JP6482965B2 - Data analysis system and data analysis method - Google Patents

Description

  The present invention relates to a data analysis system.

  In recent years, with the advancement of medical care and the progress of an aging society, the increase in medical expenses has become serious. Against this background, government agencies and hospitals require healthcare data analysis to improve medical quality and support cost optimization by utilizing medical data accumulated in medical institutions. It has been. Among these, a support system that automatically extracts disease candidates from examination results normalized by weighting according to disease names is being studied.

  As a background art of this technique, there is JP-A-2003-6329 (Patent Document 1). Patent Document 1 states that “after a patient test result is input from the test result input means, each test value is normalized by the test result normalizing means. Furthermore, each disease value is defined for each test value. The weight value is read from the weight value storage means, and the product sum value calculation means is multiplied by the weight value corresponding to each test value for each disease name, and the sum (product sum value) is calculated. The disease names are sorted in descending order and are displayed as disease candidates on the diagnosis support information display means ”(see summary).

JP 2003-6329 A

  In a medical institution, since medical data is stored for the purpose of daily medical care, there is a possibility that disease name information may not be properly registered. When such a disease name is not registered, there is a problem in that the actual medical condition of the patient and the patient information in the medical data are flawed, and the accuracy of the health care data analysis is lowered.

  In addition, a patient who develops a single disease and a patient who develops a plurality of diseases differ greatly in the pathology of the patient, and therefore the range of test results (for example, distribution of test values) is different. Furthermore, there are various combinations of diseases that develop, and the range to be taken for test results varies depending on the combination. For this reason, in the above-described conventional technology, there is a problem that an appropriate disease candidate cannot be presented in a patient who develops a plurality of diseases.

  An object of the present invention is to provide an information system that corrects omissions in the recording of disease names and supports the utilization of medical data by presenting new disease name candidates in patients who have developed multiple diseases. .

A typical example of the invention disclosed in the present application is as follows. That is, a data analysis system including a processor and a storage device connected to the processor, complication information that is a combination of disease names, and morbidity determination information that is a test value threshold value for determining morbidity Is stored in association with the patient information database and the patient information database in which the disease name information and test value information associated with the patient information are stored, and the processor is configured to store the complications diagnosed by the patient. A test information comparison unit that compares the disease determination information and the test value information based on information; and a disease name candidate analysis unit that selects a new disease name candidate of the patient based on a result of the comparison; , wherein the disease name candidate analyzer selects information complications including disease name are diagnosed by the patient, the examination information comparing unit, before Comparing the morbidity determination information of the selected complication and the test value information, the disease name candidate analysis unit, if the result of the comparison by the test information comparison unit indicates the morbidity of the selected complication When the selected complication is selected as a new disease name candidate of the patient and the result of the comparison by the examination information comparison unit does not indicate morbidity of the selected complication, the disease name diagnosed in the patient is selected. and the disease name of the difference between complications you select as the new name of the disease candidate for the patient.

  According to an aspect of the present invention, utilization of medical data can be supported. Problems, configurations, and effects other than those described above will become apparent from the description of the following embodiments.

It is a block diagram which shows the structure of the data utilization support system of the Example of this invention. It is a figure which shows the structural example of the patient information table of the Example of this invention. It is a figure which shows the structural example of the test | inspection information table of the Example of this invention. It is a figure which shows the structural example of the prescription information table of the Example of this invention. It is a figure which shows the structural example of the disease name symptom correspondence table of the Example of this invention. It is a figure which shows the structural example of the medicinal effect information table of the Example of this invention. It is a figure which shows the structural example of the determination information table of the Example of this invention. It is a figure which shows the structural example of the patient classification table of the Example of this invention. It is a figure which shows the structural example of the test | inspection information comparison result table of the Example of this invention. It is a figure which shows the structural example of the disease name candidate information table of the Example of this invention. It is a flowchart of the process which the data utilization support system of the Example of this invention performs. It is a flowchart of the complication information calculation process of the Example of this invention. It is a flowchart of the test | inspection information comparison process of the Example of this invention. It is a flowchart of the disease name candidate information calculation process of the Example of this invention. It is a flowchart of the disease name candidate information calculation process of the Example of this invention. It is a figure which shows the analysis result display screen of the Example of this invention. It is a figure which shows the setting screen of the minimum value of the number of patients of the Example of this invention. It is a figure which shows the disease determination test | inspection information setting screen of the Example of this invention.

  Embodiments of the present invention will be described below with reference to the drawings. In addition, the Example of this invention is not limited to the example mentioned later, A various deformation | transformation is possible in the range of the technical idea of the invention disclosed by the specification and drawing.

<Description of system configuration>
FIG. 1 is a block diagram illustrating a configuration of a data utilization support system 100 according to the embodiment of this invention.

  The data utilization support system 100 of this embodiment is a computer system that calculates complication information for each patient, analyzes disease name candidates based on the complication information, and visualizes and outputs the analysis results. Via the hospital information system 120 and the input / output terminal 130.

  The input / output terminal 130 includes a processor for executing a program, a memory for storing programs and data, an input device (not shown) (keyboard, mouse, touch panel, etc.), and an output device (display, printer, etc.) not shown. And a personal computer having a communication device (not shown) that communicates with the data utilization support system 100 or the like. The input / output terminal 130 is a PDA, PHS, mobile phone, smartphone, or tablet terminal having an input device such as a button or a touch panel, an output device such as a display, and a communication device that communicates with the data utilization support system 100 or the like. It may be a portable terminal.

  The input / output terminal 130 is installed in a medical institution (health care provider) such as a hospital or a clinic, and the data utilization support system 100 is installed in a data center.

  By installing the data utilization support system 100 in the data center, the user's personal information and privacy information such as data collected from the user can be centrally managed, so that information leakage can be prevented and security can be reliably managed. The data utilization support system 100 may be installed in a healthcare provider depending on the form of operation.

  The user (hereinafter referred to as “user”) of the input / output terminal 130 is a doctor, manager or manager of a medical institution. The user operates the input / output terminal 130, calculates the complication information of each patient using the data utilization support system 100, analyzes the disease name candidate information based on the calculated complication information, and displays the analysis result. Visualize.

  The data utilization support system 100 includes a control unit 101, an output unit 102, a memory 103, a communication unit 104, a display screen generation unit 105, a complication information calculation unit 107, a test information comparison unit 108, and disease name candidates that are connected to each other. An analysis unit 109, a determination database 110, an integrated database 111, a knowledge database 112, a comparative examination item setting unit 113, a disease determination value setting unit 115, a drug information determination unit 118, and an accumulated data acquisition unit 119 are included.

  The accumulated data acquisition unit 119 acquires the data accumulated in the patient information database 121, the examination information database 122, and the prescription information database 123 included in the hospital information system 120 installed in the healthcare provider, and stores the data in the integrated database 111. . The accumulated data acquisition unit 119 may be activated directly by the user or automatically at a time designated in advance by the user (for example, every Saturday night). Further, the accumulated data acquisition unit 119 may be activated when data accumulated in the patient information database 121, the examination information database 122, and the prescription information database 123 is updated.

  The control unit 101 includes, for example, a processor that executes a program stored in the memory 103, and controls each unit of the data utilization support system 100. The memory 103 is a storage device such as a DRAM (Dynamic Random Access Memory), for example, and stores data (for example, a program executed by the control unit 101) referred to by each unit of the data utilization support system 100.

  The determination database 110, the integrated database 111, and the knowledge database 112 may be stored in the memory 103, or a non-volatile storage device (for example, HDD (Hard Disk Drive) or SSD (Solid State Drive) in the data utilization support system 100. ), Not shown).

  The output unit 102 is a device that outputs a result of processing by the data utilization support system 100, and may be a display device or a printer, for example.

  The communication unit 104 is a network interface that is connected to the network 140 and communicates with the input / output terminal 130.

  The display screen generation unit 105, the complication information calculation unit 107, the examination information comparison unit 108, the disease name candidate analysis unit 109, the comparative examination item setting unit 113, and the morbidity determination value setting unit 115 realize the functions of the data utilization support system 100. Are processing units that execute processing for performing the processing, and each may be realized by dedicated hardware or may be realized by software. In the latter case, the processing executed by each processing unit in the following description is actually executed by the control unit 101 in accordance with an instruction described in a program stored in the memory 103. Details of the processing executed by each processing unit will be described later.

  The program executed by the control unit 101 is provided to the data utilization support system 100 via a removable medium (CD-ROM, flash memory, etc.) or a network, and is stored in a nonvolatile storage device that is a non-temporary storage medium. . For this reason, the data utilization support system 100 may have an interface for reading data from a removable medium.

  The display screen generation unit 105 generates data for displaying screens such as an analysis result display screen (FIG. 15), a setting screen for the minimum number of patients (FIG. 16), and a disease determination test information setting screen (FIG. 17). To do. In addition, the display screen generation unit 105 receives input and selection from the user. The complication information calculation unit 107 executes a complication information calculation process (FIG. 12) for calculating complication information corresponding to the target disease name. The inspection information comparison unit 108 executes inspection information comparison processing (FIG. 13) for comparing inspection items. The disease name candidate analysis unit 109 executes disease name candidate information calculation processing (FIG. 14) for calculating disease name candidate information.

  The comparative inspection item setting unit 113 receives the setting of the analysis target on the screen shown in FIG. The morbidity determination value setting unit 115 calculates morbidity determination test information of each test item corresponding to each complication information based on the data accumulated in the integrated database 111. Further, the morbidity determination value setting unit 115 calculates morbidity determination test information of each test item corresponding to each complication information based on the medical knowledge data accumulated in the knowledge database 112.

  The data utilization support system 100 is a computer system that is configured on a single computer or a plurality of computers that are logically or physically configured, and is a separate thread on the same computer. It may operate, and may operate on a virtual machine constructed on a plurality of physical computer resources.

  The patient information database 121, the examination information database 122, and the prescription information database 123 are stored in a nonvolatile storage device (for example, HDD (Hard Disk Drive) or SSD (Solid State Drive), not shown) in the hospital information system 120. Also good.

  The network 140 connects the data utilization support system 100, the hospital information system 120, and the input / output terminal 130. The data utilization support system 100 communicates with the hospital information system 120 and the input / output terminal 130 via the network 140. The network 140 may use wired communication using a LAN (Local Area Network) cable or wireless communication using a wireless LAN. The network 140 may use another wide area network such as the Internet, VPN, mobile phone communication network, and PHS communication network.

  Below, the structure of the table which comprises the integrated database 111 is demonstrated.

  The integrated database 111 includes a patient information table 200 that manages basic information for each patient, an examination information table 300 that stores examination information for each patient, and a prescription information table 400 that stores prescription information for each patient.

  FIG. 2 is a diagram illustrating a configuration example of the patient information table 200.

  The patient information table 200 includes a field 201 for storing a patient ID for identifying a patient, a field 202 for storing the gender of the patient, and a field for storing a hospitalization flag indicating hospital admission or outpatient data of a medical institution. 203, a field 204 for storing the date of outpatient diagnosis of the medical institution, a field 205 for storing the hospital institution's hospitalization date, a field 206 for storing the discharge date of the medical institution, and a disease name are stored. Fields 207, 208 and 209. The patient information table 200 may include a field that stores four or more disease names.

  If the value in the hospitalization flag field 203 is “1”, this indicates that the data is hospitalization data. The diagnosis date field 204 is “0”, the hospitalization date field 205 and the discharge date field 206. Stores the date. On the other hand, if the value of the hospitalization flag field 203 is “0”, this indicates that the data is outpatient data, and the diagnosis date field 204 includes the diagnosis date of outpatient, the date of hospitalization field 205 and the date of discharge. The field 206 stores “0”.

  Information relating to one hospitalization or one diagnosis of one patient is stored in each record (patient information record) of the patient information table 200. One patient's one hospitalization or one outpatient diagnosis corresponds to one record. For example, in the patient information record 200A, a case identified by the patient ID “# 1” has a gender “male”, a hospitalization flag “1”, a diagnosis date “0”, and a hospitalization date “2014 / 04/01 ”, discharge date is“ 2014/04/26 ”, disease name 1 is“ disease name A ”, disease name 2 is“ disease name B ”, and disease name 3 indicates that no information is registered. “NULL”. That is, the male patient identified by the patient ID “# 1” is hospitalized from April 1, 2014 to April 26, 2014 for disease name A and disease name B.

  FIG. 3 is a diagram illustrating a configuration example of the inspection information table 300.

  The examination information table 300 includes a field 301 for storing a patient ID, a field 302 for storing information for identifying examination items, a field 303 for storing examination dates, and a field 304 for storing examination results (examination values). Including. The inspection information table 300 may include information indicating other types of inspection results such as image inspection (for example, CT image inspection). Furthermore, information regarding the patient's subjective symptoms such as “nausea” or “vomiting” may be included.

  For example, in the example of the examination information table 300 illustrated in FIG. 3, in the patient with the patient ID “# 1”, the value of “examination item X” is “41”, “2014/04 /” in “2014/04/1”. 7 ”is“ 62 ”,“ 2014/04/13 ”is“ 180 ”,“ 2014/04/15 ”is“ 220 ”,“ 2014/04/18 ”is“ 196 ”,“ 2014/04/25 ” Is recorded as “120”. Further, the inspection information table 300 records that the value of “inspection item Y” was “38” in “2014/04/1”.

  FIG. 4 is a diagram illustrating a configuration example of the prescription information table 400.

  The prescription information table 400 includes a field 401 for storing a patient ID, a field 402 for storing information (medicine name) for identifying a drug, a field 403 for storing a prescription start date for each drug, and a prescription end date for each drug. Field 404 for storing. The prescription information table 400 may have a field for storing prescription usage / dose of each drug.

  For example, in the example of the prescription information table 400 illustrated in FIG. 4, in the patient with the patient ID “# 1”, “drug A” ranges from “2014/04/01” to “2014/04/07”. 04/08 ”to“ 2014/04/14 ”,“ Drug B ”is prescribed from“ 2014/04/03 ”to“ 2014/04/8 ”, and“ Drug D ”is“ 2014/04 / 16 ”to“ 2014/04/20 ”and“ Drug T ”is recorded from“ 2014/04/14 ”to“ 2014/04/18 ”.

  Below, the structure of the table which comprises the knowledge database 112 is demonstrated.

  The knowledge database 112 includes a disease name / symptom correspondence table 500 for managing a disease name and a symptom corresponding to the disease name, and a medicinal effect information table 600 for managing a drug and a disease corresponding to the drug. The knowledge database 112 stores medical knowledge data. The medical knowledge data is, for example, medical literature, treatment guidelines established for each country or medical institution, and may include information on morbidity determination values.

  FIG. 5 is a diagram showing a configuration example of the disease name / symptom correspondence table 500.

  The disease name / symptom correspondence table 500 includes a field 501 for storing information on a disease name and a field 502 for storing information on a symptom corresponding to a disease name. The disease name symptom correspondence table 500 may include information on other types of examination results such as an image examination (for example, occurrence of a tumor or increase in tumor size determined by CT examination), and further includes “nausea” or “ Information about the patient's subjective symptoms such as “vomiting” may be included.

  For example, in the example of the disease name / symptom correspondence table 500 shown in FIG. 5, “increase in examination item W” is registered as a symptom corresponding to “disease name A”, and “symptom of examination item V” is associated with a symptom corresponding to “disease name B”. "Increase" is registered, "Increase in test item X" and "Increase in test item Y" are registered as symptoms corresponding to "Disease name C", and "Increase in test item X" as symptoms corresponding to "Disease name G" Is recorded.

  In this manner, patients with symptoms that are not caused by the disease name affected can be selected based on the information on the symptoms corresponding to the disease names, and the accuracy of analysis of disease name candidates can be improved.

  FIG. 6 is a diagram illustrating a configuration example of the medicinal effect information table 600.

  The medicinal effect information table 600 includes a field 601 for storing a drug name and a field 602 for storing a disease corresponding to the drug name. The medicinal effect information table 600 may include a corresponding test item such as “improvement of test item A” and information related to the patient's subjective symptoms such as “nausea” or “vomiting”.

  For example, in the example of the medicinal effect information table 600 shown in FIG. 6, the disease corresponding to the drug identified by “drug A” is “disease name A”, and the disease corresponding to the drug identified by “drug B” is The disease corresponding to the drug identified by “disease name G” and “drug C” is “disease name C”, and the disease corresponding to the drug identified by “drug T” is “disease name B”. It is recorded.

  Below, the structure of the table which comprises the determination database 110 is demonstrated.

  The determination database 110 stores a determination information table 700 that stores morbidity determination test information defined for each complication, and patient classification information based on the complication information of each patient calculated by the complication information calculation unit 107. The patient classification table 800, the examination information comparison result table 900 for storing the comparison result information of the examination information of each patient calculated by the examination information comparison unit 108, and the information of the disease name candidates calculated by the disease name candidate analysis unit 109 are stored. And a disease name candidate information table 1000.

  FIG. 7 is a diagram illustrating a configuration example of the determination information table 700.

  The determination information table 700 includes a field 701 for storing complication information, a field 702 for storing a test item name used for determining the morbidity of the merger place information, and a field for storing morbidity determination test information corresponding to the test field 702. 703.

  For example, in the determination information table 700 illustrated in FIG. 7, the test items used for determining the morbidity of the complication “disease name A: disease name B” are “test item X” and “test item Y”, and “test item X”. The disease determination range of “25-90” and the disease determination range of “test item Y” is “23-80”, and the disease determination of the complication “disease name A: disease name B: disease name C” The test item to be used is “test item X”, and it is recorded that the range of morbidity determination is “165-250”.

  In this way, by recording the test items used for morbidity determination and the morbidity determination information of each test item for each complication information, select different test values for each complication patient and patients who are out of their possible range This can improve the accuracy of analysis of disease name candidates.

  FIG. 8 is a diagram illustrating a configuration example of the patient classification table 800.

  The patient classification table 800 includes a field 801 that stores complication information that is a combination of disease names, a field 802 that stores a patient ID that identifies a patient, and a field 803 that stores information on a period in which the complication falls. .

  For example, in the example of the patient classification table 800 illustrated in FIG. 8, the patients whose patient IDs are “# 1” and “# 10” have developed the complication “disease name A: disease name B”, and the patient ID is “#”. The corresponding period of the patient with “1” is “2014/04/01 to 2014/04/26”, and the corresponding period of the patient with the patient ID “# 10” is “2014/10/21 to 2014/11/03”. The patient whose patient ID is “# 2” has developed the complication “disease name C: disease name D: disease name E”, the corresponding period is “2015/03 / 31-”, and the patient ID is “ The patient of # 29 has a complication "Disease name A: Disease name B: Disease name C", and the corresponding period is recorded as "2014/08/12 to 2014/08/31".

  FIG. 9 is a diagram illustrating a configuration example of the inspection information comparison result table 900.

  The examination information comparison result table 900 includes a field 901 for storing complication information that is a combination of disease names, a field 902 for storing a patient ID for identifying a patient, a field 903 for storing an examination item name, and comparison of examination items. And a field 904 for storing the result.

  If the value of the comparison result field 904 is “1”, it means that the test item of the patient is out of the morbidity determination range in the complication (that is, the test value is out of the normal range for a certain complication). Show. On the other hand, if the comparison result is “0”, it indicates that the examination item of the patient is within the disease determination range in the complication.

  For example, in the example of the examination information comparison result table 900 illustrated in FIG. 9, the comparison result of “examination item X” of the patient “# 1” who develops a complication of “disease name A: disease name B” is “1”. The comparison result of “examination item Y” of the patient with the patient ID “# 1” is “1”, and the patient ID with the complication “disease name A: disease name B” is “# 8”. It is recorded that the comparison result of “inspection item X” of the patient is “0”. That is, “examination item X” and “examination item Y” of the patient whose patient ID is “# 1” are outside the range of the examination value of the morbidity determination of the complication “disease name A: disease name B” and suffer from another disease. It may indicate that

  FIG. 10 is a diagram illustrating a configuration example of the disease name candidate information table 1000.

The disease name candidate information table 1000 includes a field 1001 for storing a patient ID for identifying a patient, a field 1002 for storing complication information that is a combination of disease names, a field 1003 for storing patient name candidate information, and disease name candidate information. And fields 1004 and 1005 for storing information on the corresponding decision items, and a field 1006 for storing information on related drugs used for extraction of disease name candidates. It should be noted that, if there is no information to be stored in the decision item of the second after, it is sufficient to store the "NULL" to determine the item field 1005. The disease name candidate information table 1000 may include three or more determination item fields.

  For example, in the disease name candidate information table 1000 shown in FIG. 10, the patient whose patient ID is “# 1” has developed the complication “disease name A: disease name B”, but the disease name candidates are “disease name C” and “disease name G”. The determination items corresponding to the disease name candidate “disease name C” are “test item X” and “test item Y”, the related drug used for selecting the disease name candidate is “drug C”, and the disease name candidate “ The determination item corresponding to “Disease name G” is “Test item X”, and it is recorded that there is no related drug used for selecting the disease name candidate.

  In this way, by recording the disease name candidate information and the determination items in association with each other, it is possible to easily grasp which test item the disease name candidate has been determined. Further, by associating a plurality of determination items with the disease name candidate information, it is possible to select a disease name candidate using the plurality of determination items, and to improve the accuracy of analysis of the disease name candidates. In addition, by associating and recording information on a drug used for extraction of a disease name candidate, it is possible to select or exclude a disease name candidate for which the drug is prescribed, thereby improving the accuracy of analysis of the disease name candidate. In addition, it is possible to perform processing such as using the difference between the pre-prescription and post-prescription prescriptions of the drug, which is subject to analysis, such as the pre-prescription, post-prescription, and pre-prescription test values. It can assist in the determination of disease name candidates.

  Next, processing executed by the data utilization support system 100 will be described using a flowchart.

  FIG. 11 is a flowchart of processing executed by the data utilization support system 100 according to the embodiment of this invention.

  First, the control unit 101 reads out case data from the integrated database 111 and stores it in the memory 103 (S1101). In the following description, data relating to a patient, for example, information for identifying a patient, information on prescription drugs corresponding to the patient, information on test results corresponding to the patient, and the like are collectively referred to as patient data. The control unit 101 may read all patient data stored in the integrated database 111 and store the data in the memory 103.

  Next, the control unit 101 reads knowledge data from the knowledge database 112 and stores it in the memory 103 (S1102). The control unit 101 may read all data stored in the knowledge database 112 and store it in the memory 103.

  Next, the control unit 101 reads the determination information data from the determination database 110 and stores it in the memory 103 (S1103). The control unit 101 may read all data stored in the determination database 110 and store it in the memory 103.

  Next, the control unit 101 activates the display screen generation unit 105. The display screen generation unit 105 displays a screen for selecting a combination of disease names of complication information to be analyzed, disease name candidate information, the number of examination items used for calculating disease name candidate information, and the like to the user. Are generated and output to the input / output terminal 130. In addition, the control unit 101 activates the comparative inspection item setting unit 113. The comparative inspection item setting unit 113 receives the setting of the analysis target setting area 1520 on the screen shown in FIG. 15 (S1104). The screen generated by the display screen generation unit 105 in step S1104 and displayed by the input / output terminal 130 includes the analysis target setting area 1520 on the left side of the screen shown in FIG. 15, and does not include the right area.

  Hereinafter, a combination of disease names in the complication information selected in step S1104 may be described as a target disease name, complication information as a target complication, and disease name candidate information as a target disease name candidate.

  FIG. 15 shows an analysis of the combination of disease names of complication information to be analyzed by the input / output terminal 130 according to the embodiment of the present invention, disease name candidate information, and the number of examination items used for calculation of disease name candidate information. It is a figure which shows the analysis result display screen 1500 displayed on the input / output terminal 130 when selecting an option.

  The screen 1500 includes an analysis target setting area 1520, an analysis result list display area 1507, a distribution reference button 1508, a selected disease name assignment button 1509, a distribution comparison display area 1510, and an examination item setting field 1511. The analysis target setting area 1520 includes an analysis target disease name selection column 1501, an analysis target disease name candidate selection column 1502, an analysis target test item selection column 1503, an analysis option selection column 1504, and a “minimum number of patients” A button 1505A for changing “setting”, a button 1505B for changing “setting of disease determination test information”, and an “execute analysis” button 1506 are included.

  Note that the screen displayed in step S1104 includes only the analysis target setting area 1520, and the analysis result is not displayed. On the other hand, the screen displayed in step S1109 includes all of the screens shown in FIG.

  The user operates a check box in the disease name selection column 1501 to be analyzed, and selects a combination of disease names, that is, a complication to be analyzed. The user operates the check box in the disease name candidate selection column 1502 to be analyzed, and selects a disease name candidate to be analyzed. The user operates the check box in the analysis target inspection item selection field 1503 to select the analysis target inspection item. The user operates a check box in the analysis option selection field 1504 to select an analysis option to be used for analysis. Analysis options include using multiple test items to make decisions, using the minimum number of patients limit, and using drug information.

  When “Use multiple examination items for judgment” is checked, disease name candidates are analyzed using the selected number of examination items. In addition, when “Use minimum number of patients limit” is checked, the number of combinations of disease names and the minimum number of patients set for each complication are considered on the setting screen 1600 for the minimum number of patients (FIG. 16). And analyze disease name candidates. Further, when “use drug information” is checked, a complication is analyzed with reference to the related drug information field 1006 of the disease name candidate information table 1000.

  When the user operates the “setting the minimum number of patients” change button 1505A, the display screen generation unit 105 generates data for displaying the setting screen 1600 (FIG. 16) for the minimum number of patients, and inputs and outputs Output to the terminal 130.

  On the other hand, when the user operates the “setting of disease determination test information” change button 1505B, the display screen generation unit 105 generates data for displaying the disease determination test information setting screen 1700 (FIG. 17), and the input / output terminal 130. Output to.

  When the user operates the analysis execution button 1506, the control unit 101 activates the complication information calculation unit 107, the test information comparison unit 108, the disease name candidate analysis unit 109, and the drug information determination unit 118 as necessary, and merges them. Symptom information calculation processing (S1105 in FIG. 11, FIG. 12) is executed.

  In the analysis result list display area 1507, for example, the analysis result of the patient with the patient ID “# 1” is displayed. The patient with the patient ID “# 1” has been diagnosed as having developed the complication “sick name A: sick name B”, and the sick name candidates of this patient are “sick name C” and “sick name G”. It is displayed that the judgment item of “disease name C” is “examination item X” and “examination item Y”, and the related medicine is “prescription of medicine C”. Further, it is displayed that the judgment item of the disease name candidate “disease name G” is “examination item X”.

  Here, when the user selects an arbitrary disease name candidate in the analysis result list display area 1507 and operates the “reference distribution” button 1508, the distribution comparison display area 1510 corresponds to the complication information diagnosed by the patient. The distribution of the morbidity determination criteria and patient group test items, and the morbidity determination criteria and patient group test item distributions corresponding to the complication information consisting of the disease and disease name candidates diagnosed in the patient are displayed. Furthermore, the user can select the inspection item displayed in the distribution comparison display area 1510 by operating the inspection item setting field 1511.

  In addition, when it is determined that the disease name candidate selected by the user should be given to the selected patient, when the “give selected disease name” button 1509 is operated, the disease name candidates are assigned to any of the disease names 207 to 209 in the patient information table 200. (Specifically, “disease name C” is recorded in the disease name 209), and the selected disease name candidate is given as the patient's disease name.

  In this way, by narrowing down disease name candidates from a plurality of determination items, it is possible to support the determination of disease name candidates to be given to selected patients.

  Furthermore, when using information on drug prescription, it is possible to assist in determining a more appropriate disease name candidate by presenting information on whether or not a drug related to the disease name candidate is prescribed.

  FIG. 16 is a diagram showing a setting screen 1600 for the minimum number of patients according to the embodiment of the present invention.

  The setting screen 1600 for the minimum number of patients includes a basic setting area 1601, an individual setting area 1602, a save button 1603, and a cancel button 1604.

  The user can change the minimum number of patients corresponding to each number of disease name combinations by operating the up / down button 16011 for the minimum number of patients in the number of disease name combinations in the basic setting area 1601, and the minimum number of patients to be set can be changed to the basic setting area 1601. You can enter directly.

  The user can change the minimum number of patients corresponding to each complication by operating the up / down button 16021 for the minimum number of complications in the individual setting area 1602, and directly input the minimum number of patients to be set in the individual setting area 1602 it can.

  The user operates the “save” button 1603 to save the changed minimum number of patients, ends the setting screen 1600 for the minimum value of the number of patients, and returns to the analysis result display screen 1500. Further, the user operates the “Cancel” button 1604 to end the setting screen 1600 for the minimum value of the number of patients without saving the minimum number of patients, and return to the analysis result display screen 1500.

  Thus, by determining the minimum value of the number of patients, complication information with a small number of patients can be excluded from analysis, and the number of combinations of complication information can be prevented from becoming too large. Moreover, you may suppress that the number of combinations of complication information increases too much by determining the upper limit of the number of complication information.

  FIG. 17 is a diagram showing a disease determination test information setting screen 1700 according to the embodiment of this invention.

  The disease determination test information setting screen 1700 includes a disease determination test information change area 1701, an “automatic setting using stored data” button 1702, an “automatic setting using medical knowledge” button 1703, a “save” button 1704, , “Cancel” button 1705.

The user changes the lower limit value of the disease determination test information corresponding to each test item of each complication information by operating the up / down button 17011 of the lower limit value of the disease determination test information in the disease determination test information change area 1701. Further, by operating an up / down button 17012 of the upper limit value of the morbidity determination test information, the upper limit value of the morbidity determination test information corresponding to each test item of each complication information is changed. The user can directly input the disease determination test information to be set in the upper limit / lower limit value column of the disease determination test information change area 1701.

  Thus, by defining the disease determination test information for each test item for each complication information, a new disease name candidate can be appropriately selected even for a patient who has developed a plurality of diseases.

  When the user operates the “automatic setting using accumulated data” button 1702, the morbidity determination value setting unit 115 is activated, and based on the data accumulated in the integrated database 111, each examination item corresponding to each complication information is displayed. The disease determination test information is calculated, and the lower limit value and the upper limit value of the disease determination test information in the disease determination test information change area 1701 are changed using the calculation result. For example, patients recorded in the integrated database 111 are classified according to complication information, and the standard deviation, 99% confidence interval, 95% confidence interval, average value, and median value of each test item in the patient group classified according to complication information Based on a statistical value such as a mode value, morbidity determination test information can be calculated. Note that the statistical values used for calculating the disease determination test information are not limited to those described above, and other statistical values may be used.

  Note that the disease determination test information may be calculated using only specific test values. For example, by using a test value that is close to the diagnosis date, a test value that correctly represents the disease state can be selectively used, and the accuracy of analysis of disease name candidates can be improved.

  Further, when “use drug information” in the analysis option selection field 1504 is checked, the disease determination test information may be calculated only for a specific test value related to the drug effect. For example, only for pre-prescription test values of related drugs, only for post-prescription test values, comparing test values before and after prescription, or only for test values on the outpatient diagnosis date And so on. By calculating the disease determination test information only for test values that satisfy specific conditions in this way, test values that correctly represent the disease state can be selectively used, improving the accuracy of analysis of disease name candidates. it can.

  Further, when the user operates the “automatic setting using medical knowledge” button 1703, the disease determination value setting unit 115 is activated and corresponds to each complication information based on the medical knowledge data stored in the knowledge database 112. The disease determination test information for each test item is calculated, and the lower limit value and the upper limit value of the disease determination test information in the disease determination test information change area 1701 are changed using the calculation result. For example, the medical knowledge data may use information on morbidity determination values described in literatures and guidelines, or information on morbidity determination values determined for each country or medical institution.

  The user operates the “automatic setting using medical knowledge” button 1703 to automatically set the lower limit value and the upper limit value of the disease determination test information, and then operates the up / down buttons 17011 and 17012 to detect the disease. The lower limit value and upper limit value of the judgment inspection information may be finely adjusted.

  In addition, the user operates the “save” button 1704 to save the lower limit value and upper limit value of the changed morbidity determination test information, ends the morbidity determination test information setting screen 1700, and displays the analysis result display screen 1500. Return. In addition, the user operates the “Cancel” button 1705 to end the disease determination test information setting screen 1700 without saving the lower limit value and the upper limit value of the disease determination test information, and return to the analysis result display screen 1500. .

  Returning to FIG. 11, the description will be continued. When the user operates the analysis execution button 1506 on the screen 1500, the control unit 101 activates the complication information calculation unit 107, the test information comparison unit 108, the disease name candidate analysis unit 109, and the drug information determination unit 118 as necessary. The drug information determination unit 118 is activated when “use drug information” is selected in the analysis option selection field 1504 (FIG. 15). The complication information calculation unit 107 executes a complication information calculation process for calculating complication information corresponding to the target disease name selected in step S1104 from the data of the integrated database 111 stored in the memory 103 (S1105). Details of the complication information calculation process will be described later with reference to FIG.

  Next, the control unit 101 activates the examination information comparison unit 108 and executes examination information comparison processing for comparing examination items for the patient whose complication information is calculated in step S1105 (S1106). Details of the inspection information comparison process will be described later with reference to FIG.

  Next, the control unit 101 activates the disease name candidate analysis unit 109, and executes disease name candidate information calculation processing for calculating disease name candidate information for the patient whose test information and morbidity determination test information are compared in step S1106 (S1107). ). Details of the disease name candidate information calculation process will be described later with reference to FIG.

  Next, the control unit 101 activates the display screen generation unit 105. The display screen generation unit 105 generates data for displaying the analysis result display screen (FIG. 15) for displaying the result of the analysis processing based on the disease name candidate information calculated in step S1107 (S1108). The data is output to the output terminal 130 (S1109).

  FIG. 12 is a flowchart of the complication information calculation process according to the embodiment of the present invention.

  First, the complication information calculation unit 107 reads all the data stored in the patient information table 200 and stores it in the memory 103 (S1201).

  Next, the complication information calculation unit 107 determines whether the processing has been completed for all patient IDs recorded in the patient information table 200 (S1202). If the process is completed for all patient IDs, the complication information calculation process is terminated. On the other hand, if the process has not been completed for some patient IDs, the process proceeds to step S1203.

  Next, the complication information calculation unit 107 determines whether a disease name is selected in the disease name selection column 1501 to be analyzed (S1203). If a disease name is selected in the disease name selection column 1501 to be analyzed, the complication information calculation unit 107 selects a patient in which the disease name selected in the disease name selection column 1501 to be analyzed is stored in the disease name field (S1204). ). On the other hand, if a disease name is not selected in the disease name selection column 1501 to be analyzed, the process proceeds to step S1205.

  Next, the complication information calculation unit 107 acquires all disease names and corresponding periods stored in the disease name fields 207 to 209 of the patient information table 200, and calculates complication information that is a combination of disease names (S1205). . For example, when “disease name A” is stored in the disease name 1 field and “disease name B” is stored in the disease name 2 field, the complication information is “disease name A: disease name B”. Further, the relevant period of each complication may be a period from the hospitalization date 205 to the discharge date 206, or may be from the first diagnosis date to the last diagnosis date.

  Next, the complication information calculation unit 107 registers the complication information 801, the patient ID 802, and the corresponding period 803 in the patient classification table 800 in association with each other (S1206).

  FIG. 13 is a flowchart of the inspection information comparison process according to the embodiment of the present invention.

  First, the examination information comparison unit 108 reads all the data stored in the patient classification table 800 created in step S1206 and stores it in the memory 103 (S1301).

  Next, the inspection information comparison unit 108 reads all the data stored in the determination information table 700 and stores it in the memory 103 (S1302).

  Next, the examination information comparison unit 108 determines whether processing has been completed for all complication information recorded in the patient classification table 800 (S1303). If the processing is completed for all complication information, the examination information comparison processing is ended. On the other hand, if the processing has not been completed for some complication information, the process proceeds to step S1304.

  Next, the examination information comparison unit 108 determines whether the processing has been completed for all patient IDs corresponding to the complication information to be processed (S1304). If the process has been completed for all patient IDs, the process returns to step S1303 to execute the process for the next complication information. On the other hand, if the processing has not been completed for some patient IDs, the process proceeds to step S1305.

  Next, the examination information comparison unit 108 selects an examination item corresponding to the patient ID to be processed from the examination information table 300 and stores it in the memory 103 (S1305). At this time, all the examination items corresponding to the patient ID may be read, or only the examination items performed within the corresponding period corresponding to the complication information and the patient ID of the patient classification table 800 may be read.

  Next, the inspection information comparison unit 108 determines whether the processing has been completed for all inspection items (S1306). If the process has been completed for all examination items, the process returns to step S1304 to execute the process for the next patient ID. On the other hand, if the processing has not been completed for some of the inspection items, the process proceeds to step S1307.

  Next, the examination information comparison unit 108 reads out from the judgment information table 700 morbidity determination examination information corresponding to the examination item to be processed with the patient ID to be processed as complication information to be processed (S1307).

  Next, the inspection information comparison unit 108 registers 0 as an initial value in the comparison result (S1308). The initial value of the comparison result may be a value other than 0, such as a NULL value.

  Next, the examination information comparison unit 108 determines whether the examination value of the examination item to be processed is outside the range of the morbidity determination examination information acquired in step S1307 (S1309). When at least one test value of the test item to be processed is outside the range of the disease determination test information, the comparison result is set to 1 (S1310). On the other hand, when all the test values of the test items to be processed are within the range of the disease determination test information, the process proceeds to step S1311.

  Only specific test values may be compared with the disease determination test information. For example, by using a test value that is close to the diagnosis date, a test value that correctly represents the disease state can be selectively used, and the accuracy of analysis of disease name candidates can be improved.

  Further, when “use drug information” in the analysis option selection field 1504 is checked, only a specific test value related to the drug effect may be compared with the disease determination test information. For example, only the test values before prescription of the related drugs are compared, only the test values after prescription are compared, or only the test values on the outpatient diagnosis date are compared. In this way, by comparing only test values that satisfy a specific condition with the disease determination test information, test values that correctly represent the disease state can be selectively used, and the accuracy of analysis of disease name candidates can be improved.

  In addition, even if the comparison result is set to 1 when the predetermined number of test values are outside the range of the disease determination test information, the processing in steps S1309 and S1310 is outside the range of the disease determination test information. Even if the comparison result is set to 1, the comparison result may be set to 1 when all the test values are out of the range of the morbidity determination test information, and various statistical processing is performed. The value may be compared with morbidity test information. As described above, the determination logic in step S1309 may be arbitrarily selected by the user.

  Next, the examination information comparison unit 108 associates the complication information 901, the patient ID 902, the examination item 903, and the set comparison result 904 and registers them in the examination information comparison result table 900 (S1311).

  Thus, in the examination information comparison process, since it is determined whether the examination value is out of the range that can be taken by complications using the morbidity determination examination information of each examination item corresponding to the complication information, it is currently diagnosed. The likelihood of complications can be determined.

  14A and 14B are flowcharts of disease name candidate information calculation processing according to the embodiment of this invention.

  First, the disease name candidate analysis unit 109 obtains all data stored in the examination information comparison result table 900, all data stored in the determination information table 700, and all data stored in the disease name symptom correspondence table 500. Read and store in the memory 103 (S1401).

  Next, the disease name candidate analysis unit 109 determines whether the processing has been completed for all complication information recorded in the examination information comparison result table 900 (S1402). If the processing is completed for all complication information, the disease name candidate information calculation processing is ended. On the other hand, if the processing has not been completed for some complication information, the process proceeds to step S1403.

  Next, the disease name candidate analysis unit 109 determines whether the processing has been completed for all patient IDs corresponding to the complication information to be processed (S1403). If the process has been completed for all the patient IDs, the process returns to step S1402 to execute the process for the next complication information. On the other hand, if the process has not been completed for some patient IDs, the process proceeds to step S1404.

  Next, the disease name candidate analysis unit 109 selects, from the examination information comparison result table 900, examination items in which 1 is registered in the comparison result among the examination items corresponding to the patient ID to be processed (S1404).

  Next, the disease name candidate analysis unit 109 determines whether the processing has been completed for all examination items (S1405). If the process has been completed for all examination items, the process returns to step S1403 to execute the process for the next patient ID. On the other hand, if the processing has not been completed for some inspection items, the process proceeds to step S1406.

  Next, the disease name candidate analysis unit 109 selects complication information including complication information diagnosed in the patient to be processed (S1406). The included complication information is complication information that includes all of the disease names that constitute the complication information being diagnosed and also includes other disease names. For example, when the complication information of the selected patient is “disease name A: disease name B”, “disease name A: disease name B: disease name C” or “disease name A: disease name” which is complication information including disease name A and disease name B “B: Disease name G” or the like is selected.

  Next, the disease name candidate analysis unit 109 selects the complication information in which the correspondence between the disease name added in the complication information selected in step S1406 and the examination item to be processed is recorded in the disease name symptom correspondence table 500 ( S1407).

  Next, the disease name candidate analysis unit 109 determines whether the processing has been completed for all the complication information selected in step S1406 (S1408). If processing has been completed for all complication information, the process returns to step S1405 to execute processing for the next examination item. On the other hand, if the processing has not been completed for some complication information, the process proceeds to step S1409.

  Next, the disease name candidate analysis unit 109 determines whether the test value of the test item to be processed is within the range of the morbidity determination test information acquired in step S1401 (S1409). If at least one test value of the test item to be processed is within the range of the disease determination test information, it is determined whether the number of test items is satisfied (S1410). On the other hand, when all the test values of the test items to be processed are out of the range of the disease determination test information, the process returns to step S1408, and the process is executed for all the complication information.

  Note that the processing in step S1409 proceeds to step S1410 when the predetermined number of test values are within the range of the disease determination test information, but proceeds to step S1410 when the predetermined percentage of test values are within the range of the disease determination test information. However, if all the test values are within the range of the disease determination test information, the process may proceed to step S1410, and the test values subjected to various statistical processes may be compared with the disease determination test information. As described above, the determination logic in step S1409 may be arbitrarily selected by the user.

  Next, the disease name candidate analysis unit 109 selects complication information that satisfies the number of examination items (S1410). That is, if “use a plurality of examination items for judgment” is checked in the analysis option selection field 1504, the disease name candidates are analyzed using the selected number of examination items. For this reason, when the number of examination items is less than the set value, a complication candidate cannot be selected. If “Use multiple examination items for determination” is not checked, the examination item used for analysis of disease name candidates is 1.

  Next, when “use drug information” is checked in the analysis option selection field 1504, the disease name candidate analysis unit 109 obtains the drug name prescribed to the patient during the complication period from the prescription information table 400. By selecting and referring to the relationship between the drug name 601 and the corresponding disease 602 in the medicinal effect information table 600, a complication candidate in which a drug corresponding to the disease name added in the complication information is prescribed is selected (S1411). If “Use medicine information” is not checked, step S1411 is skipped.

  Next, the disease name candidate analysis unit 109 extracts a difference disease name between the diagnosed complication information and the complication information to be processed among the complication information selected in step S1411 as a disease name candidate (S1412). . For example, when the complication information diagnosed in a patient is “disease name A: disease name B” and the complication information to be processed is “disease name A: disease name B: disease name C”, the disease name candidate is “disease name C”. Is.

  Next, the disease name candidate analysis unit 109 uses the examination items and related drugs as determination items, and registers the patient ID, complication information, disease name candidate information, and determination items (test items, related drugs) in association with each other in the disease name candidate information table 1000. (S1413).

  Thus, in the disease name candidate information calculation process, by comparing the patient's complication information and the morbidity determination test information of the complication information including the disease name other than the complication information, the abnormality of the test value is caused by the complication. Therefore, it is possible to determine whether a new disease name has occurred or not, and an appropriate disease name candidate can be extracted.

  As described above, according to the data utilization support system 100 of the present embodiment, the examination information comparison unit 108 calculates the disease determination examination information 703 and the examination value 304 based on the complication diagnosed by the patient. In comparison, the disease name candidate analysis unit 109 selects a new disease name candidate of the patient based on the result of the comparison, so that a new disease name candidate can be accurately selected for a patient who has developed a plurality of diseases. For this reason, it is possible to easily grasp the difference between the disease state of a patient who has developed a plurality of diseases and the disease name information of the patient, and to support the utilization of data.

  In addition, when the test information comparison unit 108 compares the morbidity determination test information 703 of the complication diagnosed in the patient with the test value 304 does not indicate the morbidity of the complication diagnosed in the patient, the comparison result 904 is set to “1” and the disease name candidate analysis unit 109 selects a new disease name candidate for the patient when the comparison result 904 does not indicate the occurrence of the complication. Candidate names can be determined.

  In addition, since the test information comparison unit 108 selects the test value 304 that correctly represents the patient's pathological condition, such as before the drug prescription or close to the diagnosis date, and compares it with the disease determination test information 703, the patient's pathological condition is correctly The accuracy of disease name candidates can be improved by selectively using the test results that are represented.

  In addition, the disease name candidate analysis unit 109 selects complication information including complications diagnosed in the patient, and determines the patient's name from the difference between the complication diagnosed in the patient and the selected complication. Since a new disease name candidate is selected, the candidate disease name can be accurately determined.

  Further, the disease name candidate analysis unit 109 selects a new disease name candidate of the patient based on the result of comparison of the test values for the symptom 502 related to the difference disease name with reference to the knowledge database (disease name symptom correspondence table 500). Therefore, the disease name corresponding to the test value can be narrowed down, and the candidate disease name can be determined accurately.

  Further, the disease name candidate analysis unit 109 compares the test value 304 with the morbidity determination test information 703, selects information on complications indicating morbidity, and determines the complications diagnosed by the patient and the selected complications. Therefore, a candidate disease name can be accurately determined from a test value that does not reach the doctor's subjectivity.

  Moreover, since the disease name candidate analysis unit 109 selects a new disease name candidate of the patient based on the comparison result between the plural types of test values 304 and the morbidity determination test information 703, the candidate disease name can be accurately determined. . For example, disease names with similar pathologies can be isolated.

  Further, the disease name candidate analysis unit 109 determines the patient's based on the comparison result between the test value 304 and the disease determination test information 703 and the comparison between the drug information 400 prescribed to the patient and the disease name 600 corresponding to the drug. Since a new disease name candidate is selected, it is possible to extract a disease name that the doctor forgot to input. That is, when a medicine is prescribed, it is possible to supplement a disease name that has not been input to determine the treatment of the disease diagnosed by the doctor.

  In addition, since the disease determination value setting unit 115 calculates the disease determination test information based on the data stored in the patient information table 200, the candidate disease name can be determined even if the disease name is different depending on the medical institution. In addition, since the morbidity determination value setting unit 115 calculates the morbidity determination test information based on the data stored in the knowledge database 112, it is possible to correct the bias of the test value for each medical institution and determine a candidate disease name. it can.

  In addition, the display screen generation unit 105 generates screen data for displaying information on complications diagnosed by the patient, selected disease name candidates, and judgment materials (test values and drugs) from which the disease name candidates are selected. The analysis result including the reason for determination can be displayed in an easy-to-understand manner.

  In addition, the display screen generation unit 105 generates screen data for displaying the distribution of the test values of complications diagnosed by the patient and the distribution of the test values of complications including the selected disease name candidates. , Can support the selection of disease name candidates.

  The present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the scope of the appended claims. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and the present invention is not necessarily limited to those having all the configurations described. A part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Moreover, you may add the structure of another Example to the structure of a certain Example. In addition, for a part of the configuration of each embodiment, another configuration may be added, deleted, or replaced.

  In addition, each of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, with an integrated circuit, etc. It may be realized by software by interpreting and executing the program to be executed.

  Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

  Further, the control lines and the information lines are those that are considered necessary for the explanation, and not all the control lines and the information lines that are necessary for the mounting are shown. In practice, it can be considered that almost all the components are connected to each other.

DESCRIPTION OF SYMBOLS 100 Data utilization support system 101 Control part 102 Output part 103 Memory 104 Communication part 105 Display screen generation part 107 Complication information calculation part 108 Examination information comparison part 109 Disease name candidate analysis part 110 Judgment database 111 Integrated database 112 Knowledge database 113 Comparative examination Item setting unit 115 Disease determination value setting unit 118 Drug information determination unit 119 Accumulated data acquisition unit 120 Hospital information system 121 Patient information database 122 Examination information database 123 Prescription information database 130 Input / output terminal 140 Network

Claims (8)

A data analysis system comprising a processor and a storage device connected to the processor,
A determination database in which information on complications that are combinations of disease names and morbidity determination information that is a threshold of test values for determining morbidity are stored in association with each other, and disease name information and test value information associated with patient information Access to a stored patient information database,
The processor, based on information on complications diagnosed by a patient, a test information comparison unit that compares the disease determination information and the test value information,
The processor comprises a disease name candidate analysis unit that selects a new disease name candidate of the patient based on the result of the comparison ;
The disease name candidate analysis unit selects information on complications including disease names diagnosed in the patient,
The test information comparison unit compares the selected complication disease determination information with the test value information,
The disease candidate analysis unit
If the result of the comparison by the examination information comparison unit indicates the morbidity of the selected complication, the selected complication is selected as a new disease name candidate of the patient,
If the result of the comparison by the examination information comparison unit does not indicate that the selected complication is afflicted, the disease name of the difference between the disease name diagnosed in the patient and the selected complication is determined as a new disease name candidate for the patient. to that data analysis system selection as.   The data analysis system according to claim 1,
  The test information comparison unit is a data analysis system that selects test value information that correctly represents the pathology of the patient and compares it with the disease determination information.   The data analysis system according to claim 1,
  The said disease name candidate analysis part is a data analysis system which selects the new disease name candidate of the said patient based on the result of the comparison with multiple types of said test value information and the said disease determination information.   The data analysis system according to claim 3,
  Has access to a knowledge database that stores the name of the disease corresponding to the drug,
  The patient information database further stores information on drugs prescribed to the patient,
  The disease name candidate analysis unit, based on a result of comparison between the test value information and the morbidity determination information and information on a drug prescribed to the patient and a result of comparison with a disease name corresponding to the drug, A data analysis system that selects new disease name candidates.   The data analysis system according to claim 1,
  Has access to a knowledge database in which medical knowledge is stored,
  A data analysis system, wherein the processor includes a disease determination value setting unit that calculates the disease determination information based on data stored in the patient information database or the knowledge database.   The data analysis system according to claim 1,
  A display screen generating unit that generates screen data for displaying the selected disease name candidates;
  The display screen generation unit is a data analysis system that generates screen data for displaying information on complications diagnosed by the patient, the selected disease name candidate, and a determination material selected from the disease name candidate.   The data analysis system according to claim 6, wherein
  The display screen generation unit generates data for generating screen data for displaying a distribution of test values for complications diagnosed in the patient and a distribution of test values for complications including the selected disease name candidates. Analysis system. An analysis method executed in a computer system,
The computer system includes a processor for executing a program and a storage device connected to the processor,
The computer system includes a determination database in which complication information that is a combination of disease names and morbidity determination information that is a threshold value of a test value for determining morbidity are stored in association with each other, and disease name information that is associated with patient information. And a patient information database in which test value information is stored,
The analysis method is:
A test information comparing step in which the processor compares the morbidity determination information with the test value information based on information on complications diagnosed by a patient;
The disease name candidate analyzing step of selecting a new disease name candidate of the patient based on the result of the comparison;
In the disease name candidate analysis step, information on complications including disease names diagnosed in the patient is selected,
In the test information comparison step, the morbidity determination information of the selected complication is compared with the test value information,
In the disease name candidate analysis step,
If the result of the comparison indicates the morbidity of the selected complication, the selected complication is selected as a new candidate disease name for the patient;
If the result of the comparison does not indicate the onset of the selected complications, you select a disease name of the difference between disease name and the selected complications are diagnosed by the patient as a new disease name candidates of the patient data Analysis method.