Biological function estimation device and biological function estimation method

Abstract

A biological function estimation device includes a control unit that predicts a drug response of a patient based on an evaluation value obtained by evaluating a biological function of the patient according to a result of an examination before administration of a drug, and data of the drug administered to the patient, and corrects the evaluation value based on a comparison result of a predicted value obtained by the prediction and a measured value obtained by actually measuring the drug response after administration of the drug.

Description

TECHNICAL FIELD

[0001] The present application relates to a biological function estimation device and a biological function estimation method. BACKGROUND

[0002] A medicine administration system that measures and analyzes a value of blood of a patient, and calculates a medicine parameter is described in Patent Literature 1.

[0003] PRIOR ART DOCUMENT

[0004] PATENT LITERATURE

[0005] Patent Literature 1: Japanese Patent Application Laid-Open No. 2013-520718 SUMMARY

[0006] PROBLEMS TO BE SOLVED BY THE INVENTION

[0007] It is important to evaluate the renal function of a patient during hospitalization correctly and in real time in order to improve the therapeutic effect and suppress the occurrence of side effects such as renal dysfunction. However, in the conventional method, since blood examination is required each time, or there are problems in the characteristics or reliability of the index used for evaluation, the renal function evaluation cannot be sufficiently achieved.

[0008] An object of the present application is to evaluate the biological function of a patient with high accuracy without requiring examination each time.

[0009] MEANS FOR SOLVING THE PROBLEMS

[0010] A biological function estimation device according to one embodiment of the present application includes a control unit that predicts a medicine reaction of a patient based on an evaluation value obtained by evaluating the biological function of the patient according to a result of examination before administration of a medicine, and data of the medicine administered to the patient, and corrects the evaluation value according to a comparison result of a predicted value obtained by the prediction and a measured value obtained by measuring the medicine reaction after administration of the medicine.

[0011] According to one embodiment, the control unit changes at least either an equation or a coefficient used for calculating the evaluation value according to the comparison result.

[0012] According to one embodiment, the data includes at least either a kind of the medicine, a total amount of administration, or an administration amount per unit time.

[0013] According to one embodiment, the control unit predicts the medicine reaction for administration of the medicine at each of a plurality of time points, and corrects the evaluation value according to a comparison result of a new predicted value obtained by the prediction and a new measured value obtained by measuring the medicine reaction after administration of the medicine.

[0014] As one embodiment, the aforementioned control section predicts the aforementioned drug reaction based on a corrected value of the aforementioned evaluation value obtained for the drug administration at the aforementioned first time point and data of the drug administered to the aforementioned patient at a second time point after the aforementioned first time point, and further corrects the aforementioned evaluation value according to a comparison result of a new predicted value obtained and a new measured value obtained by actually measuring the aforementioned drug reaction after the drug administration.

[0015] As one embodiment, the aforementioned control section records a corrected value of the aforementioned evaluation value obtained for the drug administration at each of the aforementioned plurality of time points as a provisional correction value, and further corrects the aforementioned evaluation value using a plurality of provisional correction values recorded.

[0016] As one embodiment, the aforementioned control section sets a pattern of the drug administration at each of the aforementioned plurality of time points.

[0017] As one embodiment, the aforementioned control section adjusts the aforementioned pattern after the next time point according to a comparison result of a new predicted value obtained for the drug administration at any one of the aforementioned plurality of time points and a new measured value.

[0018] As one embodiment, the aforementioned control section selects a pattern candidate that differs according to each time point as the aforementioned pattern from among a predetermined pattern candidate group.

[0019] As one embodiment, the aforementioned control section sets the aforementioned pattern by setting at least either of the number of times of administration of the drug and the administration amount per unit time.

[0020] As one embodiment, the aforementioned control section sets the aforementioned pattern by setting the timing of administration of the drug.

[0021] As one embodiment, the aforementioned control section refers to actual data indicating a history of past drug administration and at least either of a predicted value and a measured value and a corrected value of an evaluation value when setting the aforementioned pattern.

[0022] As one embodiment, the history indicated in the aforementioned actual data includes a history of another patient.

[0023] As one embodiment, the aforementioned control section adjusts the timing of measurement of the aforementioned drug reaction according to the aforementioned pattern.

[0024] As one embodiment, the aforementioned control section refers to process data indicating a history of past drug administration and drug reaction when predicting the aforementioned drug reaction.

[0025] As one implementation, the history shown in the aforementioned process data includes the history of other patients.

[0026] As one implementation, the aforementioned control unit controls the pump that administers the medication to the aforementioned patient.

[0027] In one embodiment, the aforementioned control unit controls the sensor that measures the reaction of the aforementioned pharmaceutical agent.

[0028] As one embodiment, the aforementioned biological function estimation device also includes an output unit that outputs a corrected value of the aforementioned evaluation value.

[0029] In one implementation, the aforementioned control unit obtains the aforementioned inspection results and calculates the aforementioned evaluation value based on the aforementioned inspection results.

[0030] In one implementation, the aforementioned evaluation value is a value obtained by evaluating kidney function as a function of the aforementioned organism, and the aforementioned control unit predicts the amount of urine as a response to the aforementioned drug.

[0031] As one aspect of the present invention, the method for estimating biological function involves using a computer to predict the patient's drug response based on an evaluation value obtained from evaluating the patient's biological function according to the examination results before drug administration and data on the drug administered to the patient; administering the drug to the patient using a pump; measuring the drug response after drug administration using a sensor; and correcting the evaluation value using the computer based on a comparison between the predicted value and the measured value.

[0032] The effects of the invention

[0033] According to the present invention, it is possible to evaluate a patient's biological functions with high precision without requiring each examination. Attached Figure Description

[0034] [ Figure 1 [A diagram illustrating the structure and function of a system as one embodiment of the present invention.]

[0035] [ Figure 2 [A block diagram illustrating the configuration of a biological function estimation device as one aspect of the present invention.]

[0036] [ Figure 3 [A diagram illustrating the structure and function of the system according to the first embodiment.]

[0037] [ Figure 4 [A flowchart illustrating the operation of the organism function estimation device according to the first embodiment.]

[0038] [ Figure 5 [A diagram illustrating the structure and function of the system according to the second embodiment.]

[0039] [ Figure 6 ] is a flowchart showing the operation of the living body function estimation device according to the second embodiment.

[0040] [ Figure 7 ] is a diagram showing the configuration and functions of the system according to the third embodiment.

[0041] [ Figure 8 ] is a flowchart showing the operation of the living body function estimation device according to the third embodiment.

[0042] [ Figure 9 ] is a diagram showing the configuration and functions of the system according to the fourth embodiment.

[0043] [ Figure 10 ] is a flowchart showing the operation of the living body function estimation device according to the fourth embodiment. DETAILED DESCRIPTION

[0044] Hereinafter, the present application will be described with reference to the drawings.

[0045] In each drawing, the same or corresponding parts are given the same reference numerals. In the description of each embodiment, the description of the same or corresponding parts is appropriately omitted or simplified.

[0046] The structure of the system 10 as one embodiment of the present application will be described with reference to FIG. 1. Figure 1

[0047] Figure 1 The system 10 shown in FIG. 1 is provided with a living body function estimation device 20, a database 30, a pump 40, and a sensor 50.

[0048] The living body function estimation device 20 is connected to and capable of communicating with the database 30, the pump 40, and the sensor 50 directly or via a network such as a LAN. "LAN" is an abbreviation for Local Area Network.

[0049] As an example, the living body function estimation device 20 can be provided in a hospital, but can also be provided in other facilities such as a data center. The living body function estimation device 20 is a general-purpose computer such as a PC or a server computer, or a special-purpose computer. "PC" is an abbreviation for Personal Computer.

[0050] ​The database 30 is provided in a hospital, for example, but can be provided in another facility such as a data center. The database 30 is an RDBMS, for example. "RDBMS" is an abbreviation for relational database management system. The database 30 is separate from the living body function estimation device 20, for example, but can be integrated with the living body function estimation device 20.

[0051] The pump 40 is provided in a hospital. The pump 40 is an infusion pump or a syringe pump, for example. The pump 40 can also be a smart pump.

[0052] The sensor 50 is provided in a hospital. The sensor 50 is a urine volume sensor, a body temperature sensor, a blood pressure sensor, a pulse sensor, or a respiration sensor, for example.

[0053] Reference Signs List Figure 2 The structure of the living body function estimation device 20 as one embodiment of the present application will be described.

[0054] The living body function estimation device 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, and an output unit 25.

[0055] The control unit 21 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU or a GPU, or a dedicated processor specialized in a specific process. "CPU" is an abbreviation for central processing unit. "GPU" is an abbreviation for graphics processing unit. The dedicated circuit is an FPGA or an ASIC, for example. "FPGA" is an abbreviation for field-programmable gate array. "ASIC" is an abbreviation for application specific integrated circuit. The control unit 21 controls each unit of the living body function estimation device 20 while executing a process related to the operation of the living body function estimation device 20.

[0056] The storage section 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of them. The semiconductor memory is, for example, a RAM or a ROM. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read only memory. The RAM is, for example, an SRAM or a DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. The ROM is, for example, an EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read only memory. The storage section 22 functions as, for example, a main storage device, an auxiliary storage device, or a CPU cache. In the storage section 22, data used for the operation of the living body function estimation device 20 and data obtained by the operation of the living body function estimation device 20 are stored. The database 30 can also be integrated with the living body function estimation device 20 by being constructed in the storage section 22.

[0057] The communication section 23 includes at least one communication interface. The communication interface is, for example, a LAN interface. The communication section 23 receives data used for the operation of the living body function estimation device 20, and additionally transmits data obtained by the operation of the living body function estimation device 20.

[0058] The input section 24 includes at least one input interface. The input interface is, for example, a physical key, a capacitive key, a click device, a touch screen provided integrally with a display, or a microphone. The input section 24 accepts an operation that inputs data used for the operation of the living body function estimation device 20. The input section 24 can also be connected to the living body function estimation device 20 as an external input device instead of being provided to the living body function estimation device 20. As a connection method, for example, any of a USB, an HDMI (registered trademark), or Bluetooth (registered trademark) or the like can be used. "USB" is an abbreviation for Universal Serial Bus. "HDMI" (registered trademark) is an abbreviation for High-Definition Multimedia Interface.

[0059] The output section 25 includes at least one output interface. The output interface is, for example, a display or a speaker. The display is, for example, an LCD or an organic EL display. "LCD" is an abbreviation for liquid crystal display. "EL" is an abbreviation for electro luminescence. The output section 25 outputs data obtained by the operation of the living body function estimation device 20. The output section 25 can also be connected to the living body function estimation device 20 as an external output device instead of being provided to the living body function estimation device 20. As a connection method, for example, any of USB, HDMI (registered trademark), Bluetooth (registered trademark), or the like can be used.

[0060] The functions of the living body function estimation device 20 are realized by executing a program as one embodiment of the present application with a processor corresponding to the control section 21. That is, the functions of the living body function estimation device 20 are realized by software. The program causes a computer to function as the living body function estimation device 20 by causing the computer to execute the operation of the living body function estimation device 20. That is, the computer functions as the living body function estimation device 20 by executing the operation of the living body function estimation device 20 according to the program.

[0061] The program can be stored in a non-transitory computer readable medium. The non-transitory computer readable medium is, for example, a magnetic recording device, an optical disk, a magneto-optical recording medium, or a ROM. The distribution of the program is performed, for example, by selling, transferring, or renting a removable medium such as a DVD or a CD-ROM on which the program is stored. "DVD" is an abbreviation for digital versatile disc. "CD-ROM" is an abbreviation for compact disc read only memory. The program can also be distributed by storing the program in advance in a storage of a server and transmitting the program from the server to another computer. The program can also be provided as a program product.

[0062] For example, a program stored in a removable medium or a program transmitted from a server is temporarily stored in a main storage device of a computer. Then, the computer reads the program stored in the main storage device by a processor, and executes processing according to the read program by the processor. The computer can also directly read a program from a removable medium and execute processing according to the program. Whenever a program is transmitted from a server to a computer, the computer can execute processing according to the received program. The transmission of a program from a server to a computer can not be performed, and processing can be executed by a so-called ASP type of service in which only the execution of instructions and the acquisition of results are implemented. "ASP" is an abbreviation for application service provider. Information for use in processing by an electronic computer is included in a program, and is data based on the program. For example, data having the nature of specifying the processing of a computer, although not direct instructions to the computer, belongs to "data based on a program".

[0063] Part or all of the functions of the living body function estimation device 20 can also be implemented by a dedicated circuit corresponding to the control section 21. That is, part or all of the functions of the living body function estimation device 20 can also be implemented by hardware.

[0064] Reference Figure 1 and Figure 2 A function of the system 10 as one embodiment of the present application is described. The function corresponds to a living body function estimation method as one embodiment of the present application.

[0065] The database 30 holds in-hospital data such as device measurement values, examination data, and electronic medical record data. The examination data includes examination results before administration of a drug.

[0066] The control section 21 of the living body function estimation device 20 acquires in-hospital data from the database 30 via the communication section 23. The control section 21 evaluates the living body function of a patient according to the examination results before administration of a drug included in the in-hospital data. As a result, an evaluation value Ve is obtained. The living body function is, for example, an internal organ function such as a renal function, a cardiac function, a pulmonary function, or a hepatic function. In the evaluation of the living body function, not only the examination results before administration of a drug but also device measurement values and electronic medical record data before administration of a drug included in the in-hospital data can be used. As one modification, the living body function of a patient can also be evaluated by a device different from the living body function estimation device 20. That is, the control section 21 of the living body function estimation device 20 can also acquire an evaluation value Ve from another device that evaluates the living body function of a patient according to the examination results before administration of a drug via the communication section 23.

[0067] The control section 21 of the living body function estimation device 20 acquires data Dm of a medicine administered to a patient from the pump 40 or a device that monitors and controls the pump 40 via the communication section 23. The data Dm includes at least any one of a kind of the medicine, a total amount of administration, and an administration amount per unit time.

[0068] The control section 21 of the living body function estimation device 20 predicts a medicine response of the patient on the basis of the evaluation value Ve and the data Dm of the medicine. As a result, a predicted value Vp is obtained. The medicine response is, for example, a vital sign such as urine volume, body temperature, blood pressure, pulse, or respiration, or a change in the vital sign.

[0069] The pump 40 administers the medicine to the patient. The sensor 50 actually measures the medicine response after the medicine administration. As a result, an actually measured value Vm is obtained.

[0070] The control section 21 of the living body function estimation device 20 acquires the actually measured value Vm from the sensor 50 via the communication section 23.

[0071] The control section 21 of the living body function estimation device 20 corrects the evaluation value Ve on the basis of a comparison result of the predicted value Vp and the actually measured value Vm.

[0072] According to the above-described manner, the living body function of the patient can be evaluated with high accuracy without performing an examination each time.

[0073] Hereinafter, a number of embodiments of a specific example of the manner shown in Figure 1 and Figure 2 will be described with reference to the drawings.

[0074] (First Embodiment)

[0075] In the present embodiment, as shown in Figure 3 , the in-hospital data held by the database 30 includes a blood examination value as a result of an examination before the medicine administration. The blood examination value included in the in-hospital data is, for example, Cre, BUN / Cre, eGFR, Alb, or an inflammation marker. "Cre" is a value of creatinine. "BUN / Cre" is a value obtained by dividing a concentration of urea nitrogen contained in blood by a concentration of creatinine. "eGFR" is an estimated glomerular filtration rate. "Alb" is a value of albumin. The blood examination value included in the in-hospital data can also be Cys-C. "Cys-C" is a value of serum cystatin C. The electronic medical record data included in the in-hospital data is, for example, blood pressure or pulse.

[0076] In the present embodiment, the evaluation value Ve is a value obtained by evaluating the renal function as the biological function. The evaluation value Ve is, for example, GFR or eGFR. "GFR" is glomerular filtration rate. The control unit 21 of the biological function estimation device 20 predicts the urine volume per unit time as a drug reaction. The sensor 50 actually measures the urine volume per unit time as a drug reaction. That is, the sensor 50 is a urine volume sensor.

[0077] Referring to Figure 4 The operation of the biological function estimation device 20 according to the present embodiment will be described.

[0078] In step S101, the control unit 21 acquires the test results before the administration of the drug. Specifically, the control unit 21 collects, from the database 30 via the communication unit 23, the data for evaluation of the renal function such as the blood test values and the electronic medical record data included in the in-hospital data. As one modification, the control unit 21 can also accept the data for evaluation of the renal function input by the user such as a doctor or a nurse via the input unit 24 such as a touch panel. Alternatively, the control unit 21 can also accept the presence or absence of a disease such as thyroid dysfunction or a malignant tumor disease that should be considered at the time of evaluation of the renal function via the electronic medical record data or the input unit 24 such as a touch panel.

[0079] In step S102, the control unit 21 evaluates the renal function of the patient before the administration of the drug on the basis of the test results acquired in step S101. That is, the control unit 21 calculates the evaluation value Ve on the basis of the test results before the administration of the drug. For example, the control unit 21 calculates GFR or eGFR by substituting the values of the blood test values and the values of the electronic medical record data included in the data collected in step S101 into the formula for evaluation of the renal function. Alternatively, the control unit 21 can calculate GFR by multiplying eGFR included in the data collected in step S101 by a coefficient. In the case of the former, the information that is not numerically expressed such as the presence or absence of a disease is substituted into the formula after being normalized or numerically expressed into the state in which it can be substituted into the formula. The control unit 21 stores the obtained evaluation value Ve in the storage unit 22.

[0080] After step S102, if the number of times of administration of the drug does not reach the threshold value Vt, the process of step S103 is performed. The threshold value Vt can be any value of 1 or more, but in the present embodiment, it is set to a value of 2 or more.

[0081] In step S103, the control unit 21 acquires the data Dm of the drug to be administered to the patient. Specifically, the control unit 21 acquires the data Dm of the drug to be administered from the pump 40 or a device that monitors and controls the pump 40 via the communication unit 23. As one modification, the control unit 21 can also accept the data Dm of the drug input by the user such as a doctor or a nurse via the input unit 24 such as a touch panel.

[0082] In step S104, the control section 21 predicts the urine volume per unit time as a drug response associated with the renal function of the patient on the basis of the evaluation value Ve obtained in step S102 and the data Dm of the drug acquired in step S103. Specifically, the control section 21 refers to a table stored in advance in the storage section 22 to determine a predicted value Vp corresponding to the combination of the evaluation value Ve and the data Dm of the drug, in which at least any one of the kind of the drug, the total amount of administration, and the administration amount per unit time is included. Alternatively, the control section 21 substitutes the evaluation value Ve and the data Dm of the drug, in which at least any one of the kind of the drug, the total amount of administration, and the administration amount per unit time is included, into a formula defined in advance to calculate the predicted value Vp.

[0083] In step S105, after the administration of the drug for a certain time using the pump 40, the control section 21 acquires a result of actually measuring the urine volume per unit time as a drug response associated with the renal function of the patient using the sensor 50. Specifically, the control section 21 acquires the measured value Vm from the sensor 50 via the communication section 23. As a modification, the control section 21 can also accept the measured value Vm input by the user such as a doctor or a nurse via the input section 24 such as a touch panel.

[0084] In step S106, the control section 21 corrects the evaluation value Ve obtained in step S102 on the basis of the comparison result of the predicted value Vp obtained in step S104 and the measured value Vm obtained in step S105. Specifically, the control section 21 changes at least any one of the formula and the coefficient used in step S102 to calculate the evaluation value Ve on the basis of the comparison result of the predicted value Vp and the measured value Vm. For example, the control section 21 corrects the formula for the evaluation of the renal function applied in step S102 to reduce the difference between the predicted value Vp and the measured value Vm. Alternatively, in the case where a plurality of formulas for the evaluation of the renal function can be applied in step S102, the control section 21 reselects the formula to be used to reduce the difference between the predicted value Vp and the measured value Vm. Alternatively, the control section 21 corrects the coefficient by which the eGFR is multiplied in step S102 to reduce the difference between the predicted value Vp and the measured value Vm. Then, in step S102, the control section 21 recalculates the evaluation value Ve using at least any one of the corrected formula and the coefficient. For example, the control section 21 recalculates the GFR or the eGFR by substituting the blood test value included in the data collected in step S101 and the value of the electronic medical record data into the corrected formula for the evaluation of the renal function. That is, the control section 21 corrects the GFR or the eGFR. Alternatively, the control section 21 recalculates the GFR by multiplying the eGFR included in the data collected in step S101 by the corrected coefficient. That is, the control section 21 corrects the GFR. The control section 21 overwrites the evaluation value Ve stored in the storage section 22 with the corrected value.

[0085] After the step S102, if the number of times of administration of the medicine reaches the threshold value Vt, the process of the step S107 is performed.

[0086] In the step S107, the output section 25 outputs the corrected value of the evaluation value Ve. Specifically, the control section 21 causes the output section 25 such as a display to display the corrected value of the evaluation value Ve stored in the storage section 22.

[0087] In the present embodiment, since the threshold value Vt is set to a value of 2 or more, the medicine is administered to the patient at a plurality of time points. The control section 21 predicts the medicine reaction with respect to the administration of the medicine at each of the plurality of time points, and corrects the evaluation value Ve based on the comparison result of the new predicted value Vp and the new measured value Vm obtained by actually measuring the medicine reaction after the administration of the medicine. Specifically, the control section 21 predicts the medicine reaction based on the corrected value of the evaluation value Ve obtained with respect to the administration of the medicine at the first time point among the plurality of time points and the data Dm of the medicine administered to the patient at the second time point after the first time point, and further corrects the evaluation value Ve based on the comparison result of the new predicted value and the new measured value Vm obtained by actually measuring the medicine reaction after the administration of the medicine at the second time point.

[0088] For example, the control section 21 corrects the evaluation value Ve with respect to the administration of the medicine at the time point Tl by the processes of the steps S103 to S106. As a result, the corrected value of the evaluation value Ve is obtained in the step S102. The control section 21 corrects the corrected value of the evaluation value Ve with respect to the administration of the medicine at the subsequent time point T2 by the processes of the steps S103 to S106. That is, the control section 21 further corrects the evaluation value Ve. As a result, the further corrected value of the evaluation value Ve is obtained in the step S102. When the threshold value Vt = n and n > 2, the control section 21 further corrects the evaluation value Ve with respect to the administration of the medicine at each of the subsequent time points T3 to Tn by the processes of the steps S103 to S106. In this way, in the present embodiment, the control section 21 recursively corrects the evaluation value Ve.

[0089] As one modification of the present embodiment, the control section 21 can record the corrected value of the evaluation value Ve obtained with respect to the administration of the medicine at each of the plurality of time points as a provisional correction value, and further correct the evaluation value Ve using the recorded plurality of provisional correction values.

[0090] For example, the control section 21 recursively corrects the evaluation value Ve by performing the processes of steps S103 to S106 for the administration of the medicine at one or more time points. In step S107, the control section 21 records the value of the recursively corrected evaluation value Ve as a provisional correction value C1. The control section 21 recursively corrects the evaluation value Ve by performing the processes of steps S103 to S106 for the administration of the medicine at one or more other time points. In step S107, the control section 21 records the value of the recursively corrected evaluation value Ve as a provisional correction value C2. As a result, a plurality of provisional correction values are recorded. The number of provisional correction values can also be three or more. The control section 21 determines the final output value of the evaluation value Ve using these plurality of provisional correction values. That is, the control section 21 further corrects the evaluation value Ve. As a method of determining the final output value, any method can be used, such as calculation of an average value, calculation of a median value, univariate regression analysis, multivariate regression analysis, polynomial regression, or regularization.

[0091] As described above, in the present embodiment, the control section 21 of the living body function estimation device 20 predicts the urine volume of the patient on the basis of the evaluation value Ve obtained by evaluating the renal function of the patient on the basis of the results of the examination before the administration of the medicine and the data Dm of the medicine administered to the patient. The control section 21 corrects the evaluation value Ve on the basis of the comparison result of the obtained predicted value Vp and the measured value Vm obtained by actually measuring the urine volume after the administration of the medicine.

[0092] According to the present embodiment, it is possible to evaluate the renal function of the patient with high accuracy without performing an examination each time.

[0093] In the present embodiment, whether to perform the process of step S103 or the process of step S107 is selected on the basis of whether the number of times of administration of the medicine reaches the threshold value Vt, but the difference between the predicted value Vp and the measured value Vm can be used instead of the number of times of administration of the medicine. That is, the process of step S103 can be selected in a case where the difference between the predicted value Vp and the measured value Vm is greater than a certain threshold value, and the process of step S107 can be selected in a case where the difference is equal to or less than the certain threshold value.

[0094] Alternatively, both a threshold value Vt for the number of times of administration of the medicament and a threshold value for the difference between the predicted value Vp and the measured value Vm can be used. In this case, the condition for selecting the process of step S107 can be set to a case where both thresholds are satisfied, and in a case where the difference between the predicted value Vp and the measured value Vm is not smaller than a certain threshold value, the process of step S107 can be selected if the threshold value Vt for the number of times of administration of the medicament is satisfied. Further, even if the threshold value Vt for the number of times of administration of the medicament is not satisfied, the process of step S107 can be selected in a case where the difference between the predicted value Vp and the measured value Vm is not smaller than a certain threshold value. By combining the two threshold values as such, the upper limit value of the time required for outputting the renal function evaluation value can be set in coordination with the use scenario, while obtaining a renal function evaluation value with high accuracy.

[0095] The most accurate index of renal function evaluation is GFR obtained by measuring the inulin excretion rate of the glomerulus. However, inulin does not exist in the body. Therefore, for measurement, inulin needs to be administered by drip infusion, and strict urine collection or complete urination, and multiple blood sampling are required. Thus, the measurement of GFR is very complicated and accompanied by patient burden. Therefore, in clinical practice, GFR is not used except in cases where strict function evaluation is required for patients with renal disease or renal transplant donors, and the like.

[0096] Currently, a surrogate marker is used. eCCr calculated using the serum concentration of creatinine, which is an excretion from a living body, body weight, age, and gender, as an estimated formula is used. Alternatively, eGFR calculated from serum Cre, age, and gender is used. "eCCr" is an estimated creatinine clearance rate. As a measured value, there is measured CCr, but the measurement of CCr requires blood sampling and correct measurement of 24-hour urine volume. Therefore, in general, cases where CCr is measured for the purpose of obtaining a dosing guideline are extremely rare in clinical practice. "CCr" is a creatinine clearance rate.

[0097] As a result, measurement of serum Cre and calculation of eCCr or eGFR are performed as renal function evaluation in clinical practice. However, since these methods require blood tests, there is a problem that the frequency of implementation is limited and real-time renal function evaluation cannot be performed. Also, there is a problem that the calculated eCCr or eGFR is not correct. Unlike dextran, creatinine is not only filtered in the glomerulus but also secreted in the renal tubule, and thus CCr is about 20 to 30% higher than GFR. In addition, in sarcopenic patients in which the muscle mass is reduced and many elderly people, a decrease in renal function is not detected for serum Cre. That is, it appears that the renal function is good. In people over 85 years old, more than 50% have sarcopenia. The number of patients in Japan is about 3.7 million. In addition, in the ICU, even young patients have a decrease in muscle mass due to the need for temporary bed rest. For such patients, if serum Cre is used to calculate eCCr or eGFR, the evaluation value of renal function is calculated to be higher than the true value. "ICU" is an abbreviation for intensive care unit.

[0098] If the renal function is not properly evaluated and administered, there is a risk of side effects or a risk of drug-induced renal damage due to the administration of a normal amount of a renal excretion type drug to a patient with a decreased renal function. In particular, when the calculated eCCr or eGFR is about 60 mL / min to 100 mL / min, which is a value that is difficult to judge as being too large, administration becomes difficult. For example, in patients with CKD, proper renal function evaluation is particularly required. "CKD" is an abbreviation for chronic kidney disease.

[0099] In addition, as renal function evaluation performed in clinical practice, there are Cys-C or BUN / Cre, but like Cre, eCCr, and eGFR, blood tests are required each time, and thus real-time renal function evaluation is not suitable. In addition, there are problems with measurement accuracy.

[0100] Serum cystatin C is expressed throughout the body, and its production amount and speed are fixed and are not easily influenced by external factors such as inflammation and age. Also, cystatin C secreted to the extracellular space is 99% reabsorbed in the proximal tubule after being filtered by the glomerulus in a short time and is catabolized, and thus does not recirculate into the blood. Therefore, it is considered that serum Cys-C is determined by the glomerular filtration rate. However, it is known that the prediction accuracy of eGFR decreases in patients with end-stage renal failure. In addition, it has also been shown that in patients who are administered a large amount or a long period of steroids, serum Cys-C is higher than the true value. Also, serum Cys-C is affected by the presence of thyroid dysfunction and some malignant tumor diseases.

[0101] As for BUN / Cre, since serum CCr is used, the same problem as serum CCr is present.

[0102] According to the present embodiment, by employing one or more feedback systems, it is possible to more accurately estimate renal function without using blood tests. Also, since the feedback is performed in real time, it is possible to accurately and in real time evaluate the renal function of a patient during hospitalization.

[0103] (2nd Embodiment)

[0104] The differences from the 1st embodiment will be mainly described.

[0105] In the present embodiment, as shown in Figure 5 , in order to improve the accuracy of evaluation of renal function, a correction of the most suitable evaluation value Ve is estimated, and the mode of administration of the drug is instructed in accordance with the estimated mode. As the mode of administration of the drug, at least either one of a mode in which the drug is incrementally increased from a low dosage in stages, and a mode in which the drug is incrementally decreased from a high dosage in stages, is selected within the range of a prescribed prescription. Thus, the total amount of the administered drug conforms to the prescription.

[0106] The operation of the living body function estimation device 20 of the present embodiment will be described with reference to Figure 6 .

[0107] As for the processes of steps S201 to S206, since they are the same as the processes of steps S101 to S106 of the 1st embodiment, the description thereof will be omitted.

[0108] In step S207, the control section 21 adjusts the mode of administration of the drug for the next time and thereafter, based on the comparison result of the predicted value Vp obtained in step S204 and the measured value Vm obtained in step S205. Specifically, the control section 21 controls the pump 40 to set the mode of administration of the drug to the above-described mode by setting at least either one of the number of times of administration of the drug and the amount of administration per unit time.

[0109] In the present embodiment, the control section 21 adjusts the mode of administration of the drug in step S207 with reference to a plurality of modes of administration of the drug which are stored in advance in the storage section 22. Since the predicted value Vp obtained in step S202 continues to fluctuate, even in a case where the difference between the predicted value Vp and the measured value Vm does not converge even if the processes of steps S202 to S206 are repeated, it is possible to select the most suitable mode of administration of the drug to obtain a stable predicted value Vp.

[0110] When the predicted value Vp obtained in step S202 greatly varies each time the processes of steps S202 to S206 are performed, a primary factor is sometimes that the magnitude of the measured value Vm obtained in step S205 is inappropriate. In a case where the urine volume per unit time as the measured value Vm is too small, the measurement value is easily deviated by an error in measurement, and thus the predicted value Vp calculated on this basis is deviated. On the other hand, in a case where the urine volume per unit time is too large, since the variation amount of the urine volume generated during the processes of repeating steps S201 to S206 also becomes large, the predicted value Vp greatly varies. The urine volume per unit time depends on the balance between the renal function and the amount of administration of the drug. Therefore, within the range of a prescribed prescription, by implementing the administration of the drug from a low amount stage by stage or the administration of the drug from a high amount stage by stage, a measurement point at which the urine volume is neither too small nor too large can be obtained, and as a result, a stable predicted value Vp can be obtained.

[0111] The storage section 22 stores a plurality of drug administration patterns, and both the administration of the drug from a low amount stage by stage and the administration of the drug from a high amount stage by stage are possible. Further, for example, even in a case where the drug is administered from a low amount stage by stage, various drug administration patterns in which the time length of maintaining the low amount and the high amount is different can be selected. Then, by using the most suitable drug administration pattern, within the range in which the necessary drug effect is not inhibited, a measurement point at which the most suitable measured value Vm can be obtained in order to obtain the predicted value Vp can be obtained more.

[0112] As the drug administration pattern in step S207, the most suitable drug administration pattern is automatically selected in accordance with the difference between the predicted value Vp obtained in step S204 and the measured value Vm obtained in step S205, the magnitude of the measured value Vm itself, and the variation amount of the measured value Vm. Further, based on the state of the patient or the actual situation in the past, or the like, the drug administration pattern to be used or the drug administration pattern not to be used can be designated through the input section 24 such as a touch panel, and the drug administration pattern to be used preferentially can also be set in advance.

[0113] In the present embodiment, the control section 21 saves the measured value Vm in the storage section 22, and calculates the variation amount of the measured value Vm. As a method of calculating the variation amount, a method of finding the difference from the previous value, a method of using the time derivative of the measured value Vm, or a method of evaluating the standard deviation or the bias, or the like, a generally used calculation method can be used.

[0114] The process of step S208 is the same as the process of step S107 of the first embodiment, and thus the description is omitted.

[0115] As described above, in the present embodiment, the control section 21 sets the mode of the medicament administration at each of the plurality of time points. Specifically, the control section 21 adjusts the mode of the medicament administration after the next time point, based on the comparison result of the new predicted value Vp and the new measured value Vm obtained for the medicament administration at any one of the plurality of time points.

[0116] According to the present embodiment, even in the case where the measured value Vm temporarily deviates from the appropriate range on the basis of the predicted value Vp and the predicted value Vp continues to fluctuate, since the most appropriate medicament administration mode can be selected to obtain a stable predicted value Vp, the estimation accuracy of the renal function and the measurement efficiency are improved.

[0117] In the present embodiment, whether to perform the process of step S203 or the process of step S208 is selected based on whether the number of medicament administrations reaches the threshold value Vt, but instead of the number of medicament administrations, the difference between the predicted value Vp and the measured value Vm can be used as in the first embodiment. Alternatively, both the threshold value Vt for the number of medicament administrations and the threshold value for the difference between the predicted value Vp and the measured value Vm can be used. In any case, an appropriate medicament administration mode can be selected by the process of step S207 based on the difference between the predicted value Vp and the measured value Vm, or the magnitude or fluctuation of the measured value Vm itself.

[0118] As one modification of the present embodiment, the control section 21 can select a different mode candidate for each time point from among a predetermined set of mode candidates as the mode of the medicament administration.

[0119] As one modification of the present embodiment, the control section 21 can refer to actual data Da indicating the history of at least any one of past medicament administrations, and the corrected values of the predicted value Vp and the measured value Vm, and the evaluation value Ve when setting the mode of the medicament administration. The history shown in the actual data Da can include the history of other patients.

[0120] (Third Embodiment)

[0121] The differences from the first embodiment will mainly be described.

[0122] In the present embodiment, as shown in Figure 7 in order to improve the evaluation accuracy of the renal function, the mode of the medicament administration most suitable for the correction of the evaluation value Ve is estimated, the medicament administration is instructed in accordance with the estimated mode, and the timing of the measurement of the urine volume is instructed. In the mode of the medicament administration, the increase or decrease of the administration amount within the prescribed prescription, and the step of bolus administration or stop of administration of a fixed amount of medicament are included, and the mode of the step in which the measurement is repeatedly performed using the sensor 50 is selected in accordance with the change of these medicament administration modes.

[0123] Reference Figure 8 The operation of the living body function estimation device 20 of the present embodiment will be described.

[0124] In the present embodiment, the estimation formula for calculating the evaluation value Ve from the comparison result of the predicted value Vp and the measured value Vm in step S302, and a plurality of combinations of the medication administration modes corresponding to the estimation formula are stored in the storage section 22. Then, by selecting the most suitable medication administration mode, a higher-precision evaluation value Ve can be obtained.

[0125] As for the processes of steps S301 to S306, the same as the processes of steps S101 to S106 of the first embodiment, the description is omitted.

[0126] In step S307, the control section 21 adjusts the mode of the medication administration thereafter, based on the comparison result of the predicted value Vp obtained in step S304 and the measured value Vm obtained in step S305. Specifically, the control section 21 controls the pump 40 to set at least either one of the number of times of the medication administration and the administration amount per unit time of the medication, and sets the mode of the medication administration to the above-described mode by setting the timing of the medication administration. As the timing of the medication administration, not only the time point of the medication administration can be set, but also whether to stop the medication administration in the continuous administration, or whether to administer the medication again in the case of the stop can be set.

[0127] The urine volume per unit time depends on the balance between the renal function and the amount of the agent administered. In the case of the agent being a diuretic, the urine volume per unit time is generally increased by increasing the amount of the diuretic administered, but the increase trend varies. The increase trend is expressed in terms of the slope or the plotted shape when the amount of the diuretic administered is plotted on the horizontal axis and the urine volume on the vertical axis, the continuity of the change, or the presence or absence of a threshold. The increase trend is closely related to the desired renal function. Therefore, in the combination of the predicted value Vp and the measured value Vm for the responsiveness of the urine volume to the rapid administration of the diuretic, the combination of the predicted value Vp and the measured value Vm for the responsiveness of the urine volume to the stop of the administration, and the combination of the predicted value Vp and the measured value Vm for the fluctuation of the urine volume to the intentional increase and decrease of the amount of the administered diuretic, different convergence patterns of the difference between the predicted value Vp and the measured value Vm are obtained, respectively. Then, different evaluation values Ve are obtained from the three patterns, respectively. Depending on the difference in the mode of the administration of the agent, the degree of convergence of the difference between the predicted value Vp and the measured value Vm also differs, and thus the estimation accuracy as the renal function evaluation value also differs among the three evaluation values Ve. Therefore, by preparing a plurality of combinations of the formula for calculating the evaluation value Ve from the predicted value Vp and the measured value Vm and the mode of the administration of the agent corresponding thereto, the mode of the administration of the agent in which the difference between the predicted value Vp and the measured value Vm is sufficiently small when the processes of steps S302 to S308 are repeatedly performed can be selected, and the most suitable mode of the administration of the agent for obtaining a high-accuracy evaluation value Ve can be selected as the target renal function evaluation value.

[0128] Further, by preparing a plurality of combinations of the formula for calculating the evaluation value Ve from the predicted value Vp and the measured value Vm and the mode of the administration of the agent corresponding thereto, when the evaluation value Ve is calculated using a machine learning method, the plurality of combinations can be used as different explanatory variables, respectively. The explanatory variable is input information for estimating the evaluation value Ve. The plurality of combinations can be used as individual regression trees in a random forest method or as regularization in machine learning. These are particularly effective methods in which the difference between the predicted value Vp and the measured value Vm is sufficiently small to obtain the evaluation value Ve in a plurality of modes of the administration of the agent, but the obtained evaluation values Ve differ, and in a case where it is not possible to determine which evaluation value Ve to use.

[0129] In the case where the processes of steps S302 to S308 are repeated, the combination of the predicted value Vp and the measured value Vm is measured for each of the various modes of the administration of the agent. The obtained combination of the predicted value Vp, the measured value Vm, and the evaluation value Ve is stored in the storage section 22 in a form related to the mode of the administration of the agent. In this case, the combination of the predicted value Vp, the measured value Vm, and the evaluation value Ve can also be stored in the storage section 22 as time series data in a form related to the mode of the administration of the agent.

[0130] In step S308, the control section 21 adjusts the timing of measurement of the urine volume as a response to the medicine in accordance with the medicine administration pattern adjusted in step S307. Specifically, the control section 21 controls the sensor 50 to adjust the timing of measurement of the urine volume to coincide with the medicine administration pattern adjusted in step S307. In the present embodiment, when the medicine administration pattern is changed, accurately measuring the urine volume responsiveness corresponding to the administration pattern affects the accuracy of the estimation of the evaluation value Ve. Therefore, by performing the measurement of the urine volume in a manner that coincides with the timing of administration of the medicine and measurement of the urine volume, a high-accuracy evaluation value Ve can be obtained.

[0131] The process of step S309 is the same as the process of step S107 of the first embodiment, and thus the description is omitted.

[0132] According to the present embodiment, since the urine volume responsiveness at the time when various changes in the medicine administration pattern occur can be used to estimate the renal function, the accuracy of the estimation of the renal function is improved.

[0133] In the present embodiment, whether to perform the process of step S303 or the process of step S309 is selected in accordance with whether the number of times of administration of the medicine reaches the threshold value Vt, but instead of the number of times of administration of the medicine, the difference between the predicted value Vp and the measured value Vm can be used as in the first embodiment. Alternatively, both the threshold value Vt for the number of times of administration of the medicine and the threshold value for the difference between the predicted value Vp and the measured value Vm can be used. In either case, the measurement can be performed while changing the plurality of medicine administration patterns in a predetermined pattern, or the medicine administration pattern can be automatically selected from among several candidates stored in advance in the storage section 22 in accordance with the value or deviation of the evaluation value Ve obtained after administration of the medicine. Furthermore, the combination of the predicted value Vp and the measured value Vm obtained for a specific medicine administration pattern and the deviation of the evaluation value Ve obtained thereafter can be made smaller by repeatedly performing the same medicine administration pattern.

[0134] Furthermore, as a result of performing the processes of steps S302 to S308 in a plurality of medicine administration patterns, the predicted value Vp converges in any of the medicine administration patterns, but in a case where the difference between the predicted value Vp and the measured value Vm is not sufficiently small, the final evaluation value Ve can be obtained using a plurality of evaluation values Ve obtained in each of the medicine administration patterns. In this case, as a method of obtaining the final evaluation value Ve, any method can be selected. For example, the average or median of the plurality of evaluation values Ve can be calculated as the final evaluation value Ve, or the final evaluation value Ve can be obtained by univariate regression analysis, multivariate regression analysis, polynomial regression, or regularization.

[0135] In the storage section 22, in-house data such as examination results used in the past for renal function evaluation of different patients and the presence or absence of underlying diseases, and a drug administration mode effective for reducing the difference between the predicted value Vp and the measured value Vm can also be recorded in association. Then, in selecting the most suitable drug administration mode for the current subject, the drug administration mode effective in the past for similar patients can be preferentially selected based on the examination results used in the renal function evaluation of the current subject and the in-house data such as the presence or absence of underlying diseases, referring to similar patient information. Also, the degree of convergence of the predicted value Vp of each drug administration mode or the reduction trend of the difference between the predicted value Vp and the measured value Vm itself can be used as reference data to preferentially select a drug administration mode effective in similar cases based on the past data stored in the storage section 22.

[0136] (4th Embodiment)

[0137] The differences from the 3rd embodiment will mainly be described.

[0138] In the present embodiment, as shown in Figure 9 , process data Dp of a drug reaction for a specific drug administration is recorded. The process data Dp includes data recording daily changes during hospitalization of a patient and changes from the last discharge to readmission. In predicting a drug reaction associated with renal function, the process data Dp is referred to. The history shown in the process data Dp can also include the history of other patients.

[0139] The operation of the biological function estimation device 20 of the present embodiment will be described with reference to Figure 10 .

[0140] The processes of steps S401 to S403 are the same as the processes of steps S301 to S303 of the 3rd embodiment, and thus the description will be omitted.

[0141] In step S404, the control section 21 refers to the process data Dp showing the history of past drug administrations and drug reactions when predicting the urine volume as a drug reaction. Specifically, the control section 21 analyzes the history shown by the process data Dp and extracts characteristics of a drug reaction specific to the patient. The control section 21 corrects the predicted value Vp determined by referring to a table stored in advance in the storage section 22 according to the characteristics of the drug reaction specific to the patient. Alternatively, the control section 21 corrects the calculated predicted value Vp according to the characteristics of the drug reaction specific to the patient when calculating the predicted value Vp by applying a formula defined in advance.

[0142] The process of step S405 is the same as the process of step S305 of the 3rd embodiment, and thus the description will be omitted.

[0143] In step S406, the control section 21 records, as a part of the process data Dp, the time of administration of the medicament by the pump 40, the kind and amount of the administered medicament, and the measured value Vm obtained in step S405.

[0144] As for the processes of steps S407 to S410, the same as the processes of steps S306 to S309 of the 3rd embodiment, the explanation is omitted.

[0145] According to the present embodiment, when the predicted value Vp is sought, the various data for the evaluation of renal function and the data Dm of the medicament including the measured value Vm, and the process data Dp can be referred to, so a predicted value Vp closer to the true value can be obtained. Therefore, the number of times of repeating the processes of steps S402 to S409 can be reduced, and the time required for outputting the renal function evaluation value in step S410 can be shortened.

[0146] Reducing the number of times of repeating the processes of steps S402 to S409, and shortening the time required for outputting the renal function evaluation value in step S410 is important in the case of, for example, the ICU where the renal function of a patient needs to be evaluated in real time.

[0147] That is, according to the present embodiment, since the prediction accuracy of the predicted value Vp based on the medicament reaction is improved, the time required for outputting the renal function evaluation value can be shortened, and the estimation accuracy of the renal function can also be ensured or improved in the use method such as real-time monitoring.

[0148] As one modification of the present embodiment, the control section 21 can also update the process data Dp each time the predicted value Vp and the measured value Vm are obtained. Thereby, a predicted value Vp closer to the true value can be obtained.

[0149] As for the control section 21, in the case where the combinations of the predicted values Vp and the measured values Vm under various administration patterns applied in the past are stored as the process data Dp indicating the history of the past administration of the medicament and the medicament reaction, by using these for machine learning, a predicted value Vp more suitable for the individual of the measurement object can also be obtained.

[0150] In the present embodiment, whether to perform the process of step S403 or the process of step S410 is selected depending on whether the number of times of administration of the medicament reaches the threshold value Vt, but the difference between the predicted value Vp and the measured value Vm can also be used instead of the number of times of administration of the medicament as in the 1st embodiment. Or, both the threshold value Vt for the number of times of administration of the medicament, and the threshold value for the difference between the predicted value Vp and the measured value Vm can be used. In any case, when repeating the processes of steps S402 to S409, the process data Dp can also be referred to to predict the medicament reaction associated with the renal function.

[0151] The present application is not limited to the above-described embodiments. For example, a plurality of blocks described in the block diagram can be combined, or one block can be divided. Instead of performing a plurality of steps described in the flowchart according to a time series, a plurality of steps described in the flowchart can be performed in parallel or in a different order according to a processing capacity of an apparatus that performs each step or as needed. Furthermore, changes can be made within a scope without departing from the gist of the present application.

[0152] Explanation of Reference Signs

[0153] 10 System

[0154] 20 Biological object function estimation device

[0155] 21 Control unit

[0156] 22 Storage unit

[0157] 23 Communication unit

[0158] 24 Input unit

[0159] 25 Output unit

[0160] 30 Database

[0161] 40 Pump

[0162] 50 Sensor

Claims

1. An organism function estimation device comprising a control section that predicts a drug reaction of a patient based on an evaluation value obtained by evaluating an organism function of the patient according to a result of an examination before administration of a drug, and data of the drug administered to the patient, and corrects the evaluation value according to a comparison result of a predicted value associated with the drug reaction obtained as a result of the prediction and a measured value associated with the drug reaction obtained by actually measuring the drug reaction after administration of the drug. The evaluation value is a value obtained by evaluating a renal function as the organism function, the drug is a diuretic, and the control section predicts a urine amount as the drug reaction.

2. The biological function presumption device according to Claim 1, wherein The control section changes at least either of a formula and a coefficient used for evaluation of the renal function according to the comparison result.

3. The living body function presumption device according to claim 1 or claim 2, wherein The data includes at least either of a kind of the drug, a total amount of administration, and an administration amount per unit time.

4. The living body function presumption device according to claim 1 or claim 2, wherein The control section predicts the drug reaction for administration of the drug at each of a plurality of time points, and corrects the evaluation value according to a comparison result of a new predicted value obtained and a new measured value obtained by actually measuring the drug reaction after administration of the drug.

5. The biological function presumption device according to Claim 4, wherein The control section predicts the drug reaction for administration of the drug at a second time point after a first time point among the plurality of time points based on a corrected value of the evaluation value obtained for administration of the drug at the first time point and data of the drug administered to the patient at the second time point, and further corrects the evaluation value according to a comparison result of a new predicted value obtained and a new measured value obtained by actually measuring the drug reaction after administration of the drug.

6. The biological function presumption device according to Claim 4, wherein The control section records the corrected value of the evaluation value obtained for administration of the drug at each of the plurality of time points as a provisional correction value, and further corrects the evaluation value using a plurality of the provisional correction values recorded.

7. The biological function presumption device according to Claim 4, wherein The control section sets a pattern of administration of the drug at each of the plurality of time points.

8. The biological function presumption device according to Claim 7, wherein The control section adjusts the pattern after a next time point according to a comparison result of a new predicted value and a new measured value obtained for administration of the drug at any one of the plurality of time points.

9. The biological function presumption device according to Claim 7, wherein The control section selects a pattern candidate that differs according to each time point as the pattern from among a predetermined pattern candidate group.

10. The biological function presumption device according to Claim 7, wherein The control section sets the pattern by setting at least either of a number of times of administration of the drug and an administration amount per unit time.

11. The biological function presumption device according to Claim 7, wherein The control section sets the pattern by setting an administration timing of the drug.

12. The biological function presumption device according to Claim 7, wherein The control section refers to actual data indicating a history of at least either of a predicted value and a measured value and a corrected value of an evaluation value in association with past administration of the drug when setting the pattern.

13. The biological function presumption device according to Claim 12, wherein The history indicated in the actual data includes a history of another patient.

14. The biological function presumption device according to Claim 7, wherein The control section adjusts a measurement timing of the drug reaction according to the pattern.

15. The living body function presumption apparatus as claimed in claim 1 or claim 2, wherein The control section refers to process data indicating a history of past administration of the drug and a drug reaction when predicting the drug reaction.

16. The biological function presumption device according to Claim 15, wherein The history indicated in the process data includes a history of another patient.

17. The living body function presumption apparatus as claimed in claim 1 or claim 2, wherein The control section controls a pump that administers a medicine to the patient.

18. The living body function presumption apparatus as claimed in claim 1 or claim 2, wherein The control section controls a sensor that measures a reaction of the medicine.

19. The living body function estimation device according to claim 1 or claim 2, further comprising an output section that outputs a corrected value of the evaluation value.

20. The living body function presumption apparatus as claimed in claim 1 or claim 2, wherein The control section acquires the examination result, and calculates the evaluation value based on the examination result.

Images