Deep body temperature estimation device, deep body temperature estimation method, and storage medium

Abstract

The present application provides a kind of deep body temperature estimation device, comprising: deep body temperature acquisition unit, obtains the deep body temperature of the first time of the estimation object measured person as the object of estimating the deep body temperature;Pulse acquisition unit, obtains the pulse of the estimation object measured person including the period of first time;And estimation unit, utilizes the deep body temperature estimation model of the deep body temperature of specified time according to the deep body temperature of initial time and the pulse from the initial time to specified time, the deep body temperature of the estimation object measured person is estimated based on the deep body temperature of the first time obtained by the deep body temperature acquisition unit and the pulse including the period of first time obtained by the pulse acquisition unit.

Description

Technical Field

[0001] The present invention relates to a deep body temperature estimation device, a deep body temperature estimation method, and a deep body temperature estimation program. Background Art

[0002] In recent years, the trend toward higher temperatures has been significant, increasing the risk of heatstroke. Consequently, various technologies for counteracting heatstroke have been disclosed (e.g., see Patent Documents 1 and 2). The technology described in Patent Document 1 relates to air-conditioning clothing with a body temperature monitoring function. This temperature monitoring function is intended not only to prevent a rise in body temperature in hot environments but also to comprehensively manage the worker's physical condition.

[0003] This air-conditioning suit with a body temperature monitoring function includes: a garment portion for the worker to wear; an air supply device for supplying air between the garment portion and the worker's body; a body temperature measuring device for measuring the temperature of the worker wearing the garment portion; and an air supply control device for controlling the operation of the air supply device based on the temperature measurement result obtained by the body temperature measuring device. The air supply control device stops or reduces the air supply by the air supply device if the body temperature measurement result is below a predetermined temperature, and increases the air supply by the air supply device if the body temperature measurement result exceeds the predetermined temperature. Furthermore, the air-conditioning suit includes a heart rate measuring device for measuring the worker's heart rate.

[0004] The technology described in Patent Document 2 is used to detect a worker's risk of heat stroke before their deep body temperature becomes abnormal. This technology comprises a workload information input unit that inputs the worker's workload information; a respiration sensor that detects the worker's respiration in real time; an electrocardiograph that detects the worker's heartbeat in real time; an information recording unit that synchronizes and records the respiration curve information obtained by the respiration sensor and the heartbeat information obtained by the electrocardiograph; a respiratory sinus arrhythmia (RSA) calculation unit that derives the RSA from the respiration curve information and heartbeat information recorded in the information recording unit; and a display unit that displays the RSA calculated by the RSA calculation unit and the workload information.

[0005] Prior art literature

[0006] Patent Literature

[0007] Patent Document 1: Japanese Patent Application Laid-Open No. 2017-166075

[0008] Patent Document 2: Japanese Patent Application Laid-Open No. 2017-27123 Summary of the Invention

[0009] Problems to be solved by the invention

[0010] Heatstroke is generally believed to be related to deep body temperature. Therefore, to assess a worker's risk of heatstroke, it is ideal to measure their deep body temperature. However, in some operations, measuring a worker's deep body temperature is difficult. Therefore, there is a need to estimate deep body temperature using physiological indicators that are easier to measure than deep body temperature.

[0011] An object of the present invention is to provide a technology for estimating deep body temperature based on physiological indicators.

[0012] Solutions for solving problems

[0013] In order to solve the above problems, the following solution is adopted.

[0014] Specifically, the first embodiment adopts a deep body temperature estimating device comprising:

[0015] a deep body temperature acquisition unit that acquires a deep body temperature at a first moment of an estimation target subject, the subject of whom the deep body temperature is to be estimated;

[0016] a pulse acquisition unit that acquires the pulse of the estimation target subject during a period including a first time; and

[0017] An estimating unit estimates the deep body temperature of the estimation object subject based on the deep body temperature at the first moment acquired by the deep body temperature acquisition unit and the pulsation during the period including the first moment acquired by the pulsation acquisition unit, using a deep body temperature estimation model that estimates the deep body temperature at the specified moment based on the deep body temperature at the initial moment and the pulsation from the initial moment to the specified moment.

[0018] The solution of the present disclosure can also be implemented by executing a program by an information processing device. That is, the structure of the present disclosure can be specifically a program for causing an information processing device to execute the processing performed by each unit in the above-mentioned solution or a computer-readable recording medium having the program recorded thereon. In addition, the structure of the present disclosure can also be determined by a method in which an information processing device executes the processing performed by each of the above-mentioned units. The structure of the present disclosure can also be determined as a system including an information processing device that performs the processing performed by each of the above-mentioned units.

[0019] Effects of the Invention

[0020] According to the present invention, a technique for estimating deep body temperature based on physiological indicators can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a diagram showing an example of functional blocks of a deep body temperature estimation model building device.

[0022] Figure 2This is a diagram showing an example of functional blocks of a deep body temperature estimating device.

[0023] Figure 3 This is a diagram showing an example of the hardware configuration of an information processing device.

[0024] Figure 4 This is a diagram showing an example of the operation flow of constructing a deep body temperature estimation model in the deep body temperature estimation model construction device.

[0025] Figure 5 is an example of a Poincare Plot of RRI.

[0026] Figure 6 1 is a diagram showing an example of the relationship between the estimated value TMP of the deep body temperature and the amount of change ΔTMP in the deep body temperature.

[0027] Figure 7 This is a diagram showing an example of the operation flow of deep body temperature estimation in the deep body temperature estimation device.

[0028] Figure 8 This is a graph showing an example of changes in the deep body temperature actually measured during the exercise stress test on subject A and the deep body temperature estimated based on heart rate information.

[0029] Figure 9 This is a graph showing an example of changes in the deep body temperature actually measured during the exercise stress test performed on subject B and the deep body temperature estimated based on heart rate information.

[0030] Figure 10 This is a graph showing an example of changes in the deep body temperature actually measured during the exercise stress test on subject C and the deep body temperature estimated based on heart rate information.

[0031] Figure 11 This is a graph showing an example of changes in deep body temperature actually measured during an exercise stress test on subject D and deep body temperature estimated based on heart rate information.

[0032] Figure 12 This is a graph showing an example of changes in deep body temperature actually measured during an exercise stress test on subject E and deep body temperature estimated based on heart rate information. DETAILED DESCRIPTION

[0033] The following describes the embodiments with reference to the accompanying drawings. The configurations of the embodiments are examples, and the configuration of the present invention is not limited to the specific configurations of the embodiments disclosed herein. When implementing the invention, specific configurations corresponding to the embodiments may also be appropriately adopted.

[0034] [Implementation Method]

[0035] Figure 1 This is a diagram showing an example of functional blocks of the deep body temperature estimation model construction device according to the present embodiment. Figure 1 The deep body temperature estimation model construction device 100 includes a deep body temperature acquisition unit 102 , a heartbeat information acquisition unit 104 , an estimation model construction unit 106 , and a storage unit 108 .

[0036] The deep body temperature estimation model construction apparatus 100 acquires deep body temperature and heartbeat information of a plurality of model construction subjects during work with a predetermined load, and constructs a deep body temperature estimation model for estimating deep body temperature.

[0037] The deep body temperature acquisition unit 102 acquires the deep body temperature of the subject for model construction measured by a thermometer or the like for measuring the deep body temperature. The deep body temperature is, for example, the rectal temperature.

[0038] The heartbeat information acquisition unit 104 acquires the heartbeat information of the subject being measured for model construction, which is measured by an electrocardiograph or the like. Examples of the heartbeat information include electrocardiogram data and heartbeat data. An electrocardiograph is an example of a pulsation meter that measures pulsation.

[0039] The estimation model construction unit 106 constructs a deep body temperature estimation model for estimating the deep body temperature by regression analysis based on the acquired deep body temperature and heartbeat information of the measurement subject after the initial time for model construction.

[0040] The storage unit 108 stores programs, models, data, and the like used in the deep body temperature estimation model construction apparatus 100. The storage unit 108 stores the constructed deep body temperature estimation model, deep body temperature, heartbeat information, and the like.

[0041] Figure 2 This is a diagram showing an example of functional blocks of the deep body temperature estimating device according to this embodiment. Figure 2 The deep body temperature estimating device 200 includes an initial deep body temperature acquiring unit 202 , a heartbeat information acquiring unit 204 , an estimating unit 206 , and a storage unit 208 .

[0042] Deep body temperature estimation apparatus 200 obtains the initial deep body temperature of a target subject, who is the subject of deep body temperature estimation, and heartbeat information of the target subject during operation. It estimates the deep body temperature of the target subject using the deep body temperature estimation model constructed by deep body temperature estimation model construction apparatus 100. The model construction subject and the target subject are collectively referred to as the subject.

[0043] The initial deep body temperature acquisition unit 202 acquires the deep body temperature of the estimated target subject before work, measured by a thermometer or the like for measuring deep body temperature.

[0044] The heartbeat information acquisition unit 204 acquires the heartbeat information of the estimated subject being measured, measured by an electrocardiograph or the like. The heartbeat information is, for example, electrocardiogram data or heartbeat data. The heartbeat information acquisition unit 204 is an example of a pulsation acquisition unit.

[0045] The estimation unit 206 estimates the amount of change in deep body temperature within each reference period using the deep body temperature estimation model constructed in the deep body temperature estimation model construction device 100 based on the deep body temperature of the estimated subject at the first moment (any moment) and the heartbeat information of the period including the first moment.

[0046] The storage unit 208 stores programs, models, data, etc. used by the deep body temperature estimation apparatus 200. The storage unit 208 stores the deep body temperature estimation model constructed by the deep body temperature estimation model construction apparatus 100, estimated deep body temperature changes, deep body temperature, heart rate information, etc.

[0047] Here, heartbeat information is used, but other pulsation information can also be used instead. A heartbeat is the pulsation of the heart. A heartbeat is a type of pulsation. Pulsation is the movement produced by the repeated periodic contraction and relaxation of internal organs. Examples of other pulsations include fingertip pulse waves and earlobe pulse waves. Heart rate is the number of heartbeats in a given period. Pulse is the pulsation of an artery. The interpulsation interval is the length of one pulsation cycle.

[0048] The deep body temperature estimation model construction device 100 and the deep body temperature estimation device 200 can be implemented using a dedicated or general-purpose computer such as a personal computer (PC), a workstation (WS), a smartphone, a mobile phone, a tablet terminal, a car navigation device, a personal digital assistant (PDA), or an electronic device equipped with a computer.

[0049] Figure 3 This is a diagram showing an example of the hardware configuration of an information processing device. Figure 3 The information processing device shown has a general computer structure. The deep body temperature estimation model construction device 100 and the deep body temperature estimation device 200 are as follows. Figure 3 It is implemented by the information processing device 90 shown. Figure 3 The information processing device 90 includes a processor 91, a memory 92, a storage unit 93, an input unit 94, an output unit 95, and a communication control unit 96. These are connected to each other via a bus. The memory 92 and the storage unit 93 are computer-readable recording media. The hardware configuration of the computer is not limited to Figure 3In the examples shown, constituent elements may be omitted, replaced, or added as appropriate.

[0050] In the information processing device 90 , the processor 91 loads a program stored in a recording medium into a work area of ​​the memory 92 and executes the program. Each component is controlled by the execution of the program, thereby realizing a function consistent with a predetermined purpose.

[0051] The processor 91 is, for example, a central processing unit (CPU) or a digital signal processor (DSP).

[0052] The memory 92 includes, for example, a random access memory (RAM) and a read-only memory (ROM). The memory 92 is also called a main storage device.

[0053] The storage unit 93 is, for example, an erasable programmable read-only memory (EPROM) or a hard disk drive (HDD). Furthermore, the storage unit 93 may include removable media, that is, removable recording media. Examples of removable media include Universal Serial Bus (USB) memory or disk recording media such as compact discs (CDs) or digital versatile discs (DVDs). The storage unit 93 is also referred to as a secondary storage device.

[0054] The storage unit 93 stores various programs, data, and tables in a readable and writable manner on a recording medium. The storage unit 93 stores an operating system (OS), various programs, various tables, and the like. The information stored in the storage unit 93 can also be stored in the memory 92. Furthermore, the information stored in the memory 92 can also be stored in the storage unit 93.

[0055] The operating system is software that mediates between software and hardware, manages memory space, files, processes, and tasks. The operating system includes a communication interface. This communication interface is a program that exchanges data with other external devices connected via the communication control unit 96. Examples of external devices include other computers and external storage devices.

[0056] The input unit 94 includes a keyboard, a pointing device, a wireless remote control, a touch panel, etc. In addition, the input unit 94 may include a video or image input device such as a camera, or a sound input device such as a microphone.

[0057] Output unit 95 includes display devices such as liquid crystal displays (LCDs), electroluminescence (EL) panels, cathode ray tube (CRT) displays, and plasma display panels (PDPs), as well as output devices such as printers. Output unit 95 may also include audio output devices such as speakers.

[0058] Communication control unit 96 connects to other devices and controls communications between computer 90 and other devices. Examples of communication control unit 96 include a local area network (LAN) interface board, a wireless communication circuit for wireless communication, and a communication circuit for wired communication. The LAN interface board and wireless communication circuit connect to a network such as the Internet.

[0059] The computer implementing deep body temperature estimation model construction device 100 uses a processor to load programs stored in an auxiliary storage device onto a main storage device and execute them, thereby fulfilling the functions of deep body temperature acquisition unit 102, heartbeat information acquisition unit 104, and estimation model construction unit 106. Meanwhile, storage unit 108 is located in a storage area of ​​the main storage device or the auxiliary storage device.

[0060] The processor loads the program stored in the auxiliary storage device into the main storage device and executes it, thereby enabling the computer of deep body temperature estimation device 200 to realize the functions of initial deep body temperature acquisition unit 202, heartbeat information acquisition unit 204, and estimation unit 206. Meanwhile, storage unit 208 is provided in a storage area of ​​the main storage device or the auxiliary storage device.

[0061] <Construction of a Deep Body Temperature Estimation Model>

[0062] Figure 4This diagram illustrates an example of the operational flow for constructing a deep body temperature estimation model in a deep body temperature estimation model construction device. The deep body temperature estimation model construction device 100 acquires the deep body temperature and heart rate information of each model-building subject from the start to the end of a predetermined exercise stress test performed by multiple model-building subjects over a predetermined period, and constructs a deep body temperature estimation model for estimating the subject's deep body temperature. For example, the deep body temperature estimation model estimates the deep body temperature for each reference period divided at predetermined time intervals (referred to as time P) from the first moment based on the deep body temperature at any first moment and the heart rate information for the period including the first moment. More specifically, the deep body temperature estimation model, for example, estimates the change in deep body temperature from time t = nP to time t = (n + 1)P based on the deep body temperature at time t = nP (or the estimated deep body temperature) and heartbeat information from time t = (n - 1)P to time t = (n + 1)P (n is an integer greater than or equal to 0). During an exercise stress test, each model-building subject performs a predetermined load in a predetermined environment (prescribed temperature, prescribed humidity, etc.) from the start to the end of a predetermined period. The exercise stress test is performed, for example, in an artificial climate chamber maintained at 35°C and 50% humidity, in the following order: 6 minutes of rest, 18 minutes of exercise stress, 18 minutes of rest, 24 minutes of exercise stress, and 18 minutes of rest. The exercise stress is provided by an ergometer and is set to 80 kW or 60% of the previously measured maximum oxygen uptake of each model-building subject. During the exercise stress test, deep body temperature and heart rate information are continuously measured in parallel for each model-building subject using a thermometer or electrocardiograph. Exercise stress tests for multiple model-building subjects can be performed simultaneously or separately.

[0063] In S101, the deep body temperature acquisition unit 102 of the deep body temperature estimation model construction device 100 acquires the deep body temperature of the model construction subject, as measured by a thermometer or the like for measuring deep body temperature. The deep body temperature acquisition unit 102 acquires the deep body temperatures of multiple model construction subjects from the start to the end of an exercise stress test, using thermometers or the like connected to the deep body temperature estimation model construction device 100 directly or via a network. Alternatively, the deep body temperature acquisition unit 102 may acquire the deep body temperatures from the start to the end of the exercise stress test by having the model construction subject or another administrator input their deep body temperatures using an input device such as a keyboard. The deep body temperature acquisition unit 102 stores the acquired deep body temperatures in the storage unit 108.

[0064] In S102, the heartbeat information acquisition unit 104 acquires the heartbeat information of multiple model-building subjects from the start to the end of the exercise stress test, as measured by an electrocardiograph or the like that measures heartbeat information. The electrocardiograph, for example, is a device that includes electrodes for attachment to the skin of the model-building subject and a transmitter for storing and transmitting the heartbeat information measured by the electrodes. Alternatively, the electrocardiograph may be a wearable terminal that includes electrodes attached to clothing (such as a T-shirt) and a transmitter for transmitting electrocardiogram data measured by the electrodes. Alternatively, the electrocardiograph may be a wearable terminal that is worn on the wrist and performs measurements, such as a watch or wristband that acquires heartbeat information, or a clip-on wearable terminal that is worn on the fingertips or ears. The heartbeat information acquisition unit 104 acquires the heartbeat information of the model-building subjects from the start to the end of the exercise stress test, from an electrocardiograph or the like that is connected directly to the deep body temperature estimation model construction device 100 or via a network. Alternatively, the heartbeat information acquisition unit 104 may acquire heartbeat information from another information processing device, such as an electrocardiograph, via a network or the like. The heartbeat information acquisition unit 104 acquires heartbeat information from the initial time onward. The heartbeat information acquisition unit 104 stores the acquired heartbeat information of each model-building subject in the storage unit 108.

[0065] The order of the processing of S101 and S102 can also be interchanged. Furthermore, the processing of S101 and S102 can also be performed in parallel. During an exercise stress test on a subject for model construction, the deep body temperature acquisition unit 102 and the heart rate information acquisition unit 104 can also acquire deep body temperature and heart rate information, respectively, in parallel with the measurement of deep body temperature and heart rate information. The deep body temperature and heart rate information are each stored in the storage unit 108 along with time information indicating the time of measurement.

[0066] In S103, the estimation model construction unit 106 constructs a deep body temperature estimation model for estimating deep body temperature based on the acquired deep body temperature and heart rate information of the model construction subject from the initial time onwards, through regression analysis. The deep body temperature estimation model, for example, estimates the change in deep body temperature for each predetermined reference period from the initial time onwards. The deep body temperature estimation model is constructed, for example, using the heart rate information and the deep body temperature at the beginning of a reference period as explanatory variables, and the change in deep body temperature during the reference period as the target variable. The target variable may also be an estimated value of the deep body temperature. The deep body temperature estimation model may also estimate the deep body temperature for each reference period from the initial time onwards.

[0067] The estimation model construction unit 106 calculates the RR interval (RRI: R-Rinterval) based on the acquired heartbeat information. The RRI is the time difference between the generation time of the R wave in the electrocardiogram and the generation time of the previous R wave. The RRI is the length of one heartbeat (one cycle). The RRI is an example of the beat-to-beat interval. The fluctuation of the RRI is called heartbeat fluctuation. The estimation unit 106 calculates the RRI based on the acquired heartbeat information. The estimation model construction unit 106 divides the calculated RRI for each heartbeat into each reference period (for example, three minutes) from the initial time, and creates a Poincare map for each reference period. The length of one heartbeat calculated by other known methods may be used instead of the RRI. The length of the reference period is not limited to three minutes and can be longer or shorter than three minutes. From the statistical perspective of calculating an indicator reflecting heartbeat fluctuations, which will be described later, the length of the reference period is preferably one minute or longer. In addition, from the perspective of the accuracy of deep body temperature estimation and operation, the length of the reference period is preferably fifteen minutes or less.

[0068] Example of a Poincaré Map

[0069] Figure 5 is an example of the Poincaré map of RRI. Figure 5 The Poincare map shown is an example of a Poincare map created for each reference period (e.g., three minutes) while a model-building subject wears an electrocardiograph or the like that measures heartbeat information and performs a predetermined task (exercise).

[0070] exist Figure 5 In the Poincare diagram, within a reference period, the horizontal axis is set to the RRI (ms) of the nth beat, and the vertical axis is set to the RRI (ms) of the n+1th beat, indicating the relationship between the nth beat and the n+1th beat. Figure 5 In , the line whose coordinates on the horizontal axis are equal to those on the vertical axis is called the identity line. Figure 5 The center of gravity of all the marked points is shown in Figure 1. The coordinates (X, Y) of the center of gravity are obtained as (the average value of the coordinates of the points on the horizontal axis and the average value of the coordinates of the points on the vertical axis). The straight line passing through the center of gravity and parallel to the identity line is called the first center of gravity line, and the straight line passing through the center of gravity and perpendicular to the identity line is called the second center of gravity line. Here, the distance from the i-th point (the coordinates of the horizontal axis are the RRI of the i-th beat, and the coordinates of the vertical axis are the RRI of the i+1-th beat) to the identity line is set as v i , set the distance from the i-th point to the second centroid line as h i Using these, the indices SD1 and SD2 of the Poincare map based on RRI are obtained as follows.

[0071] [Formula 1]

[0072]

[0073] Here, N is the total number of points in a Poincare map. SD1 and SD2 are indices reflecting heart rate fluctuations. It should be noted that SD1 and SD2 are each 0 or a positive value. SD1 and SD2 are examples of indices obtained by analyzing the Poincare map of RRI.

[0074] The estimation model construction unit 106 calculates SD2 for each benchmark period based on RRI. Let SD2 of the x-th benchmark period (x-th benchmark period) be SD2(x). The estimation unit 106 constructs a deep body temperature estimation model for estimating the deep body temperature every time a benchmark period (for example, three minutes) has passed since the initial moment. Here, when the length of the benchmark period is set to P, the moment after the first benchmark period has passed since the initial moment (set as t=0) is t=1×P, and the moment after the j-th benchmark period has passed is t=jP. That is, the first benchmark period starts from the initial moment (t=0) and ends at the moment after the first benchmark period has passed (t=1×P). The j-th benchmark period starts from the moment after the j-1-th benchmark period has passed (t=(j-1)×P) and ends at the moment after the j-th benchmark period has passed (t=j×P). The estimation model construction unit 106 performs the following regression analysis to construct a deep body temperature estimation model: SD2(j) and SD2(j-1) obtained from the analysis of the Poincare maps of the RRI for the j-th reference period and the j-1-th reference period, and the estimated value of the deep body temperature at time t=(j-1)P after the j-1-th reference period (at the beginning of the j-th reference period) (referred to as TMP(j-1)) are used as explanatory variables, and the change in deep body temperature from time t=(j-1)P to time t=jP (the change in deep body temperature during the j-th reference period) is used as the target variable. Statistical analysis methods such as multiple regression analysis and logistic regression analysis can be used for the regression analysis. When the change in deep body temperature from time t=(j-1)P to time t=jP (the change in deep body temperature during the j-th reference period) is referred to as ΔTMP(j), it is expressed as follows.

[0075] [Formula 2]

[0076] ΔTMP(j) = f(SD2(j), SD2(j-1), TMP(j-1)). Here, f(SD2(j), SD2(j-1), TMP(j-1)) is a function of SD2(j), SD2(j-1), and TMP(j-1). Furthermore, TMP(0) is the deep body temperature at the initial time. f(SD2(j), SD2(j-1), TMP(j-1)) is expressed, for example, as follows.

[0077] [Formula 3]

[0078] f(SD2j),SD2(j-1),TMP(j-1))=A1+A2×log SD2(j)+43×SD2(j) / SD2(j-1)+A4×TMP(j-1)

[0079] Here, A1, A2, A3, and A4 are coefficients obtained through regression analysis. Log is the common logarithm. The formula obtained through regression analysis is not limited to the one shown here. Furthermore, the estimated value TMP(j) of the deep body temperature at time t = jP is obtained as follows.

[0080] [Formula 4]

[0081]

[0082] Here, TMP(0) is the deep body temperature at the initial time (t=0) obtained by measurement. The estimated value TMP(j) of the deep body temperature at time t=jP is obtained by adding the change in the deep body temperature estimated in each reference period from time t=0 to time t=jP to the deep body temperature TMP(0) at the initial time. The estimation model construction unit 106 stores the constructed deep body temperature estimation model (ΔTMP, TMP) in the storage unit 108. Thus, a deep body temperature estimation model is constructed in the deep body temperature estimation model construction device 100. In the deep body temperature estimation model, ΔTMP and TMP are expressed as functions of TMP(0) and SD2. Since SD2 is included in the deep body temperature estimation model, the deep body temperature can be calculated based on the heartbeat fluctuation.

[0083] Figure 6 1 is a diagram showing an example of the relationship between the estimated value TMP of the deep body temperature and the amount of change ΔTMP in the deep body temperature. Figure 6 The horizontal axis of the graph represents time t, and the vertical axis represents the estimated value TMP of the deep body temperature. Here, TMP(0) is the measured value of the deep body temperature at the initial time. Each ΔTMP(j) can be estimated each time a reference period passes. For example, the change in deep body temperature in the second reference period ΔTMP(2) is the change in deep body temperature from the time when the first reference period passes (t=P) to the time when the second reference period passes (t=2P). In addition, for example, the estimated value TMP(2) of the deep body temperature when the second reference period passes can be expressed as TMP(1)+ΔTMP(2)=TMP(0)+ΔTMP(1)+ΔTMP(2). When the nth reference period passes (t=nP) is the same as when the n+1th reference period starts (t=(n+1)P-P=nP).

[0084] The estimation model construction unit 106 can also use other physiological indicators as explanatory variables when constructing the deep body temperature estimation model. Examples of other physiological indicators include gender, age, skin temperature, blood pressure, exhaled breath, pulse wave, blood oxygen concentration, blood flow, physical activity, and respiratory rate. Furthermore, temperature inside clothing, wet-bulb globe temperature (WBGT), and meteorological data can also be added as explanatory variables. By constructing the deep body temperature estimation model incorporating these explanatory variables, a more accurate estimation can be achieved.

[0085] <Estimation of Deep Body Temperature>

[0086] Figure 7 This is a diagram showing an example of the operation flow of deep body temperature estimation in a deep body temperature estimation device. Here, the deep body temperature estimation device 200 obtains the deep body temperature of the estimated subject at the initial moment (first moment) and the heartbeat information during the period including the first moment, and uses Figure 4 The deep body temperature estimation model constructed in the deep body temperature estimation model construction device 100 according to the action flow of the estimation model is used to estimate the deep body temperature of the estimated object subject. For the estimated object subject, the heartbeat information is measured by an electrocardiograph or the like. In addition, for the estimated object subject, the deep body temperature is measured at the initial moment (first moment) by a thermometer or the like. For the estimated object subject, the deep body temperature is estimated based on the deep body temperature at the initial moment and the heartbeat information during the period including the initial moment. For the estimated object subject, the deep body temperature is not measured after the initial moment. For example, it is assumed that the estimated object subject is performing some work.

[0087] In S201, the initial deep body temperature acquisition unit 202 of the deep body temperature estimation device 200 acquires the deep body temperature of the subject being estimated at the initial moment, as measured by a thermometer or the like for measuring deep body temperature. The initial moment is the start time of the period during which the deep body temperature is estimated. The initial deep body temperature acquisition unit 202 acquires the deep body temperature of the subject being estimated at the initial moment using a thermometer or the like connected to the deep body temperature estimation device 200 directly or via a network or the like. Alternatively, the initial deep body temperature acquisition unit 202 may acquire the deep body temperature of the subject being estimated by having the subject being estimated or another administrator input the deep body temperature using an input unit such as a keyboard. The initial deep body temperature acquisition unit 202 stores the acquired deep body temperature in the storage unit 208. The initial deep body temperature acquisition unit 202 acquires the deep body temperature of the subject being estimated at the initial moment and does not acquire deep body temperatures after the initial moment. In addition, when it is difficult to directly measure the deep body temperature of the estimated subject at the initial moment, the deep body temperature estimated based on the tympanic membrane temperature and skin surface temperature of the estimated subject at the initial moment can also be set as the deep body temperature at the initial moment.

[0088] In S202, the heartbeat information acquiring unit 204 acquires the heartbeat information of the estimated subject measured by an electrocardiograph or the like that measures the heartbeat information. Figure 4 The same electrocardiograph used in S102 of . The heartbeat information acquisition unit 204 acquires the heartbeat information of the estimated subject from the electrocardiograph connected to the deep body temperature estimation device 200 directly or via a network. In addition, the heartbeat information acquisition unit 204 can also acquire the heartbeat information via a network from other information processing devices that acquire the heartbeat information from the electrocardiograph. The heartbeat information acquisition unit 204 acquires the heartbeat information of the period including the initial moment. The heartbeat information acquisition unit 204 acquires the heartbeat information from the moment before a reference period relative to the initial moment to any moment after the initial moment, for example. The length of the reference period is, for example, three minutes. The length of the reference period here is the same as the length of the reference period when constructing the deep body temperature estimation model. The heartbeat information acquisition unit 204 stores the acquired heartbeat information of the estimated subject in the storage unit 208.

[0089] The deep body temperature and heartbeat information are stored in the storage unit 208 together with time information indicating the time of measurement.

[0090] In S203, the estimation unit 206 uses the acquired deep body temperature of the estimation target subject at the initial time and the heartbeat information after the initial time to estimate the target subject. Figure 4 The deep body temperature is estimated using a deep body temperature estimation model constructed based on the operation flow. The estimation unit 206 estimates the deep body temperature by adding the deep body temperature at the initial time (first time) to the change in deep body temperature during each reference period using the change in deep body temperature estimated by the deep body temperature estimation model.

[0091] The estimation unit 206 extracts the deep body temperature estimation model stored in the storage unit 208. Furthermore, the estimation unit 206 calculates the RRI for each heartbeat based on the acquired heartbeat information. The estimation unit 206 divides the calculated RRI for each heartbeat into each reference period (e.g., three minutes) starting from the time one reference period prior to the initial time, and creates a Poincare map for each reference period. Based on the Poincare map of the RRI, the estimation unit 206 calculates the index SD2 for each reference period. Based on the deep body temperature of the estimated subject at the initial time (any time) and the index SD2 for each reference period, the estimation unit 206 uses the deep body temperature estimation model to estimate the change in deep body temperature (ΔTMP) for each reference period. Furthermore, the estimation unit 206 estimates the deep body temperature (TMP) for each reference period (the end time of each reference period) of the estimated subject by adding the change in deep body temperature for each reference period to the deep body temperature at the initial time. The estimated deep body temperature and the like are stored in the storage unit 208 .

[0092] Furthermore, if the estimated deep body temperature is above a predetermined threshold, the estimating unit 206 may issue a warning regarding the risk of heat stroke, etc. The estimating unit 206 may also output the warning regarding the risk of heat stroke, etc. using an output unit such as a display or speaker. This allows the subject being estimated to understand the risk of heat stroke, etc. The estimating unit 206 may also output only the estimated deep body temperature using the output unit. This allows the subject being estimated to understand the estimated deep body temperature based on heartbeat information.

[0093] The estimating unit 206 may also calculate SD2 based on the RRI for each reference period to estimate the deep body temperature. Furthermore, the estimating unit 206 may output the estimated deep body temperature using an output unit for each reference period. This allows the subject being estimated, etc., to grasp their deep body temperature in real time via the output unit of the deep body temperature estimating device 200.

[0094] The deep body temperature estimation device 200 can also be pre- Figure 4 The deep body temperature estimation model construction device 100 is integrated with the operation flow of the deep body temperature estimation model. Furthermore, the deep body temperature estimation device 200 may also include an electrocardiograph that measures the heartbeat information of the subject being estimated. In this case, the heartbeat information acquisition unit 204 of the deep body temperature estimation device 200 acquires the heartbeat information using the electrocardiograph.

[0095] In the deep body temperature estimation device 200, SD2(0) is required when calculating ΔTMP(1), but SD2(0) is calculated from the heartbeat information from the time before the initial time P (t=-P) to the initial time (time t=0). Here, for example, the deep body temperature TMP(1) at time t=P can be measured by a thermometer or the like (or the deep body temperature TMP(1) at time t=P can be estimated based on the eardrum temperature or skin surface temperature at time t=P), and the deep body temperature TMP(1) at time t=P can be obtained, and ΔTMP(j) and TMP(j) after time t=2×P(j=2) can be calculated. In addition, the deep body temperature TMP(1) at time t=P can be regarded as the same as the deep body temperature TMP(0) at time t=0, and TMP(1)=TMP(0). That is, the heartbeat information from time t=-P to time t=0 is not required.

[0096] (other)

[0097] Figures 8 to 12 The following are graphs showing examples of changes in deep body temperature actually measured during the exercise stress test for subjects A to E and deep body temperature estimated based on heart rate information obtained by the above method. Figures 8 to 12 In each graph, the horizontal axis represents the time from the start of the exercise stress test, and the vertical axis represents the deep body temperature. Figures 8 to 12 In each graph, the dotted line represents the measured deep body temperature, and the solid line represents the estimated deep body temperature. During the exercise stress test, each subject performs a prescribed load operation under a prescribed environment (prescribed air temperature, prescribed humidity, etc.) from the start time to the end time of the prescribed period. Here, the exercise stress test is performed in an artificial climate chamber adjusted to an air temperature of 35°C and a humidity of 50% during exercise stress and rest in the order of 6 minutes of rest (R1), 18 minutes of exercise stress (E1), 18 minutes of rest (R2), 24 minutes of exercise stress (E2), and 18 minutes of rest (R3). The exercise load is provided by a dynamometer and is set to 80kW or 60% of the maximum oxygen uptake of each subject measured in advance. For each subject, in this exercise stress test, deep body temperature and heartbeat information are measured continuously and in parallel by a thermometer, an electrocardiograph, etc. When estimating the deep body temperature, the measured deep body temperature of the subject at the start of the exercise stress test is used. Figures 8 to 12 In each graph, it can be confirmed that the estimated deep body temperature of each subject roughly matches the measured deep body temperature of each subject. By estimating the deep body temperature using the above method, the deep body temperature of the subject can be estimated.

[0098] (Functions and Effects of Implementation Methods)

[0099] The deep body temperature estimation model construction device 100 obtains the deep body temperature (for example, rectal temperature, etc.) and heart rate information (for example, electrocardiogram data, etc.) of multiple subjects for model construction after the initial time. The deep body temperature estimation model construction device 100 calculates RRI (or other beat intervals) based on the heart rate information and creates a Poincare map of RRI for each reference period. The deep body temperature estimation model construction device 100 calculates SD2 for each reference period based on RRI. The deep body temperature estimation model construction device 100 performs the following regression analysis to construct a deep body temperature estimation model: SD2(j) and SD2(j-1) obtained from the analysis of the Poincare map of RRI and the estimated value TMP(j-1) of the deep body temperature are set as explanatory variables, and the estimated change in deep body temperature ΔTMP(j) is set as the target variable. The estimated deep body temperature value TMP(j) at time t=jP is expressed as TMP(j-1)+ΔTMP(j). Furthermore, TMP(0) is the deep body temperature at the initial time. The deep body temperature estimation model construction device 100 can construct a deep body temperature estimation model that estimates the deep body temperature based on the deep body temperature and heartbeat information of the model construction subject from the initial time onward.

[0100] The deep body temperature estimation device 200 obtains the deep body temperature of the target subject at the initial time. The deep body temperature estimation device 200 obtains the target subject's heart rate information for the period including the initial time. Using a deep body temperature estimation model, the deep body temperature estimation device 200 estimates the target subject's deep body temperature based on the initial deep body temperature and the heart rate information for the period including the initial time. The deep body temperature estimation device 200, using the deep body temperature estimation model, can easily estimate the target subject's deep body temperature using physiological indicators such as heart rate information, even though it is difficult to measure during normal work, for example.

[0101] The deep body temperature estimation model construction device 100 constructs a deep body temperature estimation model using the deep body temperature and heart rate information measured during the aforementioned exercise stress test for the model construction subject. The deep body temperature estimation device 200 calculates an estimated deep body temperature based on the constructed deep body temperature estimation model using the deep body temperature at the initial moment and the measured heart rate information. The average error between the measured deep body temperature and the estimated deep body temperature obtained by the deep body temperature estimation model is -0.007°C (maximum -0.50°C), and the average error rate is -0.02% (maximum -1.30%). This deep body temperature estimation model enables high-precision estimation of deep body temperature using the deep body temperature and heart rate information at the initial moment.

[0102] <Computer-readable recording medium>

[0103] A program that causes a computer or other machine or device (hereinafter referred to as a computer, etc.) to implement any of the above functions can be recorded on a computer readable recording medium. Then, by having the computer, etc. read and execute the program on the recording medium, the function can be provided.

[0104] Here, a computer-readable recording medium refers to a recording medium that stores information such as data and programs through electrical, magnetic, optical, mechanical, or chemical action and can be read from a computer. Computer components such as a CPU and memory may be provided in such a recording medium so that the CPU executes the program.

[0105] In addition, among such recording media, recording media that can be removed from a computer, etc. include floppy disks, magneto-optical disks, compact disk read-only memory (CD-ROM), compact disk rewritable (CD-R / W), DVDs, digital audio tapes (DAT), 8mm magnetic tapes, memory cards, etc.

[0106] In addition, as recording media fixed to a computer or the like, there are hard disks, ROMs, solid state drives (SSDs), and the like.

[0107] The embodiments of the present invention have been described above, but these are merely examples, and the present invention is not limited thereto. Various changes based on the knowledge of those skilled in the art, such as combinations of components, are possible without departing from the gist of the claims.

[0108] Description of reference numerals:

[0109] 100: Deep body temperature estimation model construction device;

[0110] 102: deep body temperature acquisition unit;

[0111] 104: heartbeat information acquisition unit;

[0112] 106: Estimation model building department;

[0113] 108: Storage Department;

[0114] 200: Deep body temperature estimation device;

[0115] 202: Initial deep body temperature acquisition unit;

[0116] 204: heartbeat information acquisition unit;

[0117] 206: Presumption Department;

[0118] 208: Storage department.

Claims

1. A deep body temperature estimation device comprising: a deep body temperature acquisition unit that acquires a deep body temperature at a first moment of an estimation target subject, the subject of whom the deep body temperature is to be estimated; a pulse acquisition unit configured to acquire the pulse of the estimation target subject during a period including a first time; as well as an estimating unit that estimates the deep body temperature of the estimation target subject based on the deep body temperature at the first moment acquired by the deep body temperature acquiring unit and the pulsation during the period including the first moment acquired by the pulsation acquiring unit, using a deep body temperature estimating model that estimates the deep body temperature at the predetermined moment based on the deep body temperature at the initial moment and the pulsation from the initial moment to the predetermined moment; The deep body temperature estimation model is a model that estimates the change in deep body temperature according to each benchmark period divided into specified time intervals. It is a model constructed by regression analysis, wherein the regression analysis uses indicators obtained by analyzing the intervals between the pulses of multiple model-building subjects, i.e., the Poincare map of the pulse intervals, and the estimated deep body temperature of the model-building subject at the beginning of the n-th benchmark period as explanatory variables, and uses the change in the deep body temperature of the model-building subject during the n-th benchmark period as a target variable.

2. The deep body temperature estimation device according to claim 1, The index is an index reflecting heartbeat fluctuations.

3. The deep body temperature estimating device according to claim 1 or 2, The estimating unit estimates the deep body temperature of the estimation target subject after the first time by adding the change in deep body temperature estimated for each reference period after the first time to the deep body temperature at the first time.

4. The deep body temperature estimating device according to claim 1 or 2, comprising: a pulsometer including electrodes for measuring the pulsation of the estimated subject; The pulse acquisition unit acquires the pulse of the estimation target subject measured by the pulse meter.

5. A method for estimating deep body temperature, wherein: Computer execution: acquiring a deep body temperature at a first moment of a subject to be measured, the subject of estimation for which deep body temperature is to be estimated; acquiring the pulse of the estimated subject during a period including a first moment; as well as using a deep body temperature estimation model that estimates the deep body temperature at the predetermined time based on the deep body temperature at an initial time and the pulsation from the initial time to the predetermined time, estimating the deep body temperature of the estimation target subject based on the deep body temperature at the first time and the pulsation during the period including the first time, The deep body temperature estimation model is a model that estimates the change in deep body temperature according to each benchmark period divided into specified time intervals. It is a model constructed by regression analysis, wherein the regression analysis uses indicators obtained by analyzing the intervals between the pulses of multiple model-building subjects, i.e., the Poincare map of the pulse intervals, and the estimated deep body temperature of the model-building subject at the beginning of the n-th benchmark period as explanatory variables, and uses the change in the deep body temperature of the model-building subject during the n-th benchmark period as a target variable.

6. A storage medium non-temporarily storing a deep body temperature estimation program, the deep body temperature estimation program being configured to cause a computer to execute: acquiring a deep body temperature at a first moment of a subject to be measured, the subject of estimation for which deep body temperature is to be estimated; acquiring the pulse of the estimated subject during a period including a first moment; as well as using a deep body temperature estimation model that estimates the deep body temperature at the predetermined time based on the deep body temperature at an initial time and the pulsation from the initial time to the predetermined time, estimating the deep body temperature of the estimation target subject based on the deep body temperature at the first time and the pulsation during the period including the first time, The deep body temperature estimation model is a model that estimates the change in deep body temperature according to each benchmark period divided into specified time intervals. It is a model constructed by regression analysis, wherein the regression analysis uses indicators obtained by analyzing the intervals between the pulses of multiple model-building subjects, i.e., the Poincare map of the pulse intervals, and the estimated deep body temperature of the model-building subject at the beginning of the n-th benchmark period as explanatory variables, and uses the change in the deep body temperature of the model-building subject during the n-th benchmark period as a target variable.

Images