Information processing device, information processing method, and program
The information processing device uses non-invasive pulse wave synchronized electromagnetic wave data to estimate blood sugar levels accurately, addressing the pain and hygiene issues of invasive methods.
Patent Information
- Application Number
- JP2023084302
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-23
- Publication Date
- 2024-12-05
AI Technical Summary
Invasive blood sugar measurement methods are painful and unhygienic, placing a significant physical burden on diabetic patients who need to measure their blood sugar levels frequently.
An information processing device that uses non-invasive pulse wave synchronized electromagnetic wave data to estimate blood components, specifically blood sugar levels, by inputting feature amounts based on the amplitude and phase of the wave data into an estimator.
Enables accurate non-invasive measurement of blood sugar levels with reduced physical burden on the patient.
Smart Images

Figure 2024167960000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]
[0002] As a method for measuring blood glucose levels, an invasive measuring method such as that disclosed in the following document has been conventionally used. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2022-185130 A Summary of the Invention [Problem to be solved by the invention]
[0004] Invasive measurement methods are painful and unhygienic, and therefore impose a significant physical burden on diabetic patients who need to measure their blood glucose levels multiple times a day.
[0005] In view of the above circumstances, the present invention provides an information processing device capable of measuring blood components using a non-invasive method that places less physical strain on the subject. [Means for solving the problem]
[0006] According to one aspect of the present invention, there is provided an information processing device. The information processing device includes a processor. The processor is configured to execute a receiving step and a processing step. In the receiving step, input of pulse wave synchronized electromagnetic wave data of a subject is received. In the processing step, a feature based on at least one of the amplitude and phase of the pulse wave synchronized electromagnetic wave data is input to an estimator, thereby estimating blood components of the subject.
[0007] According to this embodiment, blood components can be estimated with high accuracy from pulse wave synchronized electromagnetic wave data that can be measured non-invasively. In other words, blood components can be measured using a non-invasive method that imposes little physical strain on the subject. [Brief description of the drawings]
[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. [Diagram 2] 2 is a block diagram showing a hardware configuration of an information processing device 2. FIG. [Diagram 3] FIG. 2 is a block diagram showing a hardware configuration of a user terminal 3. [Figure 4] 2 is a block diagram showing functions realized by an information processing device 2 (processor 23). FIG. [Diagram 5] 2 is an activity diagram showing the flow of information processing executed by the information processing system 1. FIG. [Figure 6] FIG. 13 is a schematic diagram of a method for measuring pulse wave-synchronized electromagnetic wave data. [Figure 7] 11 is a graph showing an example of pulse wave synchronized electromagnetic wave data and a period of the probe electromagnetic wave frequency in time series. [Figure 8] 10 is a schematic diagram showing an example of measurement points and feature amounts in pulse-wave-synchronized electromagnetic wave data; FIG. [Figure 9] 11 is a graph showing an example of correction of periodic fluctuations in pulse wave-synchronized electromagnetic wave data. [Figure 10] 1 is an example of a complex neural network included in an estimator. [Figure 11] 13 is an example of a decision chart included in an estimator. [Figure 12] 1 is an example of a method for measuring pulse wave-synchronized electromagnetic wave data and blood glucose levels to obtain teacher data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic features shown in the following embodiments can be combined with each other.
[0010] Incidentally, the program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).
[0011] In addition, in this embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, in this embodiment, various information is handled, and this information is represented, for example, by physical values of signal values representing voltage and current, high and low signal values as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.
[0012] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, a memory, etc. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.
[0013] 1. Hardware Configuration This section describes the hardware configuration.
[0014] <Information Processing System 1> FIG. 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes an information processing device 2 and a user terminal 3. The information processing device 2 and the user terminal 3 are configured to be able to communicate with each other via a telecommunications line. In one embodiment, the information processing system 1 is made up of one or more devices or components. For example, if the information processing system 1 is made up of only the information processing device 2, the information processing system 1 can be the information processing device 2. These components will be described below.
[0015] <Information processing device 2> 2 is a block diagram showing a hardware configuration of the information processing device 2. The information processing device 2 includes a communication bus 20, a communication unit 21, a storage unit 22, and a processor 23. The communication unit 21, the storage unit 22, and the processor 23 are electrically connected via the communication bus 20 inside the information processing device 2.
[0016] <Communications Division 21> The communication unit 21 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the information processing device 2 may communicate various information from the outside via the communication unit 21 and the network.
[0017] <Storage section 22> The storage unit 22 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the information processing device 2 executed by the processor 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the processor 23.
[0018] <Processor 23> The processor 23 processes and controls the overall operations related to the information processing device 2. The processor 23 is, for example, a central processing unit (CPU). The processor 23 realizes various functions related to the information processing device 2 by reading out a predetermined program stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 can be specifically realized by the processor 23, which is an example of hardware, and executed as each functional unit included in the processor 23. These will be described in more detail in the next section. The processor 23 is not limited to being single, and may be implemented with multiple processors 23 for each function. Also, a combination of these may be used.
[0019] <User terminal 3> 3 is a block diagram showing a hardware configuration of the user terminal 3. The user terminal 3 includes a communication bus 30, a communication unit 31, a storage unit 32, a processor 33, a display unit 34, and an input unit 35. The communication unit 31, the storage unit 32, the processor 33, the display unit 34, and the input unit 35 are electrically connected via the communication bus 30 inside the user terminal 3. Descriptions of the communication unit 31, the storage unit 32, and the processor 33 are omitted because they are similar to the descriptions of the respective units in the information processing device 2.
[0020] <Display section 34> The display unit 34 displays a screen of a graphical user interface (GUI) that can be operated by the user. The display unit 34 may be included in the housing of the user terminal 3, or may be attached externally. Specifically, the display unit 34 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by selectively using them according to the type of the user terminal 3.
[0021] <Input section 35> The input unit 35 accepts an operation input made by a user. The operation input is transferred as a command signal to the processor 33 via the communication bus 30. The processor 33 may execute a predetermined control or calculation based on the transferred command signal as necessary. The input unit 35 may be included in the housing of the user terminal 3, or may be externally attached. For example, the input unit 35 may be implemented as a touch panel integrated with the display unit 34. When the input unit 35 is implemented as a touch panel, the user can input a tap operation, a swipe operation, or the like to the input unit 35. As the input unit 35, a switch button, a mouse, a QWERTY keyboard, or the like can be adopted instead of a touch panel.
[0022] The information processing device 2 may be an on-premise type or a cloud type. As the information processing device 2 in the cloud type, the above-mentioned functions and processes may be provided in the form of, for example, SaaS (Software as a Service) or cloud computing.
[0023] 2. Functional configuration In this section, the functional configuration of the present embodiment will be described. Information processing by software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23.
[0024] 4 is a block diagram showing functions realized by the information processing device 2 (processor 23). Specifically, the information processing device 2 (processor 23) includes a receiving unit 231, a processing unit 232, and an output unit 233.
[0025] The receiving unit 231 is configured to acquire various information. For example, the receiving unit 231 accepts input of pulse wave synchronized electromagnetic wave data of the subject. Specifically, the receiving unit 231 acquires the pulse wave synchronized electromagnetic wave data from the user terminal 3.
[0026] The processing unit 232 is configured to process various information. For example, the processing unit 232 estimates blood components (specifically, blood glucose level) of the subject by inputting a feature based on the amplitude and phase of the pulse wave synchronized electromagnetic wave data to an estimator. The estimator is stored in the storage unit 22, for example.
[0027] The output unit 233 is configured to output various information. For example, the output unit 233 outputs the estimated blood glucose level to the user terminal 3.
[0028] 3. Information processing method This section describes an information processing method of the information processing device 2. This information processing method is executed by a computer, with each unit of the information processing device 2 acting as each step.
[0029] Specifically, this information processing method includes a receiving step, a processing step, and an output step. In the receiving step, input of pulse wave synchronized electromagnetic wave data of the subject is received. In the processing step, features based on the amplitude and phase of the pulse wave synchronized electromagnetic wave data are input to an estimator to estimate blood components (specifically, blood glucose level) of the subject. In the output step, the estimated blood glucose level is output to a user terminal 3.
[0030] 5 is an activity diagram showing the flow of information processing executed by the information processing system 1. Below, the information processing will be described along with each activity in this activity diagram.
[0031] <Measurement of pulse wave synchronized electromagnetic wave data> The measurement device 10 is a device that measures pulse wave-synchronized electromagnetic wave data. For example, a VNA (vector network analyzer) capable of measuring the amplitude and phase of electromagnetic waves (particularly millimeter waves: MMW) synchronized with a pulse wave is used as the measurement device 10. This measurement device 10 is non-invasive. The measurement device 10 measures the pulse wave-synchronized electromagnetic wave data of the subject (activity A110).
[0032] Fig. 6 is a schematic diagram of a method for measuring pulse-wave-synchronized electromagnetic wave data. As shown in Fig. 6A, pulse-wave-synchronized electromagnetic wave data is obtained by detecting reflected electromagnetic waves S11 reflected on the surface of the human body. Moreover, as shown in Fig. 6B, pulse-wave-synchronized electromagnetic wave data can also be obtained by detecting transmitted electromagnetic waves S21 that have passed through the human body. The transmitted electromagnetic waves S21 are obtained as an integral value of the entire part of the human body through which the phase of the pulse-wave-synchronized electromagnetic wave data has passed. Note that the part to which the electromagnetic waves are irradiated (i.e., the part where the pulse-wave-synchronized electromagnetic wave data is measured) can be any part, but when measuring the transmitted electromagnetic waves S21, it is preferable to measure them at parts with a small thickness, such as the earlobe or the web of the palm.
[0033] Fig. 7 is a graph showing an example of pulse wave synchronized electromagnetic wave data and the period of the probe electromagnetic wave frequency in a time series. The waveform in the upper part of Fig. 7 shows the amplitude (dB) of the electromagnetic wave synchronized with the pulse wave. The waveform in the middle part of Fig. 7 shows the phase (rad) of the electromagnetic wave synchronized with the pulse wave. The lower part of Fig. 7 shows the procedure for switching the probe electromagnetic wave frequency.
[0034] The pulse wave synchronized electromagnetic wave data used in this embodiment is measured using a plurality of probe electromagnetic wave frequencies. Specifically, the pulse wave synchronized electromagnetic wave data is measured while periodically switching between three types of probe electromagnetic wave frequencies, 60 GHz, 70 GHz, and 80 GHz. Frequencies of 60-80 GHz have good sensitivity to electromagnetic waves synchronized with the pulse wave and easily penetrate the skin.
[0035] Specifically, measurements at 60 GHz, 70 GHz, and 80 GHz are repeated in this order at regular intervals as shown in Fig. 7. The length of one cycle in which measurements (sampling) at each of the three probe electromagnetic wave frequencies are performed once is preferably short, and is typically 0.000001 to 1 second, for example, about 0.130 seconds.
[0036] Furthermore, the number of measurement points (ie, the number of samplings) in one wave of pulse-wave-synchronized electromagnetic wave data is preferably large.
[0037] In the "phase" waveform in Fig. 7, the white dots are measurement points at 60 GHz, the black dots are measurement points at 70 GHz, and the hatched dots are measurement points at 80 GHz. Note that in the "amplitude" waveform in Fig. 7, the measurement points for each probe electromagnetic wave frequency are omitted. The amplitude and phase waveforms shown in Fig. 7 are each composed of a collection of measurement values at multiple probe electromagnetic wave frequencies.
[0038] In this way, by constructing pulse-wave-synchronized electromagnetic wave data using multiple probe electromagnetic wave frequencies, it is possible to extract the effects of various components contained in blood. This improves the estimation accuracy of the estimator described below. In addition, by periodically switching between multiple probe electromagnetic wave frequencies, it is possible to average out the variation in measurement values due to measurement timing and drift.
[0039] The measuring device 10 transmits the pulse wave-synchronized electromagnetic wave data acquired in the above-mentioned procedure to the user terminal 3 (activity A120).
[0040] Next, the user terminal 3 receives the pulse wave synchronized electromagnetic wave data from the measurement device 10 (activity A130). In activity A130, for example, the following two-stage information processing is executed. (1) The processor 33 receives the pulse wave synchronized electromagnetic wave data from the measurement device 10 via the communication unit 31. (2) The processor 33 stores the received pulse wave synchronized electromagnetic wave data in the memory unit 32.
[0041] After receiving the pulse wave synchronized electromagnetic wave data, the processor 33 of the user terminal 3 transmits the pulse wave synchronized electromagnetic wave data to the information processing device 2 (activity A140). In activity A140, for example, the following two-stage information processing is executed. (1) The processor 33 reads out the pulse wave synchronized electromagnetic wave data stored in the memory unit 32. (2) The processor 33 transmits the pulse wave synchronized electromagnetic wave data to the information processing device 2 via the communication unit 31.
[0042] Next, the information processing device 2 receives the pulse wave synchronized electromagnetic wave data from the user terminal 3 (activity A150). That is, the receiving unit 231 receives input of the pulse wave synchronized electromagnetic wave data of the subject. In activity A150, for example, the following two-stage information processing is executed. (1) The processor 23 receives the pulse wave synchronized electromagnetic wave data from the user terminal 3 via the communication unit 21. (2) The processor 23 stores the received pulse wave synchronized electromagnetic wave data in the memory unit 22.
[0043] <Feature extraction> After receiving the pulse wave synchronized electromagnetic wave data, the information processing device 2 extracts a feature based on the amplitude and phase of the pulse wave synchronized electromagnetic wave data (activity A160). The "feature" is an input value to an estimator that estimates the blood glucose level. In this embodiment, since the pulse wave synchronized electromagnetic wave data is measured at multiple probe electromagnetic wave frequencies, the feature is extracted from the measurement values at the multiple probe electromagnetic wave frequencies.
[0044] In this embodiment, the feature amount is a set of numerical values calculated from a plurality of measurement values of the pulse-synchronized electromagnetic wave data by a predetermined procedure, and includes an average value of each of a plurality of measurement points arranged according to the magnitude of the phase of each wave of the pulse-synchronized electromagnetic wave data.
[0045] FIG. 8 is a schematic diagram showing an example of measurement points and feature amounts in pulse-wave-synchronized electromagnetic wave data. As shown in FIG. 8A, the pulse-wave-synchronized electromagnetic wave data includes a plurality of waves W1 and W2. First, the processing unit 232 arranges a plurality of measurement points measured at a first probe electromagnetic wave frequency of 60 GHz in each wave in the order of the magnitude of the phase, that is, the first evaluation point P11, the second evaluation point P12, the third evaluation point P13, the fourth evaluation point P14, and the fifth evaluation point P15. That is, the processing unit 232 labels a plurality of measurement points in the order of the magnitude of the phase. Each evaluation point is expressed by a complex number including the amplitude and phase in the pulse-wave-synchronized electromagnetic wave data. The first evaluation point P11 is a peak point where the phase is maximum. The number of evaluation points may be two or more, and is not limited to five.
[0046] Next, the processing unit 232 calculates a complex difference for each of the first evaluation point P11 to the fifth evaluation point P15 for each wave. The complex difference is calculated by subtracting the numerical value of the measurement point with the smallest phase for each wave from the numerical value of each evaluation point.
[0047] After calculating the complex differences, the processing unit 232 calculates the average value of the complex differences of the first evaluation point P11 to the fifth evaluation point P15 in the multiple waves W1 and W2. The number of evaluation points (number of waves) for which the average value is calculated is set to the number of waves included in a measurement period of, for example, 5 seconds.
[0048] The processing unit 232 also calculates this average value for each of the multiple measurement points measured at the second probe electromagnetic wave frequency of 70 GHz and the third probe electromagnetic wave frequency of 80 GHz. As a result, the average values of the first evaluation point P11 to the fifth evaluation point P15 are calculated at each of the first probe electromagnetic wave frequency, the second probe electromagnetic wave frequency, and the third probe electromagnetic wave frequency. In other words, the average values of 15 (3 types of probe electromagnetic wave frequencies x 5 evaluation points = 15) are calculated.
[0049] Since the first evaluation point P11 is the peak point of the phase of each wave as described above, the feature value includes the average value of the peak points at which the phase of each wave of the pulse-wave-synchronized electromagnetic wave data is maximum. This eliminates the influence of noise due to the movement of the measurement site (e.g., finger), pressure change, position fluctuation, and change in skin condition (e.g., sweating) of the pulse-wave-synchronized electromagnetic wave data. In addition, the feature value is composed of measurement values at multiple probe electromagnetic wave frequencies. This makes it possible to extract the influence (feature value) of each of the various components contained in blood.
[0050] After calculating the average value, the processing unit 232 further normalizes this average value. This normalization sets the amplitude of the average value (average amplitude) of each evaluation point in the range from 0 to 1, and the phase of the average value (average phase) of each evaluation point in the range from 0 to π. For example, for the first evaluation point P11, if the minimum absolute value of the amplitude of the average value of the first evaluation point P11 at each probe electromagnetic wave frequency is Amin, the maximum absolute value is Amax, and the minimum phase value is Pmin and the maximum phase value is Pmax, the normalization of the average amplitude is realized by the following formula (1), and the normalization of the average phase is realized by the following formula (2). The same applies to the second evaluation point P12 and onwards.
number
number
[0051] The above normalization results in a feature quantity FV, as shown in FIG. 8B. The feature quantity FV includes a plurality of evaluation values V11-V35, which are complex numbers. V11, V12, V13, V14, and V15 are evaluation values obtained by normalizing the average values of the first evaluation point P11 to the fifth evaluation point P15 at the first probe electromagnetic wave frequency. V21, V22, V23, V24, and V25 are evaluation values obtained by normalizing the average values of the first evaluation point P11 to the fifth evaluation point P15 at the second probe electromagnetic wave frequency. V31, V32, V33, V34, and V35 are evaluation values obtained by normalizing the average values of the first evaluation point P11 to the fifth evaluation point P15 at the third probe electromagnetic wave frequency.
[0052] In this way, by including the average value at multiple measurement points in the feature, the change in blood flow rate can be input to the estimator, thereby improving the accuracy of blood glucose level estimation.
[0053] <Modification of feature extraction> The feature amount may include an average value of the measured values at regular intervals for each wave. Fig. 9 is a graph showing an example of correction of periodic fluctuation of pulse-wave-synchronized electromagnetic wave data. In this modification, first, as shown in Fig. 9B, raw pulse-wave-synchronized electromagnetic wave data including a plurality of waves shown in Fig. 9A is corrected to align the periods of each wave.
[0054] Specifically, the processing unit 232 corrects the periodic fluctuation of each wave of the pulse-wave-synchronized electromagnetic wave data using the pulse measured simultaneously with the pulse-wave-synchronized electromagnetic wave data. The pulse is measured by an optical measuring device such as a pulse oximeter. The processing unit 232 normalizes the period of each wave of the pulse data to the same length using the period of the pulse measured at the same timing as each wave.
[0055] After correcting the periodic variation, the processing unit 232 calculates the complex difference for each of the multiple measurement values PT1, PT2, PT3, PT4, and PT5 at a fixed timing for each wave (for example, a 1 / 5 period point, a 2 / 5 period point, etc.) in the above-mentioned procedure. Furthermore, the processing unit 232 calculates the average value of the complex differences for each of the measurement values PT1, PT2, PT3, PT4, and PT5 for the multiple waves. Note that the number of measurement values for which the average value is calculated may be 2 or more and is not limited to 5.
[0056] After calculating the average values, the processing unit 232 further normalizes the average values. This normalization sets the amplitude of the average value of each measurement value (average amplitude) in the range from 0 to 1, and sets the phase of the average value of each measurement value (average phase) in the range from 0 to π. The normalization is performed using the minimum and maximum values of the absolute value of the amplitude and the phase in the average value of each of the measurement values PT1, PT2, PT3, PT4, and PT5.
[0057] By correcting for periodic fluctuations in this way and using the average value of the measurement values at uniform timing for each wave as the feature, the effects of noise that occurs locally in time can be eliminated.
[0058] <Input to the estimator> After extracting the feature amount, the information processing device 2 inputs the feature amount to the estimator (activity A170). The estimator includes a complex neural network (CVNN) and a decision chart. The estimator is stored in the storage unit 22. FIG. 10 is an example of the complex neural network included in the estimator. FIG. 11 is an example of the decision chart included in the estimator.
[0059] The complex neural network in Fig. 10 receives as input feature quantities (group of numerical values) extracted from pulse wave synchronized electromagnetic wave data, and outputs estimation complex numbers to be input to the decision chart in Fig. 11. When the number of data (complex numbers) included in the feature quantities is 15 as in Fig. 8B, this complex neural network outputs 1 estimation complex number for the input of 15 complex numbers. This complex neural network also has one hidden layer (middle layer). The number of hidden layers may be two or more.
[0060] The phase of the estimation complex number output from the complex neural network of FIG. 10 is input to the decision chart of FIG. 11. This decision chart describes the relationship between the phase of the estimation complex number and the blood glucose level. For example, when the phase of the estimation complex number is 0, the estimator outputs "50 mg / dL" as the estimated blood glucose level, and when the phase is π, the estimator outputs "200 mg / dL" as the estimated blood glucose level. These output values can be set according to the desired blood glucose level range (typically 10 mg / dL to 600 mg / dL).
[0061] The information processing device 2 stores the blood glucose level output by the estimator in the memory unit 22 (activity A180). Furthermore, the information processing device 2 transmits the blood glucose level to the user terminal 3 (activity A190). In activity A190, for example, the following two-stage information processing is executed. (1) The processor 23 reads out the blood glucose level stored in the memory unit 22. (2) The processor 23 transmits the blood glucose level to the user terminal 3 via the communication unit 21.
[0062] Next, the user terminal 3 receives the blood glucose level from the user terminal 3 (activity A200). In activity A200, for example, the following two-stage information processing is executed. (1) The processor 33 receives the blood glucose level from the information processing device 2 via the communication unit 31. (2) The processor 33 stores the received blood glucose level in the memory unit 32.
[0063] After receiving the blood glucose level, the user terminal 3 displays the blood glucose level on the display unit 34 (activity A210). As a result, the blood glucose level of the subject estimated from the pulse wave synchronized electromagnetic wave data is output.
[0064] <Constructing an estimator> The estimator used by the processing unit 232 is constructed by machine learning using the actual measured values of blood components (specifically, blood glucose levels) linked to the feature amounts as training data. The actual measured values of blood glucose levels are values measured directly from the subject's blood using an invasive blood glucose level meter, such as by puncturing. The training data is composed of a combination of pulse wave synchronized electromagnetic wave data and blood glucose levels that are measured simultaneously. FIG. 12 shows an example of a method for measuring pulse wave synchronized electromagnetic wave data and blood glucose levels to obtain training data.
[0065] The graph in the upper part of FIG. 12 shows the timing of measurement of pulse wave synchronized electromagnetic wave data. The box marked "Measurement" indicates continuous measurement for, for example, 10 minutes. The interval between each measurement is, for example, 15 seconds. In the example of FIG. 12, after three measurements, a meal is taken for, for example, 5 minutes, and then six measurements are taken. In addition, the measurement site of the subject for the pulse wave synchronized electromagnetic wave data (i.e., the attachment position of the measuring device 10) is changed every 10 minutes (i.e., for each measurement). The measured pulse wave synchronized electromagnetic wave data is recorded, for example, every minute.
[0066] The graph in the lower part of Fig. 12 shows blood glucose levels measured simultaneously with the pulse wave synchronized electromagnetic wave data. The horizontal axis is the time axis synchronized with the pulse wave synchronized electromagnetic wave data, and the vertical axis is the magnitude of the blood glucose level. Blood glucose levels are measured, for example, every 5 minutes. Note that since there is a 10 minute time lag in blood glucose level measurements, the graph in the lower part of Fig. 12 is corrected to shift the time forward by 10 minutes at a time.
[0067] Using the teacher data obtained in this manner, the complex neural network of Fig. 10 is constructed. That is, the feature values extracted from the pulse wave synchronized electromagnetic wave data included in the teacher data are input to the complex neural network, and the weight coefficients of the complex neural network are adjusted so that the phase of the output (complex number for estimation) corresponds to the blood glucose level of the teacher data in the judgment chart of Fig. 11. For example, if the blood glucose level of the teacher data is "125 mg / dL", learning is performed so that the phase of the output becomes "π / 2" when the feature values of the pulse wave synchronized electromagnetic wave data included in this teacher data are input.
[0068] 4. Effect The operation of this embodiment can be summarized as follows: The blood glucose level can be estimated with high accuracy from the pulse wave synchronized electromagnetic wave data that can be measured non-invasively. That is, the blood glucose level can be measured by a non-invasive method that imposes little physical burden on the subject.
[0069] Although the embodiment of the present invention has been described above, the present invention is not limited to this, and can be modified as appropriate without departing from the technical concept of the invention.
[0070] 5.Other In the above embodiment, the information processing device 2 performs various storage and control, but multiple external devices may be used instead of the information processing device 2. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like.
[0071] The aspect of the present embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes each step of the information processing device 2. The program causes a computer to function as the information processing device 2.
[0072] The information processing system 1 may be an integrated unit of the information processing device 2 and the user terminal 3. That is, the information processing device 2 may receive pulse wave synchronized electromagnetic wave data from the measuring device 10 and output the blood glucose level estimation result.
[0073] The information processing device 2 may estimate the blood glucose level using the amplitude of the estimation complex number in addition to or instead of the phase of the estimation complex number output by the complex neural network. That is, a judgment chart in which the blood glucose level is linked to the amplitude, or a judgment chart in which the blood glucose level is linked to a combination of the phase and the amplitude may be used.
[0074] The information processing device 2 may estimate the blood glucose level using a feature based only on the phase of the pulse-wave-synchronized electromagnetic wave data, or a feature based only on the amplitude. That is, the information processing device 2 may input a feature based on at least one of the amplitude and phase of the pulse-wave-synchronized electromagnetic wave data to the estimator. Also, the feature may include an average value of peak points where the amplitude of each wave of the pulse-wave-synchronized electromagnetic wave data is maximum, instead of the phase. Furthermore, when only the amplitude or only the phase is used for estimation, a real neural network may be used instead of the complex neural network.
[0075] The information processing device 2 may estimate blood components other than the blood glucose level. For example, the information processing device 2 may be configured to estimate blood lipids, blood salt concentration, etc. Estimation of blood lipids makes it possible to predict the risk of cerebrovascular disease, etc., using a non-invasive method that places little physical strain on the subject.
[0076] The estimator used by the information processing device 2 does not necessarily have to include a neural network. In addition, the estimator does not necessarily have to be constructed by machine learning, and may be constructed by a statistical method other than machine learning.
[0077] It may be provided in any of the following ways:
[0078] (1) An information processing device comprising a processor, the processor being configured to execute a reception step and a processing step, in which the reception step receives input of pulse wave-synchronized electromagnetic wave data of a subject, and the processing step estimates blood components of the subject by inputting features based on at least one of the amplitude and phase of the pulse wave-synchronized electromagnetic wave data into an estimator.
[0079] (2) In the information processing device described in (1) above, the pulse wave synchronized electromagnetic wave data is measured using a plurality of probe electromagnetic wave frequencies, and the feature amount is extracted from the measurement values at the plurality of probe electromagnetic wave frequencies.
[0080] (3) In the information processing device described in (2) above, the pulse wave synchronized electromagnetic wave data is measured while periodically switching a probe electromagnetic wave frequency.
[0081] (4) In the information processing device described in any one of (1) to (3) above, the feature amount includes an average value of peak points at which the amplitude or phase is maximum in each wave of the pulse wave synchronized electromagnetic wave data.
[0082] (5) In the information processing device described in any one of (1) to (4) above, the feature amount includes an average value of each of a plurality of measurement points arranged in accordance with the magnitude of the amplitude or the phase in each wave of the pulse wave synchronized electromagnetic wave data, or an average value of each measurement value at regular intervals in each wave of the pulse wave synchronized electromagnetic wave data.
[0083] (6) In the information processing device described in (5) above, in the processing step, periodic fluctuations of each wave of the pulse wave synchronized electromagnetic wave data are corrected using a pulse rate measured simultaneously with the pulse wave synchronized electromagnetic wave data, and the feature amount includes an average value of each measurement value at regular intervals in each wave.
[0084] (7) In an information processing device described in any one of (1) to (6) above, the pulse wave synchronized electromagnetic wave data is obtained by reflecting electromagnetic waves off the body of the person being measured or by transmitting electromagnetic waves through the body of the person being measured.
[0085] (8) In the information processing device described in any one of (1) to (7) above, the estimator is constructed by machine learning using actual measured values of blood components linked to the features as training data.
[0086] (9) An information processing method comprising each step of the information processing device according to any one of (1) to (8) above.
[0087] (10) A program for causing a computer to function as an information processing device according to any one of (1) to (8) above. Of course, this is not the case.
[0088] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]
[0089] 1: Information processing system 2: Information processing equipment 3: User terminal 10: Measuring equipment 20: Communication bus 21: Communications Department 22: Storage section 23: Processor 30: Communication bus 31: Communications Department 32: Storage section 33: Processor 34: Display section 35: Input section 231: Reception 232: Processing section 233: Output section
Claims
1. An information processing device, A processor is provided. The processor is configured to perform a receiving step and a processing step; In the receiving step, input of pulse wave-synchronized electromagnetic wave data of the subject is received, In the processing step, a feature based on at least one of the amplitude and phase of the pulse wave synchronized electromagnetic wave data is input to an estimator, thereby estimating blood components of the subject.
2. 2. The information processing device according to claim 1, The pulse-wave-synchronized electromagnetic wave data is measured using a plurality of probe electromagnetic wave frequencies; The features are extracted from measurements at a plurality of probe electromagnetic frequencies.
3. 3. The information processing device according to claim 2, The pulse wave synchronized electromagnetic wave data is measured while periodically switching a probe electromagnetic wave frequency.
4. 2. The information processing device according to claim 1, The characteristic amount includes an average value of peak points at which the amplitude or phase is maximum in each wave of the pulse wave synchronized electromagnetic wave data.
5. 2. The information processing device according to claim 1, The feature value includes an average value of each of a plurality of measurement points arranged in accordance with the magnitude of the amplitude or the phase in each wave of the pulse wave synchronized electromagnetic wave data, or an average value of each measurement value at regular intervals in each wave of the pulse wave synchronized electromagnetic wave data.
6. 6. The information processing device according to claim 5, In the processing step, a periodic variation of each wave of the pulse-wave-synchronous electromagnetic wave data is corrected based on a pulse rate measured simultaneously with the pulse-wave-synchronous electromagnetic wave data; The feature amount includes an average value of each measurement value at regular intervals in each wave.
7. 2. The information processing device according to claim 1, The pulse wave synchronized electromagnetic wave data is acquired by reflecting electromagnetic waves off the body of the person being measured, or by transmitting electromagnetic waves through the body of the person being measured.
8. 2. The information processing device according to claim 1, The estimator is constructed by machine learning using actual measured values of blood components linked to the features as training data.
9. 1. An information processing method, comprising: A method comprising the steps of an information processing device according to any one of claims 1 to 8.
10. A program, A program for causing a computer to function as the information processing device according to any one of claims 1 to 8.
Citation Information
Patent Citations
Blood glucose measuring device
JP2022185130A
