Information processing method, program, and information processing device for the efficient removal of radioactive nuclides derived from radiopharmaceuticals

Abstract

To provide an information processing method, etc., that assists in selecting an adsorption column for adsorbing radioactive substances contained in the urine of patients who have received radiopharmaceuticals. [Solution] The information processing method involves acquiring patient information of a patient receiving a radiopharmaceutical, pharmaceutical information relating to the radiopharmaceutical, and configuration information of a wastewater treatment system 30 installed in a medical facility where the radiopharmaceutical is administered. When the patient information, pharmaceutical information, and configuration information are input to a learning model that outputs the configuration of an adsorption column set 36 used for treating urine excreted by the patient, the acquired patient information, the acquired pharmaceutical information, and the acquired configuration information are input to the learning model, and the computer executes a process to acquire the configuration of the adsorption column set 36 from the learning model and output the acquired configuration of the adsorption column set 36.

Description

Technical Field

[0001] The present invention relates to an information processing method, a program, and an information processing apparatus.

Background Art

[0002] There has been proposed a radioactive drug administration facility that performs the administration of a radioactive drug and a waiting period for waiting for the components of the radioactive drug to reach the patient's body at the same location (Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The urine of a patient who has received a radioactive drug contains radioactive substances that are radionuclides derived from the radioactive drug. However, the administration facility of Patent Document 1 does not have a mechanism for appropriately treating the radioactive substances contained in the urine.

[0005] In one aspect, an object is to provide an information processing method or the like that supports the selection of an adsorption column that adsorbs radioactive substances contained in the urine of a patient who has received a radioactive drug.

Means for Solving the Problems

[0006] The information processing method involves acquiring patient information of a patient receiving a radiopharmaceutical, pharmaceutical information relating to the radiopharmaceutical, and configuration information of a wastewater treatment system installed at a medical facility where the radiopharmaceutical is administered. The computer then inputs the acquired patient information, pharmaceutical information, and configuration information into a learning model that outputs the configuration of an adsorption column set used to treat urine excreted by the patient when the patient information, pharmaceutical information, and configuration information are input. The computer then retrieves the configuration of the adsorption column set from the learning model and outputs the retrieved configuration of the adsorption column set. [Effects of the Invention]

[0007] In one respect, this technology can provide information processing methods and other tools to assist in the selection of adsorption columns that adsorb radioactive substances contained in the urine of patients who have received radiopharmaceuticals. [Brief explanation of the drawing]

[0008] [Figure 1] This is an explanatory diagram illustrating the processing of radioactive nuclides excreted from patients. [Figure 2] This is an example of an adsorption column set configuration. [Figure 3] This is an explanatory diagram illustrating the configuration of a radioactive drug use system. [Figure 4] This is an explanatory diagram illustrating the structure of the learning model. [Figure 5] This is an explanatory diagram illustrating the learning process of a learning model. [Figure 6] This is a flowchart that explains the processing flow of a program. [Figure 7] This is an explanatory diagram illustrating the configuration of the radioactive drug use system according to Embodiment 2. [Modes for carrying out the invention]

[0009] [Embodiment 1] Radiopharmaceuticals are used, which are substances that tend to accumulate in target cells such as tumor cells, labeled with radionuclides. The radiation emitted by the radionuclides that accumulate in the target cells damages the target cells.

[0010] The following explanation uses Lutatera®, a radiopharmaceutical used in peptide receptor radionuclide therapy (PRRT), a treatment for neuroendocrine tumors (NETs), a type of rare cancer, as an example.

[0011] It is known that somatostatin receptors are expressed on the surface of neuroendocrine tumor cells with a high probability. In PRRT, Lutatera, a radiopharmaceutical labeled with the radionuclide 177Lu (lutetium-177) to contain a peptide that binds to somatostatin receptors and is taken up by neuroendocrine tumor cells, is administered to the patient by intravenous infusion. The radiopharmaceutical circulates throughout the patient's body via the bloodstream and is eventually taken up by neuroendocrine tumor cells. The beta and gamma rays emitted by 177Lu damage the neuroendocrine tumor cells, causing necrosis. Neuroendocrine tumors are treated through this process.

[0012] Incidentally, in the process of producing 177Lu by irradiating 176Lu (lutetium-176) with neutron beams, the heteronuclide 177m-Lu is also produced. According to the interview form issued regarding Lutatera intravenous injection, the contamination rate of 177m-Lu to 177Lu is less than 0.05 percent.

[0013] Radiopharmaceuticals that are not taken up by neuroendocrine tumor cells are metabolized in the patient's body over time and excreted mainly in the urine. Therefore, the patient's urine contains 177Lu, which has a physical half-life of 6.647 days, in addition to a small amount of 177m-Lu, which has a physical half-life of 160.4 days.

[0014] The presence of 177m-Lu is ignored in drainage standards such as guidelines. In the future, if the number of cases using lutetium increases, there are concerns about the exposure of patients and medical staff in the treatment room, and the residual radioactivity after discharge into the RI (Radio Isotope) drainage tank and sewage. Therefore, it is desirable to realize a system for appropriately collecting radioactive substances in urine at the bedside.

[0015] When a medical institution discharges so-called radioactive wastewater containing radioactive substances such as 177Lu, it is necessary to wait for the radiation dose to decrease to the value specified in the above drainage standards before discharging it into the sewer, or to lower the radiation dose by dilution. By appropriately collecting the radioactive substances contained in the patient's urine at the bedside and preventing them from flowing into the wastewater treatment system provided within the medical institution, doctors can use lutetium for necessary patients without considering the load on the wastewater treatment system.

[0016] Figure 1 is an explanatory diagram for explaining the treatment of radionuclides excreted from a patient. First, the patient will be described. The patient receiving radiotherapy in this embodiment is a patient who has confirmed that somatostatin receptors are expressed in the tumor through a prior examination.

[0017] To prevent the exposure of medical staff, the patient is isolated in a private room. The radioactive drug is administered to the patient in the private room by intravenous drip. The radiation dose emitted from the body is measured, and discharge is permitted after it is confirmed that the dose is below the standard. The hospitalization period is often about one to two days.

[0018] With the above, one administration of the radioactive drug is completed. Even after discharge, the emission of β-rays and γ-rays from 177Lu incorporated into neuroendocrine tumor cells continues, and the treatment of neuroendocrine tumors continues. The administration of the radioactive drug is, in principle, carried out four times at intervals of eight weeks.

[0019] When a toilet is provided in a private room, the wastewater from the toilet flows into the wastewater dilution tank 37 through the adsorption column set 36. An apparatus for removing solids such as feces and toilet paper may be disposed between the toilet and the adsorption column set 36. Since the removed solids and the used adsorption column set 36 are radioactive wastes, they are separately and appropriately processed.

[0020] When a toilet is not provided in a private room, a patient staying in the private room stores urine in a urine storage container. The urine storage container may be disposed in the private room or in a separate room within the radiation control area. During cleaning operations such as after the patient has left the private room, the urine stored in the urine storage container flows into the wastewater dilution tank 37 through the adsorption column set 36.

[0021] In FIG. 1, the adsorption column set 36 and the wastewater dilution tank 37 indicated by the solid-line frame process the urine of the patient shown in the upper left of FIG. 1. The adsorption column set 36 and the wastewater dilution tank 37 indicated by the dashed-line frame in FIG. 1 process the urine of another patient (illustration omitted). The adsorption column set 36 and the wastewater dilution tank 37 may be arranged to process the urine of a plurality of patients together.

[0022] The wastewater after being diluted in the wastewater dilution tank 37 is discharged into the public sewer 39 through the wastewater treatment system 30. Specifically, the wastewater after being diluted in the wastewater dilution tank 37 is first sent to the wastewater storage tank 31. General wastewater generated within the medical facility also flows into the wastewater storage tank 31.

[0023] A wastewater monitoring device 32 is installed between the wastewater storage tank 31 and the public sewer. The wastewater monitoring device 32 includes a RI monitor 321 for measuring the radiation dose in the wastewater. The wastewater monitoring device 32 may include, for example, a water quality monitoring monitor for measuring BOD (Biochemical Oxygen Demand) and COD (Chemical Oxygen Demand), a wastewater purification device, and a wastewater dilution device.

[0024] The wastewater stored in the wastewater storage tank 31 is discharged into the sewer system 39 after it has been confirmed to meet various environmental standards. In this way, the 177 Lu excreted from the patient's body is safely disposed of.

[0025] This section describes the treatment of urine using an adsorption column set 36 and a wastewater dilution tank 37. The components of excreted urine and the amount of 177Lu contained in the urine vary from patient to patient. The 177Lu content and purity in radiopharmaceuticals vary depending on the manufacturing plant of the radiopharmaceutical and the time elapsed from the manufacture of the radionuclide to administration to the patient. Therefore, even for the same patient, the amount of 177Lu excreted in the urine may vary if the manufacturing plant of the administered drug is different.

[0026] Incidentally, for each patient, if the amount of 177Lu and 177m-Lu contained in the wastewater discharged from the adsorption column set 36 or the wastewater dilution tank 37 conforms to the environmental standards for wastewater containing radionuclides, then problems caused by 177Lu and 177m-Lu excreted in the patient's urine are unlikely to occur in the wastewater monitoring device 32.

[0027] However, as shown in Figure 1, wastewater discharged from medical facilities includes general wastewater that does not contain 177Lu in the first place. In some medical facilities, the wastewater may also include wastewater discharged in connection with examinations using radionuclides with significantly different physical half-lives from 177Lu, such as 18F (fluorine-18) used in FDG-PET (fluorodeoxyglucose-positron emission tomography) and 131I (iodine-131) used in radioactive iodine therapy.

[0028] In this situation, treating the urine excreted by individual patients to a state that meets environmental standards is excessive, leading to increased operating costs for medical facilities and, consequently, increased medical expenses. In other words, the wastewater treated with the adsorption column set 36 and the wastewater dilution tank 37 from individual patients does not necessarily need to meet environmental standards.

[0029] In this embodiment, a radiopharmaceutical use system 10 is provided that uses an appropriate adsorption column set 36 for each patient to maintain the wastewater discharged from the wastewater treatment system 30 in a state that conforms to environmental standards.

[0030] The adsorption column set 36 is composed of multiple adsorption columns 361 (see Figure 2). The adsorption columns 361 are described below. Table 1 shows examples of six types of adsorption columns 361. The adsorption column 361 is, for example, roughly cylindrical in shape with an outer diameter of approximately 8 centimeters and a height of approximately 25 centimeters, and has an inlet and an outlet on its end face. Adsorption columns 361 of different sizes may be provided. 177Lu and proteins in the urine injected from the inlet are adsorbed by the adsorbent shown in Table 1. The urine after adsorption treatment flows out from the outlet.

[0031] [Table 1]

[0032] Figure 2 shows an example configuration of the adsorption column set 36. Figure 2 shows the adsorption column set 36 in which a total of three adsorption columns 361 of type A, type C, and type D are connected in series from the inlet side. In many cases, the combination of the three adsorption columns 361 can realize an adsorption column set 36 that adsorbs and efficiently removes 177 Lu from urine.

[0033] However, the composition of urine excreted by each patient is influenced by their constitution and any diseases they may have. Therefore, in some cases, it may be appropriate to use an adsorption column set 36 that combines two or fewer adsorption columns 361, or four or more. In some cases, it may be appropriate to use an adsorption column set 36 in which adsorption columns 361 are connected in parallel.

[0034] Although not shown in Table 1, the price of adsorption column 361 varies depending on the type. The configuration of the adsorption column set 36 used for each patient should ideally be determined considering not only the 177 Lu adsorption efficiency but also the price of the adsorption column 361 used.

[0035] Furthermore, the replacement of the adsorption column set 36 may involve replacing the entire adsorption column set 36, which includes multiple adsorption columns 361, or it may involve replacing only a portion of the adsorption columns 361 included in the adsorption column set 36.

[0036] Figure 3 is an explanatory diagram illustrating the configuration of the radiopharmaceutical use system 10. In addition to the aforementioned wastewater treatment system 30, the radiopharmaceutical use system 10 includes an information processing device 20, a weather forecast site 18, and an electronic medical record system 17.

[0037] The information processing device 20 comprises a control unit 21, a main memory 22, an auxiliary memory 23, a communication unit 24, a display unit 25, an input unit 26, and a bus. The control unit 21 is an arithmetic control device that executes the program of this embodiment. One or more CPUs (Central Processing Units), GPUs (Graphics Processing Units), or multi-core CPUs are used in the control unit 21. The control unit 21 is connected to each hardware component of the information processing device 20 via the bus.

[0038] The main memory 22 is a storage device such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), or flash memory. The main memory 22 temporarily stores information necessary during processing performed by the control unit 21 and the program currently being executed by the control unit 21.

[0039] The auxiliary storage device 23 is a storage device such as SRAM, flash memory, hard disk, or magnetic tape. The auxiliary storage device 23 stores the learning model 51, the program to be executed by the control unit 21, and various data necessary for the execution of the program.

[0040] The communication unit 24 is an interface for communication between the information processing device 20 and a network or other devices. The information processing device 20 is a general-purpose information device such as a personal computer or tablet used in a medical facility to select the configuration of the adsorption column set 36. The information processing device 20 may be a mainframe computer used in a medical facility, a virtual machine running on a mainframe computer, multiple personal computers performing distributed processing, or a cloud computing system.

[0041] The electronic medical record system 17 records various information about individual patients, such as their test results and treatment history. The control unit 21 acquires data from the electronic medical record system regarding patients receiving radiopharmaceuticals and other patient data. Specific examples of the data acquired by the control unit 21 from the electronic medical record system 17 will be described later.

[0042] The weather forecast website 18 is a publicly accessible website connected to the information processing device 20, for example, via the internet. The control unit 21 obtains weather information from the weather forecast website 18. The weather affects the number of patients visiting the outpatient clinic, for example. The number of patients affects the scheduled administration schedule and the amount of general wastewater generated by toilet use, etc.

[0043] Since the electronic medical record system 17 and the weather forecast website 18 are publicly known, a detailed explanation of their configurations will be omitted.

[0044] As illustrated with Figure 1, the wastewater treatment system 30 includes a wastewater storage tank 31 and a wastewater monitoring device 32. The wastewater monitoring device 32 includes an RI Monitor 321. The wastewater dilution tank 37 and the wastewater storage tank 31, the wastewater storage tank 31 and the wastewater monitoring device 32, the wastewater monitoring device 32 and the sewer 39, and the general wastewater drainage route and the wastewater storage tank 31 are each connected by drainage pipes.

[0045] The control unit 21 acquires information regarding the configuration of the wastewater treatment system 30 and data measured by the RI monitor 321 from the wastewater treatment system 30. Specific examples of the information regarding the configuration of the wastewater treatment system 30 will be described later.

[0046] Figure 4 is an explanatory diagram illustrating the configuration of the learning model. The learning model 51 is trained by reinforcement learning, as described later, to accept patient data about patients receiving radiopharmaceuticals, data about other patients, weather, information about the configuration of the wastewater treatment system 30, and data measured by the RI monitor 321, and to output information about the configuration of the adsorption column set 36 used for the urine of patients receiving radiopharmaceuticals. The patient data includes patient information and drug information. An example of patient information from the input data is shown in Table 2.

[0047] [Table 2]

[0048] Patient information may include various test results such as height, weight, body fat percentage, and BMI (Body Mass Index) for body composition tests, creatine clearance and serum creatinine for renal function tests, blood glucose levels, total cholesterol and ALT (Alanine Aminotransferase) for biochemical tests, and red blood cell count, white blood cell count and platelet count for hematological tests.

[0049] Table 3 shows an example of drug information from the input data. Note that DOTATETE in Table 3 is a synthetic somatostatin analog that binds to the somatostatin receptor, which is overexpressed in neuroendocrine tumors.

[0050] [Table 3]

[0051] The date and time of manufacture of a radionuclide is the date and time used as the basis for calculating the half-life of the radionuclide. The manufacturing information may include information such as the content of the radionuclide. In Table 3, the manufacturing location of the radioactive drug is expressed only by the country name, but the manufacturing plant may also be expressed by the name of the manufacturing plant or by a unique ID assigned to the manufacturing plant.

[0052] The drug information may include information about the transportation route, such as the flight path of the aircraft and the route of the vehicles used to transport the drug from the manufacturing site to the medical facility. The drug information may also include information about the date and time of testing of the radiopharmaceutical, and the location of testing. For example, when the adsorption column set 36 is set up before the patient enters the private room, or when the learning model 51 is used before administering the radiopharmaceutical, the scheduled date and time and the scheduled dose may be used for the administration date and time and the dose.

[0053] Other patient data includes the number of hospitalized patients, information similar to that in Tables 2 and 3 for patients receiving radiopharmaceuticals, and information in Table 2, as well as information on the surgical site and procedure, for patients undergoing surgery. Other patient data may also include the number of outpatient appointments or expected outpatient numbers, and the estimated number of emergency admissions.

[0054] Weather conditions include whether it is raining or sunny, and hourly precipitation forecasts if it is raining. An example of the configuration information for the wastewater treatment system 30 is shown in Table 4.

[0055] [Table 4]

[0056] The water volume of the wastewater dilution tank 37 and the water volume of the wastewater storage tank 31 may be time-series data. If the wastewater treatment system 30 includes multiple wastewater dilution tanks 37 or wastewater storage tanks 31, the capacity and water volume of each wastewater dilution tank 37 or wastewater storage tank 31 are included in the configuration information of the wastewater treatment system 30.

[0057] The configuration information of the wastewater treatment system 30 may include water quality information such as BOD, COD, hydrogen ion concentration, and suspended solids content of the wastewater stored in the wastewater dilution tank 37 and the wastewater storage tank 31.

[0058] RI monitor data is the radiation dose of wastewater in the wastewater storage tank 31, measured by the RI monitor 321. RI monitor data may be actual measured values, for example, taken at a predetermined time. RI monitor data may also be statistical values, such as the average or maximum value of daily measurement results. RI monitor data may also be time-series data.

[0059] The configuration of the adsorption column set 36, which is the output data of the learning model 51, includes the number of adsorption columns 361 to be used, the type of each adsorption column 361, and the connection order of the adsorption columns 361, as illustrated in Figure 2.

[0060] Figure 5 is an explanatory diagram illustrating the learning process of the learning model 51. Reinforcement learning is used for machine learning of the learning model 51. Reinforcement learning is a method for training the learning model 51, an artificial intelligence agent, to select the optimal action a to achieve a goal when it is in state s in a given environment.

[0061] In reinforcement learning, if the learning model 51 selects action a in state s at the current time t, it is given a reward r according to the state s that has transitioned (changed) to at the next time t+Δt, and the action-value function Q(s,a) is updated to maximize the total reward r. The learning model 51 selects action a with a high action-value function Q(s,a). In deep reinforcement learning models, the calculation of the action-value function Q(s,a) corresponds to the calculation of the parameters of the learning model 51.

[0062] The initial state of the learning model 51 is generated by supervised machine learning using training data, which consists of numerous sets of input and output data, as explained using Figure 4, for example. The training data used in supervised machine learning is created by combining, for example, actually occurring input data or randomly generated input data with the configuration of the adsorption column set 36 determined by an experienced operator.

[0063] Machine learning algorithms used in supervised machine learning include, for example, CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), Transformer, Random Forest, or LightGBM (Light Gradient Boosting Machine). The supervised machine learning algorithms listed here are examples, and any other supervised machine learning algorithm may be used.

[0064] The initial state of the learning model 51 may be one that has already been trained through reinforcement learning at other medical facilities. Additional reinforcement learning can generate a learning model 51 that has been further trained according to the characteristics of the wastewater treatment system 30 at each facility. The initial state of the learning model 51 may also be an untrained state with randomly set parameters.

[0065] The reinforcement learning process for the initial learning model 51 will be explained. The following explanation will use the case where reinforcement learning is performed using the information processing device 20 as an example. Reinforcement learning may also be performed using a computer or other device separate from the information processing device 20.

[0066] The control unit 21 collects the input data described using Figure 4 and inputs it to the learning model 51. The input data corresponds to state s described above. The input data also includes the radiation dose measured by the RI monitor 321. The control unit 21 obtains the configuration of the adsorption column set 36 output from the learning model 51 and displays it on the display unit 25. The configuration of the adsorption column set 36 corresponds to action a described above.

[0067] The operator replaces the adsorption column set 36 connected to the toilet in the private room, or the adsorption column 361 included in the adsorption column set 36, according to the configuration displayed on the display unit 25. The operator then performs action a based on the output of the learning model 51. As described using Figure 1, the patient's urine and other wastewater that has passed through the adsorption column set 36 is discharged into the wastewater treatment system 30. The radiation level of the wastewater immediately before it is discharged from the wastewater treatment system 30 into the sewer 39 is measured by the RI monitor 321.

[0068] The control unit 21 calculates a reward r based on the radiation dose measured by the RI monitor 321. The reward r is set to be a positive value if the radiation dose meets the environmental standards for discharging wastewater into the sewer 39, and a negative value if it does not. The reward r may also be set to be calculated based on both the radiation dose measured by the RI monitor 321 and the cost of the adsorption column set 36 used. Specifically, if the radiation dose meets the environmental standards, the lower the cost of the adsorption column set 36 used, the higher the reward r will be. In this way, the control unit 21 realizes the function of the reward calculation unit 55 in reinforcement learning.

[0069] The control unit 21 adjusts the parameters of the learning model 51 to maximize the total reward r. By repeating the above process, the learning of the learning model 51 by reinforcement learning progresses, and a learning model 51 that accurately outputs the configuration of the adsorption column set 36 is generated.

[0070] Furthermore, if a simulation environment capable of accurately simulating radiation levels has already been established, instead of the operator actually replacing the adsorption column 361, the configuration of the adsorption column 361 output by the learning model 51 may be reflected in the simulation. Compared to replacing the adsorption column 361 in the real world and measuring the state of the drained liquid, reinforcement learning, as explained using Figure 5, can be executed at a much faster speed.

[0071] If a learning model 51 with sufficient accuracy has been generated, reinforcement learning may be terminated. If only the generated learning model 51 is used, the amount of computation performed by the control unit 21 is less than during reinforcement learning. Therefore, the remaining resources of the control unit 21 can be allocated to other processing.

[0072] Reinforcement learning may be continuously performed while the radiopharmaceutical use system 10 is in operation. For example, even if there are changes in the environment, such as improvements in the method of using radiopharmaceuticals, the radiopharmaceutical use system 10 can be provided that continues to learn the learning model 51 to adapt to those changes.

[0073] Figure 6 is a flowchart illustrating the program's processing flow. The program in Figure 6 is executed before a patient receiving radiopharmaceuticals enters a private room, or before processing urine collected in the private room after the patient's discharge. Figure 6 is used to illustrate the process at the stage when a sufficiently reinforcement-learned learning model 51 is deployed in a medical facility.

[0074] The control unit 21 acquires input data from the electronic medical record system 17, the weather forecast site 18, and the wastewater treatment system 30 (step S501). The control unit 21 inputs the input data into the learning model 51 and acquires the configuration of the adsorption column set 36 output from the learning model 51 (step S502). The control unit 21 displays the acquired configuration of the adsorption column set 36 on the display unit 25 (step S503). After that, the control unit 21 terminates the process.

[0075] In step S503, the control unit 21 may also transmit the configuration of the adsorption column set 36 to a mobile terminal such as a smartphone held by the person in charge of replacing the adsorption column 361. The person in charge can then confirm the configuration of the adsorption column set 36 via the mobile terminal.

[0076] In step S503, the control unit 21 may transmit the configuration of the adsorption column set 36 to a robot or the like that will replace the adsorption column 361. The robot or the like will then perform the replacement of the adsorption column 361.

[0077] Furthermore, the use of adsorption column set 36 is not limited to patients receiving radiopharmaceuticals for the treatment of neuroendocrine tumors. The radionuclides adsorbed by adsorption column set 36 are not limited to 177Lu. It is desirable that adsorption columns 361 be provided that are tailored to the radiopharmaceuticals administered for the treatment or examination of any disease.

[0078] Examples of radiopharmaceuticals administered to patients include 177Lu-PSMA (Prostate Specific Membrane Antigen), 177Lu-DOTATATOC, 225Ac (Actinium-225)-PSMA, 225Ac-DOTATATE, 225Ac-DOTATOC, 68Ga (Gallium-68)-PSMA-11, 68Ga-DOTATETE, and 68Ga-DOTATOC. DOTATOC is a synthetic somatostatin analog that binds to somatostatin receptors overexpressed in neuroendocrine tumors.

[0079] According to this embodiment, a radiopharmaceutical use system 10 can be provided that assists in the selection of an adsorption column set 36 for adsorbing radioactive substances contained in the urine of patients who have received a radiopharmaceutical. By using an adsorption column set 36 that combines multiple adsorption columns 361 with different characteristics, radionuclides can be efficiently adsorbed according to the characteristics of each patient's urine.

[0080] According to this embodiment, radioactive waste in the urine excreted by individual patients is efficiently removed by adsorption onto the adsorption column set 36, while ensuring that the wastewater discharged from the medical facility meets environmental standards. Rather than striving for perfect treatment of the urine of individual patients, the aim is to ensure that the entire wastewater discharged from the medical facility meets environmental standards, thus providing a relatively low-cost radiopharmaceutical handling system 10.

[0081] [Embodiment 2] This embodiment relates to a configuration in which a radiopharmaceutical system 10 is realized by operating a general-purpose computer 90 in combination with a program 97. Parts common to Embodiment 1 will not be described.

[0082] Figure 7 is an explanatory diagram illustrating the configuration of the radiopharmaceutical use system 10 of Embodiment 2. The radiopharmaceutical use system 10 includes an electronic medical record system 17, a weather forecast site 18, a wastewater treatment system 30, and a computer 90. The computer 90 includes a control unit 21, main memory 22, auxiliary memory 23, communication unit 24, display unit 25, input unit 26, and bus as described above, as well as a reading unit 27.

[0083] Program 97 is recorded on a portable recording medium 96. The control unit 21 reads Program 97 via the reading unit 27 and saves it to the auxiliary storage device 23. The control unit 21 may also read Program 97 stored in a semiconductor memory 98, such as flash memory, implemented in the computer 90. Furthermore, the control unit 21 may download Program 97 from another server computer (not shown) connected via the communication unit 24 and a network (not shown) and save it to the auxiliary storage device 23.

[0084] Program 97 is installed as a control program for the computer 90, loaded into the main memory 22, and executed. This completes the realization of the radiopharmaceutical usage system 10 described in Embodiment 1. Program 97 in this embodiment is an example of a program product.

[0085] Program 97 may be provided on a recording medium or distributed from an external computer. Computer programs can be deployed to run on a single computer, at a single site, or distributed across multiple sites and interconnected by a communication network.

[0086] The technical features (constituent elements) described in each embodiment are combinable with each other, and by combining them, new technical features can be formed. The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims, not in the sense described above, and all modifications within the sense and scope equivalent to the claims are intended to be included.

[0087] The independent and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. Furthermore, while the claims use a multi-claim format in which claims refer to two or more other claims (multi-claim format), this is not the only option. Claims may also be described using a multi-claim format in which at least one multi-claim is referenced (multi-multi-claim format). [Explanation of Symbols]

[0088] 10. Radiopharmaceutical Use Systems 17. Electronic medical record system 18 Weather forecast websites 20 Information Processing Devices 21 Control Unit 22 Main storage 23 Auxiliary storage device 24 Communications Department 25 Display section 26 Input section 27 Reading section 30 Wastewater Treatment Systems 31 Drainage storage tank 32 Drainage monitoring device 321 RI Monitor 36 Adsorption Column Set 361 Adsorption Column 37 Waste water dilution tank 39 Sewer 51 Learning Models 55 Compensation Calculation Department 90 Computer 96 Portable recording media 97 Programs 98 Semiconductor memory

Claims

1. The system acquires patient information of patients receiving radiopharmaceuticals, pharmaceutical information relating to the radiopharmaceuticals, and configuration information of the wastewater treatment system installed at the medical facility where the radiopharmaceuticals are administered. When patient information, drug information, and configuration information are input, a learning model that outputs the configuration of an adsorption column set used to process urine excreted by a patient is input, and the acquired patient information, acquired drug information, and acquired configuration information are input to obtain the configuration of the adsorption column set from the learning model. Output the configuration of the acquired adsorption column set. An information processing method in which a computer performs the processing.

2. The configuration of the adsorption column set includes the number of adsorption columns to be used, the type of each adsorption column, and the order in which the adsorption columns are connected to each other. The information processing method according to claim 1.

3. The aforementioned drug information includes the radionuclide contained in the radiopharmaceutical, the date and time of manufacture of the radionuclide, and the date and time of administration to the patient and the dosage. The information processing method according to claim 1.

4. The aforementioned pharmaceutical information further includes information regarding the manufacturing location of the radiopharmaceutical and the transportation route from the manufacturing location to the medical facility. The information processing method according to claim 3.

5. The aforementioned patient information includes information regarding the patient's gender, medical history, and current illness. The information processing method according to claim 1.

6. The configuration information includes information regarding the capacity and water volume of the wastewater storage tank included in the wastewater treatment system installed at the medical facility, and the measurement results from the RI (Radio Isotope) monitor. The information processing method according to claim 1.

7. The aforementioned learning model is a learning model that, when given patient information, drug information, configuration information, and weather information as input, outputs the configuration of an adsorption column set used for processing urine excreted by a patient. Obtain further weather information, The acquired patient information, the acquired drug information, the acquired configuration information, and the acquired weather information are input into the learning model to obtain the configuration of the adsorption column set from the learning model. The information processing method according to claim 1.

8. The aforementioned learning model, when inputting patient information, drug information, configuration information, and information about other patients visiting the medical facility, outputs the configuration of an adsorption column set used for processing urine excreted by a patient receiving the radiopharmaceutical. We will obtain further information about other patients, The acquired patient information, the acquired drug information, the acquired configuration information, and the acquired information about other patients are input into the learning model to obtain the configuration of the adsorption column set from the learning model. The information processing method according to claim 1.

9. The learning model is trained using reinforcement learning, which rewards the wastewater from the wastewater treatment system when it meets the criteria. The information processing method according to claim 1.

10. The radiopharmaceutical contains 177Lu (lutetium-177). The information processing method according to any one of claims 1 to 8.

11. The system acquires patient information of patients receiving radiopharmaceuticals, pharmaceutical information relating to the radiopharmaceuticals, and configuration information of the wastewater treatment system installed at the medical facility where the radiopharmaceuticals are administered. When patient information, drug information, and configuration information are input, a learning model that outputs the configuration of an adsorption column set used to process urine excreted by a patient is input, and the acquired patient information, acquired drug information, and acquired configuration information are input to obtain the configuration of the adsorption column set from the learning model. Output the configuration of the acquired adsorption column set. A program that instructs a computer to perform a process.

12. An information processing device having a control unit, The control unit, The system acquires patient information of patients receiving radiopharmaceuticals, pharmaceutical information relating to the radiopharmaceuticals, and configuration information of the wastewater treatment system installed at the medical facility where the radiopharmaceuticals are administered. When patient information, drug information, and configuration information are input, a learning model that outputs the configuration of an adsorption column set used to process urine excreted by a patient is input, and the acquired patient information, acquired drug information, and acquired configuration information are input to obtain the configuration of the adsorption column set from the learning model. Output the configuration of the acquired adsorption column set. Information processing device.

Images