratory rate (for example, “18”), activity amount (for example, “65”)) are stored.

  The biometric information value is stored in the biometric information value data 132 every minute, but may be every predetermined time such as every 5 seconds, every 30 seconds, every 2 minutes, and every 10 minutes. Also, the stored range may be stored within a predetermined range such as 24 hours, the patient being in bed, or overnight. In addition, biometric information values for a predetermined period of two days, three days, and one week may be stored.

[2.1.2 Sleep state determination unit]
The sleep state determination unit 104 determines the sleep state of the patient. As the sleep state, first, “exit” and “being in bed” of the patient are determined, and “sleep” and “wakefulness” are further determined when in bed. Further, the determined sleep state may further determine a stage such as REM / non-REM sleep.

  As a method for determining the sleep state of these patients, for example, JP 2010-264193 A (invention name: sleep state determination device, program and sleep state determination system, filing date: May 18, 2009), The sleep state determination method described in Japanese Patent Application No. 2014-229118 (Title of Invention: Sleep State Determination Device, Sleep State Determination Method and Program, Application Date: November 11, 2014) can be used. This patent application is incorporated by reference in its entirety.

  The sleep state determined by the sleep state determination unit 104 is stored in the sleep state data 134 of the storage unit 130. The sleep state data 134 stores the sleep state of the patient every predetermined time.

  The determination of getting out of bed / being present may be made based on a biological signal received from the detection device 3, or may be made by using a separately provided bed / being bed sensor. When the sleep state is determined in the detection device 3, the sleep state determination unit 104 may receive the sleep state determined by the detection device 3.

  That is, it is possible to output a sleep index such as a patient's sleep time and sleep latency from the sleep state stored in the sleep state data 134.

[2.1.3 Index output unit]
The index output unit 106 outputs an index (for example, patient index) according to the patient's sleep state and the patient's sleep habit. The index according to the patient's sleep habit is input by a patient or a user other than the patient (a medical worker, a caregiver, etc.), calculated from a biological information value, or determined from a sleep state.

  The index output by the index output unit 106 is stored in the parameter table 136. The index output unit 106 further outputs a sleep index related to the patient's sleep, an index related to sleep disorder (failure index), and an index based on the biological information value (vital index).

  FIG. 3B shows an example of the parameter table 136. Here, the sleep index, the disorder index, and the vital index stored as parameters are as follows.

(1) Date This is the time used to calculate or specify each value. For example, in FIG. 3B, a value calculated and specified over “2018/02 / 01-2018 / 02/02” is stored.

(2) Sleep time (for example, “6 hours 16 minutes”)
This is the total amount of time actually sleeping from bedtime to wakeup time. The sleep time may be automatically calculated (for example, calculated based on the sleep state acquired from the sleep state data 134) or may be manually input.

(3) Bedtime (for example, “8 hours 13 minutes”)
This is the total time from bedtime to wakeup time. The bedtime may be automatically calculated or manually input.

(4) Bedtime (for example, “22:59”)
It's time to go to bed at night. It may be when the sleeping state is in bed for a certain period of time, or may be manually input.

(5) Wake-up time (for example, “7:13”)
It is the time away from the bed in the morning. The sleep state may be when the user has left bed for a certain period of time, or may be manually input.

(6) Sleep latency (for example, “23.4 minutes”)
The time taken from bedtime to falling asleep is defined as the sleep latency. The sleep latency can be calculated based on the sleep state acquired from the sleep state data 134, for example.

(7) Sleep efficiency (eg, “76.2%”)
Of the time from getting up to getting up, the ratio of the actual sleeping time is defined as sleep efficiency. The sleep efficiency is calculated by “sleep time ÷ bed time × 100”. The sleep efficiency can be calculated based on the sleep state acquired from the sleep state data 134, for example.

(8) Mid-wake time (for example, “92.1 minutes”)
The total amount of time that the user wakes up in the middle of the sleep from falling asleep until getting up is defined as the mid-wake time. The midway awakening time can be calculated based on the sleep state acquired from the sleep state data 134, for example.

(9) Number of getting out of bed (for example, “once”)
The number of times the patient has left bed. For example, the number of sections in which “sleeping” occurred while “sleep” continues as the patient's condition may be the number of times of getting out of bed, or the number of times that bed leaving was simply detected regardless of the patient's state of being in bed. It is good. In addition, the number of times of getting out of bed can be calculated based on the sleeping state acquired from the sleeping state data 134, for example, or may be the number of times detected by the bed leaving sensor or the like. Further, the bed leaving time may be acquired together with the number of times of bed leaving.

(10) Respiratory disorder index (for example, “24.4 times / hour”)
It is an index that can estimate the possibility of sleep apnea syndrome. This is the number of breathing problems per hour during bedtime.

(11) Periodic body motion index (for example, “13.5 times / hour”)
It is an index that can estimate the possibility of periodic limb movement disorder. The number of periodic limb movements per hour while sleeping.

(12) Activity amount (for example, “61.4 count / hour”)
This is the amount of activity per minute measured during bedtime (the amount that correlates with the intensity and frequency of body movement by the number of counts when body movement is detected).

(13) (Average) respiratory rate (for example, “15.8 times / minute”)
The number of breaths per minute measured while sleeping.

(14) (Average) heart rate (for example, “56.2 times / minute”)
Heart rate per minute measured while sleeping.

  The indices (1) to (14) corresponding to the sleep habits and sleep states of these patients are (1) to (9) a sleep index, (10) and (11) are disorder indices, and (12) to (12) (14) is called a vital index.

[2.1.4 Indicator evaluation unit]
The index evaluation unit 108 evaluates an index corresponding to the patient's sleep habit and sleep state. There are various methods for evaluation. For example, evaluation is performed by determining whether or not a set threshold value is exceeded, ranking according to the value (for example, four stages such as A to D, level 1) To 5 grades, etc.). Moreover, you may perform comprehensive determination from a some parameter | index.

  Further, a message or the like corresponding to the content to be evaluated is stored in the sleep evaluation table 138 of the storage unit 130. FIG. 4 is an example of the sleep evaluation table 138, and the contents of evaluating the index are stored.

  For example, a parameter “S005” that uniquely identifies a parameter (sleep index, biological information value, failure index, vital index, etc.) that is an index is associated with each corresponding parameter (for example, “sleep latency”). Is stored as a message.

  In the case of sleep latency, since the index evaluation unit 108 evaluates with ranks A to D, a message corresponding to each evaluation is stored.

  The index evaluation unit 108 may determine a threshold for determining the rank in the process, and may store the threshold and the determination value in the sleep evaluation table 138. That is, the index evaluation unit 108 only needs to be able to evaluate according to the biometric information value and the value of each index.

[2.1.5 Diary Creation Department]
The diary creation unit 110 creates a sleep diary. The sleep diary creates a graph that takes time in the horizontal direction and shows the date in the vertical direction.

  FIG. 5 shows an example of a sleep diary. The sleep diary in FIG. 5A is a diary of 2/1 to 2/3, and is a graph in which the states of “sleep” and “wakefulness” of the patient are understood. In addition, the graph has an identification display indicating “wake-up time” and “getting-up time”, and an identification display that understands “getting out”.

  In addition, as a graph which the diary creation part 110 outputs as a diary, although a sleep diary is mainly demonstrated, the body movement (activity amount) diary which is a graph which shows a body movement (activity amount), and a respiratory rate other than this are also shown. Respiratory diary that is a graph that identifies and displays color, Heart rate diary that is a graph that identifies and displays heart rate by color, Respiratory diary that is a graph that identifies and displays respiratory disorders, and a graph that identifies and displays periodic body movements A periodic body motion diary or the like can be output.

  Further, when the number of measurement days is one day, a graph displaying a plot in which the transition of the value of the day is understood may be generated (for example, FIG. 5B).

[2.1.6 Bed leaving cause estimation unit]
The bed leaving cause estimating unit 112 estimates the cause of getting out of the patient from the biological information value, an index corresponding to the patient's sleep state, and the like. There are various causes for getting out of bed. For example, the following causes of getting out of bed can be considered.

・ Restless Legs Syndrome (RLS)
Obstructive Sleep Apnea Syndrome (OSAS)
-Periodic limb movement disorder-REM sleep behavior disorder-Frequent urination-Dementia-Based on patient symptoms such as infection, pain, itch, worse prognosis The cause of bed leaving estimates the bed leaving cause estimation unit 112 The estimation method will be described later.

  The evaluation corresponding to the cause of bed removal estimated by the bed leaving cause estimation unit 112 is stored in the bed removal evaluation table 140 of the storage unit 130. An example of the bed leaving evaluation table 140 is shown in FIG.

  The bed leaving evaluation table 140 includes a code for identifying the cause of bed leaving (for example, “M001”), the cause for bed leaving (for example, “Mizuzuzu syndrome”), and countermeasures and advice (for example, “Possibility of Mizuzuzu syndrome”). The contents such as "Normal ...") are memorized.

  The code is only added for explanation, and at least countermeasures and advice for each cause of getting out of bed need only be stored.

[2.1.7 Evaluation report output section]
The evaluation report output unit 114 outputs an evaluation report. The evaluation report outputs an index (sleep index, disorder index, vital index), an evaluation based on the index, and advice based on the evaluation. In addition, the meaning of the index, the sleep diary, etc. may be output. These evaluation reports are displayed, for example, by being output to a display device by the output unit 170, or printed on recording paper by being output to a printing device.

  Moreover, it may be output to a server device, an electronic medical record system, etc. via the communication part 150, for example, and may be output to portable terminals, such as a smart phone. Moreover, you may display by the browser of another apparatus by outputting as HTML / XML.

[2.2 Communication section]
The communication unit 150 communicates with an external device, a server, and the like. In the present embodiment, communication with the detection device 3 is performed. The communication method may be WLAN (IEEE802.11a / b / g / n) or near field communication (for example, Bluetooth (registered trademark)). Further, it may be connected to the server device via another network by WLAN, wired LAN, LTE / 5G or the like.

  Further, the communication unit 150 may receive parameters and biological information values from a storage medium (for example, a USB memory or an SD card (registered trademark)). In this case, the communication unit 150 is configured as an interface unit to which a storage medium can be connected.

[2.3 Input section and output section]
The input unit 160 receives an operation input from a user. The output unit 170 outputs various information and an evaluation report. For example, the input unit 160 may perform an operation input from a software key realized by a touch panel, or may be connected to an input device such as a keyboard or a mouse, and the operation input may be performed from the input device.

  The output unit 170 may be connected to a display device constituted by a liquid crystal display or an organic EL display, and an operation screen or an evaluation report may be output. Moreover, a printing apparatus may be connected and an evaluation report may be printed.

  In the case of a tablet or a notebook computer, the input device and the display device may be configured integrally with the sleep evaluation device 5.

[2.4 Detector]
It is connected to the detection device 3 via the communication unit 150. The detection device 3 is a biological signal acquisition unit that acquires a biological signal of a patient.

  The biological signal acquisition unit acquires the biological signal of the patient P in FIG. In the present embodiment, as an example, body vibration, which is a type of biological signal, is acquired using a sensor that detects a pressure change. The acquired body vibration is converted into biological information value data such as a respiratory rate, a heart rate, and an activity amount, and is output. Furthermore, the detection device 3 or the sleep evaluation device 5 acquires the patient's bed state (for example, whether or not the patient P is in bed, staying in bed, getting out of bed, sitting in an end position, etc.) based on the body vibration data. As described above, it is possible to acquire a sleep state (sleep, awakening).

  Note that the biological signal acquisition unit in the present embodiment acquires, for example, the patient's body vibration using a pressure sensor and acquires respiration and heartbeat from the body vibration, but changes in the patient's center of gravity (body motion) using the load sensor. It is also possible to acquire a biological signal using a radar, or to acquire a biological signal based on the displacement of the body surface or bedding using a radar, or to provide a microphone to provide a biological signal based on the sound picked up by the microphone. You may get What is necessary is just to be able to acquire a patient's biological signal using any sensor.

  That is, the biological signal acquisition unit may be provided in a device such as the detection device 3 or may be configured to receive a biological signal from an external sensor device.

[3. Process flow]
[3.1 Main processing]
It continues and the process which outputs the sleep evaluation report in the sleep evaluation apparatus 5 is demonstrated based on the processing flow of FIG. The processing flow in FIG. 7 is a process realized by reading a program stored in the storage unit 130 and executing it by the control unit 100.

  First, a biometric information value is acquired by the biometric information acquisition unit 102 (step S100). The biological information value may be received from the detection device 3, or the control unit 100 may calculate the biological information value based on a biological signal received from the detection device 3 or the like. The biometric information value acquisition process is executed in real time in the present embodiment by the biometric information acquisition unit 102, but may be acquired by an instruction from a user (patient, medical worker, caregiver, etc.).

  Here, when it is determined that the evaluation report is output (step S200; Yes), the control unit 100 transitions to a process for outputting the evaluation report. Note that the control unit 100 determines that the evaluation report is output when it is determined that the evaluation report is output by the user, or at a predetermined timing (for example, morning, noon, wake-up, data on sleep for several days). For example, when a history is stored).

  In order to output the evaluation report, first, the control unit 100 executes a parameter calculation process (step S300). In the parameter calculation process, for example, the sleep state is output by the sleep state determination unit 104, or an index corresponding to the sleep habit and sleep state of the patient is calculated and output by the index output unit 106.

  Subsequently, the control unit 100 executes a sleep diary creation process (step S400). That is, the diary creation unit 110 creates a sleep diary.

  The controller 100 executes a parameter evaluation process (step S500). That is, the index evaluation unit 108 evaluates and outputs parameters such as the biological information value and each index. Details of the parameter evaluation process will be described later.

  The control unit 100 executes the bed leaving cause estimation process (step S600). That is, the bed leaving cause estimation unit 112 estimates the bed leaving cause and outputs it. Details of the bed leaving cause identification process will be described later.

  The control unit 100 executes an evaluation report output process (step S700). That is, the evaluation report output unit 114 includes a biometric information value, an index according to the sleep habit and sleep state of the patient, a sleep diary created by the sleep diary creation process, an evaluation result evaluated by the parameter evaluation process, The cause of bed removal estimated in the bed leaving cause estimation process is output as an evaluation report.

  In the flow of FIG. 7, each process is executed when an evaluation report is output, but may be executed as appropriate. That is, step S300, step S400, etc. may be executed at any time between step S100 and step S200.

[3.2 Parameter evaluation processing]
The parameter evaluation process executed in step S500 will be described. The index evaluation unit 108 performs parameter evaluation processing to evaluate and output an index corresponding to the sleep habit and sleep state of the patient. Hereinafter, typical parameters and an example of an evaluation method will be described.

(1) Sleep time A to D are evaluated as the sleep time. For example,
A: 6.5 hours to less than 8 hours B: 6 hours to less than 6.5 hours, 8 hours to less than 9 hours C: 5 hours to less than 6 hours, 9 hours to less than 10 hours D: less than 5 hours, 10 hours The sleep time parameter is evaluated during the above time.

(2) Bedtime As the bedtime, A to D are evaluated. For example, the same value as the sleep time may be used as the evaluation reference time.

(3) Sleep latency The sleep latency is evaluated as A to D. For example,
A: Less than 10 minutes B: 10 minutes or more and less than 20 minutes C: 20 minutes or more and less than 30 minutes D: 30 minutes or more The parameters of sleep latency are evaluated.

(4) Sleep efficiency A to D are evaluated as sleep efficiency. For example,
The parameters of sleep efficiency are evaluated at a ratio of A: 95% or more, B: 85% or more and less than 95%, C: 75% or more and less than 85%, D: less than 75%.

(5) Midway awakening time A to D are evaluated as the midway awakening time. For example,
A: Less than 10 minutes B: 10 minutes or more and less than 20 minutes C: 20 minutes or more and less than 40 minutes D: 40 minutes or more

(6) Respiratory disorder index and periodic body motion index The respiratory disorder index and periodic body motion index are determined by a threshold value. For example, if it is 15.0 times / hour or more, it is evaluated that there is an abnormality (there is a problem).

(7) Activity amount, respiration rate, heart rate Activity amount, respiration rate, and heart rate are determined by the magnitude of the value. For example, the activity amount is preferably as low as possible, but it is evaluated that there is an abnormality when the activity amount is 40 counts / hour or more.

[3.3 Bed leaving cause estimation process]
Next, the bed leaving cause estimation process will be described. In addition, a bed leaving cause estimation process estimates a bed leaving cause based on the parameter | index according to a patient's sleep habit and sleep state. At this time, when the number of times of bed leaving is equal to or less than a predetermined threshold value (for example, equal to or less than a second threshold value described later), the process may not be executed.

[3.3.1 First bed leaving cause estimation process]
The first bed leaving cause estimation process will be described with reference to FIG. The first bed leaving cause estimation process estimates the bed leaving cause with reference to the obstacle index when the number of bed leaving is large.

  First, the control unit 100 refers to the sleep state data 134 and determines whether or not the number of times the patient has left the bed is greater than or equal to the first threshold (step S6102).

  Moreover, as a period which acquires the frequency | count of getting out of bed, it may be a patient's overnight period (one cycle from a patient falling asleep to awakening), and may be a period at bedtime. Moreover, the average of the sleep period of several days may be sufficient.

  Here, the first threshold is, for example, “4 times”. For example, when the number of times the patient leaves the bed is 4 times or more, it is determined as restless foot syndrome (step S6102; Yes → step S6108). Here, the determination code is output as M001.

  Thereby, in the evaluation report output process, the evaluation report output unit 114 estimates the cause of getting out of bed corresponding to the determination code by referring to the getting out evaluation table 140. Also, advice corresponding to the estimated cause of getting out of bed is read out from the getting out evaluation table 140 and output.

  Returning to FIG. 8, it is determined whether or not the number of times of getting out of bed is equal to or greater than the second threshold (step S6104). Here, the second threshold value is, for example, “one time”, and when the number of bed leaving times is “less than once”, another determination is performed (step S6104; No).

  Subsequently, when the number of bed departures is equal to or greater than a second threshold (for example, “1 time”) (step S6104; Yes) and the periodic body motion index is high (step S6106; Yes), the bed leaving cause estimating unit 112 The code that is determined as the cause of getting out of the bed patient is “M001”, that is, it is determined (estimated) as restless foot syndrome. Here, the phrase “the periodic body motion index is high” means, for example, a case where the periodic body motion index is equal to or greater than the periodic body motion threshold (for example, “15.0”).

  Subsequently, when the periodic body motion index is not high, but the respiratory disorder index is high (step S6106; No-> step S6110; Yes), the code that the bed leaving cause estimating unit 112 determines as the bed leaving cause of the patient is “M003”. That is, it is determined (estimated) as obstructive sleep apnea syndrome (OSAS). Here, the high respiratory disorder index means, for example, a case where the respiratory disorder index is equal to or greater than a respiratory disorder index threshold (for example, “15.0”).

  As described above, when the cause of getting out of bed is estimated by the cause of getting out of bed 112, the evaluation report output unit 114 outputs advice corresponding to the cause of getting out of bed. For example, if the possibility of restless legs syndrome is high, normal sleeping pills are not effective, so it is advised to consult a specialist to prescribe a special medicine or check if there is not enough iron If it seems to be deficient, it can be advised to take iron and restrict intake of alcohol and caffeine.

  In the case of the code “M003”, frequent urination occurs, but it is estimated that the cause is obstructive sleep apnea syndrome. Therefore, advice to consider a specialist visit for diagnosis and treatment of obstructive sleep apnea syndrome as well as urological treatment is displayed as advice.

  In the present embodiment, the cause of getting out is estimated from the number of getting out of bed, the periodic body motion index, and the respiratory disorder index. At this time, for example, it may be determined that the other sleep index and vital index correspond to normal.

  Further, when the periodic body motion index is high (step S6106; Yes), it may be determined whether or not the respiratory disorder index is higher. In this case, the bed leaving cause estimating unit 112 estimates the possibility of restless foot syndrome and the possibility of obstructive sleep apnea syndrome as the bed leaving causes. That is, depending on the patient, there may be two causes.

[3.3.2 Second bed leaving cause estimation process]
The second bed leaving cause estimation process will be described. The second bed leaving cause estimation process is a process for estimating whether the cause corresponds to each bed leaving cause based on a plurality of sleep indexes or the like. The bed leaving cause estimating unit 112 estimates the bed leaving cause depending on whether or not the following conditions are met.

(1) Sleep efficiency is low, activity level is high, and other sleep indices are normal. The bed leaving cause estimating unit 112 wakes up because of itching or not sleeping due to dementia, Presumed that he is getting out of bed.
(2) Getting out of bed during REM sleep It is estimated that you are getting up due to REM sleep behavior disorder.

(3) Vital (e.g., heart rate, respiratory rate, etc.) increases immediately before leaving the bed The cause-of-bed estimating unit 112 estimates that the bed is based on urinary intention.

(4) Sleep efficiency is low, breathing disorder index is high, other sleep indices are normal. It is estimated that he is getting out of bed.

(5) When sleep efficiency is low and there is a problem with lifestyle habits For example, when bedtime is long, sleeping time is long, or you go to bed immediately after dinner The cause estimating unit 112 estimates that there is a problem with lifestyle habits.

  In this way, it is possible to estimate the cause of getting out of bed by combining the results of comparing a plurality of sleep indices, vital values, disorder indices, and the like with their respective reference values.

  Rather than comparing with the reference value, the result of multivariate analysis using the number of daily bed departures as an objective variable, multiple sleep indicators, vital values, disability indicators, etc. as the explanatory variables. It may be estimated as the cause of this. For example, as shown in FIG. 9, explanatory variables may be stored in association with objective variables for each date.

  Here, in the case of the method of comparing with the reference value, if the reference value is exceeded even if it is not related to getting out of bed, an indicator exceeding the reference value is estimated as the cause of getting out of bed. In the case of using, there is an advantage that the index is extracted as a cause that is linked with the change in the number of times of bed leaving.

  For example, it is a method that exerts an effect when the number of bed leavings varies greatly depending on the day or when it suddenly increases from a certain point in time. In addition, vital values and disability indicators are small in daily changes, but sleep indicators such as sleep efficiency and the number of bed leaving are inherently related and tend to be pseudo-correlated, so it is more appropriate to exclude sleep indicators from explanatory variables. Can often be estimated.

[3.3.3 Third bed leaving cause estimation process]
The third bed leaving cause estimation process will be described. This embodiment demonstrates the case where the bed leaving cause estimation part 112 determines a patient's attitude | position using artificial intelligence (machine learning).

  Here, the operation of the bed leaving cause estimation unit 112 in the present embodiment will be described. The bed leaving cause estimation unit 112 estimates the patient's posture by using vibration data and the patient's state as input values (input data) and using artificial intelligence and various statistical indexes.

  As illustrated in FIG. 10, the bed leaving cause estimation unit 112 includes a feature extraction unit 1120, an identification unit 1122, an identification dictionary 1124, and a patient state output unit 1126. Here, the identification dictionary 1124 may be stored in the storage unit 130.

  First, as input data input to the bed leaving cause estimating unit 112, various parameters are input and used. For example, in the present embodiment, vibration data as vibration data, a biological information value calculated from the vibration data, and a parameter obtained from the biological information value and the patient state are used. These inputs may be one or a combination of a plurality.

  Then, the feature extraction unit 1120 extracts each feature point and outputs it as a feature vector. Here, what the feature extraction part 1120 extracts as a feature point can consider the following, for example.

(1) Values and relationships between the number of getting out of bed and periodic body motion index (2) Values and relationships between the number of getting out of bed and respiratory disorder index (3) Values and relationships between sleep efficiency and respiratory disorder index (4) Sleep efficiency and Values and relationships with lifestyle habits (such as bedtime) (5) Changes in sleep diaries and changes in vital diaries (6) Values and relationships between sleep efficiency and activity

  The feature extraction unit 1120 outputs a feature vector by combining one or more of these feature points. In addition, what was demonstrated as a feature point is an example, and is not limited to the said value. Also, as described above, each value is a value for convenience of explanation. Then, “1” may be output as the corresponding feature point, “0” may be output as the non-applicable feature point, or a random variable may be output.

  When all the above-described feature points are included, the feature space is 6-dimensional and is output to the identification unit 1122 as a 6-dimensional feature vector.

  The identification unit 1122 identifies a class corresponding to the patient state from the input feature vector. At this time, the class is identified by collating with a plurality of prototypes prepared in advance as the identification dictionary 1124. The prototype may be stored as a feature vector corresponding to each class, or a feature vector representing a class may be stored.

  If a feature vector representing a class is stored, the class to which the closest prototype belongs is determined. At this time, the identification unit 1122 may determine by the nearest neighbor determination rule, or may identify by the k-nearest neighbor method.

  The identification dictionary 1124 used by the identification unit 1122 may store a prototype in advance or may store it using machine learning.

  Then, corresponding to the class identified by the identification unit 1122, the cause of getting out of bed is output by the bed leaving cause output unit 1226. As the cause of bed removal, contents such as “restless feet syndrome”, “obstructive sleep apnea syndrome”, “abnormal sleep habits”, “frequent urination”, “infection”, “pain”, “prognosis worsening” and “itchiness” are identified. Alternatively, the random variable may be output as it is.

  Thereby, according to this embodiment, it becomes possible to acquire the vibration data (biological information value) output from the sensor and to infer the cause (the cause of getting out of bed) when the patient gets out of bed from these information. .

[3.4.4 Fourth bed leaving cause estimation process]
The fourth bed leaving cause estimation process will be described. The fourth bed leaving cause estimation process is an embodiment in the case where the cause of bed leaving is estimated using deep learning using a deep neural network.

  In the present embodiment, the patient's biological information value, sleep index, and sleep diary are input to the bed leaving cause estimation unit 112. The bed leaving cause estimation unit 112 estimates the bed leaving cause from the input biological information value (parameter of the biological information). As the processing for the estimation, deep learning (deep neural network) is used. For example, processing in deep learning will be briefly described with reference to FIG.

  First, the bed leaving cause estimation unit 112 inputs parameters such as a biological information value and a sleep index into a neural network including a plurality of layers and neurons included in each layer. Each neuron receives signals from a plurality of other neurons and outputs the processed signals to another plurality of neurons. When the neural network has a multilayer structure, they are called an input layer, an intermediate layer (hidden layer), and an output layer in the order in which signals flow.

  A neural network that consists of multiple layers is called a deep neural network (for example, a convolutional neural network with a convolution operation), and the machine learning method using this is called deep learning. Call.

  The waveform data is subjected to various operations (convolution operation, pooling operation, normalization operation, matrix operation, etc.) on the neurons of each layer of the neural network, flows while changing its shape, and a plurality of signals are output from the output layer.

  Each of the plurality of output values from the neural network is associated with the cause of getting out of the patient, and processing such as inferring that the cause of getting out of bed is associated with the output value having the largest value. Alternatively, the cause of getting out of bed may be estimated from the output of the classifier by passing one or a plurality of output values through the classifier without directly outputting the cause of getting out of the patient.

  Parameters that are coefficients used for various computations of neural networks are input to the neural network in advance a number of biological information values and corresponding causes of bed leaving in the sleep index, and the error between the output value and the correct value is calculated by the error back propagation method. It is determined by propagating through the neural network in the reverse direction and updating the parameters of the neurons in each layer many times. The process of updating and determining parameters in this way is called learning.

  The structure of the neural network and the individual calculations are known techniques described in books and papers, and any one of these techniques may be used.

  In this way, by using the bed leaving cause estimating unit 112, the bed leaving cause is output by referring to the biological information value calculated from the vibration data output from the sensor and the parameters of the biological information.

  Further, not only parameters such as biometric information values and sleep indices, but also diary data, for example. For example, it is possible to input and learn computable diary data such as a sleep diary, body movement diary, and respiratory disorder diary.

[4. Output of evaluation report]
Here, an example of the evaluation report output from the output unit 170 by the evaluation report output unit 114 will be described.

[4.1 First evaluation report]
FIG. 12 is an example of the first evaluation report W100. The evaluation report W100 includes each sleep index, an actual measurement value (calculated value), an evaluation value evaluated by the index evaluation unit 108 based on the measurement value (calculated value), and advice based on the evaluation value, in the region R100. Is output. Moreover, comprehensive determination (comprehensive evaluation) based on the sleep index is output to the region R105.

  The comprehensive evaluation (overall evaluation) is determined by the index evaluation unit 108 or the evaluation report output unit 114. Various methods can be considered as a method for comprehensive determination. For example, an average of sleep indices or an index that can be comprehensively determined using weights may be calculated and used. You may use the worst one.

  In addition, a sleep diary is output to the region R110 in the evaluation report W100. As described above, by using the first evaluation report W100, it is possible to easily confirm the sleep index, evaluation, advice, and sleep diary.

[4.2 Second evaluation report]
FIG. 13 is an example of the second evaluation report W200. Similar to the first evaluation report W100, in the evaluation report W200, information related to the sleep index is output to the region R200.

  Here, in the second evaluation report, the cause of getting out of bed and advice are displayed in the region R210. Thereby, the user can easily confirm the cause of getting out of the patient. Therefore, for example, it is possible to reduce the number of bed leaving by eliminating the cause of bed leaving.

  Moreover, you may identify and display the sleep parameter | index relevant to the cause of getting out of bed. For example, in FIG. 13, the parameters (sleep index) of “number of times of getting out” and “periodic body motion index” are identified and displayed (for example, different from other indices), which is problematic. Can be easily grasped from the evaluation report.

  Therefore, an identification display R220 is attached to “number of times of getting out of bed”, and an identification display R222 is attached to “periodic body motion index”.

  Thus, according to the second evaluation report W200, the user can grasp the cause of getting out of bed with the evaluation report. Moreover, the problem of getting out of bed can be easily confirmed by identifying and displaying a troublesome sleep index.

[4.3 Third evaluation report]
FIG. 14 is an example of a third evaluation report. In the third evaluation report, sleep, breathing, heartbeat, activity amount, respiratory disorder, and fluctuations in periodic body movement are output. In addition, a sleep index and advice are output together.

  As described above, according to the third evaluation report, it is possible to easily check the fluctuation of the biological information value, the fluctuation of the sleep index, and the like. These fluctuations in biometric information values and fluctuations in sleep indices can be displayed in units of several days. In addition, by arranging a plurality of graphs with 24 hours per day as a single graph, it is possible to check changes in biological information values, sleep indices, and abnormalities in units of several days.

[5. effect]
Thus, according to this embodiment, it is possible to estimate the cause of getting out of the patient with reference to various information such as the biological information value of the patient and the sleep index.

  In particular, the evaluation of sleep requires the amount of sleep, the quality of sleep, sleep habits (sleep regularity), sleep disorders, and vital values during sleep. As described above, the amount of sleep is evaluated by sleep time, and the quality of sleep can be evaluated by a sleep index (such as mid-wake time, number of getting out of bed, sleep efficiency). Moreover, sleep habits can be evaluated based on bedtime, wake-up time, change in bedtime / wake-up time, and the like.

  Considering the items necessary for the evaluation of sleep, a sleep evaluation report is output.

[6. Modified example]
The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and the design and the like within the scope of the present invention are also within the scope of the claims. include.

  Moreover, in this embodiment, although the sleep evaluation report is output in the sleep evaluation apparatus 5 based on the result output by the detection apparatus 3, you may calculate all by the detection apparatus 3. FIG. Moreover, not only can an application be installed and realized in a terminal device (for example, a smartphone, a tablet, or a computer), but processing can be performed on the server side and the processing result returned to the terminal device.

  For example, the processing described above may be realized on the server side by uploading the biological information from the detection device 3 to the server. This detection device 3 may be realized by a device such as a smartphone incorporating an acceleration sensor or a vibration sensor, for example.

  In addition, the program that operates in each device in the embodiment is a program (a program that causes a computer to function) that controls the CPU and the like so as to realize the functions of the above-described embodiments. Information handled by these devices is temporarily stored in a temporary storage device (for example, RAM) at the time of processing, and then stored in various ROM, HDD, and SSD storage devices, and read by the CPU as necessary. Correction and writing are performed.

  In addition, when distributing to the market, the program can be stored and distributed in a portable recording medium, or transferred to a server computer connected via a network such as the Internet. In this case, of course, the storage device of the server computer is also included in the present invention.

DESCRIPTION OF SYMBOLS 1 System 3 Detection apparatus 5 Sleep evaluation apparatus 100 Control part 102 Biometric information value acquisition part 104 Sleep state determination part 106 Index output part 108 Index evaluation part 110 Diary preparation part 112 Bed leaving cause estimation part 114 Evaluation report output part 130 Storage part 132 Living body Information value data 134 Sleep state data 136 Parameter table 138 Sleep evaluation table 140 Bed removal evaluation table 150 Communication unit 160 Input unit 170 Output unit

Claims (9)

A storage unit capable of storing the biological information of the user;
An evaluation apparatus, comprising: a control unit that estimates a cause of getting out of the user based on the number of times of getting out in the first section and the biological information. The controller is
Obtaining a sleep index indicating the quality of sleep of the user;
Estimating the cause of getting out of bed based on the number of getting out of bed, the biological information, and the sleep index,
The evaluation apparatus according to claim 1, wherein: The controller is
Obtaining a failure index indicating abnormal sleep of the user;
Estimating the cause of getting out of bed based on the number of times of getting out of bed, the biological information, the sleep index, and the disorder index.
The evaluation apparatus according to claim 2, wherein: The controller is
When the number of times of bed leaving is equal to or greater than a threshold value, the cause of bed leaving is estimated based on the periodic motion index and / or respiratory disorder index of the user.
The evaluation apparatus according to claim 1, wherein: The controller is
Estimating whether the cause of getting out of bed is restless foot syndrome based on the number of getting out of the user and the periodic body motion index.
The evaluation apparatus according to claim 4. The controller is
Estimating whether the cause of getting out is obstructive sleep apnea syndrome based on the number of getting out of the user, the periodic body motion index, and the respiratory disorder index,
The evaluation apparatus according to claim 4. The controller is
The sleep index and the cause of getting out of bed are output together as an evaluation report.
The evaluation apparatus according to claim 2 or 3, wherein The controller is
Outputting an evaluation report identifying and displaying the sleep index associated with the cause of getting out of bed,
The evaluation apparatus according to claim 7. In a computer having a storage unit capable of storing user biometric information,
A program for realizing a function of estimating a cause of getting out of the user based on the number of times of getting out in the first section and the biological information.