Biological information processing method, biological information processing device, and computer program

Abstract

To diversify the environment for evaluating the measurement waveforms of biological parameters acquired from a subject.SOLUTION: The first data D1 corresponding to a measurement waveform of at least one biological parameter of a subject is acquired. The probability that the value of the biological parameter is measured correctly is inferred on the basis of the first data D1. The second data D2 in which the probability is given to a measured value of the biological parameter is generated. The second data D2 given with a probability exceeding a threshold is extracted as the third data D3. A condition sudden change score S representing a sudden change risk of the condition of the subject is determined on the basis of the third data D3. The threshold is changed on the basis of the condition sudden change score S.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to a method and apparatus for processing biometric information. The present disclosure also relates to a computer program executable by a processor included in the apparatus. [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 embodiment of the present disclosure provides a biometric information processing method, comprising: acquiring first data corresponding to a measured waveform of at least one biological parameter of the subject; inferring a probability that the value of the biological parameter is correctly determined based on the first data; generating second data in which the probability is assigned to the measurement value of the biological parameter; extracting the second data to which the probability exceeding a threshold is assigned as third data; determining a sudden change in condition score representing a risk of a sudden change in the subject's condition based on the third data; The threshold value is changed based on the sudden change in condition score.

[0006] One aspect provided by the present disclosure is a biometric information processing device, an interface for receiving second data corresponding to a measurement value of at least one bioparameter of a subject, the second data being assigned a probability that the value of the bioparameter is correctly measured, the probability being inferred based on first data corresponding to a measurement waveform of the bioparameter; A processor that extracts the second data to which the probability of exceeding a threshold is assigned as third data, determines a sudden change in condition score representing a risk of a sudden change in the subject's condition based on the third data, and changes the threshold based on the sudden change in condition score; It is equipped with:

[0007] One aspect provided by the present disclosure is a computer program executable by a processor installed in a biometric information processing device, By executing the above, the biometric information processing device receiving second data corresponding to a measurement value of at least one biological parameter of the subject, the second data being assigned a probability that the value of the biological parameter is correctly measured, the probability being inferred based on first data corresponding to a measurement waveform of the biological parameter; extracting the second data to which the probability exceeding a threshold is assigned as third data; determining a sudden change in condition score representing a risk of a sudden change in the subject's condition based on the third data; The threshold value is changed based on the sudden change in condition score.

[0008] According to the configurations relating to each of the above example aspects, the monitoring sensitivity of the subject can be dynamically changed based on a sudden change in condition score that indicates the risk of a sudden change in the subject's condition, which is determined based on the measurement waveforms of the subject's biological parameters.

[0009] Specifically, by lowering the reliability probability threshold, the monitoring sensitivity of the subject is increased. In other words, by increasing the amount of third data to be evaluated, the ability to detect sudden changes in the subject can be improved. On the other hand, by increasing the reliability probability threshold, the monitoring sensitivity of the subject is decreased. In other words, by reducing the amount of third data to be evaluated, the frequency of alerts can be suppressed.

[0010] Therefore, it is possible to diversify the environments in which the measurement waveforms of the biological parameters obtained from the subject are evaluated. [Brief description of the drawings]

[0011] [Figure 1] 2 illustrates an example of a functional configuration of a biological information processing system according to an embodiment. [Diagram 2] 1 illustrates an example of measured respiration rate over time. [Diagram 3] 13 shows the change in respiratory rate measurement over time according to another example. [Figure 4] 2 illustrates an example of a biometric information processing method executed by the system of FIG. 1. [Diagram 5] 2 illustrates another example of a biometric information processing method executed by the system of FIG. 1. [Figure 6] 2 illustrates another example of a biometric information processing method executed by the system of FIG. 1. [Figure 7] 2 illustrates another example of a biometric information processing method executed by the system of FIG. 1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Exemplary embodiments are described in detail below with reference to the accompanying drawings.

[0013] 1 illustrates a functional configuration of a biological information processing system 10 according to an embodiment. The biological information processing system 10 has a configuration for processing biological information acquired from a subject 20.

[0014] The bioinformation processing 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 bioparameter of a subject 20. The first data D1 includes information indicating the time point when the measured waveform was acquired.

[0015] 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.

[0016] 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.

[0017] 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 (reliability probability) that the value of a biological parameter is correctly measured based on the measurement waveform of the biological parameter corresponding to the first data D1. The reliability probability takes a value between 0 and 1. The value 0 corresponds to 0%. The value 1 corresponds to 100%. The level of the reliability probability depends on the measurement environment of the biological parameter, the condition of the subject, etc.

[0018] The inference model 112 can be generated by performing machine learning using training data. 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, and support vector machines.

[0019] 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 reliability 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.

[0020] 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.

[0021] The biometric information processing system 10 includes a processing device 12. The processing device 12 is provided with an input interface 121. The input interface 121 is configured as a hardware interface that accepts the second data D2.

[0022] 1, the processing device 12 includes a processor 122. The processor 122 is configured to extract, from the second data D2 received by the input interface 121, data that has been assigned a reliability probability exceeding a threshold value as third data D3.

[0023] 2 illustrates the change over time of the measured respiration rate as an example of a biological parameter of the subject 20. The horizontal axis represents the passage of time, and the vertical axis represents the measured respiration rate value. That is, each of the gray plots represents the respiration rate value measured at a certain point in time, and corresponds to the above-mentioned second data D2.

[0024] Each of the black plots in Fig. 2 corresponds to the third data D3 extracted as described above. That is, among the measured values ​​of the respiratory rate corresponding to the grey plots, those that are inferred to have a reliability probability exceeding a threshold are represented as black plots.

[0025] The processor 122 of the processing device 12 is configured to determine, based on the third data D3, a sudden change in condition score representing a risk of a sudden change in the condition of the subject 20. Specifically, the processor 122 identifies an evaluation value of the respiratory rate based on the third data D3, and determines the sudden change in condition score based on the evaluation value.

[0026] As an example, the respiration rate estimate may be determined by calculating a respiration rate statistic over a predetermined period of time, such as the past hour. Examples of the statistic include the mean, median, mode, maximum, minimum, etc.

[0027] The horizontal axis of the histogram H in Fig. 2 represents the frequency of occurrence of the measured respiration rate values ​​during the depicted time period. Alternatively, the assessment value of the respiration rate may be determined by calculating a statistical value of the frequency of occurrence. Examples of the statistical value include the mean, median, maximum, etc.

[0028] Determining the condition change score based on the respiratory rate assessment value may be based on, for example, the following rules: A higher score value represents a higher risk of condition change. 12-20 times per minute: 0 9-11 times per minute: 1 21-24 times per minute: 2 8 or less per minute or 25 or more per minute: 3

[0029] 1, the biological information processing system 10 includes an output device 14. On the other hand, the processing device 12 has an output interface 123 configured as a hardware interface. The processor 122 is configured to output, from the output interface 123, notification data N that causes the output device 14 to perform a notification based on the determined sudden change in condition score.

[0030] The notification data N may be provided in the form of analog data or digital data depending on the specifications of the output device 14. When the notification data N is in the form of analog data, the output interface 123 includes an appropriate conversion circuit including a D / A converter. This description is similarly applied to other data that can be output by the output interface 123, which will be described later.

[0031] For example, if the sudden change in condition score indicates that the subject 20 is at high risk of a change in condition, an appropriate notification may be made through the output device 14. The notification may be made through at least one of a visual notification, an audible notification, and a tactile notification. The output device 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. The output device 14 may be a device that is placed at a specific location, or may be a device that can be carried by a medical professional.

[0032] The processor 122 of the processing device 12 is configured to change the threshold of the reliability probability applied to the second data D2 based on the determined sudden change in condition score. Specifically, the processor 122 lowers the threshold in response to a higher sudden change in condition score and raises the threshold in response to a lower sudden change in condition score. The correspondence between the score and the threshold can be appropriately determined.

[0033] Figure 3 illustrates the third data D3 when an increased threshold is applied to the same second data D2 as illustrated in Figure 2. Figure 2 illustrates the case where the reliability probability threshold is 0.65, and Figure 3 illustrates the case where the reliability probability threshold is 0.80. Comparing Figures 2 and 3, it can be seen that the amount of the third data D3 extracted is reduced by increasing the threshold.

[0034] By lowering the threshold of the reliability probability, the sensitivity of monitoring the subject is increased. In other words, by increasing the amount of third data D3 to be evaluated, the ability to detect a sudden change in the subject 20 can be improved.

[0035] On the other hand, by increasing the reliability probability threshold, the monitoring sensitivity of the target person is decreased. In other words, the third data D3 to be evaluated is reduced, and the frequency of issuing alerts can be suppressed.

[0036] The biometric information processing method executed by the biometric information processing system 10 configured as above will be described again with reference to FIG.

[0037] First data D1 corresponding to a measurement waveform of a biological parameter of a subject obtained through at least one sensor is acquired. The first data D1 is input to an inference model M. The inference model M infers a reliability probability of the measurement waveform corresponding to the first data D1. Second data D2 is generated by assigning the inferred reliability probability to the first data D1. In the configuration illustrated in FIG. 1, the inference of the reliability probability and the generation of the second data D2 are performed by the inference model 112 and the processor 113 of the inference device 11, respectively.

[0038] The second data D2 is input to a filter F. The filter F has a function of extracting, from the input second data D2, data to which a reliability probability exceeding a threshold has been assigned as third data D3. In the configuration illustrated in Fig. 1, the function of the filter F is realized by the processor 122 of the processing device 12.

[0039] The third data D3 is input to a calculator C. The calculator C has a function of determining a sudden change in condition score S, which indicates a risk of a sudden change in the subject's condition, based on the third data D3. In the configuration illustrated in FIG. 1, the function of the calculator C is realized by the processor 122 of the processing device 12.

[0040] The sudden change in condition score S is fed back to the filter F. The filter F also has a function of changing a threshold for extracting the third data D3 according to the sudden change in condition score S. The filter F lowers the threshold in response to a higher sudden change in condition score and raises the threshold in response to a lower sudden change in condition score. In the configuration illustrated in FIG. 1, this function is also realized by the processor 122 of the processing device 12.

[0041] According to the configuration described above, the monitoring sensitivity of the subject can be dynamically changed based on the sudden condition change score S, which indicates the risk of a sudden change in the condition of the subject, determined based on the measurement waveforms of the subject's biological parameters. In other words, it is possible to diversify the environment for evaluating the measurement waveforms of the biological parameters obtained from the subject.

[0042] 5 shows another example of a biological information processing method executed by the biological information processing system 10. In this example, a measured waveform of a first biological parameter and a measured waveform of a second biological parameter are acquired from a subject through at least one sensor. In this example, a case will be described in which the first biological parameter is a respiratory rate and the second biological parameter is a percutaneous arterial oxygen saturation (SpO2).

[0043] First data D11 corresponding to a measured waveform of a first biological parameter is acquired. The first data D11 is input to an inference model M1. The inference model M1 infers a reliability probability of the measured waveform corresponding to the first data D11. The inferred reliability probability is assigned to the first data D11 to generate second data D21. In the configuration illustrated in FIG. 1, the inference of the reliability probability and the generation of the second data D21 are performed by the inference model 112 and the processor 113 of the inference device 11, respectively.

[0044] The second data D21 is input to the filter F1. The filter F1 has a function of extracting, from the input second data D21, data to which a reliability probability exceeding a threshold is assigned as third data D31. In the configuration illustrated in FIG. 1, the function of the filter F1 is realized by the processor 122 of the processing device 12.

[0045] The third data D31 is input to the calculator C1. The calculator C1 has a function of determining a first sudden change score S1 indicating a risk of a sudden change in the first biological parameter based on the third data D31. When the first biological parameter is a respiratory rate, an evaluation value of the respiratory rate is specified as described above, and the first sudden change score S1 is determined, for example, based on the evaluation value and the following rule. A larger score value indicates a higher risk. 12-20 times per minute: 0 9-11 times per minute: 1 21-24 times per minute: 2 8 or less per minute or 25 or more per minute: 3

[0046] Similarly, first data D12 corresponding to the measured waveform of the second biological parameter is acquired. The first data D12 is input to the inference model M2. The inference model M2 infers the reliability probability of the measured waveform corresponding to the first data D12. The inferred reliability probability is assigned to the first data D12 to generate second data D22. In the configuration illustrated in FIG. 1, the inference of the reliability probability and the generation of the second data D22 are performed by the inference model 112 and the processor 113 of the inference device 11, respectively.

[0047] The second data D22 is input to the filter F2. The filter F2 has a function of extracting, from the input second data D22, data to which a reliability probability exceeding a threshold is assigned as third data D32. In the configuration illustrated in FIG. 1, the function of the filter F2 is realized by the processor 122 of the processing device 12.

[0048] The third data D32 is input to the calculator C2. The calculator C2 has a function of determining a second sudden change score S2 indicating a risk of a sudden change in the second biological parameter based on the third data D32. When the second biological parameter is SpO2, an evaluation value is specified in the same manner as the respiratory rate, and the second sudden change score S2 is determined, for example, based on the evaluation value and the following rules. A larger score value indicates a higher risk. 96+:0 94~95:1 92~93:2 91 and under: 3

[0049] The first sudden change score S1 and the second sudden change score S2 are input to a calculator C3. The calculator C3 has a function of determining a sudden condition change score S, which indicates a risk of a sudden change in the subject's condition, based on the first sudden change score S1 and the second sudden change score S2. In the configuration illustrated in FIG. 1, the function of the calculator C3 is realized by the processor 122 of the processing device 12.

[0050] In this example, the sudden change in condition score S may be determined based on the sum of the first sudden change score S1 and the second sudden change score S2. A larger value of the sudden change in condition score S indicates a higher risk of a change in condition.

[0051] The sudden change in condition score S is fed back to the filter F1 and the filter F2. The filter F1 also has a function of changing a threshold for extracting the third data D31 according to the sudden change in condition score S. The filter F2 also has a function of changing a threshold for extracting the third data D32 according to the sudden change in condition score S. Each of the filters F1 and F2 lowers the threshold in response to a higher sudden change in condition score and raises the threshold in response to a lower sudden change in condition score. In the configuration illustrated in FIG. 1, this function is also realized by the processor 122 of the processing device 12.

[0052] According to such a configuration, a more comprehensive assessment result of the risk of a change in the subject's condition based on a plurality of biological parameters can be reflected in a dynamic change in the monitoring sensitivity of the subject.

[0053] The number of types of biological parameters to be acquired may be three or more. In this case, the sudden change in condition score S to be determined may be determined based on rules defined in various early warning scores used to construct an in-hospital rapid response system. Examples of such evaluation scores include NEWS2 (National Early Warning Score 2), qSOFA (quick Sequential Organ Failure Assessment), and APACHE II (Acute Physiologic Assessment and Chronic Health Evaluation II). The types of biological parameters to be acquired are appropriately determined according to the score to be adopted.

[0054] 1, the biological information processing system 10 may include a user interface 15. The user interface 15 is configured to receive an instruction to change the weighting of each biological parameter when determining a sudden change in condition score S of a subject based on a plurality of biological parameters. The user interface 15 is configured to output weighting data W corresponding to the instruction. The user interface 15 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.

[0055] The weighting data W is received by the input interface 121 of the processing device 12. The weighting data W may be provided in the form of analog data or in the form of digital data, depending on the specifications of the user interface 15. When the weighting data W is provided in the form of analog data, the input interface 121 includes an appropriate conversion circuit including an A / D converter. This description is similarly applied to other data that can be received by the input interface 121, which will be described later.

[0056] In this case, the calculator C3 is configured to calculate the sudden change in condition score S by multiplying each of the first sudden change score S1 and the second sudden change score S2 by a coefficient defined by the weighting data W and then adding them together. For example, if the weighting data W is configured to increase the weighting of SpO2, the calculator C3 calculates the sudden change in condition score S by multiplying the second sudden change score S2 by a larger coefficient and then adding it to the first sudden change score S1.

[0057] According to such a configuration, it is possible to customize which of a plurality of bioparameters is to be emphasized for monitoring according to the attributes of the subject (age, sex, height, weight, medical history, medical condition, length of hospitalization, etc.) and the medical environment provided to the subject. This makes it possible to further increase the diversity of the environment for evaluating the measurement waveforms of the bioparameters obtained from the subject.

[0058] Such customization can also be achieved by another example of the biometric information processing method illustrated in Fig. 6. Elements common to the method illustrated in Fig. 5 are given the same reference numerals, and repeated explanations will be omitted.

[0059] In this example, the first sudden change score S1 calculated by the calculator C1 is fed back to the filter F1 in addition to the sudden change score S of the condition, and is used to change the threshold. Similarly, the second sudden change score S2 calculated by the calculator C2 is fed back to the filter F2 in addition to the sudden change score S of the condition, and is used to change the threshold.

[0060] In this example, the first sudden change score S1 and the second sudden change score S2 are each multiplied by a coefficient defined by weighting data W provided through the user interface 15, and then added to the sudden change in condition score S. For example, if the weighting data W is configured to increase the weighting of the respiratory rate, the first sudden change score S1 is multiplied by a larger coefficient before being added to the sudden change in condition score S, and the threshold value is changed according to the result.

[0061] Fig. 7 shows another example of a biometric information processing method executed by the biometric information processing system 10. Elements common to those in the method shown in Fig. 5 are given the same reference numerals, and repeated explanations will be omitted.

[0062] In addition to or instead of the method described with reference to Fig. 6, in this example, the first sudden change score S1 calculated by the calculator C1 is fed back to the filter F2 in addition to the sudden change score S in condition, and is used to change the threshold for extracting the third data D32. That is, a score indicating a sudden change risk of a certain biological parameter is referred to in order to determine a score indicating a sudden change risk of another biological parameter.

[0063] According to the configuration of this example, the strength of the correlation between the multiple biological parameters referenced to evaluate the risk of sudden change in the condition of the subject can be reflected in the processing. For example, when the first biological parameter has a strong correlation with the second biological parameter and the first biological parameter is determined to have a high risk of sudden change, the threshold value of the filter F2 can be lowered to increase the monitoring sensitivity of the second biological parameter. Therefore, the diversity of the environment for evaluating the measurement waveform of the biological parameter obtained from the subject can be further increased.

[0064] Although not shown in the figure, in addition to or instead of the feedback from the calculator C1 to the filter F2, the second sudden change score S2 calculated by the calculator C2 may be fed back to the filter F1 in addition to the sudden change in condition score S, and used to change the threshold for extracting the third data D31.

[0065] 1, the user interface 15 can be configured to receive information related to the medical environment provided to the subject 20, and output environmental data E corresponding to the information. Examples of the information related to the medical environment include the day of the week, the time period (daytime, nighttime), the proficiency of the medical staff, the number of medical staff, the distance from the nurse's station to the room in which the subject is located, and the like.

[0066] The environmental data E is received by the input interface 121 of the processing device 12. The environmental data E may be provided in the form of analog data or digital data depending on the specifications of the user interface 15.

[0067] The processor 122 is configured to change the threshold of the filter F used to extract the third data D3 according to the environmental data E. For example, when the environmental data E indicates that the medical resources (number of people, time) that can be provided to the subject are relatively few, processing may be performed to increase the threshold (reduce the monitoring sensitivity) to suppress frequent occurrence of alerts. This can further increase the diversity of the environment for evaluating the measurement waveforms of the biological parameters acquired from the subject.

[0068] The above description regarding the environmental data E can be similarly applied to the threshold of the filter F1 used to extract the third data D31 and the threshold of the filter F2 used to extract the third data D32.

[0069] 1, the processor 122 of the processing device 12 can be configured to output, from the output interface 123, display control data D for causing the output device 14 to display changes over time in the measured values ​​of the acquired biological parameters. The display control data D may be provided in the form of analog data or digital data, depending on the specifications of the output device 14.

[0070] In this case, the display control data D is configured to visualize the second data D2 and the third data D3 in a distinguishable manner while being synchronized in time. This realizes the display manner as exemplified in Figures 2 and 3. Examples of distinguishable manners include differences in shading, colors, and plot shapes.

[0071] According to this configuration, it is possible to easily visually confirm a dynamic change in the monitoring sensitivity based on a change in the threshold for extracting the third data D3.

[0072] The above explanation regarding the display control data D can be similarly applied to the visualization of the second data D21 and the third data D31 related to the first biometric parameter, as well as the visualization of the second data D22 and the third data D32 related to the second biometric parameter.

[0073] Each of the processor 113 of the inference device 11 and the processor 122 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 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.

[0074] Each of processor 113 of inference device 11 and processor 122 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 122 of processing device 12 may also be realized by a combination of a general-purpose microprocessor and a dedicated integrated circuit.

[0075] The configurations referred to above are merely examples for facilitating understanding of the present disclosure. Each configuration example may be appropriately modified or combined with other configuration examples within the scope of the present disclosure.

[0076] In the above example embodiment, reasoning device 11 and processing device 12 are described as separate devices. However, reasoning device 11 and processing device 12 may be implemented as different functional modules in a single device. In this case, output interface 114 of reasoning device 11 and input interface 121 of processing device 12 may be implemented as a logical interface rather than a hardware interface.

[0077] 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. [Explanation of symbols]

[0078] 12: Processing device, 121: Input interface, 122: Processor, 20: Subject, D1, D11, D12: First data, D2, D21, D22: Second data, D3, D31, D32: Third data, S: Sudden change in condition score, S1: First sudden change score, S2: Second sudden change score

Claims

1. acquiring first data corresponding to a measured waveform of at least one biological parameter of the subject; inferring a probability that the value of the biological parameter is correctly determined based on the first data; generating second data in which the probability is assigned to the measurement value of the biological parameter; extracting the second data to which the probability exceeding a threshold is assigned as third data; determining a sudden change in condition score representing a risk of a sudden change in the subject's condition based on the third data; Changing the threshold value based on the sudden change in condition score. Biometric information processing method.

2. The at least one biological parameter includes a first biological parameter and a second biological parameter; obtaining the first data, the second data, and the third data for each of the first biological parameter and the second biological parameter; determining a first acute change score representing a risk of an acute change in the first biological parameter based on the third data obtained for the first biological parameter; determining a second acute change score representing a risk of an acute change in the second biological parameter based on the third data obtained for the second biological parameter; determining the sudden change score based on the first sudden change score and the second sudden change score; A threshold value associated with a probability that the value of the first biological parameter is correctly calculated and a threshold value associated with a probability that the value of the second biological parameter is correctly calculated are changed based on the sudden change in condition score. The method for processing biological information according to claim 1 .

3. Varying a threshold associated with a probability that the value of the first biological parameter is correctly calculated based on the first sudden change score; Varying a threshold associated with a probability that the value of the second biological parameter is correctly calculated based on the second sudden change score; Do at least one of the following: The method for processing biological information according to claim 2 .

4. Varying a threshold associated with a probability that the value of the first biological parameter is correctly calculated based on the second sudden change score; Varying a threshold associated with a probability that the value of the second biological parameter is correctly calculated based on the first sudden change score; Do at least one of the following: The method for processing biological information according to claim 2 or 3.

5. Varying the threshold based on the medical environment provided to the subject. The method for processing biological information according to claim 1 .

6. visualizing the second data and the third data in a distinguishable manner while being synchronized in time; The method for processing biological information according to claim 1 .

7. an interface for receiving second data corresponding to a measurement value of at least one bioparameter of a subject, the second data being assigned a probability that the value of the bioparameter is correctly measured, the probability being inferred based on first data corresponding to a measurement waveform of the bioparameter; A processor that extracts the second data to which the probability of exceeding a threshold is assigned as third data, determines a sudden change in condition score representing a risk of a sudden change in the subject's condition based on the third data, and changes the threshold based on the sudden change in condition score; Equipped with Biometric information processing device.

8. A computer program executable by a processor installed in a biometric information processing device, By executing the above, the biometric information processing device receiving second data corresponding to a measurement value of at least one biological parameter of the subject, the second data being assigned a probability that the value of the biological parameter is correctly measured, the probability being inferred based on first data corresponding to a measurement waveform of the biological parameter; extracting the second data to which the probability exceeding a threshold is assigned as third data; determining a sudden change in condition score representing a risk of a sudden change in the subject's condition based on the third data; Changing the threshold value based on the sudden change in condition score. Computer program.

Images