Medical information processing equipment

Abstract

To assist in preferentially heightening the diagnosis accuracy of a case that is emphasized in diagnosis by a doctor in learning a clinical decision-making assistance system.SOLUTION: A medical information processing device according to an embodiment comprises an acquisition unit, a case example extraction unit and an output control unit. The acquisition unit acquires a first diagnosis result by a clinical decision-making assistance system before learning first data, a second diagnosis result by the clinical decision-making assistance system after learning the first data, the diagnosis result of a doctor, and the first data. The case example extraction unit extracts, as the case example to be presented, a case example that is affected by updating of the clinical decision-making assistance system more than a defined criterion. The output control unit causes the output unit to output the case example to be presented, in association with a diagnosis influence index that indicates the degree of influence exerted upon diagnosis by a doctor by the clinical decision-making assistance system. The first data includes a plurality of case examples in which information relating to diseases for each of a plurality of patients having undergone diagnosis and a true value that indicates the result of medical treatment for each of the plurality of patients having under gone diagnosis are associated with each other.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing device. [Background technology]

[0002] Conventionally, there is known a technology of Clinical Decision Support Systems (CDSS) that supports doctors in making diagnoses when treating patients. Generally, a CDSS uses a trained model that presents information on a patient's disease and a treatment method for the disease based on the results of learning learning data based on past performance by machine learning or the like. In addition, even after the start of operation, a CDSS may update the model by learning based on new learning data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2017 / 081984 Summary of the Invention [Problem 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 support, in the learning of a clinical decision support system, the preferential improvement of diagnostic accuracy of cases that are important when a doctor diagnoses. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0005] A medical information processing apparatus according to an embodiment includes an acquisition unit, a case extraction unit, and an output control unit. The acquisition unit acquires a first diagnosis result for each of a plurality of diagnosed patients by the clinical decision support system before learning the first data, a second diagnosis result for each of the plurality of diagnosed patients by the clinical decision support system after learning the first data, a doctor's diagnosis result for each of the plurality of diagnosed patients, and the first data. The case extraction unit extracts a first diagnosis result based on the first diagnosis result, the second diagnosis result, and the doctor's diagnosis result. Calculate an update impact index and a diagnosis impact index for each of a plurality of cases included in the first data. Among the multiple cases included in the first data, Update impact index The effect of updating the clinical decision support system by learning from the first data is evaluated to be equal to or greater than a first prescribed standard. And the diagnostic impact index is below the standard specified in the second provision. The output control unit converts the presentation target cases into a diagnosis influence index that indicates the degree of influence that the clinical decision support system has on the doctor's diagnosis for the presentation target cases. Update impact index The first data includes a plurality of cases in which information on a disease for each of a plurality of diagnosed patients is associated with a true value indicating a treatment result for each of a plurality of diagnosed patients. The update influence index is an index based on a difference between the first diagnosis result and a true value and a difference between the second diagnosis result and a true value. The diagnosis influence index is an index based on a difference between the first diagnosis result and a doctor's diagnosis result. [Brief description of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram illustrating an example of an overall configuration of an information processing system according to the first embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of a decision tree used in the CDSS according to the first embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of a change in output before and after updating the CDSS according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of information acquired by the medical information processing apparatus according to the first embodiment. [Diagram 5] FIG. 5 is a diagram showing an example of the relationship between the diagnosis result of the CDSS and the diagnosis result of a doctor according to the first embodiment. [Figure 6] FIG. 6 is a diagram showing another example of the relationship between the diagnosis result of the CDSS and the diagnosis result of a doctor according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing yet another example of the relationship between the diagnosis result of the CDSS and the diagnosis result of a doctor according to the first embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a method for extracting an influential variable according to the first embodiment. [Figure 9] FIG. 9 is a diagram showing an example of the analysis screen according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of adding a new case according to the first embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of classification of variables according to the first embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of the learning process according to the first embodiment. [Figure 13] FIG. 13 is a flowchart showing an example of the flow of the update support process according to the first embodiment. [Figure 14] FIG. 14 is a diagram showing an example of an analysis screen according to the second embodiment. [Figure 15] FIG. 15 is a diagram showing an example of an analysis screen according to the first modification. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an embodiment of a medical image processing apparatus will be described in detail with reference to the drawings.

[0008] (First embodiment) Fig. 1 is a diagram showing an example of the overall configuration of an information processing system S according to the first embodiment. As shown in Fig. 1, the information processing system S includes a medical information processing device 10 and a CDSS (Clinical Decision Support System) 20. The medical information processing device 10 and the CDSS 20 are installed in a medical institution such as a hospital. The medical information processing device 10 is communicatively connected to the CDSS 20 via a network 300 such as an in-hospital LAN (Local Area Network). In addition, an electronic medical record system (not shown) or the like may be further connected to the medical information processing device 10 and the CDSS 20.

[0009] The CDSS 20 provides information useful for medical professionals such as doctors to make clinical decisions. In this embodiment, the CDSS 20 supports doctors by presenting a diagnosis result for a patient based on the result of learning data based on past performance through deep learning or other machine learning. More specifically, the CDSS 20 of this embodiment outputs a treatment method estimated to be effective for the disease suffered by the patient and an estimated treatment result when the treatment method is performed.

[0010] The CDSS 20 includes a trained model that has been trained using training data. The trained model is, for example, a trained model generated by deep learning such as a neural network. As a deep learning method, a decision tree, a convolutional neural network (CNN), a recurrent neural network (RNN), or the like can be applied, but is not limited to these.

[0011] FIG. 2 is a diagram showing an example of a decision tree D used in the CDSS20 according to the first embodiment. As shown in FIG. 2, for example, the decision tree D estimates an outcome based on information about a patient's disease, such as a patient's medical image, blood test results, tumor markers, vital data, and blood test results such as a doctor's findings recorded in an electronic medical record. The outcome of the decision tree D shown in FIG. 2 is the presence or absence of a side effect in the patient. The trained model used in the CDSSS20 may employ either a regression or classification method. The outcome output by the CDSSS20, i.e., the diagnosis result, may be not only a classification such as the presence or absence of a side effect, but also a numerical value such as a side effect risk score estimated by a regression method.

[0012] The CDSS 20 is configured, for example, by a server device or a normal computer such as a PC (Personal Computer).

[0013] Furthermore, even after the start of operation, the CDSS 20 can improve its accuracy by learning new learning data. Improving accuracy means bringing the estimated treatment results output by the CDSS 20 closer to the actual treatment results of the patient. In this embodiment, the CDSS 20 learning new learning data is referred to as updating the CDSS 20. The new learning data is an example of the first data in this embodiment.

[0014] Furthermore, the updated CDSS 20 may output results that are different from those of the CDSS 20 before the update. Ideally, updating the CDSS 20 would improve the accuracy of the CDSS 20 in all cases, but in reality, it may be difficult to improve diagnostic accuracy equally in all cases. Therefore, in this embodiment, the medical information processing device 10 described below prioritizes improving accuracy in cases in which the CDSS 20 has a high degree of influence on the doctor's diagnosis.

[0015] Fig. 3 is a diagram showing an example of a change in output before and after updating the CDSS 20 according to the first embodiment. In the example shown in Fig. 3, the upper part shows the CDSS 20 before learning new learning data, and the lower part shows the CDSS 20 after learning the new learning data. Note that the "CDSS 20 before learning new learning data" may be a CDSS that has been repeatedly learned multiple times in the past, or may be a CDSS that was learned before the start of operation but has not yet been trained since the start of operation.

[0016] In the example shown in FIG. 3, the pre-update CDSS 20 and the post-update CDSS 20 output a diagnosis result for patient P when patient information for patient P is input.

[0017] Specifically, the CDSS 20 outputs a treatment method estimated to be effective for the disease suffered by the patient P, and an estimated treatment result when the treatment method is implemented. For example, the CDSS 20 outputs the type of drug to be administered and the dosage as the treatment method. Furthermore, the CDSS 20 outputs a side effect risk score when the drug is administered as the treatment result. The side effect risk score is, for example, a numerical value indicating the intensity of side effects caused by the administration of the drug. Note that the information included in the diagnosis result is not limited to this.

[0018] The patient information includes information about the patient P's disease and the patient P's attribute information.

[0019] The attribute information of the patient P includes, but is not limited to, the name, age, sex, height, weight, etc. of the patient P. It should be noted that the ID of the patient P may be used instead of the name.

[0020] The information on the disease of patient P includes multiple types of test results on patient P. The multiple types of test results include, for example, vital data such as body temperature and blood pressure, blood test results such as white blood cell count, major markers, image measurement values ​​such as tumor size, etc. Furthermore, in this embodiment, the test results include not only quantitative test results, but also findings by a doctor or nurse such as the presence or absence of appetite or the presence or absence of loss of appetite. Note that the findings may be included in the information on patient P's disease as information different from the test results. Furthermore, information on patient P's disease, such as the name of the disease, may be included.

[0021] 3, the CDSS 20 before the update outputs a side effect risk score of “50” as a diagnostic result. The diagnostic result output by the CDSS 20 before the update is an example of the first diagnostic result in this embodiment.

[0022] In addition, in FIG. 3, not only the CDSS 20 but also the doctor 4 diagnoses the patient P. The doctor 4's diagnosis result is a side effect risk score of "55." In the example shown in FIG. 3, the doctor 4 makes a diagnosis in consideration of the diagnosis result output from the CDSS 20 before the update, his / her own experience, and other information. The doctor 4 is an example of a user according to this embodiment.

[0023] Even when using the CDSS 20, the final diagnosis is generally made by the doctor 4. For this reason, this embodiment is also based on the premise that the doctor 4 has issued a diagnosis for the patient P who has already been diagnosed.

[0024] The "true value" shown in Figure 3 indicates the actual treatment result of patient P. While the CDSS 20 and the diagnosis result of doctor 4 are estimated values ​​before the actual treatment is administered, the "true value" is the treatment result determined by tests, etc. after the actual treatment is administered. In this example, the actual severity of side effects of patient P is assumed to be about a side effect risk score of "58."

[0025] 3, even if the updated CDSS 20 receives the same patient information as before the update, it outputs a different side effect risk score of "25" from before the update. The diagnosis result output by the updated CDSS 20 is an example of the second diagnosis result in this embodiment.

[0026] The difference between the side effect risk score of "50" output by the CDSS20 before the update and the true side effect risk score of "58" was "8." In contrast, the difference between the side effect risk score of "25" output by the CDSS20 after the update and the true side effect risk score of "58" is "33." In this case, the difference between the diagnosis result of the CDSS20 after the update and the true value is larger than the difference between the diagnosis result of the CDSS20 before the update and the true value.

[0027] In such a case, after the CDSS20 has been updated, if Doctor 4 refers to the diagnosis results of the CDSS20 when diagnosing a patient similar to Patient P, there is a possibility that the updated CDSS20 will lead Doctor 4 to make a judgment that deviates from the true value.

[0028] The difference between the first diagnostic result output by the CDSS 20 before the update and the true value is an example of the first difference in this embodiment, and the difference between the second diagnostic result output by the CDSS 20 after the update and the true value is an example of the second difference in this embodiment.

[0029] 1, the medical information processing device 10 performs an update simulation and processes the learning data before the CDSS 20 learns new learning data. The medical information processing device 10 is also called, for example, a CDSS update support device.

[0030] The medical information processing device 10 is, for example, a server device or a PC, and includes a NW (Network) interface 110, a storage circuitry 120, an input interface 130, a display 140, and a processing circuitry 150.

[0031] The NW interface 110 is connected to the processing circuit 150, and controls the transmission and communication of various data between the medical image processing device 10 and the CDSS 20. The NW interface 110 is realized by a network card, a network adapter, a NIC (Network Interface Controller), or the like.

[0032] The memory circuitry 120 pre-stores various types of information used by the processing circuitry 150. The memory circuitry 120 also stores various programs.

[0033] The input interface 130 is realized by a trackball, a switch button, a mouse, a keyboard, a touch pad that performs an input operation by touching the operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, a voice input circuit, etc. The input interface 130 is connected to the processing circuit 150, and converts an input operation received from an operator into an electric signal and outputs it to the processing circuit 150. Note that in this specification, the input interface is not limited to an input interface having physical operation parts such as a mouse and a keyboard. For example, an electric signal processing circuit that receives an electric signal corresponding to an input operation from an external input device provided separately from the device and outputs the electric signal to the processing circuit 150 is also included as an example of the input interface 130.

[0034] The display 140 is a liquid crystal display, an organic electro-luminescence (OEL) display, or the like. The input interface 130 and the display 140 may be integrated. For example, the input interface 130 and the display 140 may be realized by a touch panel. The display 140 is an example of an output unit in this embodiment. In this embodiment, the display 140 is included in the medical information processing device 10, but the display 140 may be provided outside the medical information processing device 10.

[0035] The processing circuit 150 is a processor that reads out a program from the storage circuit 120 and executes it to realize a function corresponding to each program. The processing circuit 150 of this embodiment includes an acquisition function 151, a case extraction function 152, an influence variable extraction function 153, an output control function 154, a reception function 155, a data processing function 156, a generation function 157, a classification function 158, and a learning control function 159. The acquisition function 151 is an example of an acquisition unit. The case extraction function 152 is an example of a case extraction unit. The influence variable extraction function 153 is an example of an influence variable extraction unit. The output control function 154 is an example of an output control unit. The reception function 155 is an example of a reception unit. The data processing function 156 is an example of a data processing unit or a conversion unit. The generation function 157 is an example of a generation unit. The classification function 158 is an example of a classification unit. The learning control function 159 is an example of a learning control unit.

[0036] Here, for example, each processing function of the components of the processing circuit 150, that is, the acquisition function 151, the case extraction function 152, the influence variable extraction function 153, the output control function 154, the reception function 155, the data processing function 156, the generation function 157, the classification function 158, and the learning control function 159, is stored in the storage circuit 120 in the form of a program executable by a computer. The processing circuit 150 is a processor. For example, the processing circuit 150 realizes a function corresponding to each program by reading the program from the storage circuit 120 and executing it. In other words, the processing circuit 150 in a state in which each program has been read has each function shown in the processing circuit 150 of FIG. 1. 1, the processing functions performed by the acquisition function 151, the case extraction function 152, the influence variable extraction function 153, the output control function 154, the reception function 155, the data processing function 156, the generation function 157, the classification function 158, and the learning control function 159 are realized by a single processor, but it is also possible to combine multiple independent processors to configure the processing circuit 150 and have each processor execute a program to realize the function. Also, in FIG. 1, it is described that a single storage circuit 120 stores a program corresponding to each processing function, but it is also possible to dispose multiple storage circuits in a distributed manner and have the processing circuit 150 read out the corresponding program from each storage circuit.

[0037] In the above description, an example has been described in which the "processor" reads out and executes a program corresponding to each function from a storage circuit, but the embodiment is not limited to this. The term "processor" refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). When the processor is, for example, a CPU, the processor realizes a function by reading out and executing a program stored in a storage circuit. On the other hand, when the processor is an ASIC, instead of storing a program in the storage circuit 120, the function is directly incorporated as a logic circuit in the circuit of the processor. Note that each processor in this embodiment is not limited to being configured as a single circuit for each processor, and may be configured as one processor by combining multiple independent circuits to realize the function. Furthermore, multiple components in FIG. 1 may be integrated into one processor to realize the functions thereof.

[0038] The acquisition function 151 acquires, from the CDSS 20, a first diagnosis result, a second diagnosis result for each of a plurality of diagnosed patients P, and a diagnosis result of the doctor 4 for each of a plurality of diagnosed patients P under the support of the CDSS 20 before the update. The acquisition function 151 also acquires new learning data from the CDSS 20.

[0039] The new training data is an example of the first data, and is training data to be used to update the CDSS 20. In this case, the first diagnostic result is the diagnostic result by the CDSS 20 before the new training data is trained, and the second diagnostic result is the diagnostic result by the CDSS 20 after the new training data is trained.

[0040] At the time of acquisition, the update of the CDSS 20 has not been finalized. For example, the second diagnosis result is not an actual update result but a simulation result of what would happen if the CDSS 20 were updated. The acquisition function 151 may acquire the second diagnosis result from an information processing device other than the CDSS 20, for example, an information processing device dedicated to simulation.

[0041] The new learning data of this embodiment includes a plurality of cases in which information about the disease for each of a plurality of diagnosed patients P is associated with a true value representing the treatment outcome for each of the plurality of diagnosed patients.

[0042] As described in Fig. 3, the information on the disease includes multiple types of test results on patient P. Note that the cases do not necessarily have to be for each patient P, and when one patient P visits the hospital multiple times for multiple diseases, each case may be included in the new learning data as a separate case. Also, as described above, the information on the disease includes attribute information on each of multiple diagnosed patients.

[0043] 4 is a diagram showing an example of information acquired by the medical information processing apparatus 10 according to the first embodiment. One record of the acquired data 800 shown in FIG. 4 corresponds to one case.

[0044] 4, the patient information of each diagnosed patient P, the true value, the diagnosis result of the CDSS 20 before the update (first diagnosis result), the diagnosis result of the CDSS 20 after the update (second diagnosis result), and the diagnosis result of the doctor 4 are associated with each other for each case. Note that, although FIG. 4 illustrates the data in table format for the sake of explanation, each piece of information included in the acquired data 800 only needs to be associated with each case, and does not need to be organized as a single table.

[0045] The acquisition function 151 sends the acquired new learning data, the first diagnosis result, the second diagnosis result, and the diagnosis results of the doctor 4 for each of the multiple diagnosed patients P under the support of the CDSS 20 before the update to the case extraction function 152.

[0046] Returning to FIG. 1, the case extraction function 152 extracts, from among the multiple cases included in the new learning data, cases of the multiple diagnosed patients P that are affected by the update of the CDSS 20 due to learning of the new learning data by a first specified criterion or more, as presentation target cases, based on the first diagnosis result, the second diagnosis result, and the diagnosis result of the doctor 4 for each of the multiple diagnosed patients P with the support of the CDSS 20 before the update. The presentation target cases refer to cases displayed on an analysis screen, which will be described later. In this embodiment, the case extraction function 152 extracts the presentation target case when it determines that one of the multiple cases is a presentation target case.

[0047] In this embodiment, a case in which the update of CDSS20 is affected by more than the first specified standard refers to a case in which the second diagnostic result of CDSS20 after the update deviates from the true value more than the first diagnostic result of CDSS20 before the update.

[0048] In this embodiment, the difference between the first difference, which is the difference between the first diagnostic result and the true value, and the second difference, which is the difference between the second diagnostic result and the true value, is taken as an example of the update impact index. More specifically, the update impact index is a value obtained by subtracting the first difference from the second difference. In this case, the larger the second difference is than the first difference, that is, the more the diagnostic result deviates from the true value due to the update, the larger the update impact index becomes.

[0049] In addition, in this embodiment, the case extraction function 152 further sets as a condition for a presented case that the influence on the diagnosis result of the doctor 4 is greater than a third specified criterion. In this embodiment, the case extraction function 152 determines that the higher the similarity between the first diagnosis result and the diagnosis result of the doctor 4 for each of the multiple diagnosed patients P under the support of the CDSS 20 before the update, the greater the influence on the diagnosis result of the doctor 4. For this reason, the case extraction function 152 also sets as a condition for a presented case that the difference between the first diagnosis result and the diagnosis result of the doctor 4 under the support of the CDSS 20 is equal to or less than the second specified criterion. Note that, if the difference between the first diagnosis result and the diagnosis result of the doctor 4 is equal to or less than the second specified criterion, the influence on the diagnosis result of the doctor 4 is determined to be greater than the third specified criterion.

[0050] The difference between the first diagnosis result and the diagnosis result of the doctor 4 with the support of the CDSS 20 is an example of a diagnosis influence index in this embodiment. The smaller the difference between the first diagnosis result and the diagnosis result of the doctor 4 with the support of the CDSS 20, the larger the diagnosis influence index.

[0051] That is, the case extraction function 152 determines, among the multiple cases included in the new learning data, a case in which the first difference is equal to or smaller than the second difference and the difference between the first diagnosis result and the diagnosis result of the doctor 4 with the support of the CDSS 20 is equal to or smaller than the second specified criterion as a presentation target case. The second specified criterion is, for example, a predetermined threshold value. More specifically, the case extraction function 152 extracts a case that satisfies both formulas (1) and (2) as a presentation target case.

[0052]

number

[0053] Equation (1) specifies that the absolute value of the value obtained by subtracting the diagnosis result of doctor 4 from the first diagnosis result of the CDSS 20 before the update is equal to or less than a threshold value. Moreover, equation (2) specifies that the absolute value of the value obtained by subtracting the true value from the first diagnosis result of the CDSS 20 before the update is equal to or less than the absolute value of the value obtained by subtracting the true value from the second diagnosis result of the CDSS 20 after the update.

[0054] The threshold value in formula (1) may be set by a user such as the doctor 4, or may be the average or median of the absolute values ​​of the results of subtracting the diagnosis result of the doctor 4 from the first diagnosis result of the CDSS 20 before the update. Note that the extraction conditions for the presentation target cases are not limited to formulas (1) and (2).

[0055] In addition, when the diagnosis result is not expressed as a numerical value, a condition other than the threshold value may be used as the second prescribed criterion. For example, when the diagnosis result is output as a binary value of "yes" or "no" such as the presence or absence of a side effect, "there is no difference between the first diagnosis result and the diagnosis result of the doctor 4 under the support of the CDSS20" may be used as the second prescribed criterion. In this case, if there is no difference between the first diagnosis result and the diagnosis result of the doctor 4 under the support of the CDSS20, it is equivalent to the second prescribed criterion. In such a case, since "the difference is equal to or less than the second prescribed criterion," the condition that "the difference between the first diagnosis result and the diagnosis result of the doctor 4 under the support of the CDSS20 is equal to or less than the prescribed criterion" is satisfied. Alternatively, the case extraction function 152 may convert a non-numerical diagnosis result into a numerical value and then calculate the difference.

[0056] In other words, the patient P who satisfies the formula (2) is a patient P whose diagnostic result accuracy has decreased before and after updating the CDSS 20. For such a patient P, the diagnostic result obtained by the CDSS 20 is significantly affected by the update.

[0057] Furthermore, as exemplified by formula (1), a patient P for whom the difference between the first diagnosis result and the diagnosis result of the doctor 4 with the support of the CDSS 20 is equal to or less than the second prescribed standard is, in other words, a patient P for whom the diagnosis result of the doctor 4 is similar to the first diagnosis result. In this embodiment, when the first diagnosis result and the diagnosis result of the doctor 4 with the support of the CDSS 20 are similar, it is assumed that there is a possibility that the doctor 4 was influenced by the diagnosis result of the CDSS 20 in diagnosing the patient P.

[0058] Here, the influence of the CDSS 20 on the diagnosis result by the doctor 4 will be described with reference to Figures 5 to 7. It is assumed that the diagnosed patients P1 to P3 shown in Figures 5 to 7 are different persons. When there is no particular distinction between the diagnosed patients P1 to P3, they will be simply referred to as patient P.

[0059] FIG. 5 is a diagram showing an example of the relationship between the diagnosis result of the CDSS 20 and the diagnosis result of the doctor 4 according to the first embodiment.

[0060] In the example shown in Fig. 5, the CDSS 20 before the update outputs a first diagnosis result that patient P1 will have side effects. Similarly to the CDSS 20 before the update, doctor 4 also outputs a diagnosis result that patient P1 will have side effects. If the second prescribed criterion is that "the first diagnosis result and the diagnosis result of doctor 4 are identical," that is, if the difference threshold is "0," then the difference between the first diagnosis result for patient P1 and the diagnosis result of doctor 4 with the support of the CDSS 20 is equal to or less than the second prescribed criterion.

[0061] In this case, it is highly likely that Doctor 4 made a diagnosis based on the first diagnosis result of the pre-update CDSS 20. For example, if another patient P with similar test results to those of Patient P1 receives the diagnosis, Doctor 4 may make a diagnosis under the influence of the diagnosis result of the CDSS 20, as in the case of Patient P1.

[0062] The treatment result for patient P1, that is, the true value, was "side effects." In this case, the first diagnosis result is equal to the true value. In contrast, the second diagnosis result of the updated CDSS20 is "no side effects," which is different from the true value. In this case, the first difference is smaller than the second difference, and formula (2) is satisfied.

[0063] Since the first difference for patient P1 shown in Figure 5 is less than or equal to the second difference, and the difference between the first diagnostic result and the diagnostic result of doctor 4 with the assistance of CDSS 20 is less than or equal to the second specified standard, the case extraction function 152 extracts the case of patient P1 as a case to be presented.

[0064] FIG. 6 is a diagram showing another example of the relationship between the diagnosis result of the CDSS 20 according to the first embodiment and the diagnosis result of the doctor 4. In the example shown in FIG. 6, the doctor 4 issues a diagnosis result different from the first diagnosis result of the CDSS 20 before the update. If the second prescribed criterion is that "the first diagnosis result and the diagnosis result of the doctor 4 are identical," that is, if the difference threshold is "0," the case of the patient P2 does not satisfy the criterion. As shown in FIG. 6, if the difference between the diagnosis result of the CDSS 20 before the update and the diagnosis result of the doctor 4 is large, it is generally estimated that the influence of the CDSS 20 before the update on the doctor 4 is small. In this case, the case extraction function 152 does not extract the case of the patient P2 as a presentation target case.

[0065] FIG. 7 is a diagram showing yet another example of the relationship between the diagnosis result of the CDSS 20 according to the first embodiment and the diagnosis result of the doctor 4. In the example shown in FIG. 7, the first diagnosis result of the CDSS 20 before the update for the patient P3 is "side effects present", the second diagnosis result of the CDSS 20 after the update is "no side effects", and the true value is "no side effects". That is, in the example shown in FIG. 7, the accuracy of the diagnosis of the patient P3 by the CDSS 20 is improved by the update. In this case, the first difference is larger than the second difference, and the formula (2) is not satisfied. In this case, the case extraction function 152 does not extract the case of the patient P3 as a case to be presented.

[0066] Although the same doctor 4 makes the diagnosis in each of the examples shown in Figs. 5 to 7, different doctors 4 may make the diagnosis.

[0067] The case extraction function 152 sends to the output control function 154 those corresponding to the extracted presentation target cases among the new learning data, the first diagnosis result, the second diagnosis result, and the diagnosis result of the doctor 4 for each of the multiple diagnosed patients P with the support of the CDSS 20 before the update. In addition, the case extraction function 152 sends to the output control function 154 the diagnosis influence index and the update influence index corresponding to the extracted presentation target cases.

[0068] Returning to Fig. 1, the influential variable extraction function 153 extracts, from among a plurality of types of test results for each of a plurality of diagnosed patients P included in the new learning data, items that have influenced changes in the diagnosis results of the CDSS 20 before and after the update as influential variables. In this embodiment, since the influential variables are determined by the classification function 158 described below, more accurately, the influential variable extraction function 153 extracts "influential variable candidates." Hereinafter, unless a special distinction is made in the description, the influential variable candidates will also be referred to as influential variables.

[0069] In this embodiment, each item included in the test result is called a variable. In other words, when the first diagnostic result and the second diagnostic result of the CDSS 20 are different, the influencing variable extraction function 153 estimates which variable has influenced the change. The influencing variable extraction function 153 extracts the variables that influenced the change in the diagnostic result of the CDSS 20 as the influencing variables.

[0070] Fig. 8 is a diagram showing an example of a method for extracting influential variables according to the first embodiment. As shown in Fig. 8, the influential variable extraction function 153 inputs, to a prediction model 70, patient information for each case included in new learning data and whether or not the diagnosis result of the CDSS 20 has changed before and after the update for each case.

[0071] The presence or absence of a change is also called a label for the patient information. The influential variable extraction function 153 associates the label "changed" with cases in which the diagnosis result of the CDSS20 changed before and after the update, and the label "unchanged" with cases in which the diagnosis result of the CDSS20 did not change before and after the update, and inputs them into the prediction model 70. Cases in which the diagnosis result of the CDSS20 changed before and after the update are also called "changed cases," and cases in which the diagnosis result of the CDSS20 did not change before and after the update are also called "unchanged cases."

[0072] More specifically, the presence or absence of change in the diagnosis result of the CDSS 20 before and after the update refers to the presence or absence of a difference between the first diagnosis result and the second diagnosis result. Note that, when the first diagnosis result and the second diagnosis result are expressed as numerical values, the influential variable extraction function 153 may determine that the difference between the first diagnosis result and the second diagnosis result is "unchanged" if it is equal to or smaller than a specified threshold, and may determine that the difference is "changed" if it is larger than the specified threshold.

[0073] As described above, the test results include, for example, vital data such as the patient P's body temperature and blood pressure, blood test results such as white blood cell count, major markers, image measurements such as tumor size, and findings by a doctor or nurse. The prediction model 70 outputs the magnitude of influence of each item of these test results, i.e., each variable, on the change in the diagnosis result of the CDSS 20 before and after the update. In this embodiment, the magnitude of influence of each variable on the change in the diagnosis result of the CDSS 20 before and after the update is called the importance of each variable. In the example shown in FIG. 8, the prediction model 70 expresses the importance of each variable as a decimal value between 0 and 1. The larger the value, the greater the influence of the variable on the change in the diagnosis result of the CDSS 20 before and after the update.

[0074] The prediction model 70 is a trained model generated by machine learning such as random forest. The machine learning method is not limited to this, and other known machine learning methods can be adopted. The prediction model 70 may be stored in the storage circuit 120 or may be incorporated in the influential variable extraction function 153.

[0075] In this embodiment, the influencing variable extraction function 153 determines a variable whose importance is greater than or equal to a specified criterion as an influencing variable. The influencing variable extraction function 153 extracts an influencing variable when it determines that a variable is an influencing variable from among a plurality of variables.

[0076] The influence variable extraction function 153 sends the extracted influence variables and the importance of the influence variables to the output control function 154 .

[0077] Returning to FIG. 1, the output control function 154 causes the presentation target cases extracted by the case extraction function 152 to be output to the display 140 in association with the diagnostic impact index. In this embodiment, the screen on which the presentation target cases and the diagnostic impact index are displayed is called an analysis screen. In this embodiment, the term "output" includes "display." Furthermore, the output method is not limited to display. For example, the output control function 154 may output the presentation target cases to an information processing device other than the medical information processing device 10 in association with the diagnostic impact index.

[0078] FIG. 9 is a diagram showing an example of an analysis screen according to the first embodiment. As shown in FIG. 9, the output control function 154 displays a list 91 of influencing variables extracted by the influencing variable extraction function 153 on the analysis screen on the display 140. The list 91 includes, as an example, the name and importance of the variable. The user can select any influencing variable from the list 91 as the analysis target. In the example shown in FIG. 9, three influencing variables, "white blood cell count," "tumor marker," and "body temperature," are selected by the user.

[0079] The output control function 154 causes the presentation target case to be output to the display 140 in association with the influencing variables. More specifically, the output control function 154 causes a graph having two variables as axes among the multiple influencing variables selected by the user to be displayed on the analysis screen. In the example shown in FIG. 9, three types of graphs are displayed: a graph having "tumor marker" and "white blood cell count" as axes, a graph having "tumor marker" and "body temperature" as axes, and a graph having "white blood cell count" and "body temperature" as axes. Note that, in the example shown in FIG. 9, only the influencing variables selected by the user are used as the axes of the graphs, but all the extracted influencing variables may be used as the axes of the graphs.

[0080] On each graph, the presentation target cases extracted by the case extraction function 152 are mapped. For example, point 8 on the graph with the axes of “tumor marker” and “white blood cell count” indicates that the “white blood cell count” is “2500 / mm 3 This is an example of a patient named "XX" who has a "tumor marker" value of "8 ng / ml" and a "neoplasms level" value of "1 ng / ml." The graph shown in FIG. 9 is an example of a plane defined by the values ​​of two types of test results.

[0081] In addition, when a user selects a point representing a case, for example with a mouse pointer, the output control function 154 may display the patient information, true value, first diagnosis result, second diagnosis result, and doctor 4's diagnosis result corresponding to the case.

[0082] In addition, the output control function 154 associates the diagnosis impact index and the update impact index with the presentation target case and outputs them to the display 140. In the example shown in Fig. 9, the output control function 154 highlights on the graph the presentation target case whose diagnosis impact index or update impact index is equal to or greater than the threshold. This allows the user to know whether the diagnosis impact index or update impact index of each presentation target case mapped on the graph is equal to or greater than the threshold. In the example shown in Fig. 9, points indicating presentation target cases whose diagnosis impact index or update impact index is equal to or greater than the threshold are displayed larger than points indicating presentation target cases whose diagnosis impact index or update impact index is smaller than the threshold.

[0083] The threshold value of the diagnostic impact index and the threshold value of the update impact index can each be changed by the user in a threshold adjustment section 90 on the analysis screen. The output control function 154 displays the threshold adjustment section 90 including an operable knob and bar. In FIG. 9, the diagnostic impact index is expressed as "the difference between the CDSS (before update) and the user's diagnosis result," and the update impact index is expressed as "the difference between the CDSS before and after the update and the true value," so that the user can understand the content of each index.

[0084] In the example shown in Figure 9, the cases to be highlighted are those for which both the diagnostic impact index and the update impact index are above a threshold value, but the condition for highlighting may also be that at least one of the diagnostic impact index and the update impact index is above a threshold value.

[0085] 9, the case of patient name "XX" corresponding to point 8 has both the diagnosis influence index and the update influence index greater than or equal to the threshold. In other words, although the influence of the case of patient name "XX" on the diagnosis of doctor 4 is greater than or equal to the threshold, the update has caused the diagnosis result to deviate from the true value by more than the threshold compared to before the update.

[0086] Presentation target cases associated with a diagnosis impact index equal to or greater than a threshold value set by the user and an update impact index equal to or greater than the threshold value are given priority as targets for improving the diagnosis accuracy of the CDSS 20 in the update process described below.

[0087] Returning to Fig. 1, the reception function 155 receives an operation by a user via the input interface 130. For example, the reception function 155 receives an operation by a user to adjust the threshold of a diagnosis influence index or the threshold of an update influence index in the threshold adjustment unit 90 on the analysis screen. The reception function 155 also receives an operation by a user to select a variable from a list 91 of influencing variables on the analysis screen.

[0088] The reception function 155 sends the received operation content to the output control function 154 and the data processing function 156 .

[0089] The data processing function 156 processes new learning data by the user based on the threshold value of the diagnostic influence index and the threshold value of the update influence index determined by the user, and the importance of each variable calculated by the influence variable extraction function 153.

[0090] More specifically, the data processing function 156 includes a generation function 157 and a classification function 158 .

[0091] The generation function 157 copies an example of a plurality of examples included in the new learning data, the example having a diagnostic influence index equal to or greater than a threshold value, to generate a new example, and adds the new example to the new learning data.

[0092] Fig. 10 is a diagram showing an example of adding a new case according to the first embodiment. As shown in Fig. 10, the generation function 157 duplicates a case of patient name "XX" in which both the diagnosis influence index and the update influence index are equal to or greater than the threshold value among a plurality of cases included in new learning data, and generates cases of patient name "XX2" and patient name "XX3". The cases of patient name "XX2" and patient name "XX3" are pseudo data that are not actual diagnosis histories. The cases of patient name "XX2" and patient name "XX3" include the same information as the case of patient name "XX" except for identification information such as the patient name.

[0093] Such duplication increases the number of cases in the new learning data that have similar patient information and true values ​​to the case with patient name "XX," so that learning is performed to improve the diagnostic accuracy for cases with patient information similar to the patient name "XX" in updating the CDSS 20. The generation function 157 duplication of cases to increase the number of samples in the new learning data that have similar patient information and true values ​​is an example of a method of increasing the weight for the case.

[0094] The generating function 157 may automatically select cases to be copied, in addition to cases specified by the threshold value of the diagnosis impact index and the threshold value of the update impact index determined by the user.

[0095] In addition, the classification function 158 classifies multiple variables included in the new learning data into "influence variables" that have a large influence on updating the CDSS 20 and "non-influence variables" that have a small influence on the CDSS 20.

[0096] Fig. 11 is a diagram showing an example of classification of variables according to the first embodiment. In the example shown in Fig. 11, among the influencing variable candidates extracted by the influencing variable extraction function 153, three variables selected by the user on the analysis screen are classified as "influencing variables", and the other influencing variable candidates are classified as "non-influencing variables". In addition, variables that are not extracted as influencing variable candidates are also classified as "non-influencing variables".

[0097] The classification function 158 may classify the influencing variables into "influencing variables" and "non-influencing variables" based on the importance of each influencing variable candidate, rather than on the basis of a user's selection. Alternatively, the classification function 158 may classify all influencing variable candidates extracted by the influencing variable extraction function 153 into "influencing variables", and classify only variables that were not extracted as influencing variable candidates into "non-influencing variables".

[0098] Returning to Figure 1, the learning control function 159 controls the learning process in learning the CDSS 20 so that, among the multiple cases included in the new learning data, the case in which the difference between the first diagnosis result and the diagnosis result of doctor 4 is smaller is given a higher priority.

[0099] More specifically, the learning control function 159 controls the learning process in learning of the CDSS 20 so as to minimize the difference between the second diagnosis result of the CDSS 20 and the true value.

[0100] Furthermore, the learning control function 159 classifies the multiple types of test results included in the disease information into a first test result that has a large influence on the change between the first diagnostic result and the second diagnostic result, and a second test result that has a smaller influence on the change between the first diagnostic result and the second diagnostic result than the first test result. The learning control function 159 also inputs the first test result to the first model and inputs the second test result to the second model. Then, the learning control function 159 adjusts the weighting coefficient so that the weight of the output result of the first model is increased, calculates a weighted average of the output result of the first model and the output result of the second model, and outputs the calculation result of the weighted average as a prediction result. That is, the learning control function 159 adjusts the influence of the "influence variable" on the update by adjusting the weighting coefficient. It is assumed that both the first model and the second model are CDSS.

[0101] Fig. 12 is a diagram showing an example of the learning process according to the first embodiment. The learning control function 159 updates the CDSS 20 based on the processed learning data obtained by processing new learning data by the data processing function 156. Note that the "correct label" shown in Fig. 12 refers to a true value.

[0102] As shown in Fig. 12, the learning control function 159 obtains a first learning result 61 in which only the "influence variables" of the new learning data have been learned, and a second learning result 62 in which only the "non-influence variables" of the new learning data have been learned. The learning control function 159 then uses the result of multiplying the second learning result 62 by a weighting coefficient and the first learning result 61 not multiplied by a weighting coefficient as further learning data, thereby increasing the influence of the "non-influence variables" and decreasing the influence of the "influence variables" in updating the CDSS 20. Note that the values ​​of the weighting coefficients shown in Fig. 12 are merely examples and are not limited to these.

[0103] 12, the processed learning data includes new cases that have been copied by the generation function 157. Therefore, the learning control function 159 performs learning of the CDSS 20 by applying two types of weighting: a first weighting due to the addition of new cases, and a second weighting for the "non-influential variables."

[0104] Furthermore, the learning control function 159 also performs weighting in the learning processing algorithm, in which the priority is increased for cases in which the difference between the first diagnosis and the diagnosis by doctor 4 is small, that is, cases with a larger value of the diagnostic influence index, among the multiple cases included in the processed learning data.

[0105] In this embodiment, the learning control function 159 performs learning using a minimization model of a weighted loss function. For example, the learning control function 159 employs a mean square error (MSE). Here, a model for bringing the second diagnosis result of the CDSS 20 closer to the true value by the MSE is generally shown as equation (3).

[0106]

number

[0107] However, the learning control function 159 of this embodiment performs learning using a minimization model of equation (4) which is a weighted version of equation (3). In equation (4), the weighting coefficient is increased for cases in which the difference between the first diagnosis result and the diagnosis result of doctor 4 is small. For this reason, equation (4) not only brings the second diagnosis result closer to the true value, but also increases the influence of cases with large values ​​of the diagnostic influence index on learning of the CDSS 20. Note that the learning method is not limited to MSE, and other machine learning methods may be adopted.

[0108]

number

[0109] In this embodiment, the learning control function 159 of the medical image processing apparatus 10 controls the learning process of the CDSS 20 . However, the learning control function 159 may be a function of the CDSS 20 .

[0110] Next, a flow of the update support process for the CSDD 20 executed by the medical image processing device 10 configured as above will be described.

[0111] FIG. 13 is a flowchart showing an example of the flow of the update support process according to the first embodiment.

[0112] First, the acquisition function 151 acquires data to be used in the update support process (S1) from the CDSS 20. Specifically, the acquisition function 151 acquires a first diagnosis result, a second diagnosis result for each of a plurality of diagnosed patients P, a diagnosis result by the doctor 4 for each of a plurality of diagnosed patients P under the support of the CDSS 20 before the update, and new learning data.

[0113] Next, the case extraction function 152 extracts, from among the multiple cases included in the new learning data, cases of the multiple diagnosed patients P that are affected by the update of the CDSS 20 due to learning of the new learning data by a specified standard or more, as cases to be presented, based on the first diagnosis result, the second diagnosis result, and the diagnosis result of the doctor 4 for each of the multiple diagnosed patients P with the support of the CDSS 20 before the update (S2). The case extraction function 152 also calculates an update impact index and a diagnosis impact index for each case.

[0114] In addition, the influential variable extraction function 153 extracts, from among the multiple types of test results for each of the multiple diagnosed patients P included in the new learning data, items that influenced the changes in the diagnostic results of the CDSS 20 before and after the update as influential variables (S3).

[0115] Then, the output control function 154 causes the display 140 to display an analysis screen showing the presentation target cases extracted by the case extraction function 152 in association with the updated influence index, the diagnostic influence index, and the influence variables extracted by the influence variable extraction function 153 (S4). In addition, the reception function 155 receives various operations by the user on the analysis screen.

[0116] The generating function 157 and the classifying function 158 included in the data processing function 156 process the new learning data based on the user's setting of the threshold for the update influence index, the setting of the threshold for the diagnosis influence index, and the selection of the influence variable (S5). Note that the generating function 157 and the classifying function 158 may process the new learning data based on a specified standard or a calculation result, etc., instead of a user's operation.

[0117] Then, the learning control function 159 uses the processed learning data to update the CDSS 20 (S6), at which point the process of this flowchart ends.

[0118] In this manner, the medical information processing device 10 of this embodiment displays on the display 140, among the cases included in the new learning data, cases that are affected by the update of the CDSS 20 by a first specified criterion or more in association with the diagnostic influence index. Therefore, the user can easily grasp, among the presented cases that are affected by the update of the CDSS 20 by a specified criterion or more, those that have a large degree of influence on the diagnosis of the doctor 4, and the user can select cases that should be prioritized in learning the CDSS 20. Therefore, the medical information processing device 10 of this embodiment can support, in learning the CDSS 20, preferentially improving the diagnostic accuracy of cases that are important when the doctor 4 makes a diagnosis.

[0119] Moreover, the medical information processing device 10 of this embodiment associates the update influence index with the presentation target case examples and displays them on the display 140. Therefore, according to the medical information processing device 10 of this embodiment, the user can easily grasp which of the presentation target cases will be strongly influenced by the update of the CDSS 20.

[0120] Furthermore, the medical information processing device 10 of this embodiment extracts, from among the multiple cases included in the new learning data, cases in which the first difference is smaller than the second difference and the difference between the first diagnosis result and the diagnosis result of the doctor 4 with the support of the CDSS 20 is equal to or smaller than a second specified standard, as presentation target cases. Therefore, according to the medical information processing device 10 of this embodiment, the user can easily grasp cases in which the diagnosis result of the CDSS 20 was influenced when the doctor 4 made a diagnosis.

[0121] The diagnostic influence index of this embodiment indicates the degree of influence that the CDSS 20 has on the diagnosis of the doctor 4. The diagnostic influence index has a larger value as the difference between the first diagnosis result and the diagnosis result of the doctor with the support of the CDSS 20 becomes smaller. Therefore, the medical information processing device 10 of this embodiment can easily determine whether or not the case is one in which the diagnosis result of the CDSS 20 influenced the doctor 4's diagnosis.

[0122] Furthermore, the medical information processing device 10 of this embodiment copies cases whose diagnostic influence index is equal to or greater than a threshold among the multiple cases included in the new learning data to generate new cases, and adds the new cases to the new learning data. Therefore, according to the medical information processing device 10 of this embodiment, by increasing the number of samples whose diagnostic influence index is equal to or greater than a threshold in the new learning data, it is possible to focus on improving the diagnostic accuracy of the CDSS 20 for cases that are likely to be referred to by the doctor 4 when making a diagnosis.

[0123] Furthermore, the medical information processing device 10 of this embodiment controls the learning process in learning the CDSS 20 so that, among multiple cases included in new learning data, a case in which the difference between the first diagnosis result and the diagnosis result of the doctor 4 with the support of the CDSS 20 is smaller is given a higher priority. Therefore, according to the medical information processing device 10 of this embodiment, it is possible to focus on improving the diagnostic accuracy of the CDSS 20 for cases that are likely to be referred to by the doctor 4 when making a diagnosis.

[0124] Furthermore, the medical information processing device 10 of this embodiment controls the learning process so as to minimize the difference between the second diagnosis result and the true value of the CDSS 20 in learning the CDSS 20. Therefore, according to the medical information processing device 10 of this embodiment, it is possible to improve the accuracy of diagnosis by the CDSS 20 through learning.

[0125] In addition, the medical information processing device 10 of this embodiment controls the learning process so as to lower the priority of those types of test results included in the new learning data that affect changes in the first and second diagnostic results.Therefore, the medical information processing device 10 of this embodiment reduces significant changes in the diagnostic results due to updates to the CDSS 20.

[0126] Furthermore, the medical information processing device 10 of this embodiment extracts items related to the difference between the first and second diagnostic results from among the items of multiple types of test results included in the new learning data as influencing variables that affect the update of the CDSS 20, and displays the presentation target cases in association with the influencing variables on the display 140. Therefore, according to the medical information processing device 10 of this embodiment, the items related to the difference between the first and second diagnostic results can be used as an analysis axis for the presentation target cases.

[0127] In this embodiment, the influencing variable extraction function 153 and the classification function 158 are described as different functions, but the influencing variable extraction function 153 and the classification function 158 may be configured as one function. The influencing variable extraction function 153 extracts, for example, examination items with high importance as influencing variables with high importance for updating the CDSS20. The influencing variable extraction function 153 extracts influencing variables with high importance based on the variable importance output from a prediction model trained using a label indicating a classification of "important" or "unimportant" for each examination item as a correct answer. In addition, a case in which the diagnosis result by the CDSS20 before the update is close to the diagnosis result by the doctor 4 (high diagnostic influence) and the difference between the diagnosis result by the CDSS20 before the update and the diagnosis result by the CDSS20 after the update is large (high update influence) is determined as important, and a case that is not important is determined as unimportant. More specifically, it is a test item for cases where the difference between the diagnosis result based on the CDSS 20 before the update and the diagnosis result by doctor 4 with the support of the CDSS 20 is equal to or less than the second prescribed criterion, and the difference between the diagnosis result based on the CDSS 20 before the update and the diagnosis result based on the CDSS 20 after the update is equal to or more than the fourth prescribed criterion. The fourth prescribed criterion may be a numerical value or another condition.

[0128] Second Embodiment In the above-described first embodiment, the medical information processing device 10 displays cases related to diagnosed patients P on the analysis screen. In this second embodiment, the medical information processing device 10 also displays cases of patients who have not yet been diagnosed on the analysis screen.

[0129] The information processing system S of this embodiment includes a medical information processing device 10 and a CDSS 20, similar to the first embodiment.

[0130] Further, the medical information processing device 10 of this embodiment includes a NW interface 110, a storage circuitry 120, an input interface 130, a display 140, and a processing circuitry 150, similarly to the first embodiment.

[0131] Similar to the first embodiment, the processing circuit 150 of this embodiment includes an acquisition function 151, a case example extraction function 152, an influencing variable extraction function 153, an output control function 154, a reception function 155, a data processing function 156, a generation function 157, a classification function 158, and a learning control function 159. The case example extraction function 152, the influencing variable extraction function 153, the reception function 155, the data processing function 156, the generation function 157, the classification function 158, and the learning control function 159 have the same functions as those of the first embodiment.

[0132] The acquisition function 151 of this embodiment acquires undiagnosed patient information including a plurality of undiagnosed cases related to information on diseases of a plurality of patients that have not been diagnosed by the doctor 4 and the CDSS 20, in addition to the functions of the first embodiment. The source of the undiagnosed patient information is, for example, an electronic medical record system.

[0133] The undiagnosed patient information is an example of the second data in this embodiment. The undiagnosed patient information includes information on diseases for each of a plurality of patients for which a diagnosis has not been performed. In the undiagnosed patient information, for example, information on a disease associated with one patient is regarded as one undiagnosed case. The undiagnosed patient information includes a plurality of undiagnosed cases.

[0134] Furthermore, the information on diseases contained in the undiagnosed patient information includes multiple types of test results for multiple undiagnosed patients, that is, variables.

[0135] In addition to the functions of the first embodiment, the output control function 154 of this embodiment causes the display 140 to display information indicating the likelihood that the diagnostic results of the CDSS 20 for multiple patients included in the undiagnosed patient information will change before and after learning new learning data.

[0136] The information representing the likelihood that the CDSS20 diagnostic results for multiple patients included in the undiagnosed patient information will change before and after learning new training data is, for example, information indicating whether multiple undiagnosed cases included in the undiagnosed patient information fall into a range of variable values ​​for which the difference in the CDSS20 diagnostic results before and after the update is large.

[0137] FIG. 14 is a diagram showing an example of an analysis screen according to the second embodiment. In the example shown in FIG. 14, the output control function 154 displays on the graph an area 93c-93c (hereinafter simply referred to as area 93) in which the difference between the diagnostic result of the CDSS 20 before and after the update of the CDSS 20 is large. The difference between the diagnostic result of the CDSS 20 before and after the update of the CDSS 20 is large means that the difference between the first diagnostic result and the second diagnostic result is equal to or larger than the fourth specified criterion. As described above, the fourth specified criterion may be a numerical value or other conditions. In the example shown in FIG. 14, the area 93 is a range in which the difference between the first diagnostic result and the second diagnostic result of the diagnosed patient P is equal to or larger than the fourth specified criterion on a graph with the variable "tumor marker value" on the vertical axis and the variable "body temperature" on the horizontal axis.

[0138] The output control function 154 maps and displays, on a graph defined by two types of variables, multiple cases of diagnosed patients P included in the new learning data and multiple undiagnosed cases related to multiple patients who have not been diagnosed, included in the undiagnosed patient information, as in the graph shown in Fig. 14. The graph on the analysis screen shown in Fig. 14 is an example of a plane defined by values ​​of two types of test results.

[0139] For this reason, when an undiagnosed case mapped on the graph falls within region 93, there is a high possibility that the diagnosis result of the CDSS 20 for the patient of that medical diagnosis case will change before and after learning new training data. When many undiagnosed cases fall within region 93, it is desirable for the user to carefully select the threshold value, etc., so that updating the CDSS 20 does not decrease the accuracy of diagnosis for patients corresponding to these undiagnosed cases.

[0140] In this way, the medical information processing device 10 of this embodiment acquires undiagnosed patient information, and displays on the display 140 information indicating the likelihood that the diagnosis results of the CDSS 20 for multiple patients included in the undiagnosed patient information will change before and after learning new learning data. Therefore, the medical information processing device 10 of this embodiment has the effects of the first embodiment, and also allows the user to easily understand the impact that an update of the CDSS 20 will have on diagnoses for patients who have not yet been diagnosed. For example, by using the medical information processing device 10 of this embodiment, the user can understand, before updating the CDSS 20, to what extent the update will affect the diagnoses of patients who are to be diagnosed in the future.

[0141] Furthermore, the medical information processing device 10 of this embodiment maps and displays on a graph defined by two types of variables a plurality of diagnosed patient P cases included in the new learning data and a plurality of undiagnosed cases related to a plurality of undiagnosed patients included in the undiagnosed patient information. Therefore, the medical information processing device 10 of this embodiment allows the user to visually grasp the distribution of diagnosed patient cases and the distribution of undiagnosed patient cases.

[0142] (Variation 1) Although the analysis screen in each of the above-described embodiments displays the simulation results when the CDSS 20 is updated under one condition, simulation results under a plurality of different conditions may be displayed on one screen.

[0143] Fig. 15 is a diagram showing an example of an analysis screen according to Modification 1. As shown in Fig. 15, the output control function 154 of this modification causes presentation target cases when the CDSS 20 is updated under a plurality of different conditions to be output on the same screen for each of the plurality of different conditions.

[0144] The first screen area 7a and the second screen area 7b of the analysis screen shown in Fig. 15 each represent a presentation target case in the CDSS 20 updated under different conditions. The content displayed in each screen area is the same as that of the analysis screen in the first embodiment described in Fig. 9 or the analysis screen in the second embodiment described in Fig. 14. For example, the first screen area 7a and the second screen area 7b include threshold adjustment sections 90a and 90b, lists of influential variables 91a and 91b, and a graph with the selected variable as an axis.

[0145] Different conditions include, for example, but are not limited to, that the content of the new learning data is different, that the algorithm of the CDSS20 to be updated is different, or that the past learning data used in the update prior to the update with the new learning data is different.

[0146] In this way, by displaying simulation results under a plurality of different conditions on one screen, the user can easily compare and consider which conditions should be adopted.

[0147] (Variation 2) In the analysis screen of each of the above-described embodiments, the diagnostic influence index is determined based on the difference between the first diagnostic result and the diagnostic result of the doctor 4 with the support of the CDSS 20. However, the method of finding the magnitude of the influence of the CDSS 20 on the diagnosis of the doctor 4 is not limited to this.

[0148] For example, the degree of influence of the CDSS20 on the diagnosis of the doctor 4 may be self-reported by the doctor 4. The diagnostic influence index of this modification is the report result of the doctor 4 who diagnosed the patient P of the presented case regarding the degree of influence of the CDSS20 at the time of diagnosis. The report result is the result of the doctor 4 himself reporting whether or not the doctor 4 was influenced by the diagnosis result of the CDSS20 at the time of diagnosis. The report result may be information that expresses not only the presence or absence of influence but also the magnitude of the degree of influence as a numerical value or a level. The acquisition function 151 of this modification acquires the report result for each case from, for example, an electronic medical record system. Alternatively, the reception function 155 may receive the input of the report result for each case by the doctor 4.

[0149] (Variation 3) The configuration of the information processing system S is not limited to the above-mentioned example. For example, in each of the above-mentioned embodiments, the CDSS 20 and the medical information processing device 10 are described as separate devices, but the CDSS 20 and the medical information processing device 10 may be integrated into one device. In this case, the CDSS 20 may be an example of the medical information processing device.

[0150] Furthermore, the information processing system S may include a plurality of CDSSs 20. Furthermore, some or all of the CDSSs 20 and the medical information processing apparatus 10 may be realized in a cloud environment.

[0151] (Variation 4) In addition, the trained models in each of the above-mentioned embodiments include "self-learning models" that further update the internal algorithms of the trained models by allowing a user to provide feedback on the results output by these trained models.

[0152] Furthermore, in each of the above-described embodiments, the processing described as an example of a method for realizing a trained model may be realized by a method other than machine learning or deep learning.

[0153] (Variation 5) In each of the above-described embodiments, the user indirectly selects cases to be prioritized in updating the CDSS 20 by adjusting the threshold of the diagnosis impact index or the threshold of the update impact index using the threshold adjustment unit 90 on the analysis screen. The selection method is not limited to this, and the user may directly select cases to be prioritized in updating the CDSS 20 by selecting point 8 displayed on the graph on the analysis screen.

[0154] According to at least one of the embodiments described above, in the learning of the clinical decision support system, it is possible to support preferentially improving the diagnostic accuracy of cases that are important when a doctor makes a diagnosis.

[0155] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various 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 modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0156] 4. Doctor 7a First Screen Area 7b Second Screen Area 8 points 10 Medical information processing device 20 CDSS 61,62 Learning Results 70 Predictive Models 90a, 90b Threshold adjustment unit List of 91a and 91b 93,93a~93c area 110 Network Interface 120 Memory circuit 130 Input Interface 140 Display 150 Processing circuit 151 Acquisition Function 152 Case Extraction Function 153 Influence variable extraction function 154 Output control function 155 Reception Function 156 Data processing function 157 Generation function 158 Classification function 159 Learning control function 300 Network 800 Acquired Data P,P1~P3 patient S Information Processing System

Claims

1. an acquisition unit that acquires a first diagnosis result for each of a plurality of diagnosed patients by the clinical decision support system before learning first data, a second diagnosis result for each of the plurality of diagnosed patients by the clinical decision support system after learning the first data, a doctor's diagnosis result for each of the plurality of diagnosed patients, and the first data; a case extraction unit that calculates an update influence index and a diagnosis influence index for each of a plurality of cases included in the first data based on the first diagnosis result, the second diagnosis result, and the doctor's diagnosis result, and extracts, from the plurality of cases included in the first data, cases in which the update influence index is equal to or greater than a first specified standard and the diagnosis influence index is equal to or less than a second specified standard, as presentation target cases; an output control unit that causes an output unit to output the presented case examples in association with a diagnosis influence index indicating the degree of influence that the clinical decision support system has on a doctor's diagnosis in the presented case examples, and the update influence index; The first data includes a plurality of cases in which information on a disease for each of the plurality of diagnosed patients is associated with a true value representing a treatment outcome for each of the plurality of diagnosed patients; the update influence index is an index based on a difference between the first diagnosis result and the true value and a difference between the second diagnosis result and the true value, The diagnostic influence index is an index based on a difference between the first diagnostic result and the doctor's diagnostic result. Medical information processing equipment.

2. The update impact index represents a magnitude of a difference between a first difference, which is a difference between the first diagnosis result and the true value, and a second difference, which is a difference between the second diagnosis result and the true value. The medical information processing device according to claim 1 .

3. the case extraction unit extracts, from among the multiple cases included in the first data, cases in which the first difference is smaller than the second difference and the diagnostic impact index is equal to or smaller than a second specified standard, as the presentation target cases; The medical information processing device according to claim 2 .

4. The diagnostic influence index has a larger value as the difference between the first diagnostic result and the diagnostic result of a doctor under the support of the clinical decision support system becomes smaller. The medical information processing device according to claim 1 .

5. A reception unit that receives a selection by a user of setting a first threshold value of the update impact index and setting a second threshold value of the diagnosis impact index; a generation unit that generates a new case by duplicating a case of the plurality of cases included in the first data, the case having the update influence index equal to or greater than a first threshold and the diagnosis influence index equal to or greater than the second threshold, and adds the new case to the first data to generate the processed first data, the first data being training data to be used to update the clinical decision support system; the second diagnosis result is a simulation result of a diagnosis for each of the plurality of diagnosed patients by the clinical decision support system after learning the first data; The doctor's diagnosis results are diagnosis results for each of the plurality of diagnosed patients under the support of the clinical decision support system before the update. The medical information processing device according to claim 1 .

6. a learning control unit that controls a learning process in the learning of the clinical decision-making support system so that a higher priority is given to an example of a case in which a difference between the first diagnosis result and a diagnosis result of the doctor under the support of the clinical decision-making support system is smaller among the multiple examples included in the processed first data. The medical information processing device according to claim 5 .

7. the learning control unit controls the learning process so as to minimize a difference between the second diagnosis result of the clinical decision support system and the true value in learning of the clinical decision support system. The medical information processing device according to claim 6 .

8. The information about the disease included in the first data includes a plurality of types of test results for each of the plurality of diagnosed patients; The learning control unit is classifying the plurality of types of test results into a first test result having a large influence on the change between the first diagnostic result and the second diagnostic result, and a second test result having a smaller influence on the change between the first diagnostic result and the second diagnostic result than the first test result; inputting the first test results into a first model; inputting the second test results into a second model; a weighting coefficient is adjusted so that the weight of the output result of the first model is increased, and then a weighted average of the output result of the first model and the output result of the second model is calculated, and the calculated weighted average is output as a prediction result. The medical information processing device according to claim 6 or 7.

9. The case extraction unit determining that the influence is greater as the degree of similarity between the first diagnosis result and the diagnosis result of the doctor under the support of the clinical decision support system increases; extracting, from among the plurality of cases included in the first data, cases that have a greater influence on the diagnosis result of the doctor than a third prescribed standard as the presentation target case; The medical information processing device according to claim 1 .

10. an influence variable extraction unit for extracting, from among a plurality of types of test result items included in the disease information, test items having a high degree of importance as influence variables having a high degree of importance for updating the clinical decision support system; the influential variable extraction unit extracts influential variables having a high degree of importance based on the variable importance output from a prediction model trained using labels indicating classifications of important or unimportant for the items of the multiple types of test results as correct answers; The output control unit causes the output unit to output the presentation target example in association with the influencing variable, Among the test items, test items related to cases in which a difference between the first diagnostic result and a diagnostic result of the doctor under the support of the clinical decision support system is equal to or less than a second prescribed standard and a difference between the first diagnostic result and the second diagnostic result is equal to or more than a fourth prescribed standard are important test items; Among the test items, test items relating to cases in which a difference between the first diagnostic result and a diagnostic result of the doctor under the support of the clinical decision support system is greater than a second specified criterion, or a difference between the first diagnostic result and the second diagnostic result is less than a fourth specified criterion, are non-important test items. The medical information processing device according to claim 1 .

11. The acquisition unit acquires second data including information on a disease for each of a plurality of patients that has not yet been diagnosed by a doctor and the clinical decision support system; The output control unit causes the output unit to output information indicating a likelihood that a diagnosis result of the clinical decision support system for the plurality of patients, which is included in the second data, will change before and after learning the first data. The medical information processing device according to claim 1 .

12. The information about the disease included in the first data or the second data includes a plurality of types of test results for each of the plurality of diagnosed patients or each of the plurality of undiagnosed patients, the output control unit causes the plurality of cases included in the first data and the cases related to the plurality of patients for whom the diagnosis has not been performed included in the second data to be mapped and displayed on a plane defined by values ​​of two types of test results among the results of the plurality of types of tests. The medical information processing device according to claim 11.

13. The output control unit outputs the presentation target cases when the clinical decision support system is updated under a plurality of different conditions on the same screen for each of the plurality of different conditions. The medical information processing device according to claim 1 .

14. The diagnostic influence index is a report of a doctor who diagnosed a patient of the presented case regarding the degree to which the clinical decision support system influenced the diagnosis. The medical information processing device according to claim 1 .

15. an acquisition unit that acquires first data used for training a clinical decision-making support system, second data including information on a doctor and a disease for each of a plurality of patients for which a diagnosis has not been made by the clinical decision-making support system, a first diagnosis result for each of the plurality of diagnosed patients by the clinical decision-making support system before training with the first data, a second diagnosis result for each of the plurality of diagnosed patients by the clinical decision-making support system after training with the first data, and a doctor's diagnosis result for each of the plurality of diagnosed patients; a case extraction unit that calculates an update influence index and a diagnosis influence index for each of a plurality of cases included in the first data based on the first diagnosis result, the second diagnosis result, and the doctor's diagnosis result, and extracts, from the plurality of cases included in the first data, cases in which the update influence index is equal to or greater than a first specified standard and the diagnosis influence index is equal to or less than a second specified standard, as presentation target cases; an output control unit that outputs information indicating a likelihood that a diagnosis result of the clinical decision support system for the plurality of patients included in the second data will change before and after learning the first data to an output unit, and also outputs the presented cases to the output unit in association with a diagnosis influence index indicating the degree of influence that the clinical decision support system has on a doctor's diagnosis in the presented cases and an update influence index; Equipped with The first data includes a plurality of cases in which information on a disease for each of the plurality of diagnosed patients is associated with a true value representing a treatment outcome for each of the plurality of diagnosed patients; the update influence index is an index based on a difference between the first diagnosis result and the true value and a difference between the second diagnosis result and the true value, The diagnostic influence index is an index based on a difference between the first diagnostic result and the doctor's diagnostic result. Medical information processing equipment.

Images