Inspection planning support device, inspection planning support system, inspection planning support program, and inspection planning support method

Abstract

To reduce the workload associated with assigning laboratory units that perform diagnostic imaging tests. [Solution] The examination planning support device according to this embodiment comprises an acquisition unit, a calculation unit, and a generation unit. The acquisition unit acquires examination information of multiple subjects to be examined by a medical imaging diagnostic device, limitation information regarding restrictions on examinations by the medical imaging diagnostic device, and examination room information regarding multiple examination rooms, each of which is equipped with a medical imaging diagnostic device. The calculation unit calculates the degree of suitability for each of the multiple examination rooms for the examinations of multiple subjects based on the examination information, limitation information, and examination room information. The generation unit generates information indicating which of the multiple examination rooms each examination of multiple subjects should be performed in, based on the calculated degree of suitability, so that the total time required for multiple examinations assigned to one examination room included in the multiple examination rooms does not exceed the upper limit of the examination time for one examination room.

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to an inspection plan support device, an inspection plan support system, an inspection plan support program, and an inspection plan support method.

Background Art

[0002] Conventionally, for example, it is known that a radiological technologist or hospital staff manually assigns which examination room will conduct an imaging diagnostic examination. When the number of examination orders increases, the assignment of examination rooms becomes a heavy burden on radiological technologists and hospital staff.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to reduce the burden associated with the assignment work of examination rooms for conducting imaging diagnostic examinations. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. It is also possible to position the problems corresponding to the respective effects of each configuration shown in the embodiments described later as other problems.

Means for Solving the Problems

[0005] The examination planning support device according to this embodiment comprises an acquisition unit, a calculation unit, and a generation unit. The acquisition unit acquires examination information of a plurality of subjects to be examined by a medical imaging diagnostic device, limitation information regarding limitations on examinations by the medical imaging diagnostic device, and examination room information regarding a plurality of examination rooms, each of which is equipped with the medical imaging diagnostic device. The calculation unit calculates the degree of suitability for each of the plurality of examination rooms for the examinations of the plurality of subjects based on the examination information, the limitation information, and the examination room information. The generation unit generates information indicating which of the plurality of examination rooms each of the plurality of examinations should be performed in, based on the calculated degree of suitability, so that the total time required for the plurality of examinations assigned to one of the plurality of examination rooms does not exceed the upper limit of the examination time for that one examination room. [Brief explanation of the drawing]

[0006] [Figure 1] A diagram showing an example of a network configuration including an inspection planning support device according to the first embodiment. [Figure 2] A diagram illustrating the method for calculating the degree of fit according to the first embodiment. [Figure 3] A figure showing an example of a user interface displayed on a display according to the first embodiment. [Figure 4] A flowchart illustrating the processing procedure according to the first embodiment. [Figure 5] A diagram illustrating the method for calculating the degree of fit according to the first modified example in the first embodiment. [Figure 6] A figure showing an example of a user interface displayed on a display according to a second modified example of the first embodiment. [Figure 7] A figure showing an example of a user interface displayed on a display according to a third modified example of the first embodiment. [Figure 8] A figure showing an example of a user interface displayed on a display according to a fourth modification of the first embodiment. [Figure 9]A figure showing an example of a user interface displayed on a display according to a fifth modified example of the first embodiment. [Figure 10] A flowchart illustrating the method for determining the optimal combination when performing difference detection in inspection information according to the second embodiment. [Modes for carrying out the invention]

[0007] The following describes in detail an embodiment of the inspection planning support device with reference to the drawings.

[0008] (First embodiment) Figure 1 shows an example of a network configuration including the examination planning support device 100 according to this embodiment. For example, as shown in Figure 1, the examination planning support device 100 according to this embodiment includes a processing circuit 23, an input device 24, a display 25, and a storage circuit 26. The examination planning support device 100 is configured to exchange data with, for example, a radiology information system (RIS) 20, a restriction information database 21, an examination room database 22, and a medical image diagnostic device 3 via a network.

[0009] Medical imaging diagnostic equipment 3 includes, for example, MRI (Magnetic Resonance Imaging) equipment, X-ray diagnostic equipment, X-ray CT (Computed Tomography) equipment, ultrasound diagnostic equipment, SPECT (Single Photon Emission Computed Tomography) equipment, PET (Positron Emission Computed Tomography) equipment, etc.

[0010] The input device 24 is, for example, a pointing device such as a mouse or trackball, or an input device such as a keyboard. The input device 24 is an interface that accepts input.

[0011] The display 25, under the control of the processing circuit 23, displays a GUI (Graphical User Interface) or the like for receiving input related to the assignment of diagnostic imaging examinations to examination rooms. The display 25 may be a display device such as a liquid crystal display, and may also serve as an interface for receiving input.

[0012] The processing circuit 23 is a processor. For example, as shown in Figure 1, in this embodiment, the processing circuit 23 reads programs corresponding to each function from the storage circuit 26 and executes them to perform the acquisition function 231, the fitness calculation function 232, the optimization function 233, and the display control function 234. In other words, the processing circuit 23, in the state where each program has been read, has each processing function shown in the processing circuit 23 of Figure 1. Here, the acquisition function 231 is an example of an acquisition unit, the fitness calculation function 232 is an example of a calculation unit, the optimization function 233 is an example of a generation unit, and the display control function 234 is an example of a display control unit.

[0013] RIS20 is a system that manages the appointment status of examinations and information related to examinations performed by the medical imaging diagnostic device 3, for each examination ID. RIS20 stores examination information. This information includes, for example, examination ID, examination date and time, examination disease name, examination site, examination position, and patient attribute information. RIS20 stores information for examinations for which an examination room has not yet been assigned, and information for examinations that have already been completed. The examination site refers to a specific part of the subject's body that is the target of the examination, such as the brain, arms, chest, or legs. The examination position refers to the posture of the subject when imaging is performed by the medical imaging diagnostic device 3 during the examination, such as lying down, sitting, or standing.

[0014] The patient attribute information included in the inspection information includes, for example, patient ID, name, age, gender, metal implanted in the body, the ward used, the means of movement within the hospital (walking, wheelchair, bed, etc.), inpatient / outpatient classification, whether pregnant or not, symptoms of the patient to be considered when using the medical imaging diagnostic device 3 (such as claustrophobia), etc. The information on the metal implanted in the body is, for example, information on whether a pacemaker or artificial joint is implanted in the body. The RIS 20 stores these patient attribute information in association with the inspection ID.

[0015] The restricted item information database 21 stores information on combinations restricted in inspections. Note that the "restriction" according to this embodiment may include not only cases where the combination is completely prohibited but also cases where attention is required when implementing the combination.

[0016] Combinations restricted in inspections are, for example, combinations of patient attribute information and inspections. For example, when a pacemaker is implanted in the body, depending on the type of pacemaker, the inspection itself using an MRI device may be impossible, or imaging may be prohibited only for inspections using an MRI device with a high static magnetic field strength such as 3 tesla [T], or the inspection site may be restricted. In this case, by including the presence or absence of a pacemaker and the type of pacemaker as patient attribute information and including the static magnetic field strength of the MRI device and the information on the inspection site as inspection information, a combination of patient attribute information and inspection information restricted in the inspection can be created.

[0017] In addition to the combinations exemplified above, it is also possible to create in advance information on combinations restricted in inspections based on prohibited items and precautions stipulated by laws, regulations, guidelines, and the attached documents of medical devices. Further, information provided by a compatibility search system that can search the compatibility between medical devices such as the pacemaker used by the patient and the medical imaging diagnostic device may be stored in the restricted item information database 21.

[0018] The laboratory database 22 stores information about laboratories within the hospital. This laboratory information includes, for example, travel time information regarding the time it takes to travel from each patient room to the laboratory, equipment information, and information about the staff in charge of each laboratory.

[0019] Travel time information includes, for example, the distance from the patient's room to each examination room, the mode of transportation within the hospital (walking, wheelchair, bed, etc.), and the travel time from the patient's room to each examination room depending on the mode of transportation.

[0020] The device information includes, for example, information about the type of medical imaging device 3 and the device configuration. Information about the device configuration, for example in the case of an MRI device, includes information such as static magnetic field strength, magnet type, bore diameter, and the presence or absence of a noise reduction function. Static magnetic field strength is expressed, for example, in Tesla [T]. Magnet type is, for example, information indicating whether it is a tunnel type or an open type. Bore diameter information is information about the size of the aperture diameter of the imaging port used to examine the patient, or whether it is standard or large diameter. The presence or absence of a noise reduction function refers to information about the presence or absence of a noise reduction function implemented by a hardware mechanism or pulse sequence. Furthermore, information about the configuration, for example in the case of a CT device, includes information such as the number of detector rows and low-radiation exposure functions. The number of detector rows is, for example, information such as 16 rows, 64 rows, 256 rows, or 320 rows, and relates to the scannable area per detector rotation. Low-radiation exposure function information refers to information about the presence or absence of a low-radiation exposure function implemented by a hardware mechanism or image reconstruction algorithm. Furthermore, information regarding the configuration includes, for example, in the case of an X-ray imaging device, information such as the areas that can be imaged and the low-radiation exposure function. The areas that can be imaged include, for example, the oral cavity (dental) and the mammary glands. Information regarding the low-radiation exposure function refers to whether or not a low-radiation exposure function is implemented through hardware mechanisms or radiation control.

[0021] Information about the assigned staff member may include, for example, their gender and work schedule. Work schedule information may include, for example, their scheduled work hours on any given date and their available testing hours on any given date. Furthermore, if there are multiple staff members assigned to the testing laboratory, the information may include only the information of the primary worker, or it may include information for all staff members.

[0022] The acquisition function 231 acquires inspection information and inspection time information from the RIS 20, restriction information from the restriction information database 21, and laboratory information from the laboratory database 22. The acquisition function 231 provides the acquired inspection information, restriction information, and laboratory information to the fitness calculation function 232.

[0023] The examination time information is information about the time required for the examination in the medical imaging diagnostic device 3. The examination time information may be standard examination times pre-stored in RIS20 for each type of examination, or it may be the examination time measured by the medical imaging diagnostic device 3. When measuring the examination time in the medical imaging diagnostic device 3, for example, the time from the start to the end of the examination in the medical imaging diagnostic device 3 is measured, and the measured result is used as the examination time information. Also, since the examination time in the medical imaging diagnostic device 3 may vary depending on the staff member in charge, it may be stored together with information that identifies the staff member in charge. Furthermore, the examination time information is not limited to the time the medical imaging diagnostic device 3 is used for the examination, but may also include setting time, such as when the staff member adjusts the patient's posture or attaches the necessary equipment to the patient. Here, the necessary equipment for the examination is, for example, an RF (Radio Frequency) coil used in MRI examinations, or a pad for fixing the patient's position used in CT or MRI examinations. In addition, the examination time information may also include the time required to set the imaging conditions of the medical imaging diagnostic device 3.

[0024] The goodness-of-fit calculation function 232 calculates the goodness-of-fit using the examination information, limitation information, and laboratory information acquired by the acquisition function 231. For example, the goodness-of-fit calculation function 232 compares past examination information stored in RIS 20 with examinations for which no laboratory has been assigned to determine the first goodness-of-fit, p. The goodness-of-fit calculation function 232 also uses the examination information and limitation information to determine the second goodness-of-fit, q, based on the site, disease, and patient attributes. Alternatively, the goodness-of-fit calculation function 232 determines the third goodness-of-fit, r, based on the recommendation level indicating how well the examination performed on the medical imaging diagnostic device 3 installed in the laboratory is suited to the patient attributes and examination content. Finally, the goodness-of-fit calculation function 232 calculates the overall goodness-of-fit, c, based on the information from multiple goodness-of-fit levels.

[0025] The goodness-of-fit calculation function 232 searches for past tests similar to scheduled tests for which no laboratory has been assigned, identifies which laboratory was used in the past, and calculates the goodness-of-fit p. For example, the goodness-of-fit p is calculated based on the percentage of time each laboratory was used among the multiple laboratories located within the hospital, or the number of times each laboratory was used. The goodness-of-fit p is calculated based on test information and laboratory information.

[0026] The goodness-of-fit calculation function 232, in determining whether a past examination and a scheduled examination are similar, compares examination information for both the scheduled examination and the past examination, namely the examination ID, examination date and time, examination disease name, examination site, examination position, and patient attribute information. Specifically, the goodness-of-fit calculation function 232 identifies past examinations that completely match the scheduled examination in terms of examination ID, examination date and time, examination disease name, examination site, and examination position. The goodness-of-fit calculation function 232 also classifies the patient attribute information of the identified past examination and the patient attribute information of the scheduled examination into ontology-based classes. If the goodness-of-fit calculation function 232 classifies the patient attribute information of the past examination and the patient attribute information of the scheduled examination into different classes, it determines that the past examination and the scheduled examination are not similar. Conversely, if the goodness-of-fit calculation function 232 classifies the patient attribute information of the past examination and the patient attribute information of the scheduled examination into the same class, it determines that the past examination and the scheduled examination are similar. An ontology-based class is a classification of textual information, such as test information and patient attribute information, as formal conceptual information. This classification is defined based on the relationships between concepts contained in the textual information. In this embodiment, whether past tests and scheduled tests are similar was determined based on the differences in ontology-based classes. However, it may also be determined based on other criteria, such as definitions in a medical dictionary or differences in strings (where differences of three characters or less are considered synonymous) and a comparison with a predetermined threshold.

[0027] The fitness calculation function 232 calculates the fitness score q based on the restriction information. The fitness score q is calculated based on the examination information stored in the RIS 20 and the restriction information stored in the restriction information database 21. For example, if a patient has a pacemaker, the fitness score q for examination rooms equipped with MRI machines whose use is restricted will be calculated to be small. Conversely, the fitness score q will be calculated to be large for examination rooms equipped with medical imaging diagnostic equipment suitable for the patient's examination.

[0028] The conformance calculation function 232 calculates the conformance score r based, for example, on the laboratory's recommendation level for the test information. The calculation of the conformance score r based on the laboratory's recommendation level is performed based on the test information stored in the RIS 20 and the laboratory information stored in the laboratory database 22.

[0029] The goodness-of-fit (r) value, based on the laboratory's recommendation level for examination information, is calculated to be higher if the laboratory has an MRI device with a high static magnetic field strength, for example, in the case of a patient whose examination site is the brain. This is because, for example, in brain examinations, imaging with an MRI device with a high static magnetic field strength that has a high ability to visualize blood vessels is desirable in order to detect aneurysms and abnormalities in vascular anatomy. Also, generally, the higher the static magnetic field strength, the higher the signal-to-noise ratio obtained, so an MRI device with a high static magnetic field strength can obtain higher-resolution images. On the other hand, the image quality obtained may deteriorate due to static magnetic field inhomogeneity (B0) associated with the susceptibility effect, or RF magnetic field inhomogeneity (B1) or an increase in specific absorption rate (SAR) due to RF penetration and RF interference. In that case, the lower the static magnetic field strength of the MRI device installed in the laboratory, the higher the value of the goodness-of-fit (r) value. Note that the laboratory's recommendation level may be changed based on the user's experience, and it may be set so that any desired goodness-of-fit (r) can be obtained.

[0030] The goodness-of-fit calculation function 232 uses the goodness-of-fit values ​​p, q, and r described above to calculate the overall goodness-of-fit value c. The overall goodness-of-fit value c is calculated for each combination of examination information, such as examination site and disease, and patient attribute information. It is also calculated for each combination of multiple examination rooms in the hospital and examination IDs. The overall goodness-of-fit value c is calculated, for example, by averaging the goodness-of-fit values ​​p, q, and r. Note that the overall goodness-of-fit value c may be calculated using other methods, such as a weighted average, maximum value, or minimum value, rather than just the average. Furthermore, the overall goodness-of-fit value c may be calculated by weighting which of the goodness-of-fit values ​​p, q, and r is given more importance.

[0031] Figure 2 is a diagram illustrating the method for calculating the degree of fit. The table in Figure 2 explains how the degree of fit calculation function 232 calculates the degree of fit for each combination of the examination ID, examination site, examination disease name, presence or absence of an implanted pacemaker (corresponding to imaging with a low static magnetic field MRI device), and multiple examination rooms. In the example shown in Figure 2, it is assumed that an MRI device with a high static magnetic field strength is installed in examination room 1a, and an MRI device with a low static magnetic field strength is installed in examination room 1b. For example, considering the examination record, the degree of fit between examination room 1a and examination room 1b is determined by the amount of examinations performed. Also, considering the limitation information, since pacemakers are only compatible with imaging with a low static magnetic field strength MRI device, the degree of fit q for examinations with an implanted pacemaker in examination room 1a, which has a high static magnetic field strength MRI device, will be a negative value. Furthermore, considering the recommendation level, if the examination site is the brain, the degree of fit r is higher for examination room 1a, which has a higher static magnetic field strength MRI device, due to its superior imaging capability. Specifically, for example, in the case of an examination where the examination site is the brain, the disease being examined is cerebral infarction, and the patient has an implanted pacemaker, the degree of fit with examination room 1a p is "60", the degree of fit with examination room 1a q is "-1000", and the degree of fit with examination room 1a r is "80", so the overall degree of fit with examination room 1a c is "-287". Then, the degree of fit with examination room 1b p is "40", the degree of fit with examination room 1b q is "50", and the degree of fit with examination room 1b r is "40", so the overall degree of fit with examination room 1b c is "43". Also, for example, in the case of an examination where the examination site is the brain, the disease being examined is cerebral infarction, and the patient does not have an implanted pacemaker, the degree of fit with examination room 1a p is "10", the degree of fit with examination room 1a q is "50", and the degree of fit with examination room 1a r is "80", so the overall degree of fit with examination room 1b c is "47". The goodness of fit p with laboratory 1b is "90", the goodness of fit q with laboratory 1b is "50", and the goodness of fit r with laboratory 1b is "40", so the overall goodness of fit c with laboratory 1b is "60". Note that the optimization function 233 does not use combinations of tests and laboratories in determining the optimal combination if the calculated overall goodness of fit c is a negative value.

[0032] Returning to Figure 1, the optimization function 233 determines the optimal combination of scheduled tests and laboratories based on the overall fit c calculated by the fit calculation function 232, the test time information, and the upper limit time, which is the maximum time each laboratory can use. The optimization function 233 also generates information indicating which of the multiple laboratories each of the multiple scheduled tests should be performed in, based on the determined combinations.

[0033] The optimization function 233 extracts the available testing time from the staff work information included in the laboratory information and sets it as the upper limit. The optimization function 233 can also set the upper limit for each laboratory based on past testing information. For example, the average daily testing time performed in multiple laboratories over a certain period can be set as the upper limit.

[0034] The optimization function 233 estimates the examination time when a reserved examination is assigned to a laboratory based on examination time information from similar past examinations. For example, the optimization function 233 can use the average examination time from similar past examinations as the examination time when a reserved examination is assigned to a laboratory.

[0035] The optimization function 233, in determining whether a past examination and a scheduled examination are similar, compares examination information for both the scheduled examination and the past examination, namely the examination ID, examination date and time, examination disease name, examination site, examination position, and patient attribute information. Specifically, the goodness-of-fit calculation function 232 identifies past examinations that completely match the scheduled examination in terms of examination ID, examination date and time, examination disease name, examination site, and examination position. The optimization function 233 also classifies the patient attribute information of the identified past examination and the patient attribute information of the scheduled examination into ontology-based classes. If the optimization function 233 classifies the patient attribute information of the past examination and the patient attribute information of the scheduled examination into different classes, it determines that the past examination and the scheduled examination are not similar. Conversely, if the optimization function 233 classifies the patient attribute information of the past examination and the patient attribute information of the scheduled examination into the same class, it determines that the past examination and the scheduled examination are similar. An ontology-based class is a classification of textual information, such as test information and patient attribute information, as formal conceptual information. This classification is defined based on the relationships between concepts contained in the textual information. In this embodiment, whether past tests and scheduled tests are similar was determined based on the differences in ontology-based classes. However, it may also be determined based on other criteria, such as definitions in a medical dictionary or by comparing differences in strings (where differences of three characters or less are considered synonymous) with a predetermined threshold.

[0036] The optimization function 233 determines the combination of a scheduled test and a laboratory by solving an optimization problem such as maximizing the overall goodness of fit c when assigning a test to any laboratory. At this time, the optimal combination is determined under the constraint that the sum of the test times of one or more tests assigned to any laboratory does not exceed the upper limit of that laboratory. As an example, the optimization function 233 may determine the combination of a scheduled test and multiple laboratories using the following equations (1) and (2) (knapsack problem).

number

number

[0037] In this embodiment, optimization in the optimization function 233 is defined as maximizing the sum of the goodness-of-fit values. However, optimization may also be defined as minimizing the goodness-of-fit value in equation (1) multiplied by a negative sign. Alternatively, the combination of multiple examination rooms and multiple scheduled examinations may be determined by inputting multiple scheduled examination information into a trained machine learning model. The combination obtained by this method is defined as the optimal combination. Alternatively, instead of the optimal combination, a combination that satisfies equation (2) and does not maximize the sum of the goodness-of-fit values ​​may be used.

[0038] When the optimization function 233 determines the combination of a booked test and a testing room using a machine learning model, a pre-trained model is used. The training data for training the machine learning model is, for example, data on booked tests and testing rooms manually combined by users. The training data consists of test information and testing room information for booked tests. The machine learning model learns to make the combination of booked tests and testing rooms inferred from the training data approach the combination corresponding to the training data.

[0039] Returning to Figure 1, the display control function 234 displays the information generated by the optimization function 233 (i.e., information indicating which of the multiple scheduled examinations should be performed in which of the multiple examination rooms) on the display 25.

[0040] Figure 3 shows an example of the user interface displayed on the display 25. In Figure 3, the filled areas indicate cells corresponding to the optimal combination of scheduled tests and testing rooms determined by the optimization function 233. For example, the display control function 234 displays a table on the display 25 with scheduled tests on the vertical axis and testing rooms on the horizontal axis. The display control function 234 also highlights cells corresponding to the optimal combination determined by the goodness-of-fit calculation function 232. Highlighting includes processes such as coloring the cells or thickening the borders.

[0041] The display control function 234 may display the change on the display 25 when assigning a scheduled examination to a different examination room than the one previously assigned. For example, the cell corresponding to the previous examination room may be highlighted in a different color than the cell for the examination room being assigned this time, or the date may be displayed within the cell corresponding to the previous examination room. In addition to highlighting, the date and time of the previous examination may also be displayed in the cell corresponding to the previous examination room.

[0042] Furthermore, the user can manually change the results of the inspection assignment based on the optimal combination shown on the display 25. For example, when the input device 24 receives an operation from the user to change the inspection assignment, the display control function 234 displays the result on the display 25.

[0043] When the input device 24 receives a change in the inspection assignment by the user, the optimization function 233 re-determines the optimal combination of inspection and inspection room for integers j less than or equal to the number of reserved inspections excluding the inspection that has been changed by one or more, in equations (1) and (2). Also, the upper limit time t in equation (2) i The value used is the value excluding the test time l when the test was assigned to the laboratory.

[0044] Figure 4 is a flowchart illustrating the processing procedure of the inspection planning support device 100 according to the first embodiment. This flowchart is executed by the processing circuit 23.

[0045] First, in S101, the processing circuit 23 acquires inspection information and inspection time information from the RIS 20 using the acquisition function 231, acquires restriction information from the restriction information database 21, and acquires inspection room information from the inspection room database 22.

[0046] Next, in S102, the processing circuit 23 uses the fit calculation function 232 to calculate the fit p, fit q, and fit r for each of the multiple scheduled tests and each of the multiple testing rooms.

[0047] In S103, the processing circuit 23 determines the optimal combination of multiple scheduled tests and testing rooms using the optimization function 233.

[0048] Then, in S104, the processing circuit 23 generates information indicating which of the multiple scheduled tests should be performed in which of the multiple testing rooms using the optimization function 233.

[0049] Finally, in S105, the processing circuit 23 displays the information generated by the optimization function 233 on the display 25 using the display control function 234.

[0050] As described above, in this embodiment, the optimal combination of scheduled examinations and examination rooms is determined, and the results are displayed to the user. As a result, the burden on radiological technologists and medical staff in assigning examination rooms for diagnostic imaging examinations can be reduced.

[0051] Furthermore, in this embodiment, when determining the optimal combination, an upper time limit is set for each laboratory. As a result, not only is the optimal laboratory for each individual test considered, but the overall optimal combination can be displayed to the user, enabling efficient work across multiple laboratories in the hospital, thereby reducing the burden on assigning laboratory locations for diagnostic imaging tests.

[0052] (First modified example in the first embodiment) Figure 5 is a diagram illustrating the method for calculating the overall fitness c according to the first modified example in this embodiment. In the first embodiment, the fitness calculation function 232 expressed the fitness quantitatively, but in this modified example, the fitness is expressed using qualitative expressions such as "◇", "〇", and "×" instead of quantitative expressions. For example, the fitness based on past inspection results is expressed as "×" for combinations with a usage rate of 0%, "△" for combinations from 1% to 30%, "〇" for combinations from 31% to 70%, and "◇" for combinations from 71% to 100%. Also, for example, the fitness based on limitation information is expressed as "×" for combinations specified as limitations and "〇" for combinations that do not have problems. Also, for example, the fitness based on recommendation is expressed as "◇" for examination rooms where medical imaging diagnostic equipment 3 that is recommended for use is located, "〇" for examination rooms where medical imaging diagnostic equipment 3 that does not have problems for use is located, and "×" for examination rooms where medical imaging diagnostic equipment 3 that is not recommended for use is located.

[0053] When calculating the overall goodness of fit c from qualitatively expressed goodness of fit, the goodness of fit calculation function 232 determines the overall goodness of fit c according to the rules. For example, among multiple goodness of fit in the scheduled tests, the best-rated goodness of fit c can be used as the overall goodness of fit c. Alternatively, among multiple goodness of fit in the scheduled tests, the best-rated goodness of fit c can be used as the overall goodness of fit c. Furthermore, as an example, if "×" is included, "×" can be used, and if "×" is not included, the best-rated goodness of fit can be used as the overall goodness of fit. In addition to these examples, the goodness of fit calculation function 232 can calculate the overall goodness of fit c under any arbitrary rules.

[0054] The goodness-of-fit calculation function 232 converts the overall goodness-of-fit, expressed qualitatively, into a quantitative expression, and then, as in the first embodiment, allows the optimization function 233 to determine the combination of laboratory and scheduled test. The conversion to a quantitative expression can be, for example, "×" in the qualitative expression can be converted to "-1000", "△" to "20", "〇" to "60", and "◇" to "100". Alternatively, the conversion to a quantitative expression in the goodness-of-fit calculation function 232 may be performed after calculating the individual goodness-of-fit values ​​such as goodness-of-fit p, goodness-of-fit q, and goodness-of-fit r as described in the first embodiment, but before calculating the overall goodness-of-fit c. The optimization function 233 may also avoid using combinations of tests and laboratories that result in a negative overall goodness-of-fit c when determining the optimal combination.

[0055] As described above, in this modified example, the overall goodness of fit is calculated using qualitative expressions. As a result, the burden on assigning laboratory units for diagnostic imaging tests can be reduced. Furthermore, since it is easier for users to assign goodness of fit compared to quantitative expressions, it is easier to accumulate past examination results that can be used when assigning new laboratory units.

[0056] (Second modified example in the first embodiment) Figure 6 shows an example of the user interface displayed on the display 25 according to a second modified example of this embodiment. In Figure 6, the filled areas indicate cells corresponding to the optimal combinations determined by the optimization function 233, and the shaded areas indicate cells corresponding to combinations of scheduled tests and testing rooms with low fit. In this modified example, when the display control function 234 displays the combinations of scheduled tests and testing rooms determined by the optimization function 233 on the display 25, it highlights combinations with a low overall fit c that are not the optimal combination in a different manner than the optimal combination. For example, it highlights cells corresponding to combinations where the overall fit c is a negative value in blue. At this time, information that forms the basis of the fit may be displayed in the cell.

[0057] Regarding whether a combination has a low degree of fit, for example, the display control function 234 highlights combinations that are determined to be limitations when the degree of fit calculation function 232 calculates the degree of fit based on limitation information, in a manner different from the optimal combination on the display 25. Also, for example, the display control function 234 sets a threshold when determining the overall degree of fit c in the degree of fit calculation function 232, and highlights combinations that are determined to be below that threshold, in a manner different from the optimal combination on the display 25.

[0058] As described above, in this modified version, when displaying the optimal combination to the user, combinations with low suitability are also displayed simultaneously. This prevents users from assigning laboratory units that fall under the limitations when manually changing the examination assignment, thereby reducing the burden on the task of assigning laboratory units for diagnostic imaging examinations.

[0059] (Third modified example in the first embodiment) Figure 7 shows a third modified example of this embodiment. In this embodiment, when the display control function 234 displays the combination of inspection rooms and scheduled inspections determined by the optimization function 233 on the display 25, in addition to highlighting the optimal combination, it may also display to the user, for example, a star or other mark as shown in Figure 7, the cell corresponding to the combination of inspection rooms with the highest degree of fit for each inspection on the horizontal axis.

[0060] As described above, in this modified version, when displaying the optimal combination to the user, the laboratory with the highest degree of fit for each test is also displayed simultaneously. As a result, when a user manually assigns tests in a hospital, the user can find out which laboratory has the highest degree of fit for each test.

[0061] (Fourth modified example in the first embodiment) Figure 8 shows a fourth modified example of this embodiment. In Figure 8, the filled areas indicate cells corresponding to the optimal combination, the dotted areas indicate cells corresponding to combinations of reserved tests and testing rooms with a lower degree of fit than the filled areas, and the shaded areas indicate cells corresponding to combinations of reserved tests and testing rooms with a lower degree of fit than the dotted areas. In this modified example, the display control function 234 changes the display format not only according to the optimal combination of tests and testing rooms determined by the optimization function 233, but also according to, for example, the degree of fit between multiple reserved tests and each testing room calculated by the degree of fit calculation function 232.

[0062] The display control function 234 may, for example, highlight the results on the display 25 in order of decreasing degree of fit using different colors. Alternatively, the display control function 234 may highlight differently depending on whether the combination of reserved tests and testing rooms has an overall degree of fit c within a first numerical range, or a combination of tests and testing rooms has an overall degree of fit c within a second numerical range different from the first numerical range. Furthermore, the display method is not limited to highlighting; for example, the rankings may be displayed numerically as 1, 2, 3, ... in descending order of degree of fit, or the rankings may be marked in an identifiable way.

[0063] As described above, in this modified version, when displaying the optimal combination to the user, the display is categorized according to the degree of fit for each scheduled examination. As a result, the user can know the degree of fit for each laboratory for any given examination, and can use this as a reference when deciding which laboratory should perform a scheduled examination if the user manually changes the examination assignment. Consequently, the burden on the task of assigning laboratory services for diagnostic imaging examinations can be reduced.

[0064] (Fifth modified example in the first embodiment) Figure 9 shows a fifth modified example of this embodiment. In Figure 9, the wavy lines indicate past inspections, and cells labeled "Inspected" indicate that an inspection was performed in the corresponding inspection room. The grid lines indicate inspections currently in progress, and cells labeled "In Inspection" indicate that an inspection is being performed in the corresponding inspection room. The filled areas indicate cells corresponding to the optimal combination, the dots indicate cells corresponding to combinations of reserved inspections and inspection rooms with a lower degree of fit than the filled areas, and the shaded areas indicate cells corresponding to combinations of reserved inspections and inspection rooms with a lower degree of fit than the dots. In this modified example, in addition to highlighting only the optimal combinations of reserved inspections and inspection rooms determined by the optimization function 233 on the display 25, if past inspections, inspections in progress, and reserved inspections are mixed on any given date, the display control function 234 will have the optimization function 233 determine the optimal combination for reserved inspections only, and then display it on the display 25 along with the past inspection information and the inspection information in progress.

[0065] The display control function 234, when simultaneously displaying the optimal combination of past inspection information, inspection information in progress, and reserved inspections on the display 25, may rearrange the inspections according to their progress, for example, by placing the inspections that have already been completed at the top, the inspections currently being performed below them, and the reserved inspections below those.

[0066] The display control function 234 may, when displaying past inspection information on the display 25, display "Inspected" in the cell corresponding to the inspection and the laboratory in which the inspection was performed. Furthermore, when displaying inspection information in progress on the display 25, the display control function 234 may, when displaying inspection information in progress, display "Inspection in Progress" in the cell corresponding to the inspection and the laboratory in which the inspection is being performed.

[0067] The display control function 234 may display the optimal combination of reserved inspections on the display 25 using the first to fourth modified examples.

[0068] As described above, in this modified version, when displaying the optimal combination, completed tests and tests in progress are displayed simultaneously. As a result, when a user is performing test assignment tasks while multiple tests are in progress at a hospital, the user can check the progress of each test.

[0069] (Second embodiment) A second embodiment will now be described. Note that the description of parts that are the same as those in the first embodiment will be omitted. In this embodiment, the processing circuit 23, in the acquisition function 231, compares the reserved examination information, which represents a first examination, with the most recent examination information, which represents a second examination, corresponding to the same patient ID. If there is a difference in the examination information, the fit calculation function 232 and the optimization function 233 determine the optimal combination of the reserved examination and the examination room. If there is no difference, the optimization function 233 assigns the reserved examination to the same examination room as the most recent examination.

[0070] The processing circuit 23, in its acquisition function 231, performs, for example, a full-text match search as a method for detecting differences. Furthermore, the processing circuit 23, in its acquisition function 231, classifies the most recent examination information and scheduled examination information corresponding to the same patient ID into classes based on a medical dictionary or ontology. If the processing circuit 23 classifies the most recent examination information and scheduled examination information into different classes, it determines that there is a difference between the two. Conversely, if the processing circuit 23 classifies the most recent examination information and scheduled examination information into the same class, it determines that there is no difference between them.

[0071] Figure 10 is a flowchart illustrating the determination of the optimal combination when detecting differences between the most recent examination information and scheduled examinations corresponding to the same patient ID. The processing shown in this flowchart is performed by the processing circuit 23.

[0072] In S201, the processing circuit 23 acquires inspection information and inspection time information from the RIS 20 using the acquisition function 231, acquires restriction information from the restriction information database 21, and acquires inspection room information from the inspection room database 22.

[0073] Next, in S202, the processing circuit 23 uses the acquisition function 231 to compare the most recent examination information with the scheduled examination information corresponding to the same patient ID.

[0074] If there is no difference between the most recent inspection information and the scheduled inspection information in S202, in S203, the processing circuit 23, using the optimization function 233, assigns the same inspection room as the most recent inspection information to the scheduled inspection.

[0075] If there is a difference between the most recent inspection information and the scheduled inspection information in S202, in S204, the processing circuit 23 calculates the degree of fit between each of the multiple scheduled inspections and each of the multiple inspection rooms using the degree of fit calculation function 232.

[0076] Then, in S205, the processing circuit 23 determines the optimal combination of multiple scheduled tests and testing rooms using the optimization function 233.

[0077] In S206, the processing circuit 23 generates information indicating which of the multiple available testing rooms the multiple scheduled tests should be performed in, using the optimization function 233.

[0078] Finally, in S207, the processing circuit 23 displays the determined optimal combination to the user on the display 25 using the display control function 234.

[0079] As described above, in this embodiment, the most recent examination information performed for the same patient ID is compared with the scheduled examination information, and the optimal combination is calculated only when a difference is detected. As a result, the number of examinations that need to be newly assigned can be reduced, and the burden on the laboratory that performs diagnostic imaging examinations can be reduced.

[0080] According to at least one embodiment (modification) described above, the burden of assigning laboratory facilities for performing diagnostic imaging tests can be reduced.

[0081] In Figure 1, the test information, restriction information, and laboratory information were stored in three independent RIS20 systems or databases. However, the test information, restriction information, and laboratory information may be stored in a single database. In other words, the test information, restriction information, and laboratory information may be stored in at least one database.

[0082] Furthermore, although Figure 1 describes a single processor implementing each processing function in the processing circuit 23, it is also acceptable to configure the processing circuit 23 by combining multiple independent processors, with each processor executing a program to implement the function. Additionally, although Figure 1 describes a single memory circuit 26 storing programs corresponding to each processing function, it is also acceptable to distribute multiple memory circuits 26 and configure the processing circuit 23 to read the corresponding programs from individual memory circuits 26.

[0083] The above description illustrates an example in which the processor reads and executes programs corresponding to each function from the memory circuit 26, but the embodiments are not limited to this. The term "processor" refers to circuits such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), Application Specific Integrated Circuit (ASIC), and Programmable Logic Device (e.g., Simple Programmable Logic Device (SPLD), Complex Programmable Logic Device (CLPD), and Field Programmable Gate Array (FPGA)). For example, if the processor is a CPU, the processor realizes its functions by reading and executing programs stored in the memory circuit 26. On the other hand, if the processor is an ASIC, instead of storing programs in the memory circuit 26, the functions are directly incorporated as logic circuits within the processor's circuitry. In this embodiment, each processor is not limited to being configured as a single circuit; multiple independent circuits may be combined to form a single processor and realize its functions. Furthermore, the multiple components shown in Figure 1 may be integrated into a single processor to realize its functions.

[0084] While several embodiments have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be carried out in a variety of other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0085] 100 Inspection Planning Support Device 20 RIS 21 Restriction Information Database 22 Laboratory Database 23 Processing Circuit 231 Acquisition function 232. Function to calculate degree of fit 233 Optimization Function 234 Display control function 24 Input devices 25 displays 3. Medical imaging diagnostic equipment

Claims

1. An acquisition unit that acquires examination information of multiple subjects subject to examination by a medical imaging diagnostic device, restriction information regarding limitations on examinations by the medical imaging diagnostic device, and examination room information regarding multiple examination rooms in which the medical imaging diagnostic devices are each installed. A calculation unit that calculates the degree of suitability for each of the tests of the multiple subjects for each of the multiple laboratories based on the aforementioned test information, the aforementioned restriction information, and the aforementioned laboratory information, A generation unit generates information indicating which of the multiple testing rooms each of the multiple subjects should be tested in, based on the calculated degree of fit, so that the total time required for multiple tests assigned to one of the multiple testing rooms does not exceed the upper limit of the testing time for that one testing room. An inspection planning support device equipped with the following features.

2. The calculation unit calculates a first degree of fit based on the test information, a second degree of fit based on the limitation information, a third degree of fit based on the laboratory information, and calculates one overall degree of fit for each combination of the tests of the plurality of subjects and each of the plurality of laboratories based on the first degree of fit, the second degree of fit, and the third degree of fit. The generation unit generates the information based on the overall degree of fit. The inspection planning support device according to claim 1.

3. The generation unit, with the upper limit of the inspection time as a constraint, generates the combination of the inspection and the inspection room that maximizes the sum of the overall goodness of fit as information. The inspection planning support device according to claim 2.

4. The generation unit generates the information using a machine learning model. The inspection planning support device according to claim 1.

5. The system further includes a display control unit that displays the information generated by the generation unit. The inspection planning support device according to claim 1.

6. The display control unit causes the information generated by the generation unit to be highlighted. The inspection planning support device according to claim 5.

7. The system further comprises a display control unit that displays the information generated by the generation unit, The display control unit displays information indicating the combination of inspection and inspection room that the calculation unit determined to be a limitation when calculating the second degree of conformity, separately from the information generated by the generation unit. The inspection planning support device according to claim 2.

8. The system further comprises a display control unit that displays the information generated by the generation unit, The display control unit displays information indicating combinations of tests and testing rooms in which the overall fit calculated by the calculation unit falls below a threshold, separately from the information generated by the generation unit. The inspection planning support device according to claim 2.

9. The system further comprises a display control unit that displays the information generated by the generation unit, The display control unit displays information indicating the combination of one test included in the tests of the plurality of subjects and each of the plurality of testing rooms that has the highest overall fit, separately from the information generated by the generation unit. The inspection planning support device according to claim 2.

10. The system further comprises a display control unit that displays the information generated by the generation unit, The display control unit distinguishes and displays the information generated by the generation unit depending on whether the overall fit corresponding to the combination of the inspection and the inspection room is a value within a first numerical range or whether the overall fit corresponding to the combination of the inspection and the inspection room is a value within a second numerical range different from the first numerical range. The inspection planning support device according to claim 2.

11. The system further comprises a display control unit that displays the information generated by the generation unit, The display control unit displays information indicating the combination of the inspection and the inspection room in order of the magnitude of the overall degree of fit calculated by the calculation unit. The inspection planning support device according to claim 2.

12. The generation unit generates the information when the difference between the information indicating a first test relating to a test that has not been performed and the information indicating a second test relating to the most recent test performed in the past exceeds a threshold, and when the difference falls below the threshold, it applies the combination of the testing room in the second test to the first test. The inspection planning support device according to claim 1.

13. The aforementioned test information includes patient attribute information relating to the subject, The inspection planning support device according to claim 1.

14. The generating unit sets the upper limit of the inspection time based on the inspection room information. The inspection planning support device according to claim 1.

15. The inspection planning support device according to claim 1, A database containing the aforementioned inspection information, the aforementioned laboratory information, and the aforementioned restriction information, A system for supporting inspection planning, which includes the following features.

16. A process for acquiring examination information of multiple subjects subject to examination using a medical imaging diagnostic device, limitation information regarding limitations of examination using the medical imaging diagnostic device, and examination room information regarding multiple examination rooms where the medical imaging diagnostic device is installed. A process for calculating the degree of suitability of the tests for each of the multiple subjects for each of the multiple laboratories, based on the aforementioned test information, the aforementioned restriction information, and the aforementioned laboratory information. A process to generate information indicating which of the multiple laboratories each of the multiple subjects' tests should be performed in, based on the calculated degree of fit, so that the total time required for multiple tests assigned to one laboratory within the multiple laboratories does not exceed the upper limit of the testing time for that one laboratory. A test planning support program that has a computer execute the test plan.

17. The steps include obtaining examination information for multiple subjects to be examined using a medical imaging diagnostic device, limitation information regarding limitations on examinations using the medical imaging diagnostic device, and examination room information regarding multiple examination rooms where the medical imaging diagnostic devices are each installed. A step of calculating the degree of suitability for each of the tests of the multiple subjects for each of the multiple laboratories, based on the test information, the limitation information, and the laboratory information. The steps include generating information indicating which of the multiple laboratories each of the multiple subjects' tests should be performed in, based on the calculated degree of fit, so that the total time required for multiple tests assigned to one laboratory within the multiple laboratories does not exceed the upper limit of the testing time for that one laboratory, A method for supporting inspection planning, comprising the following features.

Images