Information processing method, computer program, and information processing device

Abstract

To provide an information processing method, a learning model generation method, an information collection method, a computer program, and an information processing device with which it is possible to assist in administering medicine to patients.SOLUTION: An information processing method pertaining to the present embodiment includes an information processing device acquiring the medical record data of a patient, inputting the acquired medical record data to a learning model having been trained by machine learning so as to output the type of medicine administered to the patient, dosage, and the speed of administration for the input of the medical record data of the patient, acquiring the type of medicine, dosage, and administration speed outputted by the learning model, and outputting the acquired type of medicine, dosage, and administration speed. The information processing device may acquire the identification information of the patient, and acquire medical record data corresponding to the acquired identification information from a database in which the medical record data of a plurality of patients are stored.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing method for supporting the administration of medicines to patients. ,Ko The present invention relates to a computer program and an information processing device. [Background technology]

[0002] Patent document 1 proposes an infusion volume adjusting device that is equipped with an infusion pump that is connected to both the needle and the infusion container via an infusion tube, and that adjusts the flow rate of the infusion flowing from the infusion container and sends it toward the needle, and a flow sensor that measures the flow rate of the infusion discharged from the infusion pump, and that can maintain the amount of infusion injected at a predetermined set value by controlling at least one of the voltage and frequency of the drive pulse applied to the piezoelectric element of the infusion pump so that the measured flow rate of the flow sensor becomes the set flow rate. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-177411 Summary of the Invention [Problem to be solved by the invention]

[0004] By using the infusion volume adjusting device described in Patent Document 1, it is expected that an appropriate flow rate of infusion will be administered to the patient. However, the flow rate and other settings for this device are set by a human such as a doctor or nurse, and proper administration of infusion to the patient can be achieved by a human making the appropriate settings.

[0005] The present invention has been made in view of the above circumstances, and its object is to provide an information processing method that can be expected to support the administration of medicines to patients. ,Ko The present invention aims to provide a computer program and an information processing device. [Means for solving the problem]

[0006] In one embodiment of an information processing method, an information processing device acquires a patient's medical record data, inputs the acquired medical record data into a learning model that has been machine-learned to output the type, dosage, and administration rate of a drug to be administered to the patient in response to input of the patient's medical record data, obtains the type, dosage, and administration rate of the drug output by the learning model, and outputs the acquired type, dosage, and administration rate of the drug. [Effects of the Invention]

[0007] In one embodiment, it is expected to assist in administering medication to patients. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a schematic diagram illustrating an overview of an information processing system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing a configuration of a server device according to the present embodiment. [Figure 3] FIG. 2 is a block diagram showing the configuration of a terminal device according to the present embodiment. [Figure 4] FIG. 2 is a schematic diagram for explaining the configuration of a drug prediction model according to the present embodiment. [Figure 5] 10 is a flowchart showing the procedure of a drug prediction model generation process performed by the server device according to the present embodiment. [Figure 6] FIG. 10 is a schematic diagram showing an example of display of drug administration information. [Figure 7] 10 is a flowchart showing the procedure of a drug prediction process performed by the server device according to the present embodiment. [Figure 8] 10 is a flowchart showing the procedure of a drug prediction process performed by the terminal device according to the present embodiment. [Figure 9] 10 is a flowchart showing a procedure of information collection processing on vital information by the server device according to the present embodiment. [Figure 10] FIG. 10 is a schematic diagram showing an example of a display screen for querying progress information. [Figure 11] 10 is a flowchart showing a procedure of a feedback information acquisition process performed by the server device according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Specific examples of information processing systems according to embodiments of the present invention will be described below with reference to the drawings. Note that the present invention is not limited to these examples, but is defined by the claims, and is intended to include all modifications within the meaning and scope of the claims.

[0010] <System configuration> FIG. 1 is a schematic diagram illustrating an overview of an information processing system according to the present embodiment. In the information processing system according to the present embodiment, a drug is administered to a patient 101 who requires administration of a drug at a medical institution or the like using a pump 5, such as a syringe pump or a micropump. The type, dosage, administration rate, etc. of the drug to be administered by the pump 5 are set by a doctor 102 or the like in charge of the patient 101. The information processing system according to the present embodiment is a system that supports the doctor 102 in determining the type, dosage, administration rate, etc. of the drug in a situation where the drug is administered using the pump 5. Note that in this embodiment, the doctor 102 determines the type, dosage, administration rate, etc. of the drug, and then administers the drug to the patient 101. However, the present embodiment is not limited to this. For example, the doctor 102 may determine the type, dosage, administration rate, etc. of the drug, and a person other than the doctor 102, such as a nurse, may administer the drug to the patient based on the doctor 102's determination.

[0011] In the information processing system according to this embodiment, the patient ID of the patient 101 can be obtained by reading, for example, a two-dimensional code 110 attached to the patient's 101 clothing, bed, hospital room, or a medical record printed on paper, using the terminal device 3 used by the doctor 102. The terminal device 3 that has obtained the patient ID transmits the obtained patient ID to the server device 1. The server device 1 according to this embodiment performs a process of predicting the type, dosage, administration rate, etc. of a drug suitable for administration to the patient 101 using so-called AI (artificial intelligence). The server device 1 receives the patient ID transmitted from the terminal device 3, reads the medical record data corresponding to the received patient ID from a medical record DB (database) 7, and predicts the type, dosage, administration rate, etc. of a drug suitable for the patient 101 based on the read medical record data. The server device 1 transmits the predicted results of the drug type, dosage, administration rate, etc. as drug administration information to the terminal device 3 of the doctor 102. The terminal device 3 displays the drug administration information transmitted from the server device 1. The doctor 102 refers to the type of drug, dosage, administration rate, etc. displayed on the terminal device 3, and, including his own judgment, decides the final type of drug, dosage, administration rate, etc. for the patient 101, and operates the pump 5 to administer the drug to the patient 101.

[0012] In the information processing system according to this embodiment, vital information such as heart rate, respiratory rate, blood pressure, and body temperature of patient 101 to whom a drug has been administered is measured by measuring device 6, and the measured vital information is transmitted by measuring device 6 to server device 1. Server device 1 collects, as information regarding the results of administering a drug to patient 101, the patient's medical record data used to predict the type, dosage, and administration rate of the drug, drug administration information which is the prediction result of the drug type, dosage, and administration rate based on this medical record data, and vital information of patient 101 after the drug has been administered, and records and accumulates the collected information in drug administration DB 8. Server device 1 may also determine whether the type, dosage, and administration rate of the drug administered to patient 101 were appropriate based on the patient's vital information, and record the determination result in drug administration DB 8. The information recorded in drug administration DB 8 is used to improve the accuracy of AI that predicts the type, dosage, and administration rate of the drug.

[0013] Furthermore, in the information processing system according to this embodiment, the server device 1 may acquire feedback information from the doctor 102 regarding the administration of a drug to the patient 101 via the terminal device 3, and record the acquired information in the drug administration DB 8. For example, if the doctor 102 corrects the predicted values ​​for the type, dosage, administration rate, etc. of the drug predicted by the server device 1 and uses the pump 5, the server device 1 may acquire the corrected value for the predicted value from the doctor 102 as feedback information. Also, for example, if the pump 5 is used according to the type, dosage, administration rate, etc. of the drug predicted by the server device 1, the server device 1 may acquire, as feedback information, the result of the doctor 102's subsequent examination of the patient 101's condition determining whether the type, dosage, and administration rate of the drug were appropriate, or events such as changes in the patient 101's condition. This information acquired by the server device 1 from the doctor 102 and recorded in the drug administration DB 8 may be used to improve the accuracy of AI that predicts the type, dosage, administration rate, etc. of the drug.

[0014] <Device configuration> 2 is a block diagram showing the configuration of a server device 1 according to this embodiment. The server device 1 according to this embodiment is configured to include a processing unit 11, a memory unit (storage) 12, and a communication unit (transceiver) 13. Note that although this embodiment will be described assuming that processing is performed by one server device, processing may also be performed in a distributed manner by a plurality of server devices.

[0015] The processing unit 11 is configured using an arithmetic processing device such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit) or a quantum processor, a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The processing unit 11 reads and executes a server program 12a stored in the storage unit 12, thereby performing various processes such as generating a learning model based on data acquired from the terminal device 3, and predicting the type, dosage, administration rate, etc. of a drug using the generated learning model.

[0016] The storage unit 12 is configured using a large-capacity storage device such as a hard disk. The storage unit 12 stores various programs executed by the processing unit 11 and various data required for the processing of the processing unit 11. In this embodiment, the storage unit 12 stores a server program 12a executed by the processing unit 11 and a drug prediction model 12b, which is a learning model generated by machine learning processing. The storage unit 12 also has the above-mentioned medical record DB7 and drug administration DB8. However, the medical record DB7 and drug administration DB8 may be stored in an external storage device rather than in the storage unit 12 included in the server device 1.

[0017] In this embodiment, the server program (computer program, program product) 12a is provided in a form recorded on a recording medium 99 such as a memory card or an optical disc, and the server device 1 reads the server program 12a from the recording medium 99 and stores it in the storage unit 12. However, the server program 12a may also be written to the storage unit 12, for example, during the manufacturing stage of the server device 1. Alternatively, the server program 12a may be distributed by another remote server device or the like and acquired by the server device 1 via communication. For example, the server program 12a may be read from the recording medium 99 by a writing device and written to the storage unit 12 of the server device 1. The server program 12a may be provided in a form distributed via a network or in a form recorded on the recording medium 99.

[0018] The drug prediction model 12b stored in the storage unit 12 may include configuration information indicating the configuration of the drug prediction model 12b, and information such as values ​​of internal parameters of the drug prediction model 12b determined by machine learning processing. The details of the drug prediction model 12b will be described later.

[0019] The medical record DB 7 is a database that stores medical record data including various information about the patient 101 created by the doctor 102. The medical record DB 7 stores the medical record data in association with a patient ID, which is identification information uniquely assigned to each patient. Each medical record data may include various information such as the age, weight, primary disease, test results of various tests, and treatment history of the patient 101.

[0020] The drug administration DB8 is a database that stores information about drugs administered to the patient 101. In this embodiment, the data stored in the drug administration DB8 is used for machine learning (relearning) processing to improve the prediction accuracy of the drug prediction model 12b. In this embodiment, the drug administration DB8 stores, in association with a patient ID, medical record data when a drug was administered to this patient 101, drug administration information such as the type, dosage, and administration rate of the drug predicted by the drug prediction model 12b based on this medical record data, vital information measured by the measuring device 6 of the patient 101 to whom the drug was administered, and feedback information from the doctor 102 in charge of administering the drug.

[0021] The communication unit 13 communicates with various devices via a network N, which may include a mobile phone communication network, a wireless LAN (Local Area Network), the Internet, etc. In this embodiment, the communication unit 13 communicates with the terminal device 3 and the measuring instrument 6 via the network N. The communication unit 13 transmits data provided by the processing unit 11 to other devices, and provides data received from other devices to the processing unit 11.

[0022] The storage unit 12 may be an external storage device connected to the server device 1. The server device 1 may be a multi-computer including multiple computers, or may be a virtual machine virtually constructed by software. The server device 1 is not limited to the above configuration, and may include, for example, a reading unit that reads information stored in a portable storage medium, an input unit that accepts operation input, or a display unit that displays images.

[0023] In addition, in the server device 1 according to this embodiment, the processing unit 11 reads and executes the server program 12a stored in the storage unit 12, whereby a patient ID acquiring unit 11a, a medical record data acquiring unit 11b, a drug prediction processing unit 11c, a drug administration information output unit 11d, a vital information acquiring unit 11e, a feedback information acquiring unit 11f, a learning processing unit 11g, etc. are realized as software functional units in the processing unit 11. Note that in the figure, functional units related to the prediction processing using the drug prediction model 12b and the generation processing of the drug prediction model 12b are shown as the functional units of the processing unit 11, and functional units related to other processing are not shown.

[0024] The patient ID acquiring unit 11a performs processing to acquire the patient ID assigned to the patient 101 to be administered with the drug. In this embodiment, the patient ID is acquired by the doctor 102 reading the two-dimensional code 110 using the terminal device 3, and is transmitted from the terminal device 3 to the server device 1. The patient ID acquiring unit 11a receives the patient ID transmitted by the terminal device 3 via the communication unit 13, thereby acquiring the patient ID of the target patient 101.

[0025] The medical record data acquiring unit 11b performs a process of acquiring the medical record data of the patient 101 to be administered a drug from the medical record DB 7. The medical record data acquiring unit 11b reads out the medical record data of the target patient 101 from the medical record DB 7 based on the patient ID acquired by the patient ID acquiring unit 11a from the terminal device 3.

[0026] The drug prediction processing unit 11c uses a trained drug prediction model 12b that has been previously subjected to machine learning to perform processing for predicting the type, dosage, and administration rate of a drug to be administered to the patient 101. The drug prediction processing unit 11c inputs various information included in the medical record data of the patient 101 acquired by the medical record data acquisition unit 11b to the drug prediction model 12b, and performs prediction by acquiring information on the type, dosage, and administration rate of a drug output by the drug prediction model 12b.

[0027] The drug administration information output unit 11d transmits (outputs) the results of the drug prediction processing unit 11c's prediction of the type, dosage, and administration rate of the drug to be administered to the patient 101 as drug administration information to the terminal device 3, thereby performing a process of displaying (outputting) the drug administration information on the terminal device 3. The drug administration information output unit 11d also outputs the drug administration information to the drug administration DB8, thereby storing the drug administration information in the drug administration DB8.

[0028] The vital information acquisition unit 11e acquires vital information of the patient 101 measured by the measuring instrument 6, such as the heart rate, respiratory rate, blood pressure, and body temperature, by communicating with the measuring instrument 6 via the communication unit 13. The vital information acquisition unit 11e stores the vital information of the patient 101 acquired from the measuring instrument 6 in the drug administration DB 8 together with information such as the patient ID and the time of measurement. The measuring instrument 6 continuously measures the heart rate, respiratory rate, blood pressure, body temperature, and the like of the patient 101, and periodically transmits the measurement results to the server device 1. The vital information acquisition unit 11e acquires the measurement results periodically transmitted by the measuring instrument 6 as vital information, and stores the vital information in the drug administration DB 8 each time it is acquired.

[0029] Furthermore, the vital information acquiring unit 11e may determine a change in the condition of the patient 101 to whom a drug has been administered, based on the acquired vital information. For example, the vital information acquiring unit 11e may determine that an abnormality has occurred in the patient 101 when one or more numerical values ​​included in the vital status exceed a threshold indicating an abnormality, or when the vital information acquiring unit 11e calculates the amount of change over a certain period of time for one or more numerical values ​​included in the vital status and the amount of change in any of the numerical values ​​exceeds a threshold, and may notify the terminal device 3 or the like of the abnormality. Furthermore, for example, the vital information acquiring unit 11e may determine that the patient 101 has recovered when one or more values ​​included in the vital status return from an abnormal value to a normal value, and may notify the terminal device 3 or the like of the recovery of the patient 101. When making these determinations, the vital information acquiring unit 11e stores the determination result together with the vital information in the drug administration DB 8.

[0030] The feedback information acquiring unit 11f performs a process of acquiring feedback information from the doctor 102 who administered a drug to the patient 101. In this embodiment, the feedback information acquiring unit 11f acquires, as feedback information, information such as values ​​corrected by the doctor 102 with respect to the type, dosage, and administration rate of the drug predicted by the drug prediction model 12b, a determination by the doctor 102 as to whether the type, dosage, and administration rate of the drug were appropriate based on the results of administering the drug to the patient 101, and a diagnosis by the doctor 102 of a change in the condition of the patient 101 due to the administration of the drug (e.g., recovered, worsened, etc.). This feedback information is input by the doctor 102 to the terminal device 3, and the terminal device 3 transmits the input feedback information to the server device 1. The feedback information acquiring unit 11f acquires the feedback information transmitted from the terminal device 3 by receiving it via the communication unit 13, and stores the acquired feedback information in the drug administration DB 8 in association with the patient ID of the target patient 101.

[0031] The learning processing unit 11g performs a process of generating the drug prediction model 12b in advance by performing machine learning using previously prepared learning data (teacher data). In the present embodiment, the learning processing unit 11g generates the drug prediction model 12b by performing so-called supervised learning machine learning. The drug prediction model 12b according to the present embodiment is a learning model that outputs the type of drug, the dosage, and the administration rate in response to input medical record data. For example, a neural network learning model is used for the drug prediction model 12b, and the learning processing unit 11g determines internal parameters of the neural network by performing supervised learning using the learning data and stores the determined parameters in the storage unit 12 as the drug prediction model 12b. The supervised learning process of the learning model is an existing technology and will not be described in detail here; however, the learning processing unit 11g can perform the learning process of the learning model by a method such as gradient descent, stochastic gradient descent, or backpropagation.

[0032] Furthermore, in order to improve the prediction accuracy of the drug prediction model 12b, the learning processing unit 11g may further perform machine learning processing on the trained drug prediction model 12b using information accumulated in the drug administration DB 8. In this case, the learning processing unit 11g may perform processing to generate training data by, for example, appropriately converting the information stored in the drug administration DB 8, or may also generate training data based on the information stored in the drug administration DB 8, and the learning processing unit 11g may re-train the drug prediction model 12b using the generated training data.

[0033] In the present embodiment, the server device 1 performs a process of generating the drug prediction model 12b through machine learning. However, this is not limiting. A device other than the server device 1 may generate the drug prediction model 12b and transmit information such as parameters of the generated drug prediction model 12b to the server device 1. In the present embodiment, the drug prediction model 12b is a neural network learning model. However, this is not limiting. Various learning models, such as a support vector machine (SVM) or a decision tree, may be employed. The learning processing unit 11g generates the drug prediction model 12b through supervised learning. However, this is not limiting. The learning processing unit 11g may generate the drug prediction model 12b based on a reinforcement learning technique, for example, by providing a reward according to the appropriateness of the administered drug. For example, the learning processing unit 11g may generate the drug prediction model 12b through ensemble learning, which combines multiple types of learning models.

[0034] 3 is a block diagram showing the configuration of a terminal device 3 according to this embodiment. The terminal device 3 according to this embodiment is configured to include a processing unit 31, a memory unit (storage) 32, a communication unit (transceiver) 33, a display unit (display) 34, an operation unit 35, and a camera 36. The terminal device 3 is a device used by a doctor 102 who administers a drug to a patient 101, and can be configured using an information processing device such as a smartphone, a tablet terminal device, or a personal computer.

[0035] The processing unit 31 is configured using an arithmetic processing device such as a CPU or an MPU, a ROM, etc. The processing unit 31 reads out and executes a program 32a stored in the storage unit 32 to perform various processes such as a process of acquiring a patient ID assigned to the patient 101, a process of acquiring and displaying a predicted result of drug administration by the server device 1, and a process of receiving input of feedback information regarding drug administration from the doctor 102.

[0036] The storage unit 32 is configured using, for example, a non-volatile memory element such as a flash memory or a storage device such as a hard disk. The storage unit 32 stores various programs executed by the processing unit 31 and various data required for processing by the processing unit 31. In this embodiment, the storage unit 32 stores the program 32a executed by the processing unit 31. In this embodiment, the program 32a is distributed by a remote server device or the like, and the terminal device 3 acquires it via communication and stores it in the storage unit 32. However, the program 32a may also be written to the storage unit 32, for example, during the manufacturing stage of the terminal device 3. For example, the program 32a may be recorded on a recording medium 98 such as a memory card or an optical disk, and the terminal device 3 reads the program 32a and stores it in the storage unit 32. For example, the program 32a may be recorded on the recording medium 98 and read by a writing device and written to the storage unit 32 of the terminal device 3. The program 32a may be provided in the form of distribution via a network or in the form of being recorded on the recording medium 98.

[0037] The communication unit 33 communicates with various devices via a network N including a mobile phone communication network, a wireless LAN, the Internet, etc. In this embodiment, the communication unit 33 communicates with the server device 1 via the network N. The communication unit 33 transmits data provided by the processing unit 31 to other devices, and provides data received from other devices to the processing unit 31.

[0038] The display unit 34 is configured using a liquid crystal display or the like, and displays various images, characters, etc. based on processing by the processing unit 31. The operation unit 35 accepts user operations and notifies the processing unit 31 of the accepted operations. For example, the operation unit 35 accepts user operations using an input device such as a mechanical button or a touch panel provided on the surface of the display unit 34. Furthermore, for example, the operation unit 35 may be an input device such as a mouse and a keyboard, and these input devices may be configured to be detachable from the terminal device 3.

[0039] The camera 36 is configured using an imaging element such as a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor. The camera 36 is disposed, for example, in an appropriate position on the housing of the terminal device 3. The camera 36 provides data of images (moving images) captured by the imaging element to the processing unit 31. The camera 36 may be built into the terminal device 3 or may be configured to be detachable from the terminal device 3.

[0040] In addition, in the terminal device 3 of this embodiment, the processing unit 31 reads and executes the program 32a stored in the memory unit 32, so that the patient ID acquisition unit 31a, the drug administration information acquisition unit 31b, the feedback information receiving unit 31c, etc. are realized in the processing unit 31 as software functional units.

[0041] The patient ID acquisition unit 31a performs a process of acquiring the patient ID assigned to the patient 101 to whom a drug is to be administered. In this embodiment, the patient ID is printed as a two-dimensional code 110, for example, on the patient's 101 clothing, bed, hospital room, or medical record printed on paper, and the doctor 102 acquires the patient ID by photographing the two-dimensional code 110 using the camera 36 of the terminal device 3. The patient ID acquisition unit 31a acquires an image of the two-dimensional code 110 photographed by the camera 36, ​​and converts the two-dimensional code 110 captured in the acquired image into a patient ID, thereby acquiring the patient ID. The patient ID acquisition unit 31a transmits the acquired patient ID to the server device 1.

[0042] In this embodiment, the two-dimensional code 110 is used to acquire the patient ID, but this is not limiting and a one-dimensional code (so-called barcode) may be used, and the patient ID may be acquired by any method. For example, the doctor 102 may use the operation unit 35 of the terminal device 3 to directly input the patient ID consisting of numbers and letters, or the terminal device 3 may acquire the patient ID stored as data in an IC (Integrated Circuit) tag or the like by short-range wireless communication.

[0043] The drug administration information acquiring unit 31b performs a process of acquiring drug administration information including information such as the type, dosage, and administration rate of the drug predicted by the server device 1. When the patient ID acquiring unit 31a transmits the patient ID, the server device 1 predicts the type, dosage, and administration rate of the drug to be administered to the patient 101 associated with this patient ID, and transmits the prediction result to the terminal device 3 as drug administration information. The drug administration information acquiring unit 31b acquires the drug administration information transmitted by the server device 1 by receiving it via the communication unit 13, and displays the acquired drug administration information on the display unit 34. The doctor 102 determines the type, dosage, and administration rate of the drug to be administered to the patient 101 based on the type, dosage, and administration rate displayed on the terminal device 3. Based on this determination, the doctor 102 or a nurse or the like can load the drug into the pump 5, set the dosage and administration rate, and operate the pump 5 to administer the drug to the patient 101. However, the type, dosage and administration rate of the drug to be administered to the patient 101 do not need to be exactly the same as those displayed on the terminal device 3, and can be modified or changed by the doctor 102 as appropriate.

[0044] The feedback information receiving unit 31c receives feedback information regarding drug administration from the doctor 102 who has determined the type, dosage, and administration rate of the drug to be administered to the patient 101. For example, the feedback information receiving unit 31c displays the type, dosage, and administration rate of the drug based on the drug administration information acquired from the server device 1, and inquires whether the doctor 102 has made any corrections to the displayed type, dosage, and administration rate of the drug. If the doctor 102 has made any corrections, the feedback information receiving unit 31c receives input of the corrected type, dosage, or administration rate of the drug. For example, the feedback information receiving unit 31c may inquire of the doctor 102 after a predetermined time has elapsed since the drug administration whether the type, dosage, and administration rate of the drug administered to the patient 101 were appropriate, and receive an input of the doctor's response regarding whether the drug was appropriate. If the drug was inappropriate, the feedback information receiving unit 31c may also receive input of the type, dosage, and administration rate of the drug that the doctor 102 considers appropriate. For example, the feedback information receiving unit 31c may inquire of the doctor 102 after a predetermined time has elapsed since the drug administration whether the patient 101's condition has improved or worsened, and receive an input of the response. The feedback information receiving unit 31c receives the input from the doctor 102 and transmits the input information to the server device 1 as feedback information.

[0045] <Drug prediction model generation process> 4 is a schematic diagram for explaining the configuration of a drug prediction model 12b according to this embodiment. The drug prediction model 12b according to this embodiment is a learning model generated in advance by machine learning so as to receive medical record data of a patient 101 to be administered a drug as an input, and to output the type, dosage, and administration rate of the drug to be administered to the patient 101. In this embodiment, a neural network learning model, for example, can be adopted as the drug prediction model 12b.

[0046] The medical record data input to the drug prediction model 12b may include various information such as the age, weight, primary disease, test results, and treatment history of the patient 101. The medical record data may also include information such as information input by the doctor 102 when examining the patient 101, various test results performed on the patient 101, information about surgeries performed on the patient 101, or information about drugs that have been administered to the patient 101. A plurality of pieces of information included in the medical record data are input to the drug prediction model 12b. Note that when the information included in the medical record data is numerical information, this numerical information may be input directly to the drug prediction model 12b, or may be normalized to a numerical value in the range of 0 to 1, for example, and then input to the drug prediction model 12b.

[0047] Furthermore, when the information included in the medical record data is not numerical information but information such as character strings, preprocessing is performed to appropriately convert this information into numerical information, and the converted numerical information is input to the drug prediction model 12b. For the conversion from character string information to numerical information, a learning model that performs natural language processing, such as an RNN (Recurrent Neural Network), an LSTM (Long Short Term Memory), or a BERT (Bidirectional Encoder Representations from Transformers), may be used. Alternatively, the drug prediction model 12b may be configured as a learning model that performs natural language processing, and character string information may be directly input to the drug prediction model 12b.

[0048] The medical record data may also include images such as X-rays or CT (Computed Tomography). Images included in the medical record data are converted in advance into numerical information such as multidimensional feature vectors, and then input to the drug prediction model 12b. A learning model that handles images, such as a CNN (Convolutional Neural Network), may be used to convert images into numerical information. Alternatively, the drug prediction model 12b may be a learning model that handles images, and images may be directly input to the drug prediction model 12b.

[0049] The drug prediction model 12b according to this embodiment outputs information on the type, dosage, and administration rate of a drug to be administered to the patient 101 of the input medical chart data. In the example of FIG. 4, one drug prediction model 12b is shown as outputting three types of information, namely, the type, dosage, and administration rate of a drug, but this is not limited to this. The drug prediction model 12b may be divided into three learning models, for example, a learning model that outputs the type of drug in response to input medical chart data, a learning model that outputs the dosage, and a learning model that outputs the administration rate. In this case, the type of drug may be input together with the medical chart data to the learning model that outputs the dosage and the learning model that outputs the administration rate.

[0050] The drug prediction model 12b outputs, for example, a numerical value according to the number of types of drugs, and each numerical value indicates the likelihood (certainty) of administering the corresponding drug. In the example of FIG. 4, "drug A," "drug B," "drug C," etc. are shown as output nodes. The drug corresponding to the maximum value among the multiple numerical values ​​output by the drug prediction model 12b is the type of drug to be administered to the patient 101 of the input medical record data.

[0051] Furthermore, the drug prediction model 12b outputs, for example, a numerical value of the drug dosage and a numerical value of the administration rate. In the example of FIG. 4, these are shown as output nodes of "dosage" and "administration rate." Note that in this example, the drug prediction model 12b outputs the drug dosage and administration rate as one value each, but this is not limited thereto. For example, the drug prediction model 12b may be configured to output the dosage and administration rate for each type of drug, such as the dosage and administration rate of drug A, the dosage and administration rate of drug B, the dosage and administration rate of drug C, etc.

[0052] The generation of the drug prediction model 12b according to this embodiment is performed by so-called supervised machine learning using previously prepared learning data. A designer or manager of the information processing system according to this embodiment generates learning data (supervised data) that associates the medical record data of patients to whom drugs have been administered with the appropriate type, dosage, and administration rate of the drug administered to the patient, based on past medical record data and drug administration data accumulated in the medical institution, and stores the data in the storage unit 12 of the server device 1.

[0053] 5 is a flowchart showing the procedure of the process of generating the drug prediction model 12b performed by the server device 1 according to this embodiment. The learning processing unit 11g of the processing unit 11 of the server device 1 reads out learning data stored in advance in the storage unit 12 (step S1). The learning processing unit 11g acquires one or more pieces of data from a plurality of pieces of data (data associating medical record data with drug types, dosages, and administration rates) included in the read learning data (step S2). The learning processing unit 11g inputs the medical record data included in the data acquired in step S2 to the drug prediction model 12b (step S3). The learning processing unit 11g calculates an error between the information on the drug type, dosage, and administration rate included in the data acquired from the learning data in step S2 and the information on the drug type, dosage, and administration rate output by the drug prediction model 12b in response to the input of the medical record data in step S3 (step S4). The learning processing unit 11g updates the parameters of the drug prediction model 12b based on the error calculated in step S4 (step S5).

[0054] The learning processing unit 11g determines whether the processing of steps S2 to S5 has been completed for all data included in the learning data read out in step S1 (step S6). If the processing has not been completed for all data (S6: NO), the learning processing unit 11g returns to step S2, acquires other data from the learning data, and repeats the same processing. If the processing has been completed for all data (S6: YES), the learning processing unit 11g ends the generation processing of the drug prediction model 12b. Note that in the illustrated procedure, the learning processing unit 11g performs machine learning using the learning data once and then ends the processing, but this is not limited thereto, and machine learning may be performed repeatedly using the same learning data multiple times.

[0055] <Drug prediction processing> In the information processing system according to the present embodiment, a drug prediction model 12b generated by the above-described machine learning is stored in advance in the storage unit 12 of the server device 1, and the server device 1 performs a process of predicting the type, dosage, and administration rate of a drug to be administered to the patient 101 using this drug prediction model 12b. When administering a drug to the patient 101 using the pump 5, for example, the doctor 102 in charge of the patient 101 first uses his / her terminal device 3 to obtain the patient ID of the patient 101. In the present embodiment, the patient ID is obtained by reading a two-dimensional code 110 with the terminal device 3. The terminal device 3 converts the read two-dimensional code 110 into a patient ID and transmits the patient ID to the server device 1.

[0056] The server device 1 acquires the patient ID transmitted by the terminal device 3 and reads out the medical record data corresponding to this patient ID from the medical record DB 7. The server device 1 converts the medical record data into data to be input to the drug prediction model 12b by appropriately preprocessing multiple pieces of information contained in the read medical record data. The server device 1 inputs the input data converted from the medical record data into the drug prediction model 12b and acquires the type of drug, dosage, and administration rate output by the drug prediction model 12b. The server device 1 transmits the type of drug, dosage, and administration rate predicted by the drug prediction model 12b to the terminal device 3 as drug administration information.

[0057] The terminal device 3 receives the drug administration information transmitted by the server device 1 and performs a process of displaying the received information on the display unit 34. FIG. 6 is a schematic diagram showing an example of a display of drug administration information. On the drug administration information notification screen displayed by the terminal device 3 based on the drug administration information received from the server device 1, for example, a title string of "Drug Administration Information" is displayed at the top, and information about the target patient 101, such as a "Patient ID" and a "Patient Name," is displayed below this title string. In this example, the "Patient ID" is "A1234" and the "Patient Name" is "XXXX." The information about the patient 101 displayed by the terminal device 3 on this screen is, for example, information contained in the medical record data of the patient 101. The server device 1 acquires this information necessary for display from the medical record data and transmits it to the terminal device 3 together with the drug administration information. Note that any information about the patient 101 may be displayed.

[0058] The terminal device 3 also displays the "drug type," "dosage," and "administration rate," which are the prediction results of the drug prediction model 12b, below the information about the patient 101. In this example, the "drug type" is "drug A," the "dosage" is "5.8," and the "administration rate" is "0.4." Based on this information displayed on the terminal device 3, the doctor 102 can set the specified drug type (drug A) to the pump 5 at the specified dosage (5.8), set the administration rate of the pump 5 to the specified administration rate (0.4), and operate the pump 5. Note that operations such as setting the drug in the pump 5 and setting the administration rate may not be performed directly by the doctor 102, but may be performed by a nurse or the like under the instructions of the doctor 102.

[0059] In this embodiment, the doctor 102 has the final say on the type, dosage, and administration rate of the drug to be administered to the patient 101, and the drug may be administered to the patient 101 at a type, dosage, or administration rate different from the type, dosage, and administration rate displayed by the terminal device 3. When the doctor 102 makes such corrections to the type, dosage, and administration rate of the drug, the terminal device 3 has an input box on the drug administration information notification screen for receiving input of correction values ​​in order to collect feedback information on what corrections have been made.

[0060] In the illustrated example, the information on "drug type," "dosage," and "administration rate" is displayed vertically at the lower left of the drug administration information notification screen, and the terminal device 3 displays three input boxes corresponding to "drug type," "dosage," and "administration rate" vertically at the lower right of the drug administration information notification screen, separated by a right-pointing arrow symbol. The input box corresponding to "drug type" is what is known as a pull-down box, pull-down menu, or drop-down list, and the doctor 102 can select one of multiple drugs registered in advance. The doctor 102 directly inputs numerical values ​​into the input boxes corresponding to "dosage" and "administration rate."

[0061] When the doctor 102 inputs corrected values ​​for the type, dosage, and administration rate of the drug, the terminal device 3 transmits the input values ​​as feedback information to the server device 1. The server device 1 receives the feedback information transmitted from the terminal device 3 and stores it in the drug administration DB 8. As a result, for example, for the medical record data of the patient 101, it is determined that the corrected values ​​input by the doctor 102 are appropriate, rather than the type, dosage, and administration rate of the drug predicted by the drug prediction model 12b, and learning data that associates this medical record data with the type, dosage, and administration rate of the drug corrected by the doctor 102 is generated and can be used for re-learning the drug prediction model 12b.

[0062] 7 is a flowchart showing the procedure of the drug prediction process performed by the server device 1 according to this embodiment. The patient ID acquiring unit 11a of the processing unit 11 of the server device 1 according to this embodiment determines whether or not the patient ID of the patient 101 to be administered a drug has been received from the terminal device 3 (step S21). If the patient ID has not been received, the patient ID acquiring unit 11a waits until the patient ID is received from the terminal device 3.

[0063] If the patient ID is received (S21: YES), the medical record data acquisition unit 11b of the processing unit 11 reads out the medical record data corresponding to the patient ID acquired in step S21 from the medical record DB 7 (step S22). The drug prediction processing unit 11c of the processing unit 11 inputs the medical record data of the patient 101 read out in step S22 into the drug prediction model 12b (step S23) and acquires the type, dosage, and administration rate of the drug output by the drug prediction model 12b (step S24). The drug administration information output unit 11d of the processing unit 11 transmits (outputs) the drug administration information including the type, dosage, and administration rate of the drug acquired in step S24 to the terminal device 3 (step S25), and causes the terminal device 3 to display the drug administration information.

[0064] The feedback information acquisition unit 11f of the processing unit 11 determines whether the type, dosage, and administration rate of the drug have been modified on the terminal device 3 displaying the drug administration information (step S26). If modifications have been made (S26: YES), the feedback information acquisition unit 11f acquires information on the modified type, dosage, and administration rate of the drug from the terminal device 3, stores the acquired information as feedback information in the drug administration DB8 (step S27), and terminates the process. If modifications have not been made (S26: NO), the processing unit 11 terminates the process.

[0065] 8 is a flowchart showing the procedure of the medication prediction process performed by the terminal device 3 according to this embodiment. The patient ID acquisition unit 31a of the processing unit 31 of the terminal device 3 according to this embodiment acquires the two-dimensional code 110 of the patient 101 by photographing with the camera 36 (step S41). The patient ID acquisition unit 31a converts the acquired two-dimensional code 110 into a patient ID (step S42), thereby acquiring the patient ID. The patient ID acquisition unit 31a transmits the acquired patient ID to the server device 1 (step S43).

[0066] The drug administration information acquisition unit 31b of the processing unit 31 determines whether or not the drug administration information transmitted by the server device 1 in response to the transmission of the patient ID has been received (step S44). If the drug administration information has not been received (S44: NO), the drug administration information acquisition unit 31b waits until the drug administration information is received from the server device 1. If the drug administration information has been received (S44: YES), the drug administration information acquisition unit 31b displays the acquired drug administration information on the display unit 34 (step S45).

[0067] The feedback information receiving unit 31c of the processing unit 31 determines whether the doctor 102 has made any corrections to the drug type, dosage, and administration rate of the drug administration information displayed on the display unit 34 (step S46). If the drug type, dosage, and administration rate have been corrected (S46: YES), the feedback information receiving unit 31c acquires the corrected drug type, dosage, and administration rate, and transmits this information to the server device 1 as feedback information (step S47), thereby terminating the processing. If the drug type, dosage, and administration rate have not been corrected (S46: NO), the processing unit 31 terminates the processing.

[0068] <Information collection processing> In the information processing system according to this embodiment, the server device 1 performs an information collection process of collecting information on drug administration to the patient 101 and storing and accumulating it in the drug administration DB 8. When the doctor 102 modifies the type, dosage, and administration rate of the drug on the above-mentioned drug administration information notification screen, the server device 1 also performs a process of storing the modified values ​​as feedback information in the drug administration DB 8. Note that when no modification is made by the doctor 102, the server device 1 may store the type, dosage, and administration rate of the drug predicted by the drug prediction model 12b in the drug administration DB 8.

[0069] In addition to collecting the information described above, the server device 1 according to this embodiment collects and stores in the drug administration DB8 (1) vital information of the patient 101 to whom the drug has been administered, (2) information regarding the appropriateness of the type, dosage, and administration rate of the drug administered to the patient 101, and (3) information regarding the doctor 102's judgment regarding the patient 101 to whom the drug has been administered (appropriateness of the drug, the condition of the patient 101, etc.).

[0070] (1) Vital information of the patient who received the drug In the information processing system according to this embodiment, vital information such as heart rate, respiratory rate, blood pressure, and body temperature is measured by measuring instrument 6 for patient 101 to whom a drug is administered by pump 5. Measuring instrument 6 displays the measured vital information on its own display unit and transmits it to server device 1 via the network. Server device 1 receives the vital information transmitted by measuring instrument 6 and stores the vital information in drug administration DB 8 in association with information such as the patient ID and date and time.

[0071] The measuring device 6 performs measurements at a predetermined interval, such as one second or one minute, and transmits the measurement results to the server device 1 as vital information. However, the server device 1 does not have to store all of the vital information received from the measuring device 6 in the drug administration DB 8, and may store the vital information at a frequency of, for example, once every few tens of seconds or once every few minutes. In this case, the average value, maximum value, minimum value, etc. may be calculated for multiple sets of vital information, and these calculation results may be stored in the drug administration DB 8.

[0072] (2) Information on the appropriateness of the type, dosage, and administration rate of the medication administered to the patient. The server device 1 according to this embodiment determines whether or not there is an abnormality in the patient 101 to whom a drug has been administered, based on the vital information received from the measuring device 6. For example, the server device 1 has preset thresholds for determining abnormality for each piece of information included in the vital information, such as heart rate, respiratory rate, blood pressure, and body temperature, and determines whether or not there is an abnormality in the patient 101 by comparing each piece of information included in the vital information received from the measuring device 6 with the corresponding threshold. When the server device 1 determines that there is an abnormality in the patient 101, it stores the vital information of the patient 101 at that time in association with information such as a flag indicating that there has been an abnormality in the drug administration DB 8. The threshold for determining abnormality is set in advance by, for example, the doctor 102. Any method may be used to determine whether or not there is an abnormality based on the vital information.

[0073] Furthermore, for example, if a predetermined time (e.g., several tens of minutes or several hours) has passed without any abnormalities since the start of drug administration to the patient 101, the server device 1 according to this embodiment determines whether the drug administered to the patient 101 is appropriate based on a plurality of vital sign information received from the measuring device 6 and stored in the drug administration DB 8. For example, the server device 1 compares the vital sign information immediately after the start of drug administration with the vital sign information after the predetermined time has passed, and determines whether the patient 101's vital sign has improved or deteriorated, thereby determining whether the drug was appropriate. The server device 1 determines that the patient 101 has improved if the vital sign information after the predetermined time has passed has changed in an improvement direction exceeding a threshold value compared to the vital sign information immediately after the start of drug administration. If the vital sign information has changed in a deterioration direction exceeding a threshold value, the server device 1 determines that the patient 101 has deteriorated. If there is no change exceeding either threshold, the server device 1 determines that the drug was appropriate. If the patient 101 improves, the server device 1 determines that the drug was appropriate. If the patient 101 deteriorates, the server device 1 determines that the drug was inappropriate. Whether or not the medicine was appropriate when there is no change in the vital information can be determined appropriately depending on, for example, the condition of the patient 101 or the type of medicine administered.

[0074] 9 is a flowchart showing the procedure of information collection processing on vital information by the server device 1 according to this embodiment. The vital information acquisition unit 11e of the processing unit 11 of the server device 1 according to this embodiment determines whether or not vital information such as the heart rate, respiratory rate, blood pressure, and body temperature measured for the patient 101 to whom a drug has been administered has been received from the measuring device 6 (step S61). If vital information has not been received (S61: NO), the vital information acquisition unit 11e waits until vital information is received from the measuring device 6. If vital information has been received (S61: YES), the vital information acquisition unit 11e stores the received vital information in the drug administration DB 8 (step S62).

[0075] Furthermore, the vital information acquiring unit 11e compares one or more measurement values ​​included in the received vital status with a predetermined threshold value to determine whether or not there is an abnormality in the vital information of the patient 101 (step S63). If there is an abnormality in the vital information (S63: YES), the vital information acquiring unit 11e notifies the abnormality, for example, by sending a message to the terminal device 3 (step S64). The vital information acquiring unit 11e stores in the drug administration DB 8 information that the abnormality has occurred due to drug administration (step S65), and ends the process.

[0076] If there is no abnormality in the vital information (S63: NO), the vital information acquisition unit 11e determines whether a predetermined time has elapsed since the drug was administered to the patient 101 (step S66). If the predetermined time has not elapsed (S66: NO), the vital information acquisition unit 11e returns the process to step S61 and repeats the above-mentioned process. If the predetermined time has elapsed (S66: YES), the vital information acquisition unit 11e determines whether the drug administered to the patient 101 is appropriate based on the plurality of pieces of vital information stored since the start of drug administration (step S67). The vital information acquisition unit 11e stores the determination result of the drug's appropriateness in the drug administration DB 8 as feedback information (step S68), and ends the process.

[0077] Based on this information stored in the drug administration DB8, for example, for the administration of a drug determined to be appropriate, learning data that associates the medical record data of the patient 101 at the time the drug was administered with the type, dosage, and administration rate of the drug determined to be appropriate is generated, and can be used for re-learning the drug prediction model 12b. Note that the drug administration DB8 stores the determination result based on vital information, but the vital information itself used for the determination does not need to be stored in the drug administration DB8.

[0078] (3) Information about the doctor's judgment regarding the patient to whom the drug was administered For example, when a predetermined time (e.g., several tens of minutes, several hours, etc.) has elapsed since the start of administration of a drug to the patient 101, the server device 1 according to this embodiment inquires of the doctor 102 whether the type, dosage, and administration rate of the administered drug were appropriate, and about the condition of the patient 101 after administration, and acquires a response from the doctor 102 and stores the response as feedback information in the drug administration DB 8. For example, when a predetermined time has elapsed since the server device 1 transmitted the prediction result of the drug prediction model 12b to the terminal device 3 as drug administration information, the server device 1 causes the terminal device 3 to display a progress information inquiry screen, and acquires feedback information from the doctor 102.

[0079] 10 is a schematic diagram showing an example of a display of a progress information inquiry screen. When a predetermined time has elapsed since the start of administration of a drug to the patient 101, the terminal device 3 displays the illustrated inquiry screen on the display unit 34 in response to an instruction from the server device 1. On the illustrated inquiry screen, for example, a title string of "Progress after drug administration" is displayed at the top, and information about the patient 101 to whom the drug was administered, such as "Patient ID" and "Patient Name", is displayed below this title string.

[0080] The terminal device 3 displays, below the information about the patient 101 to whom a drug was administered, the item name "<Administered drug>" and, as information about the drug administered to this patient 101, "Type of drug," "Dosage," and "Administration rate." The terminal device 3 also provides an input box on the inquiry screen for accepting input of information regarding drug correction when the doctor 102 determines that the drug administered to the patient 101 is not appropriate and that the drug needs to be corrected. In the illustrated example, the terminal device 3 displays three input boxes corresponding to the "Type of drug," "Dosage," and "Administration rate" of "<Administered drug>" provided on the left side of the inquiry screen, with "Modification required" and a right-facing arrow between them. Below these, a checkbox for selecting "No correction" is provided to respond that the doctor 102 determined that the administered drug was appropriate.

[0081] The terminal device 3 also displays, below the above-mentioned "<Administered medication>" item, the item name "<Patient's condition>" and three check boxes for receiving selections from the doctor 102. The three check boxes are for receiving selections of "improvement," "no change," or "worsening" regarding the condition of the patient 101.

[0082] In addition, a button labeled "Answer" is provided at the bottom right of the inquiry screen. When the "Answer" button is clicked or touched, the terminal device 3 transmits the information entered on the inquiry screen as feedback information to the server device 1. The server device 1 acquires the feedback information transmitted by the terminal device 3 and stores it in the drug administration DB8.

[0083] 11 is a flowchart showing the procedure of a feedback information acquisition process performed by the server device 1 according to this embodiment. The feedback information acquisition unit 11f of the processing unit 11 of the server device 1 according to this embodiment determines whether or not a predetermined time has elapsed since the start of administration of a drug to the patient 101 (step S81). If the predetermined time has not elapsed (S81: NO), the feedback information acquisition unit 11f waits until the predetermined time has elapsed. If the predetermined time has elapsed (S81: YES), the feedback information acquisition unit 11f issues a display instruction or the like to the terminal device 3 to display a progress information inquiry screen on the display unit 34, and inquires of the doctor 102 about the progress of drug administration (step S82).

[0084] The feedback information acquiring unit 11f determines whether or not there is a response from the doctor 102 to the progress inquiry based on whether or not feedback information has been sent from the terminal device 3 (step S83). If there is no response (S83: NO), the feedback information acquiring unit 11f waits until a response is received from the terminal device 3. If there is a response (S83: YES), the feedback information acquiring unit 11f stores feedback information including information such as the suitability of the drug inputted by the terminal device 3 as a response to the inquiry and changes in the condition of the patient 101 in the drug administration DB 8 (step S84), and ends the process.

[0085] Based on this information stored in the drug administration DB8, for example, for the administration of a drug that the doctor 102 judges to be appropriate and that has improved the patient's condition, learning data is generated that matches the patient's 101 medical record data at the time the drug was administered with the type, dosage, and administration rate of the drug that the doctor 102 judged to be appropriate, and can be used for re-learning the drug prediction model 12b.

[0086] <Summary> In the information processing system according to the present embodiment having the above configuration, server device 1 acquires medical record data of patient 101, inputs the medical record data to drug prediction model 12b that has undergone machine learning in advance, acquires the type, dosage, and administration rate of the drug output by drug prediction model 12b, and transmits this acquired information as drug administration information to terminal device 3, thereby displaying the drug administration information on display unit 34 of terminal device 3. As a result, the information processing system according to the present embodiment is expected to assist doctor 120 and the like in administering drugs to patient 101.

[0087] Furthermore, in the information processing system according to this embodiment, the server device 1 acquires the patient ID from the terminal device 3 that reads the patient ID of the patient 101 using the two-dimensional code 110, and acquires the medical record data corresponding to the acquired patient ID from the medical record DB 7 that stores the medical record data of multiple patients. This allows the server device 1 to easily acquire the medical record data to be input to the drug prediction model 12b.

[0088] In the information processing system according to this embodiment, the server device 1 receives, via the terminal device 3, corrections made by the doctor 102 to the type, dosage, and administration rate of the drug predicted by the drug prediction model 12b, and stores information about the corrected type, dosage, and administration rate of the drug as feedback information in the drug administration DB 8. In the information processing system according to this embodiment, the server device 1 acquires vital sign information measured by the measuring device 6 for the patient 101 to whom the drug has been administered, and stores the acquired vital sign information as feedback information in the drug administration DB 8. In the information processing system according to this embodiment, the server device 1 determines the appropriateness of the type, dosage, and administration rate of the drug predicted by the drug prediction model 12b based on the vital sign information acquired from the measuring device 6, and stores the determination result as feedback information in the drug administration DB 8. In addition, in the information processing system of this embodiment, the server device 1 accepts input of information from the doctor 102 via the terminal device 3 regarding the appropriateness of the medication administered to the patient 101, or regarding events that have occurred in response to the administration of the medication (for example, changes in the patient's 101 condition), and stores this accepted information in the medication DB 8 as feedback information.

[0089] By storing and accumulating this feedback information in the drug administration DB 8, it is possible to generate learning data for training (relearning) the drug prediction model 12b using the accumulated information. The server device 1 can acquire the learning data generated based on the feedback information stored in the drug administration DB 8 and perform re-training of the drug prediction model 12b. This is expected to improve the accuracy of the type of drug, dosage, and administration rate output by the drug prediction model 12b.

[0090] Furthermore, in the information processing system according to this embodiment, the server device 1 acquires learning data in which the patient's medical record data is associated with the type, dosage, and administration rate of a drug to be administered to the patient, and generates a drug prediction model 12b using the acquired learning data. This enables the information processing system to predict the appropriate type, dosage, and administration rate of a drug to be administered to the patient 101 using the drug prediction model 12b that has been subjected to machine learning, and is expected to support the work of a doctor 102 or the like who administers the drug.

[0091] Furthermore, in the information processing system according to this embodiment, the server device 1 collects the medical record data of the patient 101, the type, dosage, and administration rate of the drug administered to the patient 101, and vital information of the patient 101 to whom the drug was administered, and stores them in the drug administration DB 8. This makes it possible for the information processing system to generate learning data for performing machine learning of the drug prediction model 12b based on the information stored and accumulated in the drug administration DB 8.

[0092] The embodiments disclosed herein are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0093] 1. Server device 3 Terminal Devices 5. Pump 6. Measuring Instruments 7 Medical Record DB 8. Drug Administration DB 11 Processing section 11a Patient ID acquisition section 11b Medical record data acquisition section 11c Drug Prediction Processing Unit 11d Drug administration information output unit 11e Vital information acquisition unit 11f Feedback information acquisition section 11g Learning processing section 12 Storage section 12a Server Program 12b Drug Prediction Model 13 Communications Department 31 Processing section 31a Patient ID acquisition section 31b Drug administration information acquisition unit 31c Feedback Information Reception Department 32 Storage section 32a Program 33 Communications Department 34 Display section 35 Control section 36 Camera 98,99 Recording media 101 patients 102 Doctor 110 QR Code N Network

Claims

1. The information processing device Obtain patient chart data, The acquired medical record data is input into a learning model that has been machine-learned to output the type, dosage, and administration rate of a drug to be administered to the patient in response to input of the patient's medical record data, and the type, dosage, and administration rate of the drug output by the learning model are obtained; outputting a notification screen on which the acquired information on the type, dosage, and administration rate of the drug is listed and on which input boxes for correction information corresponding to each piece of information are provided; Accepting corrections to the type, dosage, and administration rate of the drug via the output notification screen; storing information regarding the type, dosage, and administration rate of the modified drug; Information processing methods.

2. An information processing device, Obtain patient chart data, The acquired medical record data is input into a learning model that has been machine-learned to output the type, dosage, and administration rate of a drug to be administered to the patient in response to input of the patient's medical record data, and the type, dosage, and administration rate of the drug output by the learning model are obtained; The acquired drug type, dosage, and administration rate are output. After a predetermined time has elapsed since the output, a query screen is output, and for the patient to whom a drug has been administered based on the type, dosage, and administration rate of the drug acquired from the learning model, input of information regarding the appropriateness of the drug or an event occurring in response to the administration of the drug is accepted; storing the received information; Acquires learning data generated based on the stored information, Performing machine learning of the learning model using the acquired learning data. Information processing methods.

3. The information processing device, obtaining an identification of the patient; acquiring medical record data corresponding to the acquired identification information from a database storing medical record data of a plurality of patients; 3. The information processing method according to claim 1.

4. The information processing device, acquiring vital information of the patient to whom a drug has been administered based on the type, dosage, and administration rate of the drug acquired from the learning model; storing the acquired vital information; 4. The information processing method according to claim 1.

5. The information processing device, determining whether the type, dosage, and administration rate of the drug obtained from the learning model are appropriate based on the acquired vital sign information; storing information relating to the suitability determination result; The information processing method according to claim 4.

6. On the computer, Obtain patient chart data, The acquired medical record data is input into a learning model that has been machine-learned to output the type, dosage, and administration rate of a drug to be administered to the patient in response to input of the patient's medical record data, and the type, dosage, and administration rate of the drug output by the learning model are obtained; outputting a notification screen on which the acquired information on the type, dosage, and administration rate of the drug is listed and on which input boxes for correction information corresponding to each piece of information are provided; Accepting corrections to the type, dosage, and administration rate of the drug via the output notification screen; Store information related to the type, dosage, and administration rate of the modified drug. A computer program that executes a process.

7. A computer, Obtain patient chart data, The acquired medical record data is input into a learning model that has been machine-learned to output the type, dosage, and administration rate of a drug to be administered to the patient in response to input of the patient's medical record data, and the type, dosage, and administration rate of the drug output by the learning model are obtained; The acquired drug type, dosage, and administration rate are output. After a predetermined time has elapsed since the output, a query screen is output, and for the patient to whom a drug has been administered based on the type, dosage, and administration rate of the drug acquired from the learning model, input of information regarding the appropriateness of the drug or an event occurring in response to the administration of the drug is accepted; storing the received information; Acquires learning data generated based on the stored information, The learning model is machine-trained using the acquired learning data. A computer program that executes a process.

8. a first acquisition unit that acquires medical record data of a patient; a second acquisition unit that inputs the acquired medical record data into a learning model that has been machine-learned to output the type, dosage, and administration rate of a drug to be administered to the patient in response to input of the patient's medical record data, and acquires the type, dosage, and administration rate of the drug output by the learning model; an output unit that outputs a notification screen on which the acquired information on the type, dosage, and administration rate of the drug is arranged and on which input boxes for correction information corresponding to each piece of information are provided; a reception unit that receives corrections to the type, dosage, and administration rate of the drug via the output notification screen; a memory processing unit that stores information related to the corrected drug type, dosage, and administration rate in a memory unit; An information processing device comprising:

9. A first acquisition unit that acquires patient medical record data; a second acquisition unit that inputs the acquired medical record data into a learning model that has been machine-learned to output the type, dosage, and administration rate of a drug to be administered to the patient in response to input of the patient's medical record data, and acquires the type, dosage, and administration rate of the drug output by the learning model; an output unit that outputs the acquired type, dosage, and administration rate of the drug; a reception unit that outputs a query screen after a predetermined time has elapsed since the output and receives input of information regarding the appropriateness of the drug or an event that occurred in response to the administration of the drug for the patient to whom the drug was administered based on the type, dosage, and administration rate of the drug acquired from the learning model; a storage processing unit that stores the received information in a storage unit; a third acquisition unit that acquires learning data generated based on the stored information; a learning processing unit that performs machine learning of the learning model using the acquired learning data; An information processing device comprising:

Images