Information processing system and model generation method

Abstract

This supports the use of control models for controlling blood purification devices. [Solution] The information processing system 100 includes a first server 46a that generates a control model for controlling the blood purification device 10a using first treatment-related data 88a acquired from the blood purification device 10a of the first facility 78a, a management server 90 that acquires the control model from the first server 46a, and a second server 46b that acquires the control model from the management server 90 and provides the control model to the blood purification device 10b of the second facility 78b.

Description

Technical Field

[0001] The present invention relates to an information processing system, a blood purification apparatus, and a model generation method.

Background Art

[0002] In blood purification therapy, a patient's blood is extracorporeally circulated through a blood circuit, and waste products and excess water in the blood are removed using a blood purifier. Further, during treatment, blood pressure values and the like indicating the patient's condition are measured periodically, and the blood flow rate, dialysate flow rate, and the like are controlled according to the patient's condition. For example, a technique is known in which blood information is input, control parameters are output from a trained model, and the operation of a blood purification system is controlled based on the control parameters (see, for example, Patent Document 1).

Prior Art Literature

Patent Literature

[0003]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] Generation of a trained model requires a large amount of data. Aggregating data acquired from other medical facilities may make it possible to prepare a large amount of data necessary for learning, but there is concern over the risk of leakage of medical data containing personal information to the outside.

[0005] The present invention has been made in view of these problems, and one exemplary object thereof is to provide a technique that supports the use of a control model for controlling a blood purification apparatus.

Means for Solving the Problem

[0006] An information processing system in one aspect of the present invention comprises: a first server that generates a control model for controlling a blood purification device using first treatment-related data acquired from a blood purification device at a first facility; a management server that acquires the control model from the first server; and a second server that acquires the control model from the management server and provides the control model to a blood purification device at a second facility.

[0007] Another aspect of the present invention is a blood purification device. This device comprises a communication unit that acquires usage history data of multiple control models, a display unit that displays the multiple control models along with the usage history data and displays a model selection screen in which at least one of the multiple control models can be selected, and a control unit that controls blood purification treatment using at least one control model selected on the model selection screen.

[0008] A further aspect of the present invention is a model generation method. This method comprises the steps of: a first server generating a control model for controlling a blood purification device using first treatment-related data obtained from a blood purification device at a first facility; obtaining the control model from the first server; providing the control model to a second server; and the second server updating the control model using second treatment-related data obtained from a blood purification device at a second facility. [Effects of the Invention]

[0009] According to the present invention, it is possible to support the use of a control model for controlling a blood purification device. [Brief explanation of the drawing]

[0010] [Figure 1] This is a perspective view showing the external appearance of a blood purification device according to an embodiment. [Figure 2] This diagram schematically shows the configuration of a blood purification device according to an embodiment. [Figure 3] This figure shows an example of the model selection screen. [Figure 4] This figure shows an example of the model evaluation screen display. [Figure 5]This diagram schematically shows the functional configuration of the information processing system according to the embodiment. [Modes for carrying out the invention]

[0011] Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the drawings. In the description, the same elements will be denoted by the same reference numerals, and redundant explanations will be omitted as appropriate. To aid in understanding the description, the dimensional ratios of each component in each drawing do not necessarily correspond to the actual dimensional ratios.

[0012] Figure 1 is a perspective view showing the external appearance of a blood purification device 10 according to an embodiment. The blood purification device 10 is used in blood purification therapies such as hemodialysis and is also called a dialysis machine or dialysis monitoring device. Figure 1 shows the device without consumables such as blood circuits and blood purifiers attached. The blood purification device 10 comprises a main body 12, a display unit 14, and an infusion pole 16.

[0013] The display unit 14 is located on the upper part of the main unit 12. The display unit 14 displays a screen showing the operating status of the blood purification device 10, etc. The display unit 14 is, for example, composed of a touch panel. Users such as medical professionals can input user operations by touching the surface of the display unit 14.

[0014] The IV pole 16 is located on the side of the main body 12. The IV pole 16 is equipped with a blood purifier holder (not shown) for attaching a blood purifier, also known as a dialyzer. An infusion hook is provided at the top of the IV pole 16 for suspending an infusion bag, such as a saline solution bag.

[0015] A blood circuit is attached to the front of the main body 12. A blood pump 18 is provided on the front of the main body 12. The blood pump 18 is, for example, a squeezing pump and houses the pump tube provided in the blood circuit. The blood pump 18 generates a flow of blood or replacement fluid within the blood circuit by squeezing the housed pump tube.

[0016] Figure 2 is a schematic diagram showing the configuration of a blood purification device 10 according to an embodiment. The blood purification device 10 uses a blood purifier 20 and a blood circuit 22. The blood purifier 20 and the blood circuit 22 are consumables and are discarded after each treatment. The blood purification device 10 includes a dialysate supply unit 24, a replacement fluid supply unit 26, and a control unit 28.

[0017] Each block shown in the block diagram of this disclosure can be realized in hardware terms by a computer processor such as a CPU (Central Processing Unit), memory such as ROM (Read Only Memory) and RAM (Random Access Memory), and in software terms by a computer program. Here, we depict functional blocks realized through the cooperation of hardware and software. Those skilled in the art will understand that these functional blocks can be realized in various ways by combinations of hardware and software.

[0018] The blood purifier 20 has a blood inlet port 20a and a blood outlet port 20b connected to the blood circuit 22, and a dialysate inlet port 20c and a dialysate outlet port 20d connected to the dialysate supply unit 24. The blood purifier 20 has a hollow fiber housed inside. The inside of the hollow fiber is a blood flow path connecting the blood inlet port 20a and the blood outlet port 20b. The outside of the hollow fiber is a dialysate flow path connecting the dialysate inlet port 20c and the dialysate outlet port 20d. The hollow fiber has numerous tiny pores, and is configured to allow waste products and excess water in the blood to permeate into the dialysate through these numerous tiny pores.

[0019] The blood circuit 22 is composed of a flexible tube that serves as a blood flow path. The blood circuit 22 includes a blood removal-side blood circuit 22a and a blood return-side blood circuit 22b. The blood removal-side blood circuit 22a is a blood removal tube that connects between a patient's blood vessel (e.g., an artery) and the blood introduction port 20a of the blood purifier 20. The blood removal-side blood circuit 22a is attached to the blood pump 18. The blood return-side blood circuit 22b is a blood return tube that connects between a patient's blood vessel (e.g., a vein) and the blood discharge port 20b of the blood purifier 20.

[0020] The dialysate supply unit 24 is configured to supply dialysate to the blood purifier 20 and discharge dialysate from the blood purifier 20. The dialysate supply unit 24 includes a supply line L1, a discharge line L2, a bypass line L3, a duplex pump 30, and a water removal pump 32.

[0021] The supply line L1 is a main pipe through which the dialysate supplied to the blood purifier 20 flows, and is connected to the dialysate introduction port 20c of the blood purifier 20. The dialysate flowing through the supply line L1 is supplied from a dialysate supply device. The discharge line L2 is a main pipe through which the dialysate discharged from the blood purifier 20 flows, and is connected to the dialysate discharge port 20d of the blood purifier 20. The duplex pump 30 is provided midway through the supply line L1 and the discharge line L2, and controls the flow rate of dialysate flowing through the supply line L1 and the discharge line L2. The water removal pump 32 is provided on the bypass line L3 that bypasses the duplex pump 30 in the discharge line L2.

[0022] The replacement fluid supply unit 26 is configured to supply replacement fluid to the blood circuit 22. The replacement fluid supply unit 26 is connected to, for example, a branch portion of the blood removal-side blood circuit 22a. The replacement fluid supply unit 26 supplies replacement fluid supplied from, for example, a replacement fluid bag to the blood circuit 22. The replacement fluid supply unit 26 may supply the dialysate supplied from the dialysate supply unit 24 to the blood circuit 22. The replacement fluid supply unit 26 can supply replacement fluid for the purpose of, for example, emergency fluid replacement during treatment.

[0023] The control unit 28 controls the overall operation of the blood purification device 10. The control unit 28 includes, for example, a processor such as a CPU (Central Processing Unit), memory such as RAM (Random Access Memory) or ROM (Read Only Memory), and storage devices such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). The control unit 28 operates according to a program, for example, by the processor executing a program stored in memory. The processor may execute a program stored in any storage device other than memory, or a program obtained from any recording medium by a reading device, or a program obtained via a network.

[0024] The control unit 28 comprises a dialysis control unit 34, a measurement unit 36, a data management unit 38, a model selection unit 40, and a communication unit 42.

[0025] The dialysis control unit 34 controls the operation of the blood pump 18, dialysate supply unit 24, and replacement fluid supply unit 26 according to the treatment conditions set for each patient. Treatment conditions include, but are not limited to, dialysis time, amount of fluid removed, fluid removal rate, blood flow rate, and treatment mode. Treatment modes include, but are not limited to, hemodiafiltration (HDF) mode, hemodialysis (HD) mode, and hemofiltration (HF) mode. Treatment conditions are set, for example, via the touch panel of the display unit 14 before the start of blood purification treatment. Depending on the treatment conditions, the replacement fluid bag may or may not be connected to the blood circuit 22.

[0026] The measurement unit 36 ​​measures the patient using the measurement device 44. The measurement device 44 is, for example, a cuff that is attached to the patient. The cuff is, for example, wrapped around the patient's upper arm and configured to pressurize the patient's blood vessels. The measurement unit 36 ​​measures blood pressure using, for example, the oscillometric method. The measurement unit 36 ​​sets the internal pressure of the cuff to be higher than the systolic blood pressure and detects the pressure oscillations superimposed on the internal pressure as a pulse wave signal during the process of gradually decreasing the internal pressure. Based on the detected pulse wave signal, the measurement unit 36 ​​obtains the pulse wave amplitude value with respect to the cuff pressure. Based on the detected pulse wave signal, the measurement unit 36 ​​obtains the patient's blood pressure value. The measurement unit 36 ​​may obtain the systolic blood pressure, diastolic blood pressure, and mean blood pressure as the blood pressure value. The measurement unit 36 ​​may obtain the pulse rate based on the detected pulse wave signal.

[0027] The measuring device 44 may be a weighing scale. The measuring unit 36 ​​may measure the patient's weight using a weighing scale. The patient's weight may be measured before the start and after the end of treatment. The measuring device 44 may be a wearable device worn by the patient. The measuring unit 36 ​​may acquire the patient's vital data (body temperature, pulse, blood pressure, etc.) through the wearable device.

[0028] The data management unit 38 manages treatment-related data concerning blood purification therapy. The data management unit 38 manages performance data generated for each blood purification therapy treatment given to a patient, as well as patient data related to the patient.

[0029] The performance data includes a patient ID that identifies the patient being treated and the date on which the blood purification treatment was performed. The performance data may also include data measured by the measuring device 44 before and after the blood purification treatment, and may include parameters such as the patient's pre-dialysis blood pressure, post-dialysis blood pressure, pre-dialysis body weight, and post-dialysis body weight. The performance data may also include treatment conditions for the blood purification treatment, and may include parameters such as dialysis time, amount of fluid removed, fluid removal rate, blood volume, treatment mode, and reference area (range from the lower limit to the upper limit of ΔBV). The performance data may also include time-series data acquired during the execution of the blood purification treatment, and may include time-series values ​​of parameters such as amount of fluid removed, fluid removal rate, blood volume, blood pressure (e.g., systolic blood pressure, diastolic blood pressure, and mean blood pressure), pulse rate, pulse wave signal, ΔBV, Kt / V, DDM absorbance, and extracorporeal blood flow rate (LDQb). The performance data may also include logs of alerts issued by the control unit 28 (such as a drop in blood pressure). Patient data may include patient attributes such as age, sex, weight (dry weight), dialysis history, blood test information, medical history, lifestyle, and medical condition. The data managed by the data management unit 38 is transmitted to the facility server 46, described later, and stored in the facility server 46.

[0030] The model selection unit 40 displays a selection screen on the display unit 14 for selecting a control model to be used by the dialysis control unit 34. The control model is, for example, a trained model generated by machine learning, and has at least one input and at least one output. Any parameters included in the treatment-related data can be used as the parameters for the input and output. Time-series data included in the treatment-related data can also be used as the input.

[0031] Figure 3 shows an example of the display of the model selection screen 50. The model selection unit 40 displays the model selection screen 50 on the display unit 14 for selecting a control model to be used by the dialysis control unit 34. The model selection screen 50 includes a patient display unit 52, a list display unit 54, and a model search unit 56.

[0032] The patient display unit 52 displays patients who are eligible for blood purification therapy. The patient display unit 52 displays, for example, the patient ID and the patient's name. The patient display unit 52 may further display patient data indicating the patient's attributes, and may be capable of displaying parameters such as age, gender, weight (dry weight), dialysis history, blood test information, medical history, lifestyle, and medical condition.

[0033] The list display unit 54 displays a list of control models available through the model selection unit 40. The control models available through the model selection unit 40 are provided by the facility server 46. The list display unit 54 may prioritize displaying control models suitable for the patient being treated.

[0034] In the example shown in Figure 3, the individual fluid removal setting model 54a, the general-purpose fluid removal setting model 54b, the blood pressure drop prediction model 54c, and the alert prediction model 54d are displayed. By pressing the buttons corresponding to each model 54a to 54d, you can individually switch between the ON state (enabled) and the OFF state (disabled) for each model 54a to 54d. In the example shown in Figure 3, the individual fluid removal setting model 54a and the blood pressure drop prediction model 54c are enabled (ON), while the general-purpose fluid removal setting model 54b and the alert prediction model 54d are disabled (OFF).

[0035] To the right of each model 54a-54d, the following are displayed: usage count 58, number of facilities 60, suitability score 62, evaluation score 64, user reviews 66, and a details button 68. Usage count 58 and number of facilities 60 are usage history data for each model 54a-54d. Usage count 58 indicates the cumulative number of times each model 54a-54d has been used in the past, and number of facilities 60 indicates the number of medical facilities that have used each model 54a-54d.

[0036] The goodness-of-fit 62 indicates the degree of agreement between the patient attributes of the treatment-related data used to generate each model 54a-54d (e.g., machine learning) and the attributes of the patients being treated (e.g., patients displayed in the patient display unit 52). If multiple conditions are used as patient attributes for the treatment-related data used to generate each model 54a-54d, the goodness-of-fit 62 is calculated based on the agreement rate with each of the conditions. For example, if the patient attributes used to generate the model are "male" and "40 years of age or older," the goodness-of-fit 62 will be 100% if both match, 50% if only one matches, and 0% if neither matches. Note that if no conditions for patient attributes are used, such as in a general-purpose model, the goodness-of-fit 62 will be 100%.

[0037] The evaluation score 64 and user review information 66 are evaluation data entered by users when using each model 54a to 54d. The evaluation score 64 and user review information 66 are entered, for example, on the model evaluation screen displayed on the display unit 14 (described later in Figure 4). The evaluation score 64 indicates the evaluation on a scale of, for example, 5. User review information 66 is a message that can be optionally entered on the evaluation input screen. The entirety of the user review information 66 can be viewed on the details screen that appears when the details button 68, indicated by "?", is pressed.

[0038] The model search unit 56 is used for searching to narrow down the control models displayed in the list display unit 54. In the example shown in Figure 3, keyword search 56a, patient information search 56b, and sort 56c are displayed. When keyword search 56a is pressed, a keyword input screen is displayed, and control models that match the entered keyword are displayed. When patient information search 56b is pressed, patient data indicating the attributes of the patient to be treated is displayed in a list. When at least one of the displayed patient data is selected, the control models suitable for the selected patient's attributes (e.g., age, gender, lifestyle, medical history) are narrowed down. When sort 56c is pressed, the display order of the control models can be changed based on the number of times 58, the number of facilities 60, the degree of fit 62, the evaluation score 64, the presence or absence of word-of-mouth information 66, etc.

[0039] The dialysis control unit 34 can control the operation of the blood purification device 10 based on the control model selected on the model selection screen 50. For example, the dialysis control unit 34 can control the operation of the blood purification device 10 based on the output of the control model by inputting treatment-related data acquired during treatment into the selected control model. When using the ultrafiltration setting model, the operation of the ultrafiltration pump 32 can be set based on the output of the ultrafiltration setting model. When using the blood pressure drop prediction model, the operation of the ultrafiltration pump 32 can be changed by predicting the timing of the occurrence of a drop in blood pressure.

[0040] Figure 4 shows an example of the display of the model evaluation screen 70. The model evaluation screen 70 is displayed on the display unit 14 after the control model selected on the model selection screen 50 has been used. The model evaluation screen 70 includes a model display unit 72, a score input unit 74, and a review input unit 76. The model display unit 72 shows the control model to be evaluated. The score input unit 74 is an input unit for evaluation scores, where evaluations can be entered, for example, on a 5-point scale. The review input unit 76 is an input unit for entering arbitrary messages. The content entered on the model evaluation screen 70 is transmitted to the facility server 46 as evaluation information.

[0041] The communication unit 42 communicates with the facility server 46 via the network 48. The communication unit 42 transmits, for example, treatment-related data managed by the data management unit 38 to the facility server 46. The communication unit 42 receives information from the facility server 46 regarding the control model selected on the model selection screen. Details of the facility server 46 will be described later with reference to Figure 5.

[0042] Figure 5 is a schematic diagram showing the configuration of the information processing system 100 according to the embodiment. The information processing system 100 comprises a plurality of facility servers 46a, 46b and a management server 90.

[0043] Multiple facility servers 46a and 46b are connected to a management server 90 via an external network 92 such as the Internet. Multiple facility servers 46a and 46b are installed in facilities 78a and 78b, such as medical institutions. In the example shown in Figure 5, multiple facility servers 46a and 46b include a first server 46a installed in the first facility 78a and a second server 46b installed in the second facility 78b. The number of multiple facility servers 46a and 46b is not particularly limited and may include 10 or more, 100 or more, or 1000 or more servers installed in each of 10 or more, 100 or more, or 1000 or more facilities.

[0044] The first server 46a is connected to the blood purification device 10a via the first network 48a. The number of blood purification devices 10a installed in the first facility 78a is not limited; it may be one, two or more, 20 or more, or 50 or more. The blood purification device 10a can be configured in the same way as the blood purification device 10 shown in Figures 1 and 2. The first network 48a is an internal network provided in the first facility 78a. The first server 46a acquires first treatment-related data from multiple blood purification devices 10a. The first treatment-related data is treatment-related data obtained from blood purification treatment at the first facility 78a.

[0045] The second server 46b is connected to the blood purification device 10b via the second network 48b. The number of blood purification devices 10b installed in the second facility 78b is not limited; it may be one, two or more, 20 or more, or 50 or more. The blood purification device 10b can be configured in the same way as the blood purification device 10 shown in Figures 1 and 2. The second network 48b is an internal network provided in the second facility 78b. The second server 46b acquires second treatment-related data from multiple blood purification devices 10b. The second treatment-related data is treatment-related data obtained from blood purification treatment at the second facility 78b.

[0046] Each of the first server 46a and the second server 46b includes a communication unit 80, a learning unit 82, and a storage unit 84. The first server 46a stores model data 86 and first treatment-related data 88a. The second server 46b stores model data 86 and second treatment-related data 88b.

[0047] The communication unit 80 communicates with the management server 90 via the external network 92. The communication unit 80 sends and receives model data with the management server 90. The communication unit 80 does not send or receive treatment-related data with the management server 90. Therefore, the communication unit 80 shares model data with the management server 90 but does not share treatment-related data. This prevents treatment-related data from leaking to the outside.

[0048] The learning unit 82 performs machine learning on a control model used to control the blood purification device 10. The learning unit 82 performs machine learning using treatment-related data stored in the memory unit 84. For example, the learning unit 82 performs machine learning using treatment-related data based on generation specifications set by the user and generates a trained model. The generated trained model is stored in the memory unit 84 as model data 86.

[0049] The learning unit 82 may update the control model by retraining or further training the control model acquired from the management server 90. For example, the control model generated using the first treatment-related data in the first server 46a may be retrained or further trained using the second treatment-related data in the second server 46b. The learning unit 82 can update the control model by transfer learning or fine-tuning. This makes it possible to generate a control model that has learned both the first and second treatment-related data.

[0050] The learning unit 82 may generate or update a control model using treatment-related data that satisfies predetermined conditions regarding the patient. The learning unit 82 can set predetermined conditions regarding the patient as specific patient attributes or the entire facility (i.e., all patients). Multiple patient attributes may be combined to set predetermined conditions regarding the patient; for example, a condition such as "female with arrhythmia" may be set.

[0051] The learning unit 82 may retrain or further train the control model generated by the first server 46a using first treatment-related data that satisfies predetermined conditions, using second treatment-related data that satisfies predetermined conditions, at the second server 46b. This makes it possible to generate a control model that has learned both the first and second treatment-related data that satisfy predetermined conditions. For example, it is possible to generate a control model that has learned both the first and second treatment-related data that satisfy specific conditions, such as a woman with arrhythmia.

[0052] Model data 86 includes information about the control model, including specification information about the control model's specifications, usage information about the control model's use, and evaluation information about the control model's evaluation. Specification information includes, for example, the control model's input parameters, the control model's output parameters, and predetermined conditions related to the patient. Usage information is generated by the blood purification device 10 and is generated for each blood purification treatment in which the control model is used. Usage information includes, for example, the control model's ID, the blood purification device 10's ID, the patient's ID, and the date and time of use. Evaluation information is generated by inputting into the model evaluation screen 70 displayed on the blood purification device 10 and includes the control model's ID, the blood purification device 10's ID, the patient's ID, the evaluation score, word-of-mouth information, and the ID of the user who entered the evaluation.

[0053] The management server 90 includes a communication unit 94 and a model management unit 96.

[0054] The communication unit 94 communicates with multiple facility servers 46a and 46b via an external network 92. The communication unit 94 sends and receives model data between the multiple facility servers 46a and 46b. The communication unit 94, for example, acquires model data generated by the first server 46a or the second server 46b. The communication unit 94, for example, transmits model data managed by the model management unit 96 to the first server 46a or the second server 46b.

[0055] The model management unit 96 manages model data related to control models. For example, the model management unit 96 stores model data for all control models available on multiple facility servers 46a and 46b. The model data of the model management unit 96 includes specification data for control models, usage history data for control models, evaluation data for control models, and learning history data for control models.

[0056] The specification data includes the input parameters of the control model, the output parameters of the control model, and predetermined conditions related to the patient. The specification data is used to generate or update the control model. The usage history data is a summary of usage information for each of the multiple facility servers 46a and 46b, and includes the cumulative number of times the control model has been used and the number of medical facilities that have used the control model. The evaluation data is a summary of evaluation information for each of the multiple facility servers 46a and 46b, and includes the average evaluation score and a list of word-of-mouth information. The learning history data is a summary of the generation or update of each of the multiple facility servers 46a and 46b, and includes a list of the facility server that performed the generation or update of the control model and the learning date and time.

[0057] Next, the operation of the information processing system 100 will be explained. Facility servers 46a and 46b can generate control models using treatment-related data stored in the memory unit 84. The generated control models are transmitted to the management server 90 and can be used by facility servers other than the facility server that generated the control model. For example, a control model generated by the first server 46a is transmitted to the management server 90, then transmitted from the management server 90 to the second server 46b, and can be used to control the blood purification device 10b connected to the second server 46b. A control model generated by the first server 46a can also be used to control the blood purification device 10a connected to the first server 46a.

[0058] Facility servers 46a and 46b can update control models acquired from the management server 90 using treatment-related data stored in the memory unit 84. The control model acquired from the management server 90 can be updated on a different facility server than the one that generated the control model. For example, a control model generated by the first server 46a using the first treatment-related data 88a can be updated by the second server 46b using the second treatment-related data 88b. This makes it possible to generate a control model using both the first treatment-related data 88a and the second treatment-related data 88b. The control model using both the first treatment-related data 88a and the second treatment-related data 88b may be used to control the blood purification device 10a connected to the first server 46a, or to control the blood purification device 10b connected to the second server 46b. It may also be used to control a blood purification device connected to a different facility server (e.g., a third server) from the first server 46a and the second server 46b.

[0059] Facility servers 46a and 46b provide control models to blood purification devices 10a and 10b. Users can select the control model to use through the model selection screen 50 displayed on the blood purification devices 10a and 10b. For example, users can select and use an appropriate control model from all the control models stored in the management server 90.

[0060] When a control model is used in blood purification devices 10a and 10b, usage information is generated. When an evaluation of the control model is entered in blood purification devices 10a and 10b, evaluation information is generated. The generated usage information and evaluation information are sent to the management server 90 and aggregated as usage history data and evaluation history data in the model management unit 96. The aggregated usage history data and evaluation history data can be viewed on the model selection screen 50.

[0061] Facility servers 46a and 46b do not transmit the treatment-related data 88a and 88b stored in the storage unit 84 to the management server 90. Therefore, each facility 78a and 78b can manage the treatment-related data 88a and 88b individually, and the leakage of the treatment-related data 88a and 88b to external parties can be prevented.

[0062] According to this embodiment, control models generated at various facilities can be shared via the management server 90. It is assumed that the control models generated at each facility include not only high-precision models but also low-precision models. The model selection screen 50 displays the usage history and evaluation history of the control models, thereby supporting the use of models with a high usage history or high evaluation.

[0063] According to this embodiment, the control model can be updated using treatment-related data from multiple facilities, thus supporting the generation of highly accurate control models based on a large amount of treatment-related data. Instead of aggregating and using treatment-related data from multiple facilities in one place, the control model is updated using facility servers installed at each facility, eliminating the need to provide treatment-related data to external parties and enhancing the security of data usage.

[0064] The present invention has been described above based on examples. Those skilled in the art will understand that the present invention is not limited to the above embodiments, that various design changes are possible, and that various modifications are possible, and that such modifications also fall within the scope of the present invention.

[0065] Several embodiments of the present invention will be described below.

[0066] A first aspect of the present invention is an information processing system comprising: a first server that generates a control model for controlling a blood purification device using first treatment-related data acquired from a blood purification device at a first facility; a management server that acquires the control model from the first server; and a second server that acquires the control model from the management server and provides the control model to a blood purification device at a second facility. According to the first aspect, the control model generated using the treatment-related data from the first facility can be used at the second facility. Furthermore, since there is no need to provide the treatment-related data from the first facility to the second facility, treatment-related data, including personal information, can be managed appropriately.

[0067] A second aspect of the present invention is an information processing system according to the first aspect, wherein the second server updates the control model using second treatment-related data acquired from the blood purification device of the second facility. According to the second aspect, since the control model provided by the first facility can be updated using treatment-related data from the second facility, a control model suitable for use at the second facility can be provided.

[0068] A third aspect of the present invention is an information processing system according to the second aspect, wherein the first server generates the control model using treatment-related data from the first treatment-related data that satisfies predetermined conditions regarding the patient, the management server obtains the predetermined conditions from the first server and provides the predetermined conditions to the second server, and the second server updates the control model using treatment-related data from the second treatment-related data that satisfies the predetermined conditions. According to the third aspect, since the control model can be generated and updated using treatment-related data that satisfies predetermined conditions regarding the patient, a control model specialized for a specific patient can be provided.

[0069] A fourth aspect of the present invention is an information processing system according to the second or third aspect, wherein the management server acquires the updated control model from the second server. According to the fourth aspect, the management server can manage a control model using treatment-related data from multiple facilities.

[0070] A fifth aspect of the present invention is an information processing system according to the fourth aspect, wherein the first server obtains the updated control model from the management server and provides it to the blood purification device of the first facility. According to the fifth aspect, a control model using treatment-related data from multiple facilities can be used at the first facility.

[0071] A sixth aspect of the present invention is an information processing system according to any one of the first to fifth aspects, wherein the management server acquires usage information from the first server and the second server indicating the use of the control model by the blood purification device, generates usage history data based on the acquired usage information, and the first server or the second server provides the usage history data acquired from the management server to the blood purification device. According to the sixth aspect, the management server can manage the usage history of the control model in multiple facilities. Users can check the usage history of the control model at the blood purification device in each facility and can decide whether or not to use the control model considering the usage history.

[0072] A seventh aspect of the present invention is an information processing system according to any one of the first to sixth aspects, wherein the management server acquires evaluation information indicating the evaluation of the control model from the first server and the second server, generates evaluation data based on the acquired evaluation information, and the first server or the second server provides the evaluation data acquired from the management server to the blood purification device. According to the seventh aspect, the evaluation of the control model in multiple facilities can be managed by the management server. Users can check the evaluation of the control model at the blood purification device in each facility and decide whether or not to use the control model considering the evaluation.

[0073] An eighth aspect of the present invention is a blood purification device comprising: a communication unit that acquires usage history data of a plurality of control models; a display unit that displays the plurality of control models together with the usage history data and displays a model selection screen in which at least one of the plurality of control models can be selected; and a control unit that controls blood purification treatment using at least one control model selected on the model selection screen. According to the eighth aspect, the user can check the usage history of the control models in the blood purification device and determine whether or not to use a control model considering the usage history.

[0074] A ninth aspect of the present invention is a blood purification device according to the eighth aspect, wherein the communication unit further acquires evaluation data of the plurality of control models, and the model selection screen displays the plurality of control models together with the evaluation data. According to the ninth aspect, the user can check the evaluation of the control models in the blood purification device and decide whether or not to use the control models considering the evaluation.

[0075] A tenth aspect of the present invention is a model generation method comprising: a first server generating a control model for controlling a blood purification device using first treatment-related data acquired from a blood purification device at a first facility; acquiring the control model from the first server; providing the control model to a second server; and the second server updating the control model using second treatment-related data acquired from a blood purification device at a second facility. According to the tenth aspect, the accuracy of the control model can be improved because a control model can be generated using treatment-related data from multiple facilities. Since there is no need to provide treatment-related data from each facility to other facilities, treatment-related data, including personal information, can be managed appropriately. [Explanation of Symbols]

[0076] 10...Blood purification device, 14...Display unit, 28...Control unit, 42...Communication unit, 46...Facility server, 46a...First server, 46b...Second server, 50...Model selection screen, 70...Model evaluation screen, 88a...First treatment-related data, 88b...Second treatment-related data, 90...Management server, 100...Information processing system.

Claims

1. A first server generates a control model for controlling the blood purification device using first treatment-related data acquired from the blood purification device of the first facility, A management server that acquires the control model from the first server, The system includes a second server that acquires the control model from the management server and provides the control model to the blood purification device of the second facility. Information processing system.

2. The second server updates the control model using the second treatment-related data obtained from the blood purification device of the second facility. The information processing system according to claim 1.

3. The first server generates the control model using the treatment-related data from the first treatment-related data that satisfies predetermined conditions regarding the patient. The management server obtains the predetermined conditions from the first server and provides the predetermined conditions to the second server. The second server updates the control model using the treatment-related data from the second treatment-related data that satisfies the predetermined conditions. The information processing system according to claim 2.

4. The management server obtains the updated control model from the second server. The information processing system according to claim 2.

5. The first server obtains the updated control model from the management server and provides it to the blood purification device of the first facility. The information processing system according to claim 4.

6. The management server acquires usage information from the first server and the second server indicating the use of the control model by the blood purification device, and generates usage history data based on the acquired usage information. The first server or the second server provides the blood purification device with the usage history data obtained from the management server. The information processing system according to any one of claims 1 to 5.

7. The management server acquires evaluation information indicating the evaluation of the control model from the first server and the second server, and generates evaluation data based on the acquired evaluation information. The first server or the second server provides the evaluation data obtained from the management server to the blood purification device. The information processing system according to any one of claims 1 to 5.

8. A communication unit that acquires usage history data for multiple control models, A display unit that displays the plurality of control models together with the usage history data, and displays a model selection screen in which at least one of the plurality of control models can be selected, The system includes a control unit that controls blood purification therapy using at least one control model selected on the model selection screen. Blood purification device.

9. The communication unit further acquires evaluation data of the multiple control models, The model selection screen displays the multiple control models along with evaluation data. The blood purification device according to claim 8.

10. The first server generates a control model for controlling the blood purification device using first treatment-related data obtained from the blood purification device of the first facility, The steps include obtaining the control model from the first server, The steps include providing the aforementioned control model to a second server, The procedure includes the step of the second server updating the control model using second treatment-related data obtained from the blood purification device of the second facility, Model generation method.

Images