JP6482962B2 - Clinical laboratory data analysis support device and analysis support method - Google Patents

Description

  The present invention relates to a clinical test data analysis support apparatus and an analysis support method. Specifically, the present invention relates to a technology that can improve the efficiency and accuracy of data analysis for clinical laboratory data including inter-facility errors.

  With the progress of computerization of medical information, there is an increasing trend to use medical information collected from multiple medical institutions to improve the quality of medical care. On the other hand, there is an inter-facility error in clinical test data due to differences in test equipment, reagents, etc., and this error reduces the effectiveness and efficiency of using medical information collected.

  As a method for dealing with the above-mentioned in-laboratory error of clinical laboratory data, a standard that extracts only clinical laboratory data estimated to be healthy laboratory data from clinical laboratory data that consists of subjects analyzed at the same facility There has been proposed a technique for correcting an inter-facility error by deriving correction parameters from clinical test data and correcting the clinical test data collected from each facility using the correction parameters (see Patent Document 1).

JP 2009-247688 A

  In the prior art, a correction parameter is derived using clinical test data of a healthy person, and the interlaboratory error is eliminated by correcting the clinical test data using the correction parameter. However, many medical institutions that do not have a medical examination institution do not sufficiently store data on healthy individuals in the database, and correction parameters are not correctly derived.

  In order to solve the above-described problems, the clinical test data analysis support apparatus according to the present invention includes an integrated clinical data table including a plurality of clinical test data received from a plurality of medical institutions and standardized test values of the respective clinical test data. A reference range table including a reference range for each test name in all or part of the plurality of medical institutions, a clinical test data collection unit that receives clinical test data from the plurality of medical institutions, and the received clinical tests A test name conversion unit that converts a test name of data into a unified test name, and determines whether or not a reference range is included in the received clinical test data, and if not included in the reference range table The reference range of the same medical institution and the name of the test included is identified and received based on the reference range included in the clinical test data or the specified reference range. Standardized laboratory values of clinical laboratory data, and a data standardization unit for storing the test values were normalized to the integrated clinical data table.

  In the clinical test data analysis support method according to the present invention, an integrated clinical data table including a plurality of clinical test data received from a plurality of medical institutions, a standardized test value of each clinical test data, and the plurality of the plurality of clinical test data A reference range table including a reference range for each test item in all or part of a medical institution, and determines whether or not a reference range is included in the received clinical test data. The reference range of the same medical institution and test item included in the reference range table is specified, and the test value of the received clinical test data is standardized based on the reference range included in the clinical test data or the specified reference range Then, the standardized test values are stored in the integrated clinical data table.

  According to the present invention, regardless of the amount of data of a healthy person, the interlaboratory error of clinical test data is corrected, and the efficiency and accuracy of data analysis are improved.

It is a network block diagram including the clinical data analysis support system of this embodiment. It is a figure which shows the hardware structural example of the data search system in this embodiment. It is a figure which shows the data structural example of the clinical test data table of this embodiment. It is a figure which shows the example of a data structure of the test name conversion table of this embodiment. It is a figure which shows the example of a data structure of the test value conversion table of this embodiment. It is a figure which shows the example of a data structure of the reference | standard range table of this embodiment. It is a figure which shows the hardware structural example of the user terminal in this embodiment. It is a flowchart which shows process sequence example 1 of the clinical data analysis assistance method in this embodiment. It is a flowchart which shows the process sequence example of the reference | standard range derivation in this embodiment.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
--- System configuration ---
FIG. 1 is a network configuration diagram including a clinical test data analysis support system 100 of the present embodiment. The clinical test data analysis support system 100 is connected to the medical institutions 200A, 200B,... Via the network 20, receives clinical data transmitted from each medical institution, and cleanses the clinical data received. This is an information processing apparatus for storing the results. The institutions that transmit clinical data are not limited to medical institutions, but include institutions that hold clinical test data such as test institutions.

  FIG. 2 is a diagram illustrating a hardware configuration example of the clinical test data analysis support system 100 according to the present embodiment. The clinical test data analysis support system 100 includes a storage device 11 composed of an appropriate nonvolatile storage device such as a hard disk drive, a memory 13 composed of a volatile storage device such as a RAM, and a program 12 held in the storage device 11. A communication device 17 connected to the network 20 and responsible for communication processing with other devices, such as a CPU that performs various determinations, computations, and control processes, and performs overall control of the device itself. Prepare.

  The data search system 100 may receive clinical data directly from the user terminal 200 instead of receiving clinical data from the user terminal 200 via the network 20 and the communication device 17. In this case, the data search system 100 includes an input device 15 that accepts key input and voice input from a user, and an output device 16 such as a display that displays processing data.

  In the storage device 11, an integrated program 12 for implementing functions necessary for the clinical test data analysis support system 100 of the present embodiment, and clinical data before cleansing and results after cleansing of a plurality of medical institutions are stored. A clinical data table 101, a test name conversion table 102 for converting a test name stored in clinical data collected from a medical institution into a unified test name, and a qualitative test or semi-stored in clinical data collected from the medical institution A test value conversion table 103 for converting a test value of a quantitative test into a unified test value, and a reference range table 104 storing a reference range for each test item for each medical institution are stored. Here, the reference range refers to the 95% confidence interval of the test value distribution measured from individuals (reference individuals) whose factors that have a clear effect on the test value are denied among healthy individuals, and interpret the measurement value. As a guideline, it is set for each clinical examination item for each medical institution.

  FIG. 3 shows an example of the integrated clinical data table 101. The integrated clinical data table 101 includes a plurality of records, and each record includes items of facility name, subject ID, age, sex, examination name, examination date, examination value, reference range-upper limit value, and reference range-lower limit value. Hold at least.

  FIG. 4 shows an example of the examination name conversion table 102. The examination name conversion table 102 includes a plurality of records, and each record holds an examination name including a notation fluctuation and a unified examination name corresponding to the examination name. Note that clinical test codes that are used as standard in Japan may be included as test names before unification.

  FIG. 5 shows an example of the inspection value conversion table 103. The test value conversion table 103 includes a plurality of records, and each record holds a notation indicating a test result of a qualitative test or a semi-quantitative test and a unified test value for the notation.

  FIG. 6 shows an example of the reference range table 104. The reference range table 104 includes a plurality of records, and each record stores information related to the reference range of one examination item of one medical institution. Each record holds at least items of facility name, inspection item, sex, inspection type, reference range, and date.

  The data terminal 200 is a terminal that transmits the clinical data 105 of the medical institution to the clinical data analysis support system 100, transmits an output request for integrated clinical data that eliminates the inter-facility error, and receives the integrated clinical data. Become. As illustrated in FIG. 7, the data terminal 200 of each medical institution has a hardware configuration as a general information processing apparatus, like the clinical test data analysis support system 100, and is appropriately non-volatile such as a hard disk drive. A storage device 21 composed of a volatile storage device, a memory 23 composed of a volatile storage device such as a RAM, and a program 22 held in the storage device 21 is read into the memory 23 and executed to perform overall control of the device itself In addition, a calculation device 24 such as a CPU for performing various determinations, calculations and control processing, an input device 25 for receiving key input and voice input from a user, and an output device 26 such as a display for displaying processing data are provided. The storage device 21 holds a clinical data table 201 and a reference range table 202 in addition to programs. However, the clinical data table 201 and the reference range table 202 are not essential depending on the processing, and may be omitted.

  Next, functions provided in the clinical test data analysis support system 100 of this embodiment will be described. As described above, the functions described below can be said to be implemented by executing the program 12 included in the clinical test data analysis support system 100, for example. In the example of FIG. 2, the clinical data collection unit 111, the examination name conversion unit 112, the data standardization unit 113, and the data correction unit 114 are mounted by executing the program 12 by the arithmetic device 14.

  The clinical test data analysis support system 100 receives clinical test data transmitted from a medical institution or the like via the network 20 and extracts information for storing the received data in a clinical test data table (clinical data collection A function of the unit 111).

  The clinical test data analysis support system 100 uses the test name conversion table 102 to convert the test name of the clinical data collected from the medical institution to a unified test name (function of the test name conversion unit 112). ).

  The clinical test data analysis support system 100 uses the reference range calculated from the data of the integrated clinical data 101 stored in the integrated clinical data table 101 or the clinical data collected from the medical institution as described above. A function for standardizing the inspection value (a function of the data standardization unit 113) is provided.

The clinical test data analysis support system 100 also has a function (data correction) that corrects the standardized test value of the integrated clinical data in which the inter-institutional error of the test value is eliminated by the data standardization unit according to the designated reference range. Function of the unit 114).
--- Example 1 ---
Hereinafter, the implementation procedure of the clinical test data analysis support method in the present embodiment will be described with reference to the drawings. Various operations corresponding to the clinical test data analysis support method described below are realized by a program that the clinical test data analysis support system 100 reads and executes in a memory or the like. And this program is comprised from the code | cord | chord for performing the various operation | movement demonstrated below.

  FIG. 8 is a flowchart showing a processing procedure example 1 of the clinical test data analysis support method in the present embodiment. First, a process in which the clinical test data analysis support system 100 receives clinical data from a medical institution and generates standardized data will be described.

  First, the clinical data collection unit 111 in the clinical test data analysis support system 100 receives clinical test data transmitted from a medical institution via a network, and stores information stored in the unified clinical data table from the received clinical test data. Extract (S801).

  Next, the examination name conversion unit 112 in the clinical examination data analysis support system 100 refers to the examination name conversion table 102 and sets the unified examination name corresponding to the examination name extracted in S801 described above to the unified examination in the integrated clinical data table 101. Store in the name field (S802).

  Next, the data standardization unit 113 in the clinical test data analysis support system 100 performs test value standardization processing in S803 to S807. First, in step S803, the data standardization unit 113 determines the inspection type of the inspection item. The test type is divided into a quantitative test in which the result is shown as a numerical value, a semi-quantitative test shown in a rough degree such as +, ++, and ++, and a qualitative test shown as positive and negative. In S803, all the test values of the same medical institution and the same test item as the test item to be determined are extracted from the integrated clinical data table 101, and the test item is a quantitative test based on the number of extracted test value patterns. Determine whether. If the number of patterns exceeds a separately defined threshold value, it is determined that the test is a quantitative test, and the process of S805 is executed. .

  In S804, the data standardization unit 113 refers to the test value conversion table 103, and uses the unified clinical data table for the unified notation corresponding to the test value of the test item determined to be other than the quantitative test (qualitative test or semi-quantitative test) in S803. 101 is stored in the unified inspection value field.

  In S805, the data standardization unit 113 determines whether or not there is a value in the upper limit field and the lower limit field of the inspection record of the inspection item determined to be the quantitative inspection.

  When both the upper limit value and the lower limit value are stored, the reference range table 104 is referred to. When the reference range table 104 does not store the reference range of the medical institution and the test item of the test record, or the upper limit value, the lower limit value stored in the test record, and the upper limit value stored in the reference range table 104 If the lower limit value is different, the reference range information of the inspection record is stored in the record of the reference range table 104, and the process of S807 is executed. If there are two or more reference ranges for the same examination at the same medical institution, determine the factors (gender, age, date), etc., that are different in the reference range, and set the same upper limit and lower limit as the patient background of the record. The upper limit value and lower limit value of

  When only one of the upper limit value and the lower limit value is stored, or when both the upper limit value and the lower limit value are not stored, the reference range table 104 is referred to. When the upper limit value and the lower limit value for the medical institution and the test item of the test record are stored, the upper limit value and the lower limit value are stored in the upper limit field and the lower limit field of the integrated clinical data table 101, respectively.

  When the upper limit value and the lower limit value of the examination item are not stored in the reference range table 104, all records of the same medical institution and the same examination item as the examination item are extracted from the integrated clinical data table 101, and the upper limit value and the lower limit value are extracted. If there is a record storing the value, the upper limit value and the lower limit value are stored as the upper limit value and the lower limit value of the inspection record. If there are two or more reference ranges for the same examination at the same medical institution, determine the factors (gender, age, date), etc., that are different in the reference range, and set the same upper limit and lower limit as the patient background of the record. The upper limit value and lower limit value of All the reference range information extracted from the integrated clinical data is stored in the reference range table 104.

  When only one of the upper limit value and the lower limit value is extracted after performing the above processing, or when both the upper limit value and the lower limit value are not extracted, the data standardization unit 113 executes S806. That is, even when the reference range of the received clinical test data and the clinical test data extracted from the integrated clinical table is combined, either the upper limit value or the lower limit value, or both the upper limit value and the lower limit value cannot be specified. It is processing.

  In S806, the data standardization unit 113 uses the temporary reference range based on clinical data for the test item in which only one of the upper limit value and the lower limit value is extracted in S805 or for which both the upper limit value and the lower limit value cannot be extracted. Is derived. The detailed flow of S806 is shown in FIG.

  The data standardization unit 113 executes S8061 when only one of the upper limit value and the lower limit value is extracted in S805, and executes S8063 when both the upper limit value and the lower limit value cannot be extracted.

  First, a process when only one of the upper limit value and the lower limit value is extracted as the reference range will be described. When only one of the upper limit value and the lower limit value is extracted as the reference range, a temporary upper limit value (temporary lower limit value) is derived for the inspection item. First, in S8061, all the test values of the test item of the medical institution stored in the integrated clinical data table 101 are extracted, and the distribution of the test value of the test item is derived. In S8062, the upper (lower) test value of 2.5% is set as the temporary upper limit value (temporary lower limit value) from the test value distribution. In S803, the inspection value is stored in the upper limit (lower limit) field of the inspection record, and the reference range information is stored in the reference range storage table.

  Next, processing when the upper limit value and the lower limit value cannot be extracted will be described. When the upper limit value and the lower limit value cannot be extracted, the temporary upper limit value and the temporary upper limit value are calculated using the distribution of the test value of the test item of the medical institution and the facility other than the medical institution stored in the integrated clinical data table 101. The lower limit is derived. In the clinical data analysis support system 100, the temporary upper limit value and the temporary lower limit value are derived by a plurality of methods. The data standardization unit 113 outputs the reference range derivation method to the user terminal, causes the user to select the reference range derivation method, and calculates the reference range by the selected method.

  First, in S8063, the reference range deriving method is output to the user terminal, and the reference range deriving method selected by the user is received.

  One of the reference range setting methods is a method of deriving a reference range from a test value distribution of a medical institution that holds the reference range of the same test item. An example in which the reference range of the examination D of the medical institution A is calculated from the data of the medical institution B will be described. In this case, all records relating to the examination D of the medical institution A and the medical institution B are extracted from the integrated clinical data table 101, and the examination value distribution for each medical institution is created (S8064). A parameter in which the test value distributions of the medical institution A and the medical institution B overlap is derived (S8065), and the medical institution B reference range is converted using the parameter to be the reference range of the medical institution A (S8066). If there are multiple medical institutions that hold the reference range of the same item, the error from the average value and standard deviation of the test value distribution of the medical institution from which the reference range is to be derived is calculated from the distribution of test values of each medical institution. The reference range is derived using the smallest inspection value distribution. The reference range may be derived from the test value distribution of each medical institution, and the standard deviation of the plurality of derived reference ranges may be used as the reliability of the reference range.

  One of the reference range setting methods is a method of calculating the reference range using data extracted by narrowing the test value distribution to patients of the same patient background (disease, age, sex) in S8064 of the above reference range setting method. . Regarding the setting method of the reference range, in the above, the setting method was presented to the user and the reference range was derived by the method selected by the user, but it is not necessary to be limited to this procedure. For example, a plurality of setting methods may be used. A reference range may be derived, a plurality of derived reference ranges may be presented to the user, and the user may select a reference range from the presented reference ranges. In the above description, one of the reference ranges derived by one reference range setting method is selected and presented to the user, but all derived reference ranges may be presented to the user. In addition, the user may manually input a reference range other than the presented reference range.

  When the reference ranges are derived or input by the above method in S806, the reference ranges are stored in the integrated clinical data table 101 and the reference range table 104 as the reference ranges of the examination item of the medical institution. However, when the upper limit value and lower limit value of the reference range are not specified even by the above method, the record for the received clinical data is left in the integrated clinical data table 101 while the unspecified reference range lower limit value and reference range upper limit value are left blank. Stored in

In S807, the data standardization unit 113 standardizes the inspection value. Specifically, the average μ and the standard deviation σ are calculated from the lower limit value L ₁ and the upper limit value H ₁ of the reference range of the test value described in the clinical data transmitted from the medical institution or derived in S806. The test value is standardized by the following formula (1). The standardized result is stored in the standardized value field of the integrated clinical data table 101. However, if the upper limit value and the lower limit value of the reference range are not specified by S806 and the reference range lower limit value and the reference range upper limit value in the integrated clinical data table 101 are blank, the standardized test value remains blank.
Average μ ₁ = (H ₁ + L ₁ ) / 2
Standard deviation σ ₁ = (H ₁ −L ₁ ) /2·1.96
Standardized value Z = (X−μ ₁ ) / σ ₁ (Formula 1)
As described above, in the apparatus and method according to the present embodiment, by using both the reference range of the test value for each medical institution and test item and the statistical data of the test value of the clinical test data according to the situation, Regardless of the amount of data, it is possible to eliminate inter-facility errors in test values.
--- Example 2 ---
In the above description, the processing up to the creation of standardized data that eliminates the error between facilities has been described. As described above, the test value standardized by the clinical data analysis support system 100 has an effect of eliminating the inter-facility error of the test value. On the other hand, standardized test values are different from the test values that you see on a daily basis, and for users of integrated clinical test data, how normal or abnormal the test values are Hard to do. Processing procedure example 2 describes a process of outputting the result of correcting the test value of the integrated clinical data into data that can be easily used by the data user using the reference range of each test item of the facility that uses the integrated clinical data. .

  The data correction unit 104 in the clinical data analysis support system 100 acquires the name of the medical institution from the data acquisition request received from the user terminal 200, and determines whether the reference range of the examination item of the medical institution is stored in the reference range table 104. judge. When the reference range of the inspection item of the medical institution is not stored in the reference range table, the user terminal 200 is requested to input the reference range for each inspection item, and the input reference range is stored in the reference range table 104. .

Next, each record of the integrated clinical data table 101 is read, and the reference range of the inspection item of the correction destination organization for the inspection item of the record is acquired from the reference range table 104. The average μ ₂ and the standard deviation σ ₂ are calculated from the lower limit value L ₂ and the upper limit value H _{2 of the} acquired reference range of the correction destination engine, and the inspection value is corrected to a value along the reference range of the analysis engine. The following equation (2) is an equation for correcting the standardized value Z to the correction value Y.
Average μ ₂ = (H ₂ + L ₂ ) / 2
Standard deviation σ ₂ = (H ₂ −L ₂ ) /2·1.96
Correction value Y = σ ₂ Z + μ ₂ (Formula 2)
The above correction is performed on all records in the integrated clinical data table 101, and the correction result is output to the user terminal 200.

  Through the above processing, the standardized test value can be returned to the test value along the reference range of any medical institution.

DESCRIPTION OF SYMBOLS 11 Storage device 12 Program 13 Memory 14 Arithmetic device 17 Communication device 20 Network 100 Data retrieval system 101 Master information table 102 Partial notation fluctuation dictionary 103 Notation fluctuation dictionary 104 Normalization rule 105 Clinical data 111 Master information reading part 112 Character string normalization part 113 Character string division unit 114 Partial notation fluctuation dictionary generation part 115 Notation fluctuation dictionary generation part 116 Notation fluctuation pattern generation part 117 Data extraction part 200 User terminal 21 Storage device 22 Program 23 Memory 24 Arithmetic device 25 Input device 26 Output device 27 Communication device

Claims (10)

A clinical test data analysis support device,
An integrated clinical data table including a plurality of clinical test data received from a plurality of medical institutions, and standardized test values of each of the clinical test data;
A reference range table including a reference range for each examination item in all or part of the plurality of medical institutions;
It is determined whether or not a reference range is included in the received clinical test data, and if not included, the reference range of the same medical institution and test item included in the reference range table is specified, and the clinical test is performed. A data standardization unit that standardizes the test values of the received clinical test data based on the reference range included in the data or the specified reference range, and stores the standardized test values in the integrated clinical data table. ,
A clinical test data analysis support device characterized by that. The clinical test data analysis support device according to claim 1,
The reference range includes an upper limit value and a lower limit value of the inspection value,
The data standardization unit determines that the reference range is not included in the received clinical test data when both the upper limit value and the lower limit value are not included in the received clinical test data ,
A clinical test data analysis support device characterized by that. The clinical test data analysis support device according to claim 2,
When the reference range of the same medical institution and test item included in the reference range table could not be specified, the clinical test data of the same medical institution and test item included in the integrated clinical data table was extracted, and the extracted Specify the reference range included in the clinical laboratory data as the reference range used for the standardization .
A clinical test data analysis support device characterized by that. The clinical test data analysis support device according to claim 3,
If only one of the upper limit value and the lower limit value can be specified even if the reference ranges included in the received clinical test data and the extracted clinical test data are combined, the distribution of the test values of the extracted clinical test data Based on the above, a reference range used for the standardization is set .
A clinical test data analysis support device characterized by that. The clinical test data analysis support device according to claim 4,
If neither the upper limit value nor the lower limit value can be specified even if the reference range included in the received clinical test data and the extracted clinical test data are combined, the same test item included in the integrated clinical data table Extracting clinical test data, and setting a reference range used for the standardization based on the distribution of test values for each medical institution of the clinical test data of the extracted same test item ,
A clinical test data analysis support device characterized by that. A clinical test data analysis support method,
An integrated clinical data table including a plurality of clinical test data received from a plurality of medical institutions, and standardized test values of each of the clinical test data;
A reference range table including a reference range for each examination item in all or a part of the plurality of medical institutions,
The data standardization unit determines whether or not the reference range is included in the received clinical test data, and if not, specifies the reference range of the same medical institution and test item included in the reference range table And standardizing the test value of the received clinical test data based on the reference range or the specified reference range included in the clinical test data, and storing the standardized test value in the integrated clinical data table.
A clinical laboratory data analysis support method characterized by the above. The clinical test data analysis support method according to claim 6,
The reference range includes an upper limit value and a lower limit value of the inspection value,
The data standardization unit determines that the reference range is not included in the received clinical test data when both the upper limit value and the lower limit value are not included in the received clinical test data ,
A clinical laboratory data analysis support method characterized by the above. The clinical test data analysis support method according to claim 7,
When the reference range of the same medical institution and test item included in the reference range table could not be specified, the clinical test data of the same medical institution and test item included in the integrated clinical data table was extracted, and the extracted Specify the reference range included in the clinical laboratory data as the reference range used for the standardization .
A clinical laboratory data analysis support method characterized by the above. The clinical test data analysis support method according to claim 8,
If only one of the upper limit value and the lower limit value can be specified even if the reference ranges included in the received clinical test data and the extracted clinical test data are combined, the distribution of the test values of the extracted clinical test data Based on the above, a reference range used for the standardization is set .
A clinical laboratory data analysis support method characterized by the above. The clinical test data analysis support method according to claim 9,
If neither the upper limit value nor the lower limit value can be specified even if the reference range included in the received clinical test data and the extracted clinical test data are combined, the same test item included in the integrated clinical data table Extracting clinical test data, and setting a reference range used for the standardization based on the distribution of test values for each medical institution of the clinical test data of the extracted same test item ,
A clinical laboratory data analysis support method characterized by the above.

Images