Evaluation system, processing apparatus, and computer program

Abstract

To diversify an environment for evaluating the measured waveform of a biological parameter acquired from an object.SOLUTION: An inference device 11 acquires first data D1 corresponding to the measured waveform of a biological parameter of an object 20, infers the probability that the value of the biological parameter is correctly measured, and generates second data D2 obtained by providing the probability to the first data D1. A processor 12 applies a predetermined evaluation function to the second data D2 to calculate a value score of the measured waveform and generates third data D3 obtained by providing the value score to the second data D2. A display unit 13 displays information based on at least one piece of third data D3 provided with a higher value score. The value score has positive correlation to the probability and has negative correlation to the time elapsed from when the biological parameter is measured.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a system for evaluating biometric information obtained from a subject, a processing device included in the system, and a computer program executable by a processor installed in the processing device. [Background technology]

[0002] Patent Document 1 discloses a device that infers the probability that the value of a biological parameter will be correctly measured by inputting data corresponding to the measured waveform of the biological parameter obtained from a subject into a machine-learned model. By identifying data that is assigned a probability below a threshold, biological information obtained in a low-reliability environment, such as under the influence of noise, can be excluded from the evaluation target. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2022-019602 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a demand for diversifying the environments in which measurement waveforms of biological parameters obtained from subjects can be evaluated. [Means for solving the problem]

[0005] One exemplary embodiment provided by the present disclosure is an evaluation system, comprising: an inference device that acquires first data corresponding to a measured waveform of a biological parameter of a subject, infers a probability that the value of the biological parameter will be correctly measured, and generates second data in which the first data is assigned the probability; A processing device that calculates a value score of the measured waveform by applying a predetermined evaluation function to the second data, and generates third data in which the value score is assigned to the second data; An output device that outputs information based on at least one of the third data to which a higher value score is assigned; It is equipped with The value score is positively correlated to the probability and negatively correlated to the time since the biological parameter was measured.

[0006] One embodiment of the present disclosure provides a processing device communicably connected to an inference device that acquires first data corresponding to a measured waveform of a biological parameter of a subject, infers a probability that a value of the biological parameter will be correctly measured, and generates second data in which the first data is assigned the probability, an interface for accepting the second data; A processor that calculates a value score of the measured waveform by applying a predetermined evaluation function to the second data, generates third data in which the value score is assigned to the second data, and outputs at least one of the third data to which a higher value score is assigned, to an output device; It is equipped with The value score is positively correlated to the probability and negatively correlated to the time since the biological parameter was measured.

[0007] One embodiment of the present disclosure provides a computer program executable by a processor mounted on a processing device that cooperates with an inference device to acquire first data corresponding to a measured waveform of a biological parameter of a subject, infer a probability that the value of the biological parameter will be correctly measured, and generate second data in which the first data is assigned the probability, comprising: When executed, the processing device: Accepting the second data; Calculating a value score of the measured waveform by applying a predetermined evaluation function to the second data; generating third data in which the value score is assigned to the second data; outputting at least one of the third data items to which the higher value score has been assigned to an output device; The value score is positively correlated to the probability and negatively correlated to the time since the biological parameter was measured.

[0008] According to the configurations of the above-mentioned embodiments, it is possible to present an evaluation result based on a new value standard that takes into account not only the probability that the value of the biological parameter is accurately measured, but also the time elapsed since the value was measured. For example, the measurement value of the biological parameter evaluated in this way can be used in addition to or instead of the measurement value of the biological parameter used for the early warning score based on the conventional evaluation standard. Therefore, it is possible to diversify the environment for evaluating the measurement waveform of the biological parameter obtained from the subject. [Brief description of the drawings]

[0009] [Figure 1] 2 illustrates an example of a functional configuration of an evaluation system according to an embodiment. [Diagram 2] 2 illustrates the time course of the probability of a normal measurement assigned by the inference device of FIG. 1. [Diagram 3] 2 shows an example of third data generated by the processing device of FIG. 1. [Figure 4] 2 shows an example of a screen displayed by the display device of FIG. 1. [Diagram 5] 13 shows another example of the third data generated by the processing device of FIG. [Figure 6] 13 shows another example of the third data generated by the processing device of FIG. [Figure 7] 10 shows another example of a screen displayed by the display device of FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Exemplary embodiments are described in detail below with reference to the accompanying drawings.

[0011] 1 illustrates a functional configuration of an evaluation system 10 according to an embodiment. The evaluation system 10 has a configuration for evaluating biological information acquired from a subject 20.

[0012] The evaluation system 10 includes an inference device 11. The inference device 11 has an input interface 111. The input interface 111 is configured as a hardware interface that receives first data D1 corresponding to a measured waveform of a biological parameter of a subject 20. The first data D1 includes information indicating the time point when the measured waveform was acquired.

[0013] The first data D1 may be received directly from the sensor 31 attached to the subject 20, or may be received via a monitor device (not shown) to which a plurality of types of sensors are connected. The first data D1 may be in the form of analog data or digital data depending on the specifications of the output source. When the first data D1 is in the form of analog data, the input interface 111 includes an appropriate conversion circuit including an A / D converter.

[0014] The term "biological parameter of a subject" as used herein refers to a measurable value among various indicators that represent the physiological state of the subject. The measured value of a biological parameter is an example of biological information.

[0015] The inference device 11 includes an inference model 112. The inference model 112 is a computer algorithm configured to output, as an inference result, the probability that the value of a biological parameter will be correctly measured based on the measurement waveform of the biological parameter corresponding to the first data D1. The probability takes a value between 0 and 1. The value 0 corresponds to 0%. The value 1 corresponds to 100%. The level of the probability depends on the measurement environment of the biological parameter, the condition of the subject, etc.

[0016] The inference model 112 can be generated by performing machine learning using training data or through an appropriate statistical method. The training data is provided as a combination of measurement waveforms of biological parameters acquired under different measurement environments and subject conditions, and annotations indicating whether the biological parameters have been calculated correctly. Examples of algorithms used in machine learning include neural networks, decision trees, random forests, support vector machines, Bayesian estimation, and Gaussian processes. Examples of statistical methods include a method using the coefficient of variation.

[0017] The inference device 11 includes a processor 113 and an output interface 114. The processor 113 is configured to input the first data D1 received by the input interface 111 to the inference model 112, and output the second data D2 generated by assigning the probability output from the inference model 112 to the first data D1 from the output interface 114. In other words, the output interface 114 is configured as a hardware interface capable of outputting the second data D2.

[0018] The processor 113 may calculate the value of the biological parameter based on the first data D1 corresponding to the measured waveform of the biological parameter. In this case, the calculated value may be included in the second data D2 as the measured value of the biological parameter. Depending on the specifications of the output source of the first data D1, the measured value of the biological parameter may be included in the first data D1.

[0019] The evaluation system 10 includes a processing device 12. The processing device 12 is equipped with an input interface 121. The input interface 121 is configured as a hardware interface that accepts second data D2.

[0020] The processing device 12 includes an evaluation model 122. The evaluation model 122 is a computer algorithm configured to calculate a value score of the measurement waveform of the biological parameter related to the first data D1 by applying a predetermined evaluation function to the second data D2. In this example, the value score ranges from 0 to 100.

[0021] The significance of the value score will be explained with reference to FIG. 2. FIG. 2 illustrates the change over time in the probability that a value estimated for each value of a biological parameter obtained from a subject 20 has been correctly measured (hereinafter referred to as "probability of correct measurement"). Thus, the horizontal axis represents the passage of time, and the vertical axis represents the probability. In this example, the biological parameter is respiration rate. Although not shown in the graph, one measured value of respiration rate is associated with each plot.

[0022] The normal measurement probability can be used, for example, in so-called data cleansing. A respiration rate measurement value to which a low probability value is assigned can be considered to be more likely to have been obtained under relatively poor measurement conditions. Factors that deteriorate the measurement conditions include the subject's body movement, sensor misalignment, and failure. By setting an appropriate threshold value Pt for the normal measurement probability and not adopting a measurement value to which a probability value below the threshold value is assigned, a highly reliable respiration rate measurement value can be selected.

[0023] In Figure 2, the probability of normal measurement assigned to the respiration rate value measured at time t1 is higher than the probability of normal measurement assigned to the respiration rate value measured at time t2. If we focus only on the probability values, it can be said that the respiration rate value measured at time t1 is more reliable than the respiration rate value measured at time t2. However, it can also be said that the respiration rate measured later in time better reflects the subject's current condition and is therefore more reliable.

[0024] In this embodiment, the value score is calculated based on the guideline that "the longer the elapsed time since the measurement, the lower the reliability of the measurement value." In other words, the value score represents the reliability of the measurement value of the respiration rate with the evaluation based on the guideline taken into account. Therefore, the above evaluation function applied to the second data D2 by the evaluation model 122 is determined so that the value score calculated as a result has a positive correlation with the probability of normal measurement and a negative correlation with the elapsed time from the time of measurement of the respiration rate.

[0025] 1, the processing device 12 includes a processor 123. The processor 123 is configured to input the second data D2 received by the input interface 121 to an evaluation model 122, and generate third data D3 by assigning a value score output from the evaluation model 122 to the second data D2.

[0026] Fig. 3 shows an example of the third data D3 generated by the processor 123. A normal measurement probability and a value score are calculated for each of the respiratory rates measured at six points in time. In Fig. 3, the third data D3 including a higher value score is shown at the top. As a result, the measurement dates and times are not arranged in chronological order, and the normal measurement probabilities are not arranged in ascending order.

[0027] The processing device 12 includes an output interface 124 configured as a hardware interface. The processor 123 is configured to output, from the output interface 124, at least one third data D3 to which a higher value score has been assigned.

[0028] The evaluation system 10 includes a display device 13. The display device 13 is configured to perform a display based on the third data D3 output from the processing device 12. The display device 13 is an example of an output device. Display is an example of output of information.

[0029] 4 illustrates a first screen 131 displayed by the display device 13. In this example, the display is based on the third data D3 to which the highest value score has been assigned. The first screen 131 includes the time point at which the measurement was performed, the measurement waveform acquired at that time point, the respiration rate calculated based on the measurement waveform, the probability of the respiration rate being normally measured, and the value score of the respiration rate.

[0030] The processor 123 of the processing device 12 outputs display control data DC for causing the display device 13 to perform the above-mentioned display from the output interface 124. The display control data DC may be in the form of analog data or digital data depending on the specifications of the display device 13. When the display control data DC is output in the form of analog data, the output interface 124 includes an appropriate conversion circuit including a D / A converter.

[0031] In order to construct an appropriate in-hospital rapid response system, it is known to use an Early Warning Score (EWS) that scores a patient's vital signs to predict a sudden change in condition. In order to improve the accuracy of prediction of the risk of a sudden change in condition, it is necessary to provide more accurate measurements of biological parameters. The above-mentioned data cleansing can be performed, for example, for the purpose of improving this prediction accuracy.

[0032] According to the configuration of this embodiment, it is possible to present an evaluation result based on a new value standard that takes into account not only the probability that the value of the biological parameter is accurately measured, but also the elapsed time from the time the value is measured. For example, the measurement value of the biological parameter evaluated in this way can be used in addition to or instead of the measurement value of the biological parameter used in the EWS based on the conventional evaluation standard. Therefore, it is possible to diversify the environment for evaluating the measurement waveform of the biological parameter obtained from the subject.

[0033] The processor 123 of the processing device 12 may be configured to vary the value score based on the consistency between the second data D2 generated for the respiration rate measured at a particular point in time and at least one of the second data D2 generated for the respiration rate measured before the particular point in time and the respiration rate measured after the particular point in time.

[0034] Specifically, the processor 123 may be configured to reduce the value score if the value of normal measurement probability assigned to a respiratory rate measured at a certain point in time deviates significantly from the values ​​of normal measurement probability assigned to respiratory rates measured before and after that point.

[0035] Fig. 5 shows another example of the third data D3 generated by the processor 123. A normal measurement probability and a value score are calculated for each of the respiratory rates measured at six points in time. In Fig. 5, the data is illustrated in chronological order. The third data D3 generated for the more recent (obtained later in time) measurement values ​​is located at the top.

[0036] In the third data D3 surrounded by a thick solid line, it can be seen that the value of the normal measurement probability assigned to the measured value of the respiration rate is significantly different from the values ​​of the normal measurement probability assigned to the respiration rates measured before and after in time. In such a case, the processor 123 reduces the value score assigned to the measured value even if the time elapsed since the measurement is short and the normal measurement probability is high.

[0037] In order to determine the degree of deviation from the probability of normal measurements, an algorithm that makes a judgment based on the difference between a moving average of a specific number of measured values ​​and a specific measured value, or an algorithm based on deep metric learning may be used.

[0038] The above-mentioned deviation can occur due to a sudden change in the value of the normal measurement probability. Such a sudden change in the probability value is likely to be caused by noise. By lowering the value of the measurement value obtained under such circumstances, it is possible to prevent the occurrence of a situation in which a measurement value that is actually unreliable is displayed on the display device 13 with a high evaluation. This can further increase the diversity of the environment in which the measurement waveforms of the biological parameters obtained from the subject are evaluated.

[0039] 1, the evaluation system 10 may include a user interface 14. The user interface 14 is configured to accept input of information related to at least one of the age, sex, and type of underlying disease of the subject 20 as attribute data AT. The user interface 14 may be provided as a part of the inference device 11 or the processing device 12, or may be provided as a part of a device independent of these.

[0040] The attribute data AT is accepted by the input interface 121 of the processing device 12. The attribute data AT may be provided in the form of analog data or in the form of digital data, depending on the specifications of the user interface 14. When the attribute data AT is provided in the form of analog data, the input interface 121 has an appropriate conversion circuit including an A / D converter. This description is similarly applied to other data that can be accepted by the input interface 121, which will be described later.

[0041] The processor 123 of the processing device 12 may be configured to vary the value score based on the attribute data AT received by the input interface 121 .

[0042] When subjects are elderly or have underlying diseases, they tend to be at higher risk of sudden changes in their condition compared to non-elderly people or those without underlying diseases, even if the measured values ​​and changes in certain biological parameters are similar. The same applies to those who are judged by medical professionals to be at higher risk of sudden changes in their condition.

[0043] As an example, when attribute data AT is input indicating that the subject is at relatively high risk of a sudden change in condition, processor 123 is configured to more greatly reduce the value score of measurement values ​​that have been measured a long time ago (to strengthen the negative correlation), making it easier for new measurement values ​​of biological parameters to be presented and increasing the possibility of responding to the risk of a sudden change in condition.

[0044] As another example, if the subject's condition improves or is showing signs of recovery, the processor 132 is configured to reduce the decline in value scores of measurements that have been taken longer than the time of measurement (to weaken negative correlations), thereby increasing the range of measurements of the presented biological parameters.

[0045] As a result, the diversity of environments in which measurement waveforms of biological parameters obtained from a subject are evaluated can be further increased.

[0046] 1, the input interface 121 of the processing device 12 can be configured to be able to accept detection data DT from a non-wearable sensor 32. The non-wearable sensor 32 is configured to detect the behavior of the subject 20 without being worn by the subject 20, and to output detection data DT corresponding to the detected behavior. Examples of the non-wearable sensor 32 include a camera, a sound-collecting microphone, and a load sensor installed on a bed. The detection data DT includes information indicating the time point at which the behavior was detected.

[0047] In this case, the processor 123 of the processing device 12 may be configured to vary the value score based on the detection data DT received by the input interface 121. Specifically, the processor 123 refers to time point information included in the detection data DT and associates it with third data D3 related to the respiratory rate measured at the same time. For example, when the detection data DT indicates a behavior that reduces the measurement accuracy of the biological parameter by the sensor 31, the processor 123 reduces the value score included in the third data D3 associated with the detection data DT. Examples of such behavior include body movement, speaking, coughing, sneezing, and snoring.

[0048] Fig. 6 shows another example of the third data D3 generated by the processor 123. A normal measurement probability and a value score are calculated for each of the respiratory rates measured at four points in time. In Fig. 6, the data are illustrated in chronological order. The third data D3 generated for the more recent (obtained later in time) measurement value is located at the top. In addition, the presence or absence of body movement of the subject 20 determined based on the detection data DT is associated with each third data D3.

[0049] For the third data D3 surrounded by a thick solid line, the body movement of the subject 20 is determined based on the detection data DT. In such a case, the processor 123 reduces the value score assigned to the measurement value even if the time elapsed since the measurement is short and the probability of normal measurement is high. As in the illustrated example, the amount by which the value score is reduced may be changed depending on the magnitude of the body movement.

[0050] That is, when the detection data DT indicates a situation in which the subject 20 is engaged in an action (body movement, coughing, talking, etc.) that reduces the accuracy of measurement of the biological parameters by the sensor 31, the processor 123 lowers the value of the measurement value acquired under that situation. This makes it possible to prevent the occurrence of a situation in which an originally unreliable measurement value is displayed on the display device 13 with a high evaluation.

[0051] As another example, when the detection data DT indicates a situation in which breathing of the subject 20 is not detected during measurement of biological parameters by the sensor 31, the processor 123 increases the value of the measurement value obtained under that situation. This can encourage the subject 20 to recognize that he is in a situation in which abnormalities such as difficulty in breathing or vomiting blood are suspected. When it is determined that the subject 20 is in that situation, it is preferable to notify a medical professional.

[0052] On the other hand, if a medical professional recognizes that the subject 20 is suffering from sleep apnea syndrome (SAS), even if the above-mentioned abnormality related to apnea is determined based on the detection data DT, it is not necessary to immediately notify the subject 20. In this case, the device may be configured to notify the subject 20 when the length of time during which the apnea state is detected exceeds a predetermined threshold.

[0053] However, when the occurrence of Cheyne-Stokes-like respiration, which is a respiration pattern that may be associated with central sleep apnea syndrome, is determined based on the detection data DT, it is preferable to immediately issue a notification. This allows for rapid first aid in the event that tongue drop or choking occurs due to loss of consciousness of the subject 20. In this example, the processor 123 may be configured to stop the calculation of the value score in order to prioritize first aid. The processor 123 can resume the calculation of the value score after the abnormality is resolved by performing a process such as setting a flag indicating that the calculation of the value score has been interrupted due to an abnormality.

[0054] As a result, the diversity of environments in which measurement waveforms of biological parameters obtained from a subject are evaluated can be further increased.

[0055] As illustrated in FIG. 1, the user interface 14 may be configured to accept feedback regarding the validity of the value score and to output feedback data FB corresponding to the feedback.

[0056] Specifically, as illustrated in Fig. 4, the first screen 131 includes a confirm button image 131a and a reject button image 131b. When the confirm button image 131a is in a selected state, feedback is given that the presented value score is valid. When the reject button image 131b is in a selected state, feedback is given that the presented value score is invalid. The user can judge the accuracy of the measurement value and the validity of the value score while referring to the measurement waveform of the respiration rate displayed on the first screen 131.

[0057] Each button image can be selected using an input device such as a mouse. If the display device 13 is a touch panel type, each button image can be selected through a touch operation by the user. In other words, the user interface 14 can be provided as a part of the display device 13.

[0058] When the reject button image 131b is selected, the second screen 132 is displayed. The second screen 132 includes a plurality of radio button images 132a. The plurality of radio button images 132a are provided for receiving more specific feedback. By selecting one of the plurality of radio button images 132a, the user can input the reason why the value score provided through the first screen 131 is considered to be invalid.

[0059] The second screen 132 further includes a back button image 132b, an omission button image 132c, and a confirmation button image 132d. When the back button image 132b is selected, the display device 13 redisplays the first screen 131. When the omission button image 132c or the confirmation button image 132d is selected, the display device 13 displays the third screen 133. The omission button image 132c is selected when it is desired to omit inputting the reason why the value score is invalid.

[0060] The third screen 133 includes information based on third data relating to respiration rates measured at other times in addition to the information provided through the first screen 131. In this example, information relating to the respiration rate that was assigned the second highest value score is displayed.

[0061] The third screen 133 includes a plurality of radio button images 133a. Each radio button image 133a is associated with information based on a corresponding measurement value of the respiration rate. When the third screen 133 is initially displayed, the radio button image 133a associated with the information provided through the first screen 131 is in a selected state.

[0062] The third screen 133 further includes a confirm button image 133b and a reject button image 133c. The confirm button image 133b is in a selected state to provide feedback that the value score associated with the selected radio button image 133a is valid. The reject button image 133c is in a selected state to provide feedback that the value score associated with the selected radio button image 133a is invalid. The user can determine the accuracy of the measurement value and the validity of the value score while referring to the measurement waveform of the respiratory rate associated with the selected radio button image 133a.

[0063] When the Reject button image 133c is selected, the display device 13 redisplays the second screen 132. The user can provide feedback on the reason why the selected value score is considered invalid through the third screen 133. When the Omit button image 132c or the Confirm button image 132d is selected, the display device 13 displays the third screen 133 including information based on third data relating to the respiration rate measured at yet another time point. The user can repeat the above operations until a measurement result to which a value score that the user considers to be valid is assigned is obtained.

[0064] Note that the information displayed on the third screen 133 in addition to the information provided through the first screen 131 may be based on the respiration rate measured at two or more points in time. In this case, two or more radio button images 133a are additionally displayed so that one of multiple candidates can be selected.

[0065] That is, the processor 123 of the processing device 12 may be configured to cause the display device 13 to display information based on at least one other third data D3 based on the feedback data FB received by the input interface 121.

[0066] There may be cases where the value score assignment criteria initially adopted by the evaluation system 10 do not conform to the user's preferences or the guidelines of the medical institution to which the user belongs. With the above-described configuration, the evaluation system 10 can be given the freedom to allow changes to make the validity of the value score closer to the user's preferences or the guidelines of the medical institution to which the user belongs. This can further increase the diversity of the environment for evaluating the measurement waveforms of the biological parameters obtained from the subject.

[0067] It is also possible to adopt a configuration in which the display of the first screen 131 is omitted and the third screen 133 is displayed from the beginning on the display device 13. In this case, the user can select one of a plurality of value scores using the radio button image 133a, and select the value score that he / she considers to be the most appropriate using the confirm button image 133b, or input the reason why he / she considers the value score to be inappropriate by displaying the second screen 132 using the reject button image 133c.

[0068] The processor 123 of the processing unit 12 may be configured to modify the evaluation function provided by the evaluation model 122 based on the feedback data FB received by the input interface 121 .

[0069] As an example, when the reason "data is old" is selected on the second screen 132 in Fig. 4, the processor 123 acquires the elapsed time from the time the respiration rate related to the selection was measured as a threshold value. In the subsequent processing, the processor 123 changes the evaluation function so as to greatly reduce the value score assigned to the second data D2 for which the elapsed time from the time the respiration rate was measured is equal to or greater than the threshold value.

[0070] As another example, when the reason "waveform is distorted" is selected on the second screen 132 in Fig. 4, the processor 123 acquires the probability that the value of the biological parameter related to the selection is correctly measured as a threshold value. In the subsequent processing, the processor 123 changes the evaluation function so as to greatly reduce the value score assigned to the second data D2 whose probability is below the predetermined threshold value.

[0071] As another example, when the reason "respiratory rate does not match" is selected on the second screen 132 of FIG. 4, a fourth screen 134 illustrated in FIG. 7 is displayed. The fourth screen 134 is provided for annotation. The fourth screen 134 includes an annotation area 134a and a respiratory rate input area 134b. The user can add annotations indicating the peaks and bottoms of the waveform to the measured respiratory rate waveform displayed on the fourth screen 134. The annotation can be added by touching the corresponding portion of the measured waveform. The user can identify the correct respiratory rate based on the annotation result and input it to the respiratory rate input area 134b.

[0072] The fourth screen 134 further includes an omit button image 134c and a confirm button image 134d. When the omit button image 134c is selected, the annotation is not added and the respiration rate is not corrected, and the display device 13 displays the third screen 133. When the confirm button image 134d is selected, the added annotation and the corrected data related to the respiration rate are validated, and the display device 13 displays the third screen 133.

[0073] According to the above-mentioned configuration, changes to bring the validity of the value score closer to the user's preference or the guidelines of the medical institution to which the user belongs can be reflected in the operation of the evaluation model 122. This can further increase the diversity of the environment for evaluating the measurement waveforms of the biological parameters obtained from the subject.

[0074] The evaluation function of the evaluation model 122 may be provided by an inference model generated through machine learning. Examples of algorithms used in machine learning include neural networks, decision trees, random forests, support vector machines, Bayesian estimation, and Gaussian processes. As training data, the results of changes made by the user (which data was selected or rejected) described with reference to Figs. 4 and 7 may be used.

[0075] 1, the evaluation system 10 may include a re-learning device 15. The re-learning device 15 is a device for re-learning the evaluation model 122 generated through machine learning. The re-learning device 15 is communicatively connected to the processing device 12.

[0076] In this case, the processor 123 of the processing device 12 is configured to generate fourth data D4 by adding information corresponding to the feedback data FB received by the input interface 121 to the third data D3. The fourth data D4 is output from the output interface 124 to the re-learning device 15.

[0077] The re-learning device 15 holds the same evaluation model M as that implemented in the processing device 12. The fourth data D4 includes information (annotation) about the value score assigned to a specific measured waveform and its validity. Therefore, by using the fourth data D4 as teacher data, the re-learning device 15 can perform re-learning on the evaluation model M to adjust the evaluation function so that a more valid value score can be assigned. The processing device 12 updates the evaluation model 122 by receiving the re-learned evaluation model M from the re-learning device 15.

[0078] Even with such a configuration, changes that bring the validity of the value score closer to the user's preferences or the guidelines of the medical institution to which the user belongs can be reflected in the operation of the evaluation model 122. Although not shown in the figure, the re-learning device 15 can be shared by multiple processing devices 12. In this case, the same evaluation model 122 can be shared between multiple evaluation systems 10 that share preferences and guidelines regarding the validity of the value score.

[0079] Each of the processor 113 of the inference device 11 and the processor 123 of the processing device 12 having the various functions described above can be realized by a general-purpose microprocessor operating in cooperation with a general-purpose memory. Examples of the general-purpose microprocessor include a CPU, an MPU, and a GPU. Examples of the general-purpose memory include a ROM and a RAM. In this case, the ROM can store a computer program that executes the above-mentioned processing. The ROM is an example of a non-transient computer-readable medium in which a computer program is stored. The general-purpose microprocessor specifies at least a part of the computer program stored on the ROM, expands it on the RAM, and executes the above-mentioned processing in cooperation with the RAM. The computer program may be pre-installed in the general-purpose memory, or may be downloaded from an external server device via a communication network and then installed in the general-purpose memory. In this case, the external server device is an example of a non-transient computer-readable medium in which a computer program is stored.

[0080] Each of processor 113 of inference device 11 and processor 123 of processing device 12 may be realized by a dedicated integrated circuit capable of executing the above computer program, such as a microcontroller, an ASIC, or an FPGA. In this case, the above computer program is pre-installed in a memory element included in the dedicated integrated circuit. The memory element is an example of a computer-readable medium on which a computer program is stored. Each of processor 113 of inference device 11 and processor 123 of processing device 12 may also be realized by a combination of a general-purpose microprocessor and a dedicated integrated circuit.

[0081] The configurations described above are merely examples for facilitating understanding of the present disclosure. Each configuration example may be appropriately modified or combined with other configuration examples without departing from the spirit of the present disclosure.

[0082] In Fig. 1, reasoning device 11, processing device 12, display device 13, and re-learning device 15 are illustrated as independent devices. However, at least two of these devices may be implemented as different functional modules in a single device. For example, if reasoning device 11 and processing device 12 are provided as a single device, output interface 114 of reasoning device 11 and input interface 121 of processing device 12 may be implemented as software interfaces rather than hardware interfaces.

[0083] The information including the value score based on the third data D3 does not necessarily need to be output through the display device 13. The information may be visualized through a printer or transmitted in a data format that can be used by other devices. In this case, the printer and the data transmission device are examples of output devices.

[0084] The inference model 112 does not necessarily have to be installed in the inference device 11. Although not shown in the figure, the inference device 11 may be communicatively connected to an external server device via a communication network. In this case, the inference model 112 may be installed in the external server device.

[0085] The evaluation model 122 does not necessarily have to be mounted on the processing device 12. Although not shown in the figure, the processing device 12 may be communicably connected to an external server device via a communication network. In this case, the evaluation model 122 may be mounted on the external server device.

[0086] The configurations listed below also form part of this disclosure. Item 1: an inference device that acquires first data corresponding to a measured waveform of a biological parameter of a subject, infers a probability that the value of the biological parameter will be correctly measured, and generates second data in which the first data is assigned the probability; A processing device that calculates a value score of the measured waveform by applying a predetermined evaluation function to the second data, and generates third data in which the value score is assigned to the second data; An output device that outputs information based on at least one of the third data to which a higher value score is assigned; Equipped with The value score is positively correlated to the probability and negatively correlated to the time since the biological parameter was measured. Rating system. Item 2: The processing device is configured to vary the value score based on consistency between the second data generated for the bioparameter measured at a specific time point and the second data generated for at least one of the bioparameter measured before the specific time point and the bioparameter measured after the specific time point. The evaluation system described in item 1. Item 3: The processing device is configured to vary the value score based on at least one of the subject's age, sex, and type of underlying disease. 3. The evaluation system according to item 1 or 2. Item 4: The processing device is configured to vary the value score based on a behavior of the subject acquired through a sensor not worn by the subject. 4. The evaluation system according to any one of items 1 to 3. Item 5: The processing device is configured to stop calculating the value score based on a behavior of the subject acquired through a sensor not worn by the subject. 4. The evaluation system according to any one of items 1 to 3. Item 6: a user interface for receiving feedback regarding the validity of the value score; The processing device causes an output device to output information based on the third data in response to the feedback. 6. The evaluation system according to any one of items 1 to 5. Item 7: The processing device modifies the evaluation function based on the feedback. The evaluation system described in item 6. Item 8: The evaluation function is provided by an inference model generated through machine learning. 8. The evaluation system according to any one of items 1 to 7. Item 9: the processing device generates fourth data in which information corresponding to the feedback is added to the third data; and a device for retraining the inference model based on the fourth data. The evaluation system described in item 6. [Explanation of symbols]

[0087] 10: evaluation system, 11: inference device, 12: processing device, 121: input interface, 122: evaluation model, 123: processor, 13: display device, 14: user interface, 15: re-learning device, 20: subject, 32: non-wearable sensor, D1: first data, D2: second data, D3: third data, D4: fourth data, DT: detection data, FB: feedback data

Claims

1. an inference device that acquires first data corresponding to a measured waveform of a biological parameter of a subject, infers a probability that the value of the biological parameter will be correctly measured, and generates second data in which the first data is assigned the probability; A processing device that calculates a value score of the measured waveform by applying a predetermined evaluation function to the second data, and generates third data in which the value score is assigned to the second data; An output device that outputs information based on at least one of the third data to which a higher value score is assigned; Equipped with The value score is positively correlated to the probability and negatively correlated to the time since the biological parameter was measured. Rating system.

2. The processing device is configured to vary the value score based on consistency between the second data generated for the bioparameter measured at a specific time point and the second data generated for at least one of the bioparameter measured before the specific time point and the bioparameter measured after the specific time point. The evaluation system according to claim 1 .

3. The processing device is configured to vary the value score based on at least one of the subject's age, sex, and type of underlying disease. The evaluation system according to claim 1 .

4. The processing device is configured to vary the value score based on a behavior of the subject acquired through a sensor not worn by the subject. The evaluation system according to claim 1 .

5. The processing device is configured to stop calculating the value score based on a behavior of the subject acquired through a sensor not worn by the subject. The evaluation system according to claim 1 .

6. a user interface for receiving feedback regarding the validity of the value score; The processing device causes an output device to output information based on the third data in response to the feedback. The evaluation system according to claim 1 .

7. The processing device modifies the evaluation function based on the feedback. The evaluation system according to claim 6.

8. The evaluation function is provided by an inference model generated through machine learning. The evaluation system according to claim 1 .

9. a user interface for receiving feedback regarding the validity of the value score; the processing device generates fourth data in which information corresponding to the feedback is added to the third data; and a device for retraining the inference model based on the fourth data. The evaluation system according to claim 8.

10. A processing device communicably connected to an inference device that acquires first data corresponding to a measured waveform of a biological parameter of a subject, infers a probability that the value of the biological parameter will be correctly measured, and generates second data in which the first data is assigned the probability, an interface for accepting the second data; A processor that calculates a value score of the measured waveform by applying a predetermined evaluation function to the second data, generates third data in which the value score is assigned to the second data, and outputs at least one of the third data to which a higher value score is assigned, to an output device; It is equipped with The value score is positively correlated to the probability and negatively correlated to the time since the biological parameter was measured. Processing unit.

11. A computer program executable by a processor mounted on a processing device that cooperates with an inference device to acquire first data corresponding to a measured waveform of a biological parameter of a subject, infer a probability that the value of the biological parameter will be correctly measured, and generate second data in which the probability is assigned to the first data, When executed, the processing device: Accepting the second data; Calculating a value score of the measured waveform by applying a predetermined evaluation function to the second data; generating third data in which the value score is assigned to the second data; outputting at least one of the third data items to which the higher value score has been assigned to an output device; The value score is positively correlated to the probability and negatively correlated to the time since the biological parameter was measured. Computer program.

Images