Information processing system, information processing device, information processing method, and program

Abstract

This information processing system comprises an anonymized-data acquisition unit that acquires anonymized electronic medical record data collected from a plurality of medical institutions, an extraction unit that extracts a plurality of test values ​​from the electronic medical record data in accordance with extraction condition settings, and a visualization unit that visualizes the plurality of test values ​​so as to able to be compared.

Description

Information Processing System, Information Processing Apparatus, Information Processing Method, and Program

[0001] The present invention relates to an information processing system, an information processing apparatus, an information processing method, and a program. This application claims the priority of Japanese Patent Application No. 2024-216531 filed in Japan on December 11, 2024, and incorporates the contents thereof herein by reference.

[0002] The analysis of medical data using electronic medical record data has become increasingly important with the progress of digitization and data utilization in the medical field.

[0003] For example, Patent Document 1 discloses a medical information acquisition unit that acquires medical information including electronic medical record data of a plurality of patients, an analysis request acquisition unit that acquires an analysis request for specifying analysis content, an analysis unit that performs an analysis according to the specified analysis content based on the data included in the electronic medical record data, and an output unit that outputs an analysis result. The analysis unit analyzes the prescription trends of test values for each case where a first drug is prescribed and a second drug different from the first drug is prescribed among the electronic medical record data corresponding to the disease name specified by the analysis request from the electronic medical record data. The prescription trend is analyzed by calculating the median of the test values of the test items to be analyzed for a plurality of patients during the analysis target period, and the output unit displays, for each of the prescription trends when the first drug is prescribed and the prescription trend when the second drug is prescribed, the ratio of the number of patients whose test values of the test items fall within the reference value and those who do not fall within the reference value on the display screen in a bar graph for each different elapsed period after the drug is administered. An analysis data providing device is disclosed.

[0004] Japanese Patent No. 7194492 Gazette

[0005] However, even though the transition of test values can be visualized for the comparison of the prescription effects of different drugs using the technology described in Patent Document 1, detailed analysis and the confirmation of the effect of a single drug could not be performed. Therefore, it was not suitable for a feasibility study.

[0006] This invention has been made in view of these circumstances, and its purpose is to provide an information processing system, information processing device, information processing method, and program that can grasp feasibility.

[0007] To solve the above-mentioned problems, one aspect of the present invention is an information processing system comprising: an anonymized data acquisition unit that acquires anonymized electronic medical record data collected from multiple medical institutions; an extraction unit that extracts multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization unit that visualizes the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0008] Furthermore, one aspect of the present invention is an information processing device comprising: an anonymized data acquisition unit that acquires anonymized electronic medical record data collected from multiple medical institutions; an extraction unit that extracts multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization unit that visualizes the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0009] Furthermore, one aspect of the present invention is an information processing method executed by a computer of an information processing device, comprising: an anonymized data acquisition step of acquiring anonymized electronic medical record data collected from multiple medical institutions; an extraction step of extracting multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization step of visualizing the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0010] Furthermore, one aspect of the present invention is a program that causes a computer of an information processing device to perform an anonymized data acquisition step of acquiring anonymized electronic medical record data collected from multiple medical institutions; an extraction step of extracting multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization step of visualizing the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0011] As described above, according to one aspect of the present invention, feasibility can be grasped.

[0012] This is a schematic block diagram showing an example of the configuration of the analysis data provision system SYS according to the first embodiment of the present invention. This is a block diagram showing an example of the configuration of the analysis data provision server 30 according to this embodiment. This is a flowchart showing an example of the processing of the analysis data provision server 30 according to this embodiment. This is a diagram showing an example of the extraction condition setting acquired by the analysis data provision server 30 according to this embodiment. This is a diagram showing an example of the input screen for extraction conditions for each level in the analysis data provision server 30 according to this embodiment. This is a diagram showing an example of the output screen displaying the analysis results obtained when statistical analysis is performed in the analysis data provision server 30 according to this embodiment. This is a diagram showing an example of the output screen displaying the analysis results obtained when outcome analysis (line graph) is performed in the analysis data provision server 30 according to this embodiment. This is a diagram showing an example of the output screen displaying the analysis results obtained when outcome analysis (scatter plot) is performed in the analysis data provision server 30 according to this embodiment. This is a diagram showing an example of the output screen displaying the analysis results obtained when outcome analysis (box plot) is performed in the analysis data provision server 30 according to this embodiment. This is a hardware configuration diagram showing an example of the hardware configuration of the analysis data provision server 30 according to this embodiment. This is a diagram showing an example of the output screen displaying the results of group comparison after statistical analysis has been performed in the analysis data provision server 30 according to this embodiment.

[0013] (First Embodiment) Hereinafter, a first embodiment of the present invention will be described with reference to the drawings.

[0014] Figure 1 is a schematic block diagram showing an example of the configuration of an analysis data provision system SYS according to the first embodiment of the present invention. In Figure 1, the analysis data provision system SYS is composed of a medical institution data provision system 10, a processed data provision server 20, an analysis data provision server 30, and a terminal device 40.

[0015] The medical institution data provision system 10 is connected to the processed data provision server 20 via a communication network. The medical institution data provision system 10 is also connected to a regional medical network system. Furthermore, the medical institution data provision system 10 is connected to terminal devices installed in hospitals, clinics, etc. The medical institution data provision system 10 acquires electronic medical record data from other devices. These other devices include, for example, the storage device of the regional medical network system and terminal devices installed in hospitals, clinics, etc. The medical institution data provision system 10 stores the acquired electronic medical record data by writing it to a storage device such as a database.

[0016] Electronic medical record data includes patient information related to medical treatment, such as basic patient information, medical information, test information, treatment information, medication information, treatment-related events, medical institution information, claims information (also called electronic claims data) including social insurance / national health insurance classification, and prescription information (Prescription Claim Data). Basic patient information includes various basic information about the patient, such as patient name, address, gender, date of birth, contact information, height, weight, and medical history. Medical information includes information about the medical treatment, such as the date of treatment, subjective symptoms, diagnosis (name of illness or disease) and date of diagnosis, treatment plan, instructions from the doctor, and the results of the doctor's examination (findings, etc.).

[0017] Examination information includes the results of various tests performed on the patient, such as blood test results, X-ray images, and ultrasound diagnostic images. Treatment information includes the details of procedures performed on the patient and surgical procedures. Medication information describes the medications prescribed to the patient, including the date and time of administration and the medications themselves. Treatment-related events include events related to diagnosis and treatment, such as the date of diagnosis, the start date of medication, the date of admission, the date of discharge, and the date of surgery. Medical institution information includes the location of the medical institution that created the electronic medical record data and information about the medical department the patient visited.

[0018] Furthermore, examination information, treatment information, medication information, and treatment-related events are compared and integrated with the information in the electronic medical record data and the information in the claims data.

[0019] The medical institution data provision system 10 transmits the electronic medical record data stored in the database to the processed data provision server 20 at regular intervals (for example, every three months) or when a certain amount of data has been accumulated.

[0020] The processed data provision server 20 receives and stores electronic medical record data transmitted from the medical institution data provision system 10. The processed data provision server 20 processes the electronic medical record data to remove information relating to individuals so that individuals cannot be identified. For example, the processed data provision server 20 assigns a patient ID to each patient included in the stored electronic medical record data, generates anonymized processed data by replacing the patient name with the patient ID, and stores it in the database within the processed data provision server 20.

[0021] Furthermore, the processed data provision server 20 may also generate anonymized processed data in which hospital names, clinic names, and other medical institution names included in the electronic medical record data in the anonymized processed data have been replaced with facility IDs that can identify medical institutions, and store this anonymized processed data in the database within the processed data provision server 20. Alternatively, the processed data provision server 20 may generate anonymized processed data and store this anonymized processed data in the database within the processed data provision server 20. The anonymized processed data is data in which patient ages are processed so that those 80 years of age or older are 80 years old, those under 5 years of age are 4 years old, and those between 5 years of age and under 80 years of age are in 5-year increments.

[0022] The analysis data provision server 30 receives anonymized processed data from the processed data provision server 20. The analysis data provision server 30 is also connected to the terminal device 40 via a network for communication. The analysis data provision server 30 receives and stores the anonymized processed data stored in the processed data provision server 20. The timing for receiving the anonymized processed data is, for example, every certain period (for example, every three months). The analysis data provision server 30 also performs analysis of the anonymized processed data in response to analysis requests transmitted from the terminal device 40. The analysis data provision server 30 uses specific treatment-related events such as the date of diagnosis, the date of surgery, and the date of medication initiation as reference points, and visualizes the changes in quantitative test values ​​before and after these reference points using box plots, etc. The analysis data provision server 30 analyzes the effects of drug administration, etc. The analysis data provision server 30 transmits the analysis results to the terminal device 40.

[0023] The terminal device 40 is connected to the analysis data provision server 30 via a network so as to be able to communicate with it. The terminal device 40 has the functions of a transmitting unit that sends an analysis request specifying the content of the analysis to the analysis data provision server 30, and a receiving unit that receives the analysis results sent from the analysis data provision server 30. The terminal device 40 has an input device and a display device, and has a display unit that displays the received analysis results on a display device (display screen) connected to the terminal device 40. The input device may be at least one of a keyboard, mouse, or touch panel. The display device is, for example, a liquid crystal display device.

[0024] Users of the terminal device 40 include, for example, pharmaceutical companies and medical device manufacturers.

[0025] Next, we will explain in detail the configuration of the analysis data provision server 30.

[0026] Figure 2 is a block diagram showing an example of the configuration of the analysis data provision server 30 according to this embodiment. The analysis data provision server 30 is composed of a communication unit 31, a storage unit 32, a medical information acquisition unit 33, an analysis request acquisition unit 34, an analysis unit 35, a control unit 36, an input unit 37, and an output unit 38. The communication unit 31 has the function of communicating with the processed data provision server 20 and the function of communicating with the terminal device 40.

[0027] The storage unit 32 stores various types of data. For example, the storage unit 32 stores anonymized processed data received from the processed data provision server 20 via the communication unit 31.

[0028] The storage unit 32 is composed of a storage medium, such as an HDD (Hard Disk Drive), flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), RAM (Random Access Read / Write Memory), ROM (Read Only Memory), or any combination of these storage media. This storage unit 32 can, for example, use non-volatile memory.

[0029] The medical information acquisition unit 33 acquires medical information, including electronic medical record data of multiple patients. The electronic medical record data included in this medical information may be anonymized data, or it may be electronic medical record data that has not been processed by the processed data provision server 20. The medical information may include not only anonymized data but also other types of data.

[0030] The analysis request acquisition unit 34 acquires an analysis request specifying the content of the analysis from the terminal device 40.

[0031] The analysis unit 35 (also referred to as the extraction unit) performs analysis in response to an analysis request based on data from at least one of the following items included in the electronic medical record data (anonymized data): disease name, test value, or prescribed medication. The analysis request may include specifying the items to be analyzed, specifying the analysis method, and specifying treatment-related events. The analysis unit 35 extracts the names of medications, disease names, etc., from the data included in the anonymized data. The analysis unit 35 assigns a drug code to identify the medication according to the drug name. The analysis unit 35 also assigns a disease name code to identify the disease name according to the disease name.

[0032] The analysis unit 35 can also transmit drug codes and / or disease name codes to the terminal device 40. In this case, the analysis unit 35 can process the data into easily handleable data (standardized data) by assigning drug codes and / or disease name codes. Therefore, the analysis unit 35 can also provide this data to the terminal device 40 as industry-wide master data.

[0033] The analysis unit 35 extracts test values ​​and other data from the anonymized data. The analysis unit 35 converts the test values ​​so that they are in units appropriate to the test values.

[0034] The analysis unit 35 identifies the disease to be analyzed by assigning drug codes and / or disease name codes, and using these codes. From among the drugs corresponding to the identified disease, the analysis unit 35 identifies the drug to be analyzed based on the drug code and performs various analyses. For example, when the analysis unit 35 receives a request that includes the name of the disease to be analyzed as an analysis request, it extracts anonymized data from the anonymized data stored in the storage unit 32 that contains the code corresponding to the name of the disease to be analyzed for multiple patients. The analysis unit 35 also extracts anonymized data from the extracted anonymized data that contains the drug code corresponding to the drug specified as the target of analysis in the analysis request for multiple patients.

[0035] The analysis unit 35 then reads multiple test values ​​for each patient in the extracted anonymized data and performs analysis by calculating the median and determining whether the values ​​fall within the reference range based on these multiple test values. The multiple test values ​​are, for example, time-series test values. More specifically, the multiple test values ​​are time-series test values ​​before and after a treatment-related event. For example, if the treatment-related event is the date of the initial diagnosis, the analysis is based on the time-series test values ​​in the first period before the initial diagnosis (e.g., 3 months) and the time-series test values ​​in the second period after the initial diagnosis (e.g., 4 months).

[0036] Here, the first period and the second period may be the same or different. Also, the trend may be obscured by simple aggregation of time-series test values ​​that occur multiple times. For this reason, the user can select the first or most recent date and test value in the aggregation period as a representative value. In this way, the analysis unit 35 can extract a single data point that will serve as a judgment criterion, especially in long-term analysis. Through such analysis, trends can be confirmed in line graphs, statistical values ​​can be compared in box plots, and distribution trends can be confirmed in scatter plots.

[0037] The analysis unit 35 analyzes multiple test values ​​before and after treatment-related events for each stage of severity corresponding to the disease name, among the electronic medical record data that correspond to the disease name and treatment-related events specified by the analysis request.

[0038] Furthermore, the analysis unit 35, in addition to narrowing down the data by patient age and gender, enables comparisons between multiple groups, such as drug administration groups and non-drug administration groups, by setting groups using exclusion conditions. This allows for an understanding of the actual situation of non-recommended prescriptions and verification of discrepancies between treatment protocols and actual clinical practice. Exclusion conditions are settings that exclude patients from analysis by the analysis unit 35. The analysis unit 35 also sets custom patient groupings by setting thresholds based on guidelines, using specific test values ​​as a basis, for disease severity and grade information that is missing from the text data of electronic medical record data.

[0039] The analysis unit 35 can perform these analyses for each analysis group. The analysis group may be one or plural.

[0040] In addition, the analysis unit 35 may perform these analyses for each of the cases where the first drug is prescribed and where a second drug, which is a drug different from the first drug, is prescribed. Further, the analysis unit 35 may perform these analyses for the case where, after the first drug is prescribed, the prescription is switched to a second drug, which is a drug different from the first drug.

[0041] The control unit 36 controls each part of the analysis data providing server 30. The input unit 37 receives operation inputs input from an input device connected to the outside of the analysis data providing server 30.

[0042] The output unit 38 outputs the analysis result. For example, the output unit 38 transmits the analysis result to the terminal device 40 via the communication unit 31.

[0043] Note that the functions of the above-described communication unit 31, medical information acquisition unit 33, analysis request acquisition unit 34, analysis unit 35, control unit 36, input unit 37, and output unit 38 may be realized by configuring them with a processing device such as a CPU (Central Processing Unit) or a dedicated electronic circuit.

[0044] Next, the processing by the analysis data providing server 30 will be described.

[0045] Figure 3 is a flowchart illustrating an example of the processing performed by the analysis data provision server 30 according to this embodiment. Here, the medical institution data provision system 10 transmits electronic medical record data of multiple patients to the processed data provision server 20 at regular intervals. The processed data provision server 20 generates anonymized processed data by processing the electronic medical record data of multiple patients, thereby processing the basic information of each patient. The processed data provision server 20 transmits the generated anonymized processed data to the analysis data provision server 30. The anonymized processed data is transmitted at regular intervals (for example, every three months). The medical information acquisition unit 33 of the analysis data provision server 30 receives the anonymized processed data from the processed data provision server 20 via the communication unit 31. The medical information acquisition unit 33 of the analysis data provision server 30 stores the anonymized processed data in the storage unit 32.

[0046] When a user of terminal device 40 requests an analysis, they enter the analysis request on the analysis request input screen of terminal device 40. For example, the analysis request may include extraction conditions for each analysis group, the name of the disease to be analyzed, the name of the drug, the analysis method (analysis menu), the analysis period, and events related to the treatment to be analyzed. For the name of the disease and the name of the drug, the user may be asked to enter keywords representing the name, or they may be able to select the name of the disease or drug, for example, from a pull-down menu. The analysis method can be specified from among various analysis methods. For example, the analysis method may include a comparison of test values ​​for drugs by the severity of the disease or injury (test value analysis), a comparison of test values ​​before and after events related to treatment (test value analysis), and other analyses. Other analyses include, for example, summary analysis, basic disease analysis, basic prescription analysis, share analysis, and drug usage analysis.

[0047] The user of the terminal device 40 inputs the analysis content on the analysis request input screen, and then inputs the determination button. As a result, the terminal device 40 transmits an analysis request corresponding to the input analysis content to the analysis data providing server 30. In step S101, the analysis request acquisition unit 34 of the analysis data providing server 30 acquires the analysis request transmitted from the terminal device 40 via the communication unit 31. Next, the analysis data providing server 30 executes the process of step S102.

[0048] In step S102, when the analysis unit 35 acquires the analysis request by the analysis request acquisition unit 34, the analysis unit 35 specifies the analysis content based on the analysis request. For example, the analysis unit 35 refers to the analysis method included in the analysis request to specify whether the analysis method is inspection value analysis or other analysis. Next, the analysis data providing server 30 executes the process of step S103. Here, the case where the analysis method is specified as inspection value analysis will be described.

[0049] In step S103, the analysis unit 35 sets the target patient group based on the analysis request. Note that the setting of the target patient group may be reset by re-inputting the extraction condition setting for each analysis group in the terminal device 40 to set the target patient group. Next, the analysis data providing server 30 executes the process of step S104.

[0050] In step S104, the analysis unit 35 extracts the patients related to injury / disease A from the target patient group. Next, the analysis data providing server 30 executes the process of step S105.

[0051] In step S105, the analysis unit 35 analyzes the time-series change of the inspection values for the drugs prescribed there, with the day when the drug was prescribed (event related to treatment) as the starting date. Next, the analysis data providing server 30 executes the process of step S106.

[0052] In step S106, when the analysis result is obtained, the analysis unit 35 transmits the analysis result to the terminal device 40 that is the transmission source of the analysis request via the communication unit 31.

[0053] Next, I will explain the analysis request in more detail.

[0054] Figure 4 shows an example of extraction condition settings acquired by the analysis data provision server 30 according to this embodiment. The analysis request includes extraction condition settings. In the extraction condition settings, extraction conditions can be set for major categories such as patient, illness / injury, drug, examination, hospitalization / outpatient, surgery / procedure, and environment. For example, for the patient category, extraction conditions can be set for the patient's age, sex, height, BMI, etc. Furthermore, for the patient's age, extraction conditions can be set for age at the time of analysis, age at diagnosis, age at the start of drug prescription, age at examination, age at treatment-related events, etc.

[0055] Furthermore, it is possible to set extraction criteria for patients who have suffered from a specific illness or injury, used medication, undergone tests, or had surgery / procedures within any period from the date of diagnosis or the start of medication. Under these extraction criteria, for example, patients whose test value in test A was less than 10 within one month of the date of diagnosis of diabetes would be extracted.

[0056] In the "Illness / Injury" section, you can set extraction conditions related to illness / injury, such as the illness / injury, duration of illness, primary illness, presence or absence of co-existing conditions, type of co-existing condition, and duration of co-existing conditions. In the "Medication" section, you can set extraction conditions related to medication, such as the medication, dosage, duration of medication, primary medication, presence or absence of co-existing medications, type of co-existing medication, and duration of co-existing medications. In the "Examination" section, you can set extraction conditions related to examinations, such as examination item, examination name, examination value, unit of examination value, and range of examination value. In the "Inpatient / Outpatient" section, you can set extraction conditions related to inpatient / outpatient care, such as admission date, discharge date, and length of hospital stay. In the "Surgery / Procedure" section, you can set extraction conditions related to surgery or procedure, such as type of surgery or procedure, and date of surgery or procedure. In the "Environment" section, you can set extraction conditions related to the patient's environment, such as the patient's region and medical department.

[0057] The analysis data provision server 30 obtains the extraction condition settings from the terminal device 40, which are transmitted when the user of the terminal device 40 enters extraction conditions for at least one item and operates the apply button. The extraction condition settings may be common settings for multiple analysis groups, or they may be individual extraction condition settings for each analysis group.

[0058] Figure 5 shows an example of extraction conditions for each hierarchical level in the analysis data provision server 30 according to this embodiment. The extraction conditions for each hierarchical level are extraction conditions as sub-items. The extraction conditions for each hierarchical level are extraction conditions for further extracting information at the sub-item level based on the extraction conditions set as major items in the condition setting. The extraction conditions for each hierarchical level can be set in multiple hierarchical levels, for example, in 10 levels from hierarchical level 1 to hierarchical level 10. At hierarchical level 2, further extraction conditions can be added to the extraction conditions of hierarchical level 1. At hierarchical level 3, further extraction conditions can be added to the extraction conditions of hierarchical level 2. In other words, the number of extraction conditions can be set to increase as you go from hierarchical level 1 to hierarchical level 10. In this way, users of the terminal device 40 can set the extraction conditions while checking the number of patients to be extracted, so as to how high the extraction conditions should be set.

[0059] The number of patients extracted according to the extraction conditions for each hierarchical level is displayed as a preview for each level, allowing for verification. In the filtering condition settings, extraction conditions can be added or modified for each level. When the button for individual analysis is operated, the analysis unit 35 presents the user with the option to select whether to output in statistical analysis or outcome analysis format. Based on the selected output format, the analysis unit 35 begins the analysis.

[0060] Figure 6 shows an example of an output screen displaying the analysis results obtained when statistical analysis is performed on the analysis data provision server 30 according to this embodiment. In statistical analysis, it is possible to select which of four forms to output the results in: horizontal bar graph, vertical bar graph, pie chart, or table. In the example shown, a horizontal bar graph is selected as the output form. In addition, in the group setting item in the example shown, it is possible to set multiple analysis groups. On the output screen, for example, it is possible to switch to outputting a horizontal bar graph for the group corresponding to the analysis group by selecting any of the analysis groups, such as outputting a horizontal bar graph for group 1, which is the first analysis group, outputting a horizontal bar graph for group 2, which is the second analysis group, and outputting a horizontal bar graph for group 3, which is the third analysis group. On the output screen, it is possible to present the horizontal bar graphs in a comparable manner in response to the group switching operation by the user of the terminal device 40.

[0061] Each analysis group allows users to set conditions such as disease code, age, gender, and additional settings. The disease code is set to an International Classification of Diseases code (e.g., ICD-10) for each disease that the user wants to analyze, such as "C900 Multiple Myeloma".

[0062] Age is set by the user to specify the age range or a particular age for the patients they want to analyze. Gender is set by the user to specify the gender they want to analyze. Gender can be set to male, female, male and female, etc.

[0063] Additional settings allow users to configure the diseases and attribute conditions they wish to analyze. These additional settings can also include medications, and users can modify the conditions while reviewing the analysis results. These conditions (extraction criteria settings) for each analysis group, such as disease code, age, gender, and additional settings, are included in the analysis request and can be configured by the user.

[0064] The statistical analysis results shown are an example of an analysis output of the number of patients for each disease name, broken down by age in 5-year increments. Here, the unassigned items display selectable items according to the extraction criteria settings. The column and row items (display axes) and the aggregated items (analysis items) can be customized by dragging and dropping the options displayed in the unassigned items to display the analysis results graph.

[0065] The aggregation items include the number of patients with the disease, the number of drug prescriptions, the number of days the disease was present, the number of days drug combinations were used, the number of days hospitalized, laboratory values, and drug dosage. The analysis results can also be output in PDF, CSV, and Excel formats.

[0066] Figure 11 shows an example of an output screen displaying the results of a statistical analysis performed by the analysis data provision server 30 according to this embodiment, and showing the results of a group comparison analysis. In addition to or instead of the example shown in Figure 6, a target group may be set as shown in the example in Figure 11 to display the groups in a comparable manner. In the example shown in Figure 11, by setting "Target Group" in the row item or column item, for example, analysis group 1, analysis group 2, and analysis group 3 can be made comparable, and the legend, row item, or column item corresponding to the item set as the target group can be displayed in a comparable manner on a single graph, such as group 1, group 2, and group 3.

[0067] Figure 7 shows an example of an output screen displaying the analysis results obtained when outcome analysis (line graph) is performed on the analysis data provision server 30 according to this embodiment. In outcome analysis, the user can select which of the four forms to output as the analysis method: time series trend (line graph / scatter plot), period comparison (box plot), data distribution (scatter plot), and intergroup comparison (box plot). In the example shown, time series trend (line graph / scatter plot) is selected, and this is an example where time series trend (line graph) is selected as the output form. With time series trend (line graph), the time series trend can be visualized as a line graph or table. In the example shown, the selection of patient groups is an operator for selecting an analysis group set as shown in the group setting items in Figure 6, and it is possible to switch the analysis group for outcome analysis by selecting one of these operators. In addition, when selecting patient groups, it is possible to display the number of patients included in each analysis group. In outcome analysis, a baseline event (a treatment-related event) can be specified, and the changes in test values ​​over a predetermined period before and / or after the baseline event can be viewed in chronological order. For each analysis group, the test name can be selected from a pull-down menu based on master data such as JLAC10. Furthermore, for each analysis group, the aggregation method can be selected, such as median, mean, or maximum value. Analysis results can also be output in PDF, CSV, Excel, and other formats.

[0068] Figure 8 shows an example of an output screen displaying the analysis results obtained when outcome analysis (scatter plot) is performed on the analysis data provision server 30 according to this embodiment. Here, the setting of conditions for the patient group and the selection of the patient group are performed in the same manner as in Figures 6 and 7. The example shown is an example of the time series trend (scatter plot) of test values ​​in the time series trend (line / scatter plot) output format. In the legend items, the range of test values ​​for each legend can be set. On the output screen, for example, it is possible to set the range of test values ​​for each legend group corresponding to each legend G2, G3, G4, G5. In this way, the analysis data provision server 30 can visualize the distribution of test values ​​according to the severity. It can also be used for purposes such as evaluating the effectiveness of drugs, considering treatment interventions, and understanding trends for each patient group. Note that on the output screen, it is also possible to select whether to display or hide the scatter plot for each legend. In the time series trend (scatter plot), it is possible to visualize the time series trend in scatter plot or tabular format. The analysis results can also be output in PDF, CSV, Excel, and other formats.

[0069] Figure 9 shows an example of an output screen displaying the analysis results obtained when outcome analysis (box plot) is performed on the analysis data provision server 30 according to this embodiment. Here, the setting of conditions for the patient population and the selection of the patient population are performed in the same manner as in Figures 6 and 7. The example shown is an example of an inter-group comparison (box plot) of test values ​​in the output format of inter-group comparison (box plot). The grade on the horizontal axis, such as "Chronic Kidney Disease, Stage 1," can be set by referring to master data. The grade can also be set by setting a specific test item and creating a group based on the test value of that test item. In inter-group comparison (box plot), the test values ​​for each group according to the severity of the disease are visualized. In inter-group comparison (box plot), it is possible to select which aggregated value of the test values ​​to use as a representative value, such as the mean of the test values, population standard deviation, third quartile, second quartile (median), first quartile, or mode. In inter-group comparison (box plot), it is possible to visualize the test values ​​for each group in box plot or tabular format. The analysis results can also be output in PDF, CSV, or Excel format. Furthermore, the analysis data provision server 30 may use test items whose grade is determined by the test values ​​to visualize the related test values ​​for each severity group using box plots.

[0070] Next, we will describe the hardware configuration of the analysis data provision server 30.

[0071] Figure 10 is a hardware configuration diagram showing an example of the hardware configuration of the analysis data provision server 30 according to this embodiment. The analysis data provision server 30 is composed of a CPU 301, a drive unit 302, a storage medium 303, an input unit 304, an output unit 305, a ROM (Read Only Memory) 306, a RAM (Random Access Memory) 307, an auxiliary storage unit 308, and an interface unit 309.

[0072] The CPU 301, drive unit 302, input unit 304, output unit 305, ROM 306, RAM 307, auxiliary storage unit 308, and interface unit 309 are interconnected via a bus. The CPU 301 referred to here is a general term for a processor, and does not only refer to the device commonly known as a CPU in the narrow sense, but also includes, for example, a GPU and a DSP. Furthermore, the CPU 301 is not limited to being implemented by a single processor, but may be implemented by combining multiple processors of the same or different types.

[0073] The CPU 301 controls the analysis data provision server 30 by reading and executing programs stored in the auxiliary storage unit 308, ROM 306, and RAM 307, and by reading various data stored in the auxiliary storage unit 308, ROM 306, and RAM 307 and writing various data to the auxiliary storage unit 308 and RAM 307. The CPU 301 also reads various data stored in the storage medium 303 via the drive unit 302 and writes various data to the storage medium 303. The storage medium 303 is a portable storage medium such as a magneto-optical disk, flexible disk, or flash memory, and stores various data. The drive unit 302 is a device that reads and writes to the storage medium 303, such as an optical disk drive, flexible disk drive, or flash memory.

[0074] The input unit 304 consists of input devices such as a mouse, keyboard, touch panel, power button, setting button, and infrared receiver. The output unit 305 consists of output devices such as a display and speaker. The ROM 306 and RAM 307 store programs and various data for operating each function unit of the analysis data provision server 30.

[0075] The auxiliary storage unit 308 is a hard disk drive, flash memory, etc., and stores programs and various data for operating each functional unit of the analysis data provision server 30. The interface unit 309 has a communication interface and is connected to other devices in the network NW and the analysis data provision system SYS by wired or wireless connection.

[0076] For example, in the functional configuration of the analysis data provision server 30 in Figure 2, the communication unit 31 corresponds to the interface unit 309 in Figure 10, the input unit 37 in Figure 2 corresponds to the input unit 304 in Figure 10, the output unit 38 in Figure 2 corresponds to the output unit 305 in Figure 10, the control unit 36 ​​in Figure 2 corresponds to the CPU 301 in Figure 10, and the storage unit 32 in Figure 2 corresponds to the storage medium 303, ROM 306, RAM 307, and auxiliary storage unit 308 in Figure 10.

[0077] As described above, the information processing system (analysis data provision system SYS) according to this embodiment includes an anonymized data acquisition unit (medical information acquisition unit 33) that acquires anonymized electronic medical record data collected from multiple medical institutions, an extraction unit (analysis unit 35) that extracts multiple test values ​​from the electronic medical record data according to the extraction condition setting, and a visualization unit (output unit 38) that visualizes the multiple test values ​​in a comparable manner.

[0078] In this way, the information processing system (analysis data provision system SYS) can compare test values ​​before and after treatment-related events such as diagnosis and medication, and visualize the changes in test values ​​over time. Therefore, the information processing system (analysis data provision system SYS) can grasp the feasibility of individual-level research using anonymized processed information. Furthermore, the information processing system (analysis data provision system SYS) can define target patient groups and show the changes in test values ​​over time, using a treatment-related event (such as the day a drug was prescribed) as the starting date. In addition, since the information processing system (analysis data provision system SYS) can visualize the changes in test values ​​for individual drugs over time, it is also possible to confirm the effects of individual drugs. Therefore, the information processing system (analysis data provision system SYS) can grasp feasibility.

[0079] Although embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to those described above, and various design changes can be made without departing from the spirit of this invention.

[0080] For example, in this embodiment, the case in which the analysis unit 35 uses electronic medical record data as anonymized data has been described, but instead of or in addition to electronic medical record data, medical billing data may also be used as anonymized data. In this case, for example, the analysis unit 35 may identify treatment-related events such as medication, surgery, and procedures from the anonymized medical billing data and generate a treatment flowchart as a patient journey that allows the flow of treatment to be visualized. In this way, the flow of treatment events for the patient can be understood.

[0081] In this case, for example, the analysis unit 35 may identify the medical fees (points) related to the treatment of the target patient from the anonymized electronic medical claim data, and perform a medical fee analysis to visualize the relationship between the cost of treatment and the treatment effect (quality-adjusted lifetime (QALY)). In this way, it is possible to understand how much it costs to treat a patient. It is also possible to understand the cost-effectiveness of the treatment.

[0082] <Note 1> An information processing system comprising: an anonymized data acquisition unit that acquires anonymized electronic medical record data collected from multiple medical institutions; an extraction unit that extracts multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization unit that visualizes the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0083] <Note 2> The information processing system described in <Note 1>, wherein the extraction unit extracts multiple test values ​​for each group according to the multiple extraction condition settings, and the visualization unit visualizes the multiple test values ​​for each group in a comparable manner, and visualizes each group in a comparable manner.

[0084] <Note 3> The extraction condition setting is the information processing system described in <Note 1> which includes at least one of the following: region, medical department, disease, test, and prescribed drug.

[0085] <Note 4> The visualization unit visualizes at least one of the following: the number of cases for each disease, the number of days of illness for each disease, the number of patients according to age and sex, the number of days of hospitalization for each disease, the number of prescriptions for each disease, the amount of prescribed drugs, the distribution of test values ​​for each disease, and the trend of test values, as described in <Note 1>.

[0086] <Note 5> The information processing system described in <Note 2>, wherein each of the above groups is configured with different conditions from the other groups, including at least one of the following: disease, patient age, patient sex, and additional settings.

[0087] <Note 6> The visualization unit is an information processing system as described in <Note 2> that visualizes the standard treatment event, the periods before and after the treatment event, the test items of the test values, and the aggregation method based on the event settings for each group.

[0088] <Note 7> The information processing system described in <Note 2>, wherein a legend group based on the maximum and minimum values ​​of the test values ​​can be set for each group, and the visualization unit visualizes the legend group for each group in a comparable manner.

[0089] <Note 8> The visualization unit visualizes the test values ​​for each group according to the severity of the disease, as described in <Note 2>.

[0090] <Note 9> The visualization unit is the information processing system described in <Note 5> that visualizes the number of patients for each predetermined age range for multiple diseases.

[0091] <Note 10> The visualization unit is the information processing system described in <Note 6> which visualizes the time course of the test values ​​for each gender of the patient for a certain test item, before and after the event related to the treatment.

[0092] <Note 11> The visualization unit visualizes the distribution of test values ​​before and after the treatment-related event for a certain test item, for each legend group, as described in <Note 7>.

[0093] <Note 12> The visualization unit is the information processing system described in <Note 7> which visualizes the number of patients for each legend group in a way that allows comparison over a predetermined period.

[0094] <Note 13> An information processing device comprising: an anonymized data acquisition unit that acquires anonymized electronic medical record data collected from multiple medical institutions; an extraction unit that extracts multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization unit that visualizes the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0095] <Note 14> An information processing method performed by a computer of an information processing device, comprising: an anonymized data acquisition step of acquiring anonymized electronic medical record data collected from multiple medical institutions; an extraction step of extracting multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization step of visualizing the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0096] <Note 15> A non-temporary storage medium wherein the computer of the information processing device is made to perform an anonymized data acquisition step of acquiring anonymized electronic medical record data collected from multiple medical institutions, an extraction step of extracting multiple test values ​​from the electronic medical record data according to the extraction condition setting, and a visualization step of visualizing the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

[0097] A program operating in a device according to one aspect of the present invention may be a program that controls a Central Processing Unit (CPU) or the like to make the computer function in order to realize the functions of the above-described embodiment relating to one aspect of the present invention. The program or information handled by the program is temporarily loaded into volatile memory such as Random Access Memory (RAM) during processing, or stored in non-volatile memory such as flash memory or a Hard Disk Drive (HDD), and read, modified, and written by the CPU as needed.

[0098] Furthermore, a part of the apparatus in the above-described embodiment may be implemented using a computer. In that case, the program for implementing this control function may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read by the computer system and executed. The term "computer system" here refers to a computer system built into the apparatus, and includes hardware such as an operating system and peripheral devices. The "computer-readable recording medium" may be any of the following: a semiconductor recording medium, an optical recording medium, a magnetic recording medium, etc.

[0099] Furthermore, "computer-readable recording media" may include those that dynamically hold programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or communication lines such as telephone lines, as well as those that hold programs for a certain period of time, such as volatile memory inside a computer system that acts as a server or client in such cases. In addition, the above-mentioned program may be for the purpose of realizing some of the functions described above, and may also be a program that can realize the above-mentioned functions in combination with a program already recorded in the computer system.

[0100] Furthermore, each functional block or feature of the apparatus used in the embodiments described above may be implemented or executed by an electrical circuit, typically an integrated circuit or a combination of integrated circuits. An electrical circuit designed to perform the functions described herein may include a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or a combination thereof. The general-purpose processor may be a microprocessor, or alternatively, the processor may be a conventional processor, controller, microcontroller, or state machine. The general-purpose processor, or each of the aforementioned circuits, may consist of digital circuits or analog circuits. Also, if advances in semiconductor technology lead to the emergence of integrated circuit technologies that replace current integrated circuits, it may be possible to use integrated circuits based on such technologies.

[0101] While embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments, and design modifications and the like that do not depart from the gist of this invention are also included. Furthermore, the present invention can be modified in various ways within the scope of the claims, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of this invention. In addition, configurations in which elements described in the above embodiments that produce similar effects are substituted for each other are also included.

[0102] For example, this embodiment describes an example of using electronic medical record data, but it is also possible to use claims information or prescription information. When using claims information or prescription information, it is also possible to perform medical fee analysis, outcome analysis of treatment events, and comparative analysis of diseases and medications in electronic medical record data and claims information.

[0103] One aspect of the present invention can be used, for example, in information processing systems, information processing devices, information processing methods, and programs.

[0104] 10 Medical Institution Data Provision System 20 Processed Data Provision Server 30 Analysis Data Provision Server 31 Communication Unit 32 Storage Unit 33 Medical Information Acquisition Unit 34 Analysis Request Acquisition Unit 35 Analysis Unit 36 ​​Control Unit 37 Input Unit 38 Output Unit 301 CPU 302 Drive Unit 303 Storage Medium 304 Input Unit 305 Output Unit 306 ROM 307 RAM 308 Auxiliary Storage Unit 309 Interface Unit 40 Terminal Device NW Network SYS Analysis Data Provision System

Claims

1. An information processing system comprising: an anonymized data acquisition unit that acquires anonymized electronic medical record data collected from multiple medical institutions; an extraction unit that extracts multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization unit that visualizes the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, admission date, discharge date, and surgery date.

2. The information processing system according to claim 1, wherein the extraction unit extracts a plurality of test values ​​for each group according to a plurality of extraction condition settings, and the visualization unit visualizes the plurality of test values ​​for each group in a comparable manner and makes each group comparable.

3. The information processing system according to claim 1, wherein the extraction condition setting includes at least one of region, medical department, disease, test, and prescribed drug.

4. The information processing system according to claim 1, wherein the visualization unit visualizes at least one of the following: the number of cases for each disease, the number of days of illness for each disease, the number of patients according to age and sex, the number of days of hospitalization for each disease, the number of prescriptions for each disease, the amount of prescribed drugs administered, the distribution of test values ​​for each disease, and the trend of test values.

5. The information processing system according to claim 2, wherein each of the aforementioned groups is configured with different conditions from the other groups, including at least one of the following: disease, patient age, patient sex, and additional settings.

6. The information processing system according to claim 2, wherein the visualization unit visualizes a standard treatment event, the periods before and after the treatment event, the test items of the test values, and the aggregation method based on the event settings for each group.

7. The information processing system according to claim 2, wherein a legend group based on the maximum and minimum values ​​of the test values ​​can be set for each group, and the visualization unit visualizes the legend groups for each group in a comparable manner.

8. The information processing system according to claim 2, wherein the visualization unit visualizes the test values ​​for each group according to the severity of the disease.

9. The information processing system according to claim 5, wherein the visualization unit visualizes the number of patients for each predetermined age range for multiple diseases.

10. The information processing system according to claim 6, wherein the visualization unit visualizes the time-series changes in test values ​​for each patient's gender for a certain test item before and after the event related to the treatment.

11. The information processing system according to claim 7, wherein the visualization unit visualizes the distribution of test values ​​before and after the treatment-related event for a certain test item, for each legend group.

12. The information processing system according to claim 7, wherein the visualization unit visualizes the number of patients for each legend group in a comparative manner over predetermined periods.

13. An information processing device comprising: an anonymized data acquisition unit that acquires anonymized electronic medical record data collected from multiple medical institutions; an extraction unit that extracts multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization unit that visualizes the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

14. An information processing method performed by a computer of an information processing device, comprising: an anonymized data acquisition step of acquiring anonymized electronic medical record data collected from multiple medical institutions; an extraction step of extracting multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization step of visualizing the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

15. A program that causes a computer in an information processing device to perform the following steps: an anonymized data acquisition step of acquiring anonymized electronic medical record data collected from multiple medical institutions; an extraction step of extracting multiple test values ​​from the electronic medical record data according to extraction condition settings; and a visualization step of visualizing the multiple test values ​​in a comparable manner, wherein the multiple test values ​​are test values ​​before and after a treatment-related event, and the treatment-related event is at least one of the date of diagnosis, the date of admission, the date of discharge, and the date of surgery.

Images