Blood purification system, control method, control program, learning device and learning method

Abstract

Provided are a blood purification system and the like, capable of more appropriately carrying out blood purification. The blood purification system comprises: a line through which a liquid including blood or filtrate flows; a plasma separation device that separates a plasma component from the blood flowing through the line; a factor separation device that separates, from the plasma component, a factor component causing a disease; a detecting unit that detects blood information relating to the blood flowing through the line; a liquid controlling mechanism that controls the flow of the liquid within the line on the basis of a controlling parameter; a parameter acquiring unit that inputs, into a learning model having been trained to output a predetermined controlling parameter when a predetermined piece of blood information is input thereinto, the detected blood information and acquires the controlling parameter output from the learning model; and a controlling unit that controls the liquid controlling mechanism on the basis of the acquired controlling parameter.

Description

[Technical field]

[0001] The present disclosure relates to a blood purification system, a control method, a control program, a learning device, and a learning method. [Background technology]

[0002] A plurality of blood purification systems used in dialysis and the like are installed in a dialysis room provided in a medical facility such as a hospital, and blood purification is performed for a large number of patients in the dialysis room. A server (central control means) is installed in the dialysis room to store management data related to blood purification (patient weight, blood pressure, etc.), and the management data is transmitted to each blood purification system for display.

[0003] For example, when a patient undergoes dialysis, first, the patient's weight and blood pressure before dialysis are measured using a weighing scale and a blood pressure monitor, and the data are sent to the central management means and stored as the patient's unique information. The central management means determines the patient's conditions based on the patient's unique information by calculation using a predetermined arithmetic formula, and transmits the determined conditions to the blood purification system, thereby performing optimal blood purification for each patient.

[0004] For example, Patent Document 1 discloses a blood purification system in which multiple monitoring devices are installed in a dialysis room in a medical facility such as a hospital. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2012-249748 A Summary of the Invention

[0006] There is a demand for blood purification systems that can purify blood more appropriately.

[0007] An object of the blood purification system, the control method, the control program, the learning device, and the learning method is to enable more appropriate implementation of blood purification.

[0008] A blood purification system according to an embodiment includes a line through which a liquid containing blood or filtrate flows, a plasma separation device which separates plasma components from the blood flowing in the line, a factor separation device which separates disease-causing factor components from the plasma components, a detection unit which detects blood information related to the blood flowing in the line, a liquid control mechanism which controls the flow of liquid in the line based on control parameters, a parameter acquisition unit which inputs the blood information detected by the detection unit into a learning model which has been trained to output predetermined control parameters when predetermined blood information is input, and acquires the control parameters output from the learning model, and a control unit which controls the liquid control mechanism based on the control parameters acquired by the parameter acquisition unit, wherein the blood information includes at least one of the following: degree of blood turbulence, blood vorticity, degree of heart murmur, blood pressure, pressure loss of blood pressure, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, fouling of the plasma separation device, fouling of the factor separation device, hematocrit value in the blood, albumin concentration in the filtrate, degree of hemolysis, and blood pressure of a patient connected to the line.

[0009] In the blood purification system according to the embodiment, the learning model has an action value function in which blood information is the state and control based on control parameters is the action, and it is preferable that the action value function is updated based on a reward that is set to be larger the smaller the change in blood information is.

[0010] In the blood purification system according to the embodiment, the liquid control mechanism includes a magnetic force regulator that applies a magnetic field to the blood in a predetermined direction, a pump that controls the flow of liquid in the line, or a resistance applying member that applies resistance to the line, and the control parameters preferably include at least one of the strength of the magnetic field applied by the magnetic force regulator, the amount of drive of the pump, and the magnitude of the resistance applied by the resistance applying member.

[0011] In the blood purification system according to the embodiment, it is preferable to further include a memory unit that stores the learning model in association with product data of the plasma separation device, data related to the blood flowing through the line, clearance data by the blood purification system, the amount of causative substance removed, or antithrombotic properties.

[0012] In the blood purification system of the embodiment, it is preferable to further have a generation unit that generates a learning model based on the blood information detected by the detection unit before and after controlling the liquid control mechanism based on the specific control parameter and the specific control parameter.

[0013] In the blood purification system according to the embodiment, the blood purification system is preferably an extracorporeal circulation blood purification system.

[0014] In the blood purification system according to the embodiment, it is preferable that the blood purification system performs apheresis by double perfusion plasma exchange.

[0015] A control method according to an embodiment is a control method for a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device that separates plasma components from the blood flowing in the line, a factor separation device that separates disease-causing factor components from the plasma components, a detection unit that detects blood information related to the blood flowing in the line, and a liquid control mechanism that controls the flow of liquid in the line based on control parameters, the control method including: inputting the blood information detected by the detection unit into a learning model that has been trained to output predetermined control parameters when predetermined blood information is input; acquiring control parameters output from the learning model; and controlling the liquid control mechanism based on the acquired control parameters, the blood information including at least one of the degree of blood turbulence, blood vorticity, degree of heart murmur, blood pressure, pressure loss of blood pressure, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, fouling of the plasma separation device, fouling of the factor separation device, hematocrit value in the blood, albumin concentration in the filtrate, degree of hemolysis, and blood pressure of a patient connected to the line.

[0016] The control program according to the embodiment is a control program for a computer included in a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device that separates plasma components from the blood flowing in the line, a factor separation device that separates disease-causing factor components from the plasma components, a detection unit that detects blood information related to the blood flowing in the line, and a liquid control mechanism that controls the flow of the liquid in the line based on control parameters, and causes the computer to input the blood information detected by the detection unit into a learning model that has been trained to output predetermined control parameters when predetermined blood information is input, obtain the control parameters output from the learning model, and control the liquid control mechanism based on the obtained control parameters, wherein the blood information includes at least one of the degree of blood turbulence, blood vorticity, degree of heart murmur, blood pressure, pressure loss of blood pressure, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, fouling of the plasma separation device, fouling of the factor separation device, hematocrit value in the blood, albumin concentration in the filtrate, degree of hemolysis, and blood pressure of a patient connected to the line.

[0017] A learning device according to an embodiment is a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device which separates plasma components from the blood flowing in the line, a factor separation device which separates disease-causing factor components from the plasma components, a detection unit which detects blood information related to the blood flowing in the line, and a liquid control mechanism which controls the flow of liquid in the line based on control parameters, the learning device having a data acquisition unit which acquires multiple combinations of blood information and control parameters, a generation unit which generates a learning model which has been trained to output predetermined control parameters when predetermined blood information is input using the combinations acquired by the data acquisition unit, and an output control unit which outputs information related to the learning model, wherein the blood information includes at least one of the degree of blood turbulence, blood vorticity, degree of heart murmur, blood pressure, pressure loss of blood pressure, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, fouling of the plasma separation device, fouling of the factor separation device, hematocrit value in the blood, albumin concentration in the filtrate, degree of hemolysis, and blood pressure of a patient connected to the line.

[0018] In the learning device of the embodiment, it is preferable that the learning device further has a communication unit for communicating with multiple blood purification systems, and the data acquisition unit acquires the combinations by receiving them from the multiple blood purification systems via the communication unit.

[0019] In the learning device of the embodiment, it is preferable that the data acquisition unit acquires the combination by controlling the liquid control mechanism based on specific control parameters and acquiring blood information detected by the detection unit before and after controlling the liquid control mechanism based on the specific control parameters.

[0020] A learning method according to an embodiment includes a computer acquiring multiple combinations of blood information and control parameters in a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device that separates plasma components from the blood flowing in the line, a factor separation device that separates disease-causing factor components from the plasma components, a detection unit that detects blood information related to the blood flowing in the line, and a liquid control mechanism that controls the flow of liquid in the line based on the control parameters, generating a learning model that has been trained to output predetermined control parameters when predetermined blood information is input using the acquired combinations, and outputting information related to the learning model, wherein the blood information includes at least one of the degree of blood turbulence, blood vorticity, degree of heart murmur, blood pressure, pressure loss of blood pressure, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, fouling of the plasma separation device, fouling of the factor separation device, hematocrit value in the blood, albumin concentration in the filtrate, degree of hemolysis, and blood pressure of a patient connected to the line.

[0021] A control program according to an embodiment is a computer control program, which causes a computer to execute the following steps in a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device that separates plasma components from the blood flowing in the line, a factor separation device that separates disease-causing factor components from the plasma components, a detection unit that detects blood information related to the blood flowing in the line, and a liquid control mechanism that controls the flow of liquid in the line based on the control parameters: acquire multiple combinations of blood information and control parameters, use the acquired combinations to generate a learning model that has been trained to output predetermined control parameters when predetermined blood information is input, and output information related to the learning model; the blood information includes at least one of the degree of blood turbulence, blood vorticity, degree of heart murmur, blood pressure, pressure loss of blood pressure, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, fouling of the plasma separation device, fouling of the factor separation device, hematocrit value in the blood, albumin concentration in the filtrate, degree of hemolysis, and blood pressure of a patient connected to the line.

[0022] The blood purification system, the control method, the control program, the learning device, and the learning method are capable of more appropriately carrying out blood purification.

[0023] The objects and advantages of the invention will be realized and obtained by means of the elements and combinations particularly pointed out in the claims. Both the foregoing general description and the following detailed description are exemplary and explanatory but are not restrictive of the invention as claimed. [Brief description of the drawings]

[0024] [Figure 1] 1 is a diagram showing a schematic configuration of a management system 100 according to an embodiment. [Diagram 2] FIG. 2 is a schematic diagram showing the blood purification unit 14. [Diagram 3] FIG. 1 is a diagram showing a schematic configuration of a blood purification system 40. [Figure 4] 13 is a schematic diagram showing an example of the data structure of a result table 553. FIG. [Diagram 5] FIG. 2 is a diagram showing a schematic configuration of a server 80. [Figure 6] 5 is a flowchart showing an example of the operation of a learning process of the control device 50. [Figure 7] 4 is a flowchart showing an example of the operation of a control process of the control device 50. [Figure 8] 13 is a flowchart showing an example of the operation of a learning process of the server 80. [Figure 9] FIG. 13 is a schematic diagram showing another blood purification unit 14-2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Hereinafter, a blood purification system, a control method, a control program, a learning device, and a learning method according to one aspect of an embodiment will be described with reference to the drawings. However, it should be noted that the technical scope of the present invention is not limited to the embodiment, but extends to the invention described in the claims and their equivalents.

[0026] FIG. 1 is a diagram showing a schematic configuration of a management system 100 according to an embodiment.

[0027] As shown in FIG. 1, the management system 100 includes one or more blood purification systems 40 and a server 80. Each blood purification system 40 and the server 80 are connected to each other via a network 70 so as to be able to communicate with each other. Each blood purification system 40 is an extracorporeal circulation blood purification system. Each blood purification system 40 performs apheresis by double filtration plasmapheresis (DFPP). Each blood purification system 40 includes a blood purification unit 14 and a control device 50. The network 70 is a wired network such as the Internet or an intranet. The network 70 may be a wireless network such as a wireless LAN (Local Area Network).

[0028] FIG. 2 is a schematic diagram showing the blood purification unit 14 included in the blood purification system 40. As shown in FIG.

[0029] As shown in FIG. 2, the blood purification unit 14 includes a plasma separation device 1, a blood sending line 3, a blood return line 4, a blood pump 5, a factor separation device 7, a plasma line 8, a plasma sending pump 9, a filtrate line 10, a filtrate pump 11, a magnetic regulator 16, a blood flow detector 17, a hematocrit detector 18, an albumin concentration detector 19, a first pressure gauge 21-23, a second pressure gauge 25, a third pressure gauge 26, a first flow meter 28, 29, a second flow meter 30, a third flow meter 31, a piping system 33, 33', (three-way) valves 34, 34', a piping system 35, 35', and a clamp 36. The blood purification unit 14 is used to utilize the plasma separation device 1 in a clinical environment. The blood purification unit 14 performs double-pass plasma exchange for the purpose of removing a disease-causing or disease-related substance having a large molecular weight.

[0030] The blood sending line 3, the blood return line 4, the plasma line 8, the filtrate line 10, and the piping systems 33 and 33' are an example of a line through which a liquid containing blood or filtrate flows, and constitute a blood circuit. For example, polyvinyl chloride tubes are used as the blood sending line 3, the blood return line 4, the plasma line 8, the filtrate line 10, and the piping systems 33 and 33'. For example, tubes having a length and a diameter such that the total volume of the liquid contained therein is about 150 ml are used as the blood sending line 3 and the blood return line 4. Other members may be used as the blood sending line 3, the blood return line 4, the plasma line 8, the filtrate line 10, and the piping systems 33 and 33'.

[0031] The piping system 33 is a blood circuit and has a blood collection section 33a from a patient (animal or human). The piping system 33' is a blood circuit and has a blood return section 33b to the patient. The blood sending line 3 sends blood drawn from the blood collection section 33a to the plasma separation device 1 via the blood pump 5. The blood return line 4 sends blood flowing out from the plasma separation device 1 to the blood return section 33b. The plasma line 8 is connected to the plasma outlet port 1b of the plasma separation device 1 and sends the filtrate (liquid containing plasma components) flowing out from the plasma outlet port 1b to the factor separation device 7 via the plasma sending pump 9. The filtrate line 10 is connected to the factor separation device 7 and sends the filtrate flowing out from the factor separation device 7 to the blood return line 4 via the filtrate pump 11.

[0032] The plasma separation device 1 separates plasma components and cellular components from blood flowing through each line. The plasma separation device 1 has a plasma outlet port 1a, a plasma outlet port 1b, a blood inlet port 1c, a blood outlet port 1d, a hollow membrane body 1e, and the like. The blood inlet port 1c is an inlet for blood drawn from a patient. The hollow membrane body 1e is formed by bundling a number of hollow fiber membranes through which blood flowing in from the blood inlet port 1c passes. The blood outlet port 1d is an outlet for blood that has passed through the hollow membrane body 1e to the outside of the device. The plasma outlet ports 1a and 1b are outlets for the filtrate that has been filtered by the hollow membrane body 1e and has permeated to the outside of the hollow membrane body 1e to the outside of the device. The plasma outlet port 1a is a spare port. The plasma components filtered and separated by the hollow membrane body 1e are discharged from the plasma outlet port 1a or 1b, and the blood with a high concentration of cellular components is discharged from the blood outlet port 1d. The plasma separation device 1 has a nominal pore size of 0.3 μm, an inner diameter of 350 μm, a membrane thickness of 50 μm, and a membrane area of ​​0.5 m. 2 A plasma separation device using a polyethylene hollow fiber membrane (Plasmaflow OP-05, manufactured by Asahi Kasei Medical Co., Ltd.) is available.

[0033] The factor separation device 7 separates disease-causing factor components from the separated plasma components. The factor separation device 7 has a filtrate outlet port 7a, a filtrate outlet port 7b, a plasma outlet port 7c, a plasma inlet port 7d, and a hollow membrane body 7e. The plasma inlet port 7d is an inlet for the filtrate flowing out from the plasma outlet port 1b of the plasma separation device 1. The hollow membrane body 7e is formed by bundling a number of hollow fiber membranes through which the filtrate flowing in from the plasma inlet port 7d passes. Adsorption beads may be used as the hollow membrane body 7e. The plasma outlet port 7c is an outlet for the disease-causing factor components that have passed through the hollow membrane body 7e to the outside of the device. The filtrate outlet ports 7a and 7b are outlets for the filtrate filtered by the hollow membrane body 7e to the outside of the device. The filtrate outlet port 7b is a spare port. 2, the filtrate line 10 is connected to the filtrate outlet port 7a, but it is more preferable to connect it to the filtrate outlet port 7b in order to effectively utilize the hollow membrane body or adsorption beads contained in the factor separation device 7. As the factor separation device 7, for example, MONET (registered trademark) manufactured by Fresenius Medical Care can be used.

[0034] The blood pump 5 is provided in the blood supply line 3 and controls the flow of blood in the blood supply line 3. The plasma supply pump 9 is provided in the plasma line 8 and controls the flow of plasma in the plasma line 8. The filtrate pump 11 is provided in the filtrate line 10 and controls the flow of filtrate in the filtrate line 10. The blood pump 5, the plasma supply pump 9, and the filtrate pump 11 are each provided so that the driving amount (output amount) can be changed according to the control of the control device 50. The blood pump 5, the plasma supply pump 9, and the filtrate pump 11 are, for example, roller pumps. The blood pump 5, the plasma supply pump 9, and the filtrate pump 11 may be other known pumps.

[0035] The magnetic force regulator 16 is provided to surround a predetermined position of the plasma separation device 1, and applies a magnetic field in a predetermined direction to the blood in the plasma separation device 1. The magnetic force regulator 16 may be provided to surround a predetermined position of the patient's body connected to the blood feed line 3, the blood return line 4, or the blood purification unit 14, and apply a magnetic field in a predetermined direction to the blood feed line 3, the blood return line 4, or the blood in the patient's body. The magnetic force regulator 16 has an annular magnet, and applies a unidirectional magnetic field parallel to or opposite to the direction of blood flow within the region inside the annular magnet. The magnetic force regulator 16 is provided so as to be able to change the strength of the magnetic field to be applied according to the control of the control device 50. The strength of the magnetic field is set to a strength sufficient to reduce the viscosity of blood by a predetermined amount and / or suppress turbulence in the blood flow by a predetermined amount at the position where the magnetic field is applied. For example, an electromagnet, a permanent magnet, a superconducting magnet, or the like is used as the magnetic force regulator 16.

[0036] The magnetic force regulator 16 can suppress clogging of blood cell components in the plasma separation device 1, suppress an increase in pressure in the plasma separation device 1, and reduce the viscosity of blood flow and blood turbulence. As a result, the blood purification unit 14 can lower the patient's blood pressure, improve hypertension, and reduce the occurrence of heart murmurs. If the strength of the unidirectional magnetic field of the magnetic force regulator 16 is less than 0.01 Tesla, the magnetic effect on red blood cells is low. On the other hand, a magnetic force regulator 16 exceeding 100 Tesla tends to be difficult to handle and expensive. Therefore, the strength of the unidirectional magnetic field of the magnetic force regulator 16 is preferably 0.01 Tesla or more and 100 Tesla or less, and more preferably 1 Tesla or more and 10 Tesla or less.

[0037] The blood pump 5 , the plasma delivery pump 9 , the filtrate pump 11 and the magnetic force regulator 16 are an example of a liquid control mechanism that controls the flow of liquid in each line of the blood purification unit 14 .

[0038] The blood flow detector 17 is provided at a predetermined position in the plasma separation device 1, and detects the direction, speed, and / or speed distribution of blood flow in the plasma separation device 1. The blood flow detector 17 may be provided at a predetermined position in the patient's body connected to the blood feed line 3, the blood return line 4, or the blood purification unit 14, and detects the direction, speed, and / or speed distribution of blood flow in the blood feed line 3, the blood return line 4, or the patient's body. As the blood flow detector 17, for example, an ultrasonic imaging diagnostic device Aixplorer manufactured by SuperSonic Imagine, Inc. can be used. The blood purification unit 14 can detect blood flow abnormalities in a short time and with high accuracy using the blood flow detector 17.

[0039] The hematocrit detector 18 is provided in the blood return line 4 and measures the hematocrit value in the blood in the blood return line 4. The hematocrit value is an index showing the concentration of blood and is indicated by the volume ratio of red blood cells to whole blood. In order to check whether there is an abnormality in the amount of plasma permeated from the plasma separation device 1, the hematocrit detector 18 is preferably provided near the blood outlet port 1d. On the other hand, in order to check the difference between the hematocrit value in the blood flowing into the blood purification unit 14 and the hematocrit value in the blood flowing out from the blood purification unit 14, the hematocrit detector 18 is preferably provided between the blood collection section 33a and the first pressure gauge 23 of the blood sending line 3 and between the first flowmeter 29 and the blood return section 33b of the blood return line 4. As the hematocrit detector 18, for example, StatStrip(R) Hb / Hct manufactured by NOVA(R) BIOMEDICAL can be used.

[0040] The albumin concentration detector 19 is provided in the filtrate line 10 and measures the albumin concentration in the filtrate in the filtrate line 10. As the albumin concentration detector 19, for example, a biochemical analyzer (DRI-CHEM NX700 manufactured by Fuji Film Corporation) can be used.

[0041] The first pressure gauge 23 is provided in the blood supply line 3 between the blood collection section 33a and the blood pump 5, and measures the blood pressure in the blood supply line 3. The first pressure gauge 21 is provided in the blood supply line 3 between the blood pump 5 and the plasma separation device 1, and measures the blood pressure in the blood supply line 3. The first pressure gauge 22 is provided in the blood return line 4 between the plasma separation device 1 and the blood return section 33b, and measures the blood pressure in the blood return line 4. The first pressure gauge 21 and the first pressure gauge 22 can constantly measure the inlet and outlet pressures of the plasma separation device 1, and the first pressure gauge 21 and the first pressure gauge 22 can measure the pressure loss of the blood pressure caused by the plasma separation device 1. The second pressure gauge 25 is provided in the plasma line 8, and measures the plasma pressure in the plasma line 8. The third pressure gauge 26 is provided in the filtrate line 10, and measures the filtrate pressure in the filtrate line 10. As the first pressure gauges 21 to 23, the second pressure gauge 25 and the third pressure gauge 26, for example, known water pressure gauges such as semiconductor piezoresistance diffusion pressure sensors can be used.

[0042] The first flowmeter 28 is provided in the blood sending line 3 and measures the blood flow rate in the blood sending line 3. The first flowmeter 29 is provided in the blood return line 4 and measures the blood flow rate in the blood return line 4. The second flowmeter 30 is provided in the plasma line 8 and measures the plasma flow rate in the plasma line 8. The third flowmeter 31 is provided in the filtrate line 10 and measures the filtrate flow rate in the filtrate line 10. The first flowmeters 28, 29, the second flowmeter 30, and the third flowmeter 31 can determine whether the flow rate in each line controlled by a pump or the like in each line is within a set range. As the first flowmeters 28, 29, the second flowmeter 30, and the third flowmeter 31, known flowmeters such as a Coriolis mass flowmeter, an electromagnetic mass flowmeter, and an ultrasonic mass flowmeter can be used.

[0043] Blood flow detector 17, hematocrit value detector 18, albumin concentration detector 19, first pressure gauges 21-23, second pressure gauge 25, third pressure gauge 26, first flow meters 28, 29, second flow meter 30 and third flow meter 31 are examples of detection units that detect blood information regarding the blood flowing in each line of blood purification unit 14.

[0044] The blood purification unit 14 in a clinical environment may include an anticoagulant injector, an air bubble detector, an alarm function, etc. For safe use, the blood purification system 40 is preferably equipped with a power generator and a battery so that it can operate even in the event of a disaster or power outage.

[0045] Blood withdrawn from the patient through the blood collection section 33a is sent to the plasma separation device 1 by the blood pump 5 through the blood sending line 3. The blood sent to the plasma separation device 1 flows into the hollow membrane body 1e from the blood inlet port 1c and flows out from the blood outlet port 1d to the blood return line 4. Meanwhile, the filtrate filtered by the hollow membrane body 1e flows out from the plasma outlet port 1b and passes through the plasma line 8 and is sent to the factor separation device 7 by the plasma sending pump 9. The filtrate sent to the factor separation device 7 flows into the hollow membrane body 7e from the plasma inlet port 7d, where disease-causing factor components are separated and flow out of the device from the plasma outlet port 7c. Meanwhile, the filtrate filtered by the hollow membrane body 7e flows out from the filtrate outlet port 7a and passes through the filtrate line 10 and is sent to the blood return line 4 by the plasma sending pump 9. The blood flowing out from the blood outlet port 1d to the blood return line 4, and the filtrate sent from the filtrate outlet port 7a to the blood return line 4, are returned to the patient via the blood return section 33b.

[0046] FIG. 3 is a diagram showing a schematic configuration of the blood purification system 40. As shown in FIG.

[0047] In addition to the above-mentioned components, the blood purification unit 14 of the blood purification system 40 further comprises a drive device 15, an electrocardiogram measuring device 41, a hemolysis measuring device 42, a pulse meter 43, a blood pressure meter 44, a blood flow meter 45, and the like.

[0048] The drive device 15 includes one or more motors, and drives the blood pump 5, the plasma delivery pump 9, and the filtrate pump 11 in accordance with control signals from the control device 50, thereby controlling the flow of liquid in each line of the blood purification unit 14.

[0049] The electrocardiogram measuring device 41 is worn by a patient connected to the blood purification unit 14, measures the patient's electrocardiogram (heart rate waveform), and outputs the measured electrocardiogram. As the electrocardiogram measuring device 41, for example, a wearable electrocardiogram measuring device such as an Apple Watch (Series 4, 5, 6) can be used. The Apple Watch (Series 4, 5, 6) has a crystal and electrodes, and records an electrocardiogram similar to a lead I electrocardiogram in cooperation with an electrocardiogram application. The electrocardiogram measuring device 41 may constantly detect the heart rate rhythm, and if an irregular heart rate rhythm that is a sign of atrial fibrillation (AFib) is detected, a notification to that effect may be given.

[0050] The hemolysis measuring device 42 is connected to a patient connected to the blood purification unit 14, and measures the degree of hemolysis of the patient. Hemolysis means destruction of blood cells, particularly red blood cells. A blood leakage detector built into all commercially available dialysis monitoring devices (e.g., Toray TR-3300M) can be used as the hemolysis measuring device 42.

[0051] The pulse meter 43 and blood pressure meter 44 are attached to a patient connected to the blood purification unit 14 and measure the patient's pulse and blood pressure, respectively. The blood flow meter 45 is connected to a patient connected to the blood purification unit 14 and measures the circulating blood flow rate of the patient. As the pulse meter 43, blood pressure meter 44, and blood flow meter 45, known measuring devices can be used.

[0052] The control device 50 is an example of a learning device, and is an information processing device such as a personal computer. The control device 50 has an input device 51, a display device 52, a first communication device 53, an interface device 54, a first storage device 55, and a first processing device 56. The input device 51, the display device 52, the first communication device 53, the interface device 54, the first storage device 55, and the first processing device 56 are connected to each other via a CPU (Central Processing Unit) bus or the like.

[0053] The input device 51 has an input device such as a touch panel type input device, a keyboard, a mouse, etc., and an interface circuit for acquiring signals from the input device, and outputs an operation signal according to an input operation by a user.

[0054] The display device 52 has a display such as a liquid crystal display or an organic EL (Electro-Luminescence) display, and an interface circuit that outputs image data to the display, and displays the image data on the display.

[0055] The first communication device 53 is an example of a communication unit. The first communication device 53 has a wired communication interface circuit according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol). The first communication device 53 is communicatively connected to the network 70 according to a communication standard such as Ethernet (registered trademark). The first communication device 53 sends data received from the server 80 via the network 70 to the first processing device 56, and transmits data received from the first processing device 56 to the server 80 via the network 70. The first communication device 53 may have an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit according to a communication protocol such as wireless LAN, and may be communicatively connected to the network 70 according to a communication standard such as wireless LAN.

[0056] The interface device 54 has an interface circuit conforming to a serial bus such as a Universal Serial Bus (USB). The interface device 54 is connected to the driving device 15, the magnetic force regulator 16, the blood flow detector 17, the hematocrit detector 18, the albumin concentration detector 19, the first pressure gauges 21-23, the second pressure gauge 25, the third pressure gauge 26, the first flow meters 28, 29, the second flow meter 30, the third flow meter 31, the electrocardiogram measuring device 41, the hemolysis measuring device 42, the pulse meter 43, the blood pressure monitor 44, and the blood flow meter 45, etc., which are included in the blood purification unit 14, and is provided so as to be able to communicate with each of the connected devices. The interface device 54 sends data received from each of the connected devices to the first processing device 56, and transmits data received from the first processing device 56 to each of the connected devices. The interface device 54 may have an interface circuit that complies with a short-range wireless communication standard such as Bluetooth, and may be communicatively connected to each component of the blood purification unit 14 wirelessly.

[0057] The first storage device 55 is an example of a storage unit. The first storage device 55 has a memory device such as a random access memory (RAM) or a read only memory (ROM), a fixed disk device such as a hard disk, or a portable storage device such as a flexible disk or an optical disk. The first storage device 55 also stores computer programs, databases, tables, and the like used for various processes of the control device 50. The computer programs may be installed in the first storage device 55 from a computer-readable portable recording medium using a known setup program or the like. The portable recording medium is, for example, a compact disc read only memory (CD-ROM) or a digital versatile disc read only memory (DVD-ROM). The computer programs may be installed from a predetermined server or the like.

[0058] The first storage device 55 stores a learning model 551, product data 552, a result table 553, and the like as data. The learning model 551 is a model for controlling the flow of blood in the blood purification unit 14. The learning model 551 is generated by the first processing device 56 or received from the server 80. The product data 552 is data related to the blood purification unit 14, and indicates the separation performance (filtration performance) of plasma components and cellular components by the plasma separation device 1, or the separation performance (filtration performance) of factor components by the factor separation device 7, and the like. The product data 552 is set in advance by the user using the input device 51. The result table 553 stores the results of blood purification for each blood purification by the blood purification system 40. Details of the result table 553 will be described later.

[0059] The first processing device 56 operates based on a program stored in advance in the first storage device 55. The first processing device 56 is, for example, a CPU. A DSP (digital signal processor), an LSI (large scale integration), an ASIC (application specific integrated circuit), an FPGA (field-programmable gate array), or the like may be used as the first processing device 56. The first processing device 56 is connected to the input device 51, the display device 52, the first communication device 53, the interface device 54, the first storage device 55, and the like, and controls each device. The first processing device 56 generates a learning model 551 and uses the generated learning model 551 to control the flow of blood in the blood purification unit 14.

[0060] The first processing device 56 reads the computer program stored in the first storage device 55 and operates according to the read computer program. As a result, the first processing device 56 functions as a first data acquisition unit 561, a first generation unit 562, a first output control unit 563, a parameter acquisition unit 564, and a control unit 565. The first data acquisition unit 561, the first generation unit 562, and the first output control unit 563 are examples of a data acquisition unit, a generation unit, and an output control unit, respectively.

[0061] FIG. 4 is a schematic diagram showing an example of the data structure of the result table 553. As shown in FIG.

[0062] In the result table 553, for each blood purification performed by the blood purification system 40, an identification number (measurement ID), learning model, patient data, product data, blood data, clearance data, amount of causative substances removed, antithrombotic properties, etc. are stored in association with each other. The learning model is the learning model 551 used in the blood purification. As the learning model, identification information or a storage address, etc. of the learning model 551 used in the blood purification may be stored. The patient data is data related to the patient, such as the name, height, weight, etc. of the patient who underwent blood purification. The product data is product data 552 set in advance by the user.

[0063] The blood data is data on blood flowing through each line of the blood purification unit 14, and includes the patient's pulse, blood pressure, circulating blood flow rate, hematocrit value in the blood, or degree of hemolysis before blood purification. The clearance data is data on blood purified by the blood purification system 40, and includes the patient's pulse, blood pressure, circulating blood flow rate, hematocrit value in the blood, or degree of hemolysis after blood purification. The clearance data may further include blood pressure, blood pressure loss, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, or albumin concentration in the filtrate, which are measured during blood purification. The amount of causative substance removed is the amount of causative substance removed by the blood purification unit 14. Antithrombotic property is the ability to inhibit activation of the blood coagulation system, and is the degree of thrombus formed in the blood purified by the blood purification unit 14.

[0064] FIG. 5 is a diagram showing a schematic configuration of the server 80. As shown in FIG.

[0065] The server 80 is a host computer of the control device 50 and is an example of a learning device. The server 80 includes a second communication device 81, a second storage device 82, and a second processing device 83. The second communication device 81, the second storage device 82, and the second processing device 83 are connected to each other via a CPU bus or the like.

[0066] The second communication device 81 is an example of a communication unit for communicating with multiple blood purification systems 40. The second communication device 81 has a wired communication interface circuit according to a communication protocol such as TCP / IP. The second communication device 81 is communicatively connected to the network 70 according to a communication standard such as Ethernet (registered trademark). The second communication device 81 sends data received from the control device 50 via the network 70 to the second processing device 83, and transmits data received from the second processing device 83 to the control device 50 via the network 70. The second communication device 81 may have an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit according to a communication protocol such as wireless LAN, and may be communicatively connected to the network 70 according to a communication standard such as wireless LAN.

[0067] The second storage device 82 includes a memory device such as a RAM or a ROM, a fixed disk device such as a hard disk, or a portable storage device such as a flexible disk or an optical disk. The second storage device 82 also stores computer programs, databases, tables, and the like used for various processes of the server 80. The computer programs may be installed in the second storage device 82 from a computer-readable portable recording medium such as a CD-ROM or a DVD-ROM using a known setup program or the like. The computer programs may be installed from a predetermined server or the like.

[0068] A learning model 821 and the like are stored as data in the second storage device 82. The learning model 821 is generated by the second processing device 83 or received from the control device 50.

[0069] The second processing device 83 operates based on a program stored in advance in the second storage device 82. The second processing device 83 is, for example, a CPU. As the second processing device 83, a DSP, an LSI, an ASIC, an FPGA, or the like may be used. The second processing device 83 is connected to the second communication device 81, the second storage device 82, and the like, and controls each device. The second communication device 81 generates a learning model 821 and transmits it to each control device 50.

[0070] The second processing device 83 reads the computer program stored in the second storage device 82 and operates according to the read computer program. As a result, the second processing device 83 functions as a second data acquisition unit 831, a second generation unit 832, and a second output control unit 833.

[0071] FIG. 6 is a flowchart showing an example of the operation of the learning process of the control device 50.

[0072] An example of the operation of the learning process of the control device 50 will be described below with reference to the flowchart shown in Fig. 6. The flow of the operation described below is executed mainly by the first processing device 56 in cooperation with each element of the control device 50 based on a program stored in advance in the first storage device 55.

[0073] First, the first data acquisition unit 561 acquires blood information on blood flowing through each line of the blood purification unit 14 (step S101). The blood information includes the degree of blood turbulence, blood vorticity, degree of heart murmur, blood pressure, blood pressure loss, plasma pressure, filtrate pressure, blood flow rate, plasma flow rate, filtrate flow rate, fouling of the plasma separation device 1, fouling of the factor separation device 7, hematocrit value in blood, albumin concentration in the filtrate, or the degree of hemolysis, pulse, blood pressure, or circulating blood flow rate of the patient. The blood information includes one or more of the above-mentioned parameters.

[0074] The first data acquisition unit 561 acquires the direction, velocity, and / or velocity distribution of the blood flow in the blood purification unit 14 from the blood flow detector 17 via the interface device 54, and calculates the degree of turbulence of the blood and the vorticity of the blood based on each acquired information. For example, the first data acquisition unit 561 calculates the Reynolds number for each blood flow detected by the blood flow detector 17, and judges whether each blood flow is turbulent or laminar depending on whether the calculated Reynolds number is equal to or greater than a predetermined threshold. The first data acquisition unit 561 calculates the ratio of the number of turbulent blood flows to the number of all blood flows detected by the blood flow detector 17 as the degree of turbulence. In addition, the first data acquisition unit 561 calculates the velocity vector of the blood flow based on the direction and velocity of the blood flow acquired from the blood flow detector 17, and calculates the rotation of the vector field formed by the calculated velocity vector as the vorticity. The vorticity is a quantity that expresses the state of rotation of a flow.

[0075] The first data acquisition unit 561 acquires an electrocardiogram of the patient connected to the blood purification unit 14 from the electrocardiogram measuring device 41 via the interface device 54, and calculates the degree of heart murmur based on the acquired electrocardiogram. Heart murmur is a heart noise that is not in harmony with the heartbeat and disturbs the rhythm. Heart murmur is a characteristic abnormal sound that is generated when blood flows through a heart valve or a blood vessel near the heart (when the valve opens and closes). Abnormal sounds are mainly generated due to defects in the heart valve. The first data acquisition unit 561 calculates the occurrence rate of an irregular heartbeat rhythm suggesting atrial fibrillation in the heartbeat rhythm shown in the acquired electrocardiogram as the degree of heart murmur. For example, the control device 50 stores a waveform pattern of the heartbeat rhythm of atrial fibrillation in the first storage device 55 in advance. The first data acquisition unit 561 detects a waveform similar to the heartbeat rhythm of atrial fibrillation in the heartbeat rhythm shown in the acquired electrocardiogram using a known pattern matching technique. Alternatively, the first data acquisition unit 561 detects P waves corresponding to each R wave within the cardiac rhythm shown in the acquired electrocardiogram, and detects the occurrence of a cardiac rhythm suggesting atrial fibrillation based on the number of lost P waves.

[0076] The first data acquiring unit 561 acquires blood pressures from the first pressure gauges 21-23 via the interface device 54. The first data acquiring unit 561 also calculates a value obtained by subtracting the blood pressure acquired from the first pressure gauge 22 from the blood pressure acquired from the first pressure gauge 21 as a pressure loss of the blood pressure. The first data acquiring unit 561 also acquires plasma pressure and filtrate pressure from the second pressure gauge 25 and the third pressure gauge 26, respectively, via the interface device 54. The first data acquiring unit 561 also acquires blood flow rate, plasma flow rate, and filtrate flow rate from the first flow meters 28, 29, the second flow meter 30, and the third flow meter 31, respectively, via the interface device 54.

[0077] The first data acquiring unit 561 also calculates the amount of filtrate in the plasma separation device 1 per unit time from the start of operation of the blood purification unit 14 to the present from the plasma flow rate acquired from the second flow meter 30. The first data acquiring unit 561 calculates the pressure difference between the current plasma pressure acquired from the second pressure meter 25 and the blood pressure acquired from the first pressure meter 21. The first data acquiring unit 561 calculates the value obtained by dividing the calculated pressure difference by the calculated filtrate amount, and further dividing the result by unit time, as the fouling of the plasma separation device 1. Similarly, the first data acquiring unit 561 calculates the amount of filtrate in the factor separation device 7 per unit time from the start of operation of the blood purification unit 14 to the present from the filtrate flow rate acquired from the third flow meter 31. The first data acquiring unit 561 calculates the pressure difference between the current filtrate pressure acquired from the third pressure meter 26 and the plasma pressure acquired from the second pressure meter 25. The first data acquiring unit 561 divides the calculated pressure difference from the calculated amount of filtrate, and further divides the result by unit time to calculate the fouling of the factor separation device 7.

[0078] The first data acquisition unit 561 acquires the hematocrit value in blood from the hematocrit value detector 18 via the interface device 54. The first data acquisition unit 561 also acquires the albumin concentration in the filtrate from the albumin concentration detector 19 via the interface device 54. The first data acquisition unit 561 also acquires the degree of hemolysis, pulse, blood pressure, and circulating blood flow rate of the patient connected to the blood purification unit 14 from the hemolysis measuring instrument 42, pulse meter 43, blood pressure meter 44, and blood flow meter 45, respectively, via the interface device 54.

[0079] Next, the first data acquisition unit 561 acquires control parameters related to the flow of liquid in the blood purification unit 14 (step S102). The control parameters include the strength of the magnetic field applied to the blood in a predetermined direction by the magnetic force regulator 16, or the driving amount of the blood pump 5, the plasma delivery pump 9, or the filtrate pump 11. The control parameters include one or more of the above-mentioned parameters.

[0080] For example, the control device 50 stores various usable values ​​for each type of control parameter in the first storage device 55, and the first data acquisition unit 561 acquires the control parameters by sequentially reading out the values ​​stored in the first storage device 55. The first data acquisition unit 561 may acquire the control parameters by generating random numbers within a usable value range for each type of control parameter. The control device 50 may also store optimal values ​​of each control parameter for each type of control parameter in the first storage device 55, and the first data acquisition unit 561 may acquire the control parameters by changing the optimal values ​​by a small amount.

[0081] Next, the first data acquisition unit 561 controls the magnetic force regulator 16 based on the acquired control parameters, or controls the blood pump 5, the plasma delivery pump 9, or the filtrate pump 11 via the drive device 15 (step S103).

[0082] Next, the first data acquisition unit 561 acquires blood information in the same manner as in the process of step S101 (step S104). In this manner, the first data acquisition unit 561 controls the liquid control mechanism of the blood purification unit 14 based on the control parameters acquired in step S102, and acquires blood information detected by the detection unit before and after controlling the liquid control mechanism based on the control parameters. In this way, the first data acquisition unit 561 acquires a combination of blood information and control parameters.

[0083] Next, the first generating unit 562 sets a reward in the learning model 551 based on the blood information acquired by the first data acquiring unit 561 (Step S105).

[0084] The learning model 551 used in the blood purification system 40 is trained, for example, by reinforcement learning. The learning model 551 is trained, for example, by Q-learning as reinforcement learning. The learning model 551 has an action value function that determines the value of control based on each control parameter, with the blood purification unit 14 as the environment, the control device 50 as the agent, blood information as the state, and control of the liquid control mechanism based on the control parameters as the action. Each of the above blood information is a physical quantity that changes by changing each of the above control parameters. That is, a correlation exists between each of the blood information and each of the control parameters, and the first generation unit 562 can generate the learning model 551 that can determine appropriate control parameters according to the state of the blood purification unit 14.

[0085] In Q-learning, the state of the environment s and the action a selected in that state s are used as independent variables, and an action value function Q(s, a) that represents the value of an action when action a is selected in state s is learned. In Q-learning, learning begins when the correlation between state s and action a is unknown, and the action value function Q is iteratively updated by repeating trial and error to select various actions a in any state s. Also, in Q-learning, a reward r is obtained when an action a in a certain state s is selected, and the action value function Q is learned so that an action a that obtains a higher reward r is selected. The update formula for the action value function Q is expressed as follows:

number

[0086] In the above formula, s t and a t are the state and action at time t, respectively, and action a t The state is s t From t+1 Changes to r t+1 is in state s t From t+1 The term maxQ means Q when action a is taken that is considered to have the maximum value Q at time t+1. α and γ are the learning coefficient and discount rate, respectively, and are set arbitrarily between 0<α≦1 (usually 0.9 to 0.99) and 0<γ≦1 (usually around 0.1).

[0087] This update formula is t Actions in a t The evaluation value Q(s t ,a t ) the next state s t+1 Best Practices in Maxa t+1 The evaluation value Q(s t+1 ,maxa t+1 ) is larger, then Q(s t ,a t ) is increased, and if it is small, Q(s t ,a t ) is also reduced. In other words, this update formula makes the value of a certain action in a certain state approach the value of the best action resulting from that state in the next state. Therefore, the action value function is updated so that the action value of the action (operating condition) that results in the most suitable state for operating the blood purification unit 14 becomes higher, that is, so that the action value of the optimal action (operating condition) for the blood purification unit 14 becomes higher.

[0088] The initial value of each action value function Q is set arbitrarily. The first generating unit 562 uses the number of times step S106 is executed as the time in the above formula. The first generating unit 562 converts the pre-control blood information acquired in step S101 into a state s t and control based on the control parameters acquired in step S102 is performed as action a t The blood information after the control acquired in step S104 is identified as state s t+1 Identify as:

[0089] The first generating unit 562 sets the reward r based on the change in blood information (condition) before and after the control. The first generating unit 562 sets the reward r so that the smaller the change (difference) in the blood information after the control relative to the blood information before the control, the larger the reward r, and the larger the change (difference), the smaller the reward r. For example, one or more thresholds are set in advance for each blood information, and the first generating unit 562 sets the reward r by comparing the amount of change in each blood information with each threshold. If the amount of change is greater than the maximum value of the threshold, the first generating unit 562 may set the reward r to 0. In this way, the first generating unit 562 sets the reward r so that the more stable the blood condition in the blood purification unit 14 is when the blood purification unit 14 is controlled based on a specific control parameter, the higher the reward r. In this way, the first generating unit 562 can generate a learning model 551 that has been trained to select control parameters that will make the blood condition in the blood purification unit 14 more stable for the current blood condition.

[0090] Next, the first generating unit 562 updates the action value function based on the combination of the blood information and the control parameters acquired by the first data acquiring unit 561 and the set reward (step S106). t , action a t , state s t+1 Based on the set reward r, the action value function Q(s t ,a t ) to update the

[0091] Next, the first generating unit 562 judges whether or not the learning end condition is satisfied (step S107). As the learning end condition, for example, the total update count of the action value function becomes a predetermined number or more, or the maximum or minimum value of the update count of each action value function becomes a predetermined number or more, is set in advance. If the learning end condition is not yet satisfied, the first data acquiring unit 561 and the first generating unit 562 return the process to step S101 and repeat the processes of steps S101 to S107. As a result, the first data acquiring unit 561 acquires a plurality of combinations of blood information and control parameters, and the first generating unit 562 updates the action value function using each combination acquired by the first data acquiring unit 561. Note that in the second and subsequent processes, the process of step S101 may be omitted, and the first data acquiring unit 561 may use the post-control blood information acquired in the immediately preceding step S104 as the pre-control blood information.

[0092] On the other hand, when the learning end condition is satisfied, the first generating unit 562 generates a learning model 551 having a combination (action value table) of the finally updated values ​​(action values) of each Q(s, a) and stores it in the first storage device 55 (step S108). When a predetermined blood information is input as a state, the learning model 551 is trained to output a control parameter corresponding to an action with the highest action value in that state, that is, a control parameter capable of stabilizing the blood information most. Note that the learning model 551 may be trained to output an action value of each control parameter (each value) in that state when a predetermined blood information is input as a state.

[0093] This allows the blood purification system 40 to automatically create optimal operating conditions for each elapsed time since the start of operation of the blood purification unit 14. As a result, the blood purification system 40 can derive optimal operating conditions for apheresis using double perfusion plasma exchange, for example.

[0094] Next, the first output control unit 563 outputs the learning model 551 generated by the first generation unit 562 by transmitting it to the server 80 via the first communication device 53 (step S109), and ends the series of steps. The learning model 551 is an example of information about the learning model. On the other hand, when the server 80 receives the learning model 551 from the control device 50 via the second communication device 81, the server 80 stores the received learning model 551 as the learning model 821 in the second storage device 82 and transmits it to the other control device 50 via the second communication device 81. When the other control device 50 receives the learning model 821 from the server 80 via the first communication device 53, the other control device 50 stores the received learning model 821 as the learning model 551 in the first storage device 55. This allows the management system 100 to share the learning model among multiple blood purification systems 40, and makes it possible to improve the efficiency of generating the learning model. Note that the process of step S109 may be omitted, and the control device 50 may use the learning model 551 generated by itself only in its own device.

[0095] FIG. 7 is a flowchart showing an example of the operation of the control process of the control device 50.

[0096] An example of the operation of the control process of the control device 50 will be described below with reference to the flowchart shown in Fig. 7. The flow of the operation described below is executed mainly by the first processing device 56 in cooperation with each element of the control device 50 based on a program previously stored in the first storage device 55. The control process is executed when the user issues an instruction to start blood purification using the input device 51.

[0097] First, similar to the processing of step S101 in FIG. 6, parameter acquisition unit 564 acquires blood information detected by the detection unit of blood purification unit 14 from blood purification unit 14 and stores it in first storage device 55 (step S201).

[0098] Next, parameter acquisition unit 564 inputs the acquired blood information to learning model 551 stored in first storage device 55, and acquires control parameters output from learning model 551 (step S202).

[0099] Next, the control unit 565 controls the magnetic force regulator 16 based on the control parameters acquired by the parameter acquisition unit 564, or controls the blood pump 5, the plasma delivery pump 9, or the filtrate pump 11 via the drive device 15 (step S203).

[0100] Next, first data acquisition unit 561 acquires blood information in the same manner as in the process of step S104 in FIG. 6, and stores the blood information in first storage device 55 (step S204).

[0101] Next, first generating unit 562 determines a reward in learning model 551 (step S205) in the same manner as in the process of step S105 in Fig. 6. First generating unit 562 sets a reward based on the blood information acquired in step S201 and the change in the blood information acquired in step S204.

[0102] Next, the first generating unit 562 updates the action value function in the same manner as the process of step S106 in FIG. 6 (step S206). The first generating unit 562 updates the action value function based on the blood information acquired in step S201, the blood information acquired in step S204, the control parameters acquired in step S202, and the reward set in step S206. Note that the processes of steps S204 to S206 may be omitted, and the first generating unit 562 may not need to update the learning model 551 in the control process.

[0103] Next, the control unit 565 determines whether or not the end of blood purification has been instructed by the user using the input device 51 (step S207). If the end of blood purification has not yet been instructed, the control unit 565 returns the process to step S201, and repeats the processes of steps S201 to S207.

[0104] On the other hand, if an instruction to end blood purification is given, the control unit 565 stores the result of the control process in the result table 553 (step S208).

[0105] The control unit 565 reads out the learning model 551 used in the current blood purification from the first storage device 55. The control unit 565 also accepts the input of patient data by the user using the input device 51. The control unit 565 also reads out product data 552 of the plasma separation device 1 and the factor separation device 7 from the first storage device 55. The control unit 565 also reads out the blood information first stored in step S201 from the first storage device 55, and acquires it as blood data related to the blood flowing through each line of the blood purification unit 14. The control unit 565 also reads out each piece of blood information stored in step S204 from the first storage device 55, and acquires it as clearance data by the blood purification system 40. The control unit 565 may acquire only the blood information last stored in step S204 as clearance data by the blood purification system 40.

[0106] The control unit 565 also accepts input of the amount of causative substances removed from the patient by the user using the input device 51. Note that a measuring device for measuring the amount of causative substances removed from the patient connected to the blood purification unit 14 may be connected, and the control unit 565 may obtain the amount of causative substances removed from the patient from the measuring device via the interface 50.

[0107] The control unit 565 also accepts the user's input of the antithrombotic properties of the patient using the input device 51. For example, after blood purification is completed, blood and plasma components are discharged from the blood purification unit 14, and a fixative such as glutaraldehyde for fixing thrombi formed in the hollow membrane body 1e is circulated in the blood feed line 3 and the blood return line 4 for a predetermined time. Thereafter, the plasma separation device 1 is removed from the blood purification unit 14, and the hollow membrane body 1e at the inlet portion of the removed plasma separation device 1 is visually observed to evaluate the presence or absence of thrombi formation. In addition, the state of thrombi inside the hollow membrane body 1e is observed for each predetermined site by a scanning electron microscope. For example, the hollow membrane body 1e is divided vertically into three regions, the filtration side, center, and outside (opposite the filtration side), and horizontally into three regions, the inlet side, center, and outlet side, and the following evaluation is performed for each site of the 3×3 region.

[0108] For example, about 15 hollow fiber membranes are randomly selected for each site, the cross-sectional area of ​​the thrombus formation portion is measured for each hollow fiber membrane, and the average value of the cross-sectional area of ​​the thrombus formation portion per hollow fiber membrane at each site is calculated. Then, for each site, the ratio of the average cross-sectional area of ​​the thrombus formation portion to the average cross-sectional area of ​​the hollow fiber membrane is calculated as the thrombus formation rate. Then, the antithrombogenicity of the plasma separation device 1 is evaluated using the thrombus formation rate as an index. For example, the thrombus formation rate is divided into five stages for each site and scored (scored). When the thrombus formation rate is less than 1%, it is given 0 points, when the thrombus formation rate is 1% or more and less than 25%, it is given 1 point, when the thrombus formation rate is 25% or more and less than 50%, it is given 2 points, when the thrombus formation rate is 51% or more and less than 75%, it is given 3 points, and when the thrombus formation rate is 76% or more, it is given 4 points. In addition, the average score may be calculated for each vertical region or each horizontal region. This allows the tendency of thrombus formation in each region of the hollow membrane body 1e to be understood. The average score for all regions may be used as an evaluation score for the antithrombogenicity of the entire plasma separation device 1. The smaller the evaluation score, the higher the antithrombogenicity is evaluated to be.

[0109] The control unit 565 associates the learning model 551, patient data, product data 552, blood data, clearance data, amount of causative substance removed, and antithrombotic property with each other, assigns a new measurement ID, and stores it in the result table 553.

[0110] Next, the first output control unit 563 outputs the blood purification result by displaying it on the display device 52 (step S208), and ends the series of steps. The blood purification result is an example of information about the learning model. This allows the user to confirm the effect of the learning model 551, identify a highly effective learning model 551, and share it with other control devices 50.

[0111] The control device 50 may acquire the control parameters using the learning model stored in the server 80 instead of using the learning model stored in the control device 50. In that case, in step S202, the parameter acquisition unit 564 transmits the blood information to the server 80 via the first communication device 53. The second processing device 83 of the server 80 receives the blood information from the control device 50 via the second communication device 81, inputs the blood information to the learning model 821 stored in the second storage device 82, and acquires the control parameters output from the learning model 821. The second processing device 83 transmits the acquired control parameters to the control device 50 via the second communication device 81, and the parameter acquisition unit 564 acquires the control parameters by receiving them from the server 80 via the first communication device 53.

[0112] By utilizing the learning model 821 stored in the server 80, the control device 50 can appropriately control the blood purification system 40 using the latest learning model 821 updated by the server 80. On the other hand, by utilizing the learning model 551 stored in the control device 50 itself, the control device 50 can appropriately control the blood purification system 40 even when the communication connection with the server 80 is disconnected.

[0113] As described above in detail, the blood purification system 40 generates a learning model 551 based on blood information about the blood flowing through the blood purification unit 14 and the control parameters of the blood purification unit 14, and controls the blood purification unit 14 using the generated learning model 551. This enables the blood purification system 40 to learn, determine, and provide optimal operating conditions by itself. Therefore, the blood purification system 40 can further stabilize the condition of the blood flowing through the blood purification unit 14, and can perform more appropriate blood purification.

[0114] In particular, the blood information includes the degree of blood turbulence or blood vorticity. The inventors have discovered that blood turbulence (a turbulent fluid whose movement is constantly fluctuating irregularly) and blood vorticity promote platelet production. Large changes in the degree of blood turbulence and blood vorticity make fouling of the plasma separation device 1 more likely to progress. The operation of the blood purification system 80 lasts for several hours to several days, and there are limitations to manual visual inspection and operation, so it is difficult to manually obtain optimal conditions for the degree of blood turbulence and blood vorticity. By using machine learning, the blood purification system 40 can obtain optimal conditions for the degree of blood turbulence and blood vorticity, especially optimal conditions that are difficult for humans to imagine, and can further reduce fouling of the plasma separation device 1.

[0115] The blood information also includes the degree of heart murmur. The greater the degree of heart murmur, the worse the efficiency of blood removal from the patient. A survey has shown that more than half of patients who use an extracorporeal blood processing device such as the plasma separation device 1 and who have been diagnosed with ischemic heart disease have no symptoms. Myocardial infarction is particularly likely to occur in the first year after using an extracorporeal blood processing device. By using machine learning, the blood purification system 40 can obtain optimal conditions for the degree of heart murmur, especially optimal conditions that are difficult for humans to imagine, and can reduce the possibility of a patient using the plasma separation device 1 developing ischemic heart disease. In addition, since the blood purification system 80 has an electrocardiogram measuring device 41, it is also possible to make the patient aware of ischemic heart disease.

[0116] The control parameters include the strength of the magnetic field applied to the blood in a predetermined direction. Since even a slight change in the strength of the magnetic field has a significant effect on the blood flow, it is difficult to appropriately control the strength of the magnetic field. In particular, when the strength of the magnetic field changes, the blood flow does not change immediately, but changes after a while, so it is difficult to appropriately control the strength of the magnetic field. Since the strength of the magnetic field requires delicate adjustment, it is difficult to obtain the optimal condition by manual visual inspection and operation. By using machine learning, the blood purification system 40 can obtain the optimal condition for the strength of the magnetic field, especially the optimal condition that is difficult for humans to imagine.

[0117] As a result of intensive research and repeated experiments, the inventors have found that optimal operating conditions can be obtained by providing the blood purification system 40 with a self-learning function. In particular, the blood purification system 40 makes it possible to clarify and provide operating conditions that can increase the antithrombotic properties of the plasma separation device 1 used in apheresis by double perfusion plasma exchange, extend the lifetime, and reduce fouling. The blood purification system 40 also makes it possible to clarify and provide operating conditions that can extend the lifetime of the factor separation device 7 and reduce fouling. The blood purification system 40 also makes it possible to clarify and provide operating conditions that can reduce disease-causing substances.

[0118] Generally, it takes about three days to obtain appropriate operating conditions using a closed circulation test device, but the blood purification system 40 can obtain appropriate operating conditions in a short time by using machine learning technology. The control device 50 can evaluate the performance of the plasma separation device 1 and the factor separation device 7 while filtering the blood in the blood purification unit 14, and can efficiently evaluate the performance of the plasma separation device 1 and the factor separation device 7. The control device 50 can set the amount of plasma components, the amount of filtration, etc. in the blood purification unit 14, and can collectively and appropriately manage the operation of multiple pumps.

[0119] Furthermore, since the control device 50 that controls the blood purification unit 14 generates the learning model 551, the blood purification system 40 is able to generate the learning model 551 with a simple configuration.

[0120] 8 is a flowchart showing an example of the operation of the learning process of the server 80 according to another embodiment. In this embodiment, the second data acquisition unit 831, the second generation unit 832, and the second output control unit 833 of the server 80 are examples of a data acquisition unit, a generation unit, and an output control unit, respectively.

[0121] An example of the operation of the learning process of the server 80 will be described below with reference to the flowchart shown in Fig. 8. The flow of the operation described below is executed mainly by the second processing device 83 in cooperation with each element of the server 80 based on a program stored in advance in the second storage device 82.

[0122] First, the second data acquisition unit 831 acquires a plurality of combinations of blood information and control parameters by receiving them from the control device 50, i.e., the blood purification system 40, via the second communication device 81 (step S301). The first data acquisition unit 561 of the control device 50 repeatedly executes the processes of steps S101 to S104 in FIG. 6 to acquire a plurality of combinations of blood information and control parameters, and transmits them to the server 80 via the first communication device 53. The second data acquisition unit 831 acquires a plurality of combinations of blood information and control parameters by receiving them from the control device 50 via the second communication device 81. The second data acquisition unit 831 may acquire the combinations of blood information and control parameters by receiving them from a plurality of control devices 50, i.e., a plurality of blood purification systems 40. This allows the second data acquisition unit 831 to efficiently acquire learning data for the learning model 821.

[0123] Next, second generating unit 832 determines a reward corresponding to each combination of blood information and control parameters, in the same manner as in the process of step S105 in FIG. 6 (step S302).

[0124] Next, the second generating unit 832 updates the action value function for each combination of blood information and control parameter based on the combination of blood information and control parameter and the set reward, in a manner similar to the processing of step S106 in FIG. 6 (step S303).

[0125] Next, the second generation unit 832 generates a learning model 821 having a combination (action value table) of the final updated values ​​(action values) of each Q(s, a), in a manner similar to the processing of step S108 in FIG. 6, and stores it in the second storage device 82 (step S304).

[0126] Next, the second output control unit 833 outputs the learning model 821 generated by the second generation unit 832 by transmitting it to each control device 50 via the second communication device 81 (step S305), and ends the series of steps. The learning model 821 is an example of information related to the learning model. On the other hand, when each control device 50 receives the learning model 821 from the server 80 via the first communication device 53, it stores the received learning model 821 in the first storage device 55 as the learning model 551.

[0127] As described above in detail, the blood purification system 40 is able to purify blood more appropriately even when the server 80 generates the learning model 821.

[0128] In particular, the management system 100 makes it possible to centrally manage the learning models used by each blood purification system 40 on the server 80, making it possible to suppress variation in the accuracy of the learning models used by each blood purification system 40.

[0129] 8 may be executed by each control device 50, instead of the server 80. That is, each control device 50 may acquire multiple combinations of blood information and control parameters from other control devices 50, and generate a learning model 551 using the acquired combinations.

[0130] FIG. 9 is a schematic diagram showing a blood purification unit 14-2 according to still another embodiment.

[0131] The blood purification unit 14-2 has each part of the blood purification unit 14 and is used in place of the blood purification unit 14. However, the blood purification unit 14-2 does not have the piping systems 33, 33', the (three-way) valves 34, 34', and the piping systems 35, 35', but instead has the blood bag 2, the resistance imparting members 6, 37, and the opening and closing ports 24, 24', 38, 39, etc. The blood purification unit 14-2 is used in a non-clinical environment not involving use on a patient, in order to utilize the plasma separation device 1 under conditions that are almost the same as those during actual use in terms of blood flow, blood pressure, plasma volume, and filtrate volume. The blood purification unit 14-2 makes it possible to carry out comparative evaluations of the performance of the plasma separation device 1, such as the complement activation inhibitory ability, antithrombotic properties (blood coagulation system activation inhibitory ability), and lifetime of the plasma separation device 1, as well as to carry out fouling evaluations of the plasma separation device 1. In addition, the blood purification unit 14-2 can suppress the loss of albumin in the factor separation device 7, and can perform comparative evaluations of the performance of separating disease-causing factors (components) from plasma components, the lifetime of the factor separation device 7, and the fouling evaluation of the factor separation device 7.

[0132] The blood purification unit 14-2 has a closed circuit in which a test liquid circulates and flows, without contact with the atmosphere, via the plasma separation device 1. Human blood (whole blood) is used as the test liquid, but the test liquid is not limited to this, and other liquids such as animal blood having blood components similar to human blood or artificial blood may also be used as the test liquid.

[0133] The blood sending line 3 and the blood returning line 4 are connected via the blood bag 2.

[0134] The resistance imparting member 6 is provided in the blood return line 4. The resistance imparting member 6 may be provided in the blood feed line 3 instead of or in addition to the blood return line 4. The resistance imparting member 37 is provided in the filtrate line 10. The resistance imparting member 6 and the resistance imparting member 37 are used to apply resistance to the blood feed line 3, the blood return line 4, or the filtrate line 10 at each arrangement position, and to adjust the flow rate or pressure of the test liquid (blood) to the actual use environment. In particular, the resistance imparting member 6 functions as a vein model that simulates the peripheral resistance of the human body to impart a throttling resistance to the blood return line 4 and simulates the veins of the human body to adjust the flow of the test liquid. For example, a clamp that can change the magnitude of the force (resistance) applied to each line by driving a motor is used as the resistance imparting member 6 and the resistance imparting member 37. Various other devices such as valves can be used as the resistance imparting member 6 and the resistance imparting member 37. The resistance imparting member 6 and the resistance imparting member 37 are examples of a liquid control mechanism. The driving device 15 further includes a motor for driving the resistance applying member 6 and the resistance applying member 37 .

[0135] The opening / closing ports 24, 24' are configured with stopcocks or the like that can be switched between an open state that allows the supply or discharge of the test liquid to or from the blood supply line 3 and a closed state that disables the supply or discharge of the test liquid. The opening / closing ports 24, 24' are set to the open state when taking a sample of the test liquid during the test or when replacing the test liquid after the test, and are set to the closed state otherwise. When the opening / closing ports 24, 24' are set to the closed state, the entire circuit of the blood purification unit 14-2 is maintained in a state of non-contact with air. Similarly, the opening / closing port 38 is configured with a stopcock or the like that can be switched between an open state and a closed state with respect to the filtrate line 10. The opening / closing port 39 is configured with a stopcock or the like that can be switched between an open state and a closed state with respect to the plasma line 8.

[0136] In order to keep the temperature of various liquids in the blood purification unit 14-2 constant, the blood purification unit 14-2 is preferably provided with a thermostatic means for adjusting the temperature of the plasma separation device 1, the blood bag 2, the factor separation device 7, and the entire blood purification unit 14-2. The thermostatic means has, for example, a water tank in which water is stored, and a heater for maintaining the temperature of the water in the water tank at a predetermined temperature. By placing the blood bag 2 and a part of the blood feed line 3 in the water tank, it is possible to maintain the test liquid flowing through the blood feed line 3 and the blood return line 4 at a constant temperature equivalent to human body temperature (approximately 36 to 37°C). Similarly, by placing the factor separation device 7 and a part of the plasma line 8 and the filtrate line 10 in the water tank, it is possible to maintain the plasma components flowing through the plasma line 8 and the filtrate line 10 at a constant temperature equivalent to human body temperature (approximately 36 to 37°C). The thermostatic means may have a heater for maintaining the sealed space in which the entire blood purification unit 14-2 is housed at a predetermined temperature.

[0137] In order to simulate the effect of differential pressure due to the height difference of each device provided in the liquid circuit of the blood purification unit 14 used during actual blood filtration, each part of the blood purification unit 14-2 is arranged to have a height difference that generates a similar pressure difference. In addition, each part of the blood purification unit 14-2 is arranged taking into account the effect of gravity due to the height difference. For example, the blood pump 5 is arranged at the highest point. The blood pump 5 is arranged at a height of about 600 mm to 700 mm from the device installation surface of the blood purification unit 14-2, which is the lowest point. In addition, the plasma separation device 1 and the factor separation device 7 are held in an orientation in which the blood inlet port 1c and the plasma inlet port 7d are on the upper side and the blood outlet port 1d and the plasma outlet port 7c are on the lower side. The upper end parts of the plasma separation device 1 and the factor separation device 7 are arranged at a height position of about 400 mm to 500 mm from the device installation surface.

[0138] The control device 50 controls the blood purification unit 14-2 in the same manner as when controlling the blood purification unit 14. However, when the blood purification unit 14-2 is used, the control parameters of the blood purification unit 14-2 include the magnitude of the resistance (resistance) provided by the resistance providing member 6 and the resistance providing member 37. Furthermore, when the blood purification unit 14-2 is used, the blood information does not include the level of heart murmur, the patient's blood pressure, the patient's level of hemolysis, pulse rate, blood pressure, or circulating blood flow rate.

[0139] Hereinafter, a test method for evaluating the antithrombotic properties and lifetime of the plasma separation device 1 using the blood purification unit 14-2 and a test method for evaluating the lifetime of the factor separation device 7 will be described.

[0140] The plasma separation device 1 and factor separation device 7 to be tested are installed (set) in the blood purification unit 14-2, and blood is filled into the blood sending line 3 and blood return line 4 as a test liquid. The blood pump 5 is driven, and the plasma sending pump 9 and the filtrate pump 11 are driven in sequence as appropriate in accordance with the arrival status of the plasma components and filtrate at the plasma sending pump 9 and the filtrate pump 11. The blood to which a pulsating flow is imparted by the blood pump 5 under the same conditions as the actual usage environment passes from the blood bag 2 through the blood pump 5, flows into the plasma separation device 1 from the blood inlet port 1c, and passes through the hollow membrane body 1e. The blood that has passed through the hollow membrane body 1e flows into the blood return line 4 from the blood outlet port 1d, passes through the resistance imparting member 6, and is returned to the blood bag 2.

[0141] The blood pump 5, the plasma delivery pump 9, and the filtrate pump 11 are continuously driven for a time period (for example, about 3 hours to 3 days) corresponding to the actual usage environment. During this time, the first pressure gauges 21-23, the second pressure gauge 25, the third pressure gauge 26, the first flow meters 28, 29, the second flow meter 30, and the third flow meter 31 are periodically monitored, and data on the change over time of the inlet pressure, the outlet pressure, or the differential pressure thereof, of the plasma separation device 1 is obtained. Similarly, data on the change over time of the inlet pressure, the filtrate pressure, and the like of the factor separation device 7 is obtained for the factor separation device 7. The control device 50 can obtain the lifetime of the plasma separation device 1 and the factor separation device 7 from the obtained data. When the inlet pressure of the plasma separation device 1 and the factor separation device 7 rises from an initial value (e.g., 70 mmHg) to a predetermined value (e.g., 150 mmHg), even if the aforementioned operating time has not elapsed, the blood pump 5, plasma delivery pump 9 and filtrate pump 11 are stopped, the test ends, and the elapsed time from the start of the test (operating time) is also obtained as data.

[0142] During the test, blood, plasma components, and filtrate flowing through the blood sending line 3, plasma line 8, and filtrate line 10 are sampled at predetermined time intervals, and various components are measured at each time, and data on changes over time of the various components is also obtained. After the test is completed, the blood and plasma components are discharged from the blood purification unit 14-2, and a fixative such as glutaraldehyde for fixing the thrombus formed in the hollow membrane body 1e is circulated in the blood sending line 3 and blood return line 4 for a predetermined time. The driving conditions of the blood pump 5, the plasma sending pump 9, and the filtrate pump 11 at this time are set to the same conditions as those in the test using blood. Then, the plasma separation device 1 is taken out from the blood purification unit 14-2, and the antithrombotic property of the plasma separation device 1 taken out is evaluated. Thus, in this embodiment, evaluation testing of the plasma separation device 1 is performed without contact with the atmosphere, while maintaining the flow rate, pressure, and components of the test liquid at desired states, and testing is performed in a non-clinical environment without a patient, which is almost identical to the actual usage environment involving a patient.

[0143] The embodiment is not limited to the above. For example, the control device 50 and the blood purification unit 14 may be configured as an integrated device rather than separate devices. In that case, for example, each device of the blood purification unit 14 is directly connected to a CPU bus or the like of the control device 50, and transmits and receives information to and from the first processing device 56 of the control device 50 via the CPU bus or the like.

[0144] The learning model may be trained by a method other than reinforcement learning. For example, the learning model is trained in advance by supervised learning such as deep learning. In this case, a plurality of blood information and a control parameter capable of stabilizing the blood state indicated by each blood information are used as teacher data. When each blood information is input, the learning model is trained to output a control parameter capable of stabilizing the blood state indicated by each blood information. The learning model may be trained by unsupervised learning, semi-supervised learning, transduction, multitask learning, etc. [Explanation of symbols]

[0145] 1 plasma separation device, 3 blood sending line, 4 blood return line, 5 blood pump, 6 resistance applying member, 7 factor separation device, 8 plasma line, 9 plasma sending pump, 10 filtrate line, 11 filtrate pump, 14, 14-2 blood purification unit, 21 to 23 first pressure gauge, 25 second pressure gauge, 26 third pressure gauge, 28, 29 first flow meter, 30 second flow meter, 31 third flow meter, 37 resistance applying member, 40 blood purification system, 50 control device, 53 first communication device, 55 first storage device, 551 learning model, 561 first data acquisition unit, 562 first generation unit, 563 first output control unit, 564 parameter acquisition unit, 565 control unit, 80 server, 81 second communication device, 821 learning model, 831 second data acquisition unit, 832 second generation unit, 833 second output control unit

Claims

1. A line through which a fluid containing blood or filtrate flows; A plasma separation device that separates plasma components from the blood flowing through the line; A factor separation device for separating disease-causing factor components from the plasma components; A detection unit that detects blood information related to blood flowing through the line; a liquid control mechanism for controlling a flow of liquid in the line based on a control parameter; a parameter acquisition unit that inputs the blood information detected by the detection unit into a learning model that has been trained to output a predetermined control parameter when predetermined blood information is input, and acquires the control parameter output from the learning model; A control unit that controls the liquid control mechanism based on the control parameters acquired by the parameter acquisition unit, The blood information includes at least one of a degree of blood turbulence, a degree of blood vorticity, a degree of heart murmur, a pressure loss of blood pressure, a plasma pressure, a filtrate pressure, fouling of the plasma separation device, fouling of the factor separation device, an albumin concentration in the filtrate, and a degree of hemolysis; The learning model is trained so that a change in the blood information before and after control of the flow of the liquid in the line based on a control parameter output from the learning model is small. A blood purification system comprising:

2. the learning model has an action value function in which the blood information is a state and the control based on the control parameter is an action, The blood purification system according to claim 1 , wherein the action value function is updated based on a reward that is set to be larger the smaller the change in the blood information is.

3. the liquid control mechanism includes a magnetic force regulator that applies a magnetic field in a predetermined direction to the blood, a pump that controls the flow of liquid in the line, or a resistance applying member that applies resistance to the line; 3. The blood purification system according to claim 1, wherein the control parameters include at least one of the strength of the magnetic field applied by the magnetic force regulator, the driving amount of the pump, and the magnitude of the resistance applied by the resistance applying member.

4. The blood purification system according to any one of claims 1 to 3, further comprising a memory unit that stores the learning model in association with product data of the plasma separation device, data on blood flowing through the line, clearance data by the blood purification system, the amount of causative substance removed, or antithrombotic properties.

5. The blood purification system according to any one of claims 1 to 4, further comprising a communication unit that receives the learning model from a learning device.

6. The blood purification system according to any one of claims 1 to 4, further comprising a generation unit that generates the learning model based on blood information detected by the detection unit before and after control of the liquid control mechanism based on specific control parameters and the specific control parameters.

7. The blood purification system according to any one of claims 1 to 6, wherein the blood purification system is an extracorporeal circulation blood purification system.

8. The blood purification system according to claim 7 , wherein the blood purification system performs apheresis using a double perfusion plasma exchange method.

9. A control method for a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device which separates plasma components from the blood flowing in the line, a factor separation device which separates disease-causing factor components from the plasma components, a detection unit which detects blood information related to the blood flowing in the line, and a liquid control mechanism which controls the flow of liquid in the line based on control parameters, comprising: inputting the blood information detected by the detection unit into a learning model that has been trained to output a predetermined control parameter when predetermined blood information is input, and acquiring the control parameter output from the learning model; controlling the liquid control mechanism based on the acquired control parameters; The blood information includes at least one of a degree of blood turbulence, a degree of blood vorticity, a degree of heart murmur, a pressure loss of blood pressure, a plasma pressure, a filtrate pressure, fouling of the plasma separation device, fouling of the factor separation device, an albumin concentration in the filtrate, and a degree of hemolysis; The learning model is trained so that a change in the blood information before and after control of the flow of the liquid in the line based on a control parameter output from the learning model is small. A control method comprising:

10. A control program for a computer included in a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device which separates plasma components from the blood flowing in the line, a factor separation device which separates disease-causing factor components from the plasma components, a detection unit which detects blood information related to the blood flowing in the line, and a liquid control mechanism which controls the flow of the liquid in the line based on control parameters, comprising: inputting the blood information detected by the detection unit into a learning model that has been trained to output a predetermined control parameter when predetermined blood information is input, and acquiring the control parameter output from the learning model; controlling the liquid control mechanism based on the acquired control parameters; The blood information includes at least one of a degree of blood turbulence, a degree of blood vorticity, a degree of heart murmur, a pressure loss of blood pressure, a plasma pressure, a filtrate pressure, fouling of the plasma separation device, fouling of the factor separation device, an albumin concentration in the filtrate, and a degree of hemolysis; The learning model is trained so that a change in the blood information before and after control of the flow of the liquid in the line based on a control parameter output from the learning model is small. A control program comprising:

11. a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device which separates plasma components from the blood flowing in the line, a factor separation device which separates disease-causing factor components from the plasma components, a detection unit which detects blood information related to the blood flowing in the line, and a liquid control mechanism which controls the flow of liquid in the line based on control parameters, the system comprising: a data acquisition unit which acquires multiple combinations of the blood information and the control parameters; a generation unit that generates a learning model that is trained to output a predetermined control parameter when predetermined blood information is input, using the combination acquired by the data acquisition unit; An output control unit that outputs information about the learning model, The blood information includes at least one of a degree of blood turbulence, a degree of blood vorticity, a degree of heart murmur, a pressure loss of blood pressure, a plasma pressure, a filtrate pressure, fouling of the plasma separation device, fouling of the factor separation device, an albumin concentration in the filtrate, and a degree of hemolysis; The learning model is trained so that a change in the blood information before and after control of the flow of the liquid in the line based on a control parameter output from the learning model is small. A learning device characterized by:

12. a communication unit for communicating with the blood purification systems; The learning device according to claim 11 , wherein the data acquisition unit acquires the combinations by receiving them from the plurality of blood purification systems via the communication unit.

13. The learning device described in claim 11, wherein the data acquisition unit acquires the combination by controlling the liquid control mechanism based on specific control parameters and acquiring blood information detected by the detection unit before and after controlling the liquid control mechanism based on the specific control parameters.

14. The computer a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device which separates plasma components from the blood flowing in the line, a factor separation device which separates disease-causing factor components from the plasma components, a detection unit which detects blood information related to the blood flowing in the line, and a liquid control mechanism which controls the flow of the liquid in the line based on control parameters, generating a learning model that is trained to output a predetermined control parameter when a predetermined blood information is input using the acquired combination; outputting information about the learning model; The blood information includes at least one of a degree of blood turbulence, a degree of blood vorticity, a degree of heart murmur, a pressure loss of blood pressure, a plasma pressure, a filtrate pressure, fouling of the plasma separation device, fouling of the factor separation device, an albumin concentration in the filtrate, and a degree of hemolysis; The learning model is trained so that a change in the blood information before and after control of the flow of the liquid in the line based on a control parameter output from the learning model is small. A learning method comprising:

15. A control program for a computer, comprising: a blood purification system having a line through which a liquid containing blood or filtrate flows, a plasma separation device which separates plasma components from the blood flowing in the line, a factor separation device which separates disease-causing factor components from the plasma components, a detection unit which detects blood information related to the blood flowing in the line, and a liquid control mechanism which controls the flow of the liquid in the line based on control parameters, generating a learning model that is trained to output a predetermined control parameter when a predetermined blood information is input using the acquired combination; outputting information about the learning model; The blood information includes at least one of a degree of blood turbulence, a degree of blood vorticity, a degree of heart murmur, a pressure loss of blood pressure, a plasma pressure, a filtrate pressure, fouling of the plasma separation device, fouling of the factor separation device, an albumin concentration in the filtrate, and a degree of hemolysis; The learning model is trained so that a change in the blood information before and after control of the flow of the liquid in the line based on a control parameter output from the learning model is small. A control program comprising:

Images