WO2002003077A1 - Clinical examination system - Google Patents

Abstract

A clinical examination system in which necessity of re-examination can be determined automatically with high accuracy for re-examination results. A logic for determining necessity of re-examination is optimized using re-examination execution information accumulating the re-examination results of specimens requiring re-examination and a part of specimens requiring no re-examination, and the inspection results.

Description

 Description Clinical test system Technical field

 The present invention relates to a clinical test system, and more particularly to a retest necessity determination method for determining whether a retest is necessary based on test results. Background art

 In the examination room of a hospital or an examination center such as an examination center, examinations are performed on various items of the subject, and when the examination results are obtained, the validity of the values is verified. For example, when an abnormal value is measured as a result of a test, it is determined whether the test value of the subject is really abnormal or an abnormal value due to a measurement defect (e.g., a device error or human error). If the possibility of measurement failure is low, the test result is reported to the clinic as correct, and if the possibility of measurement failure is high, a retest is performed. The need for retesting was determined by the laboratory technician based on past experience, referring to the combination of test values and the results of the previous test for the patient (recipient).

In recent years, clinical tests have been automated, and clinical test systems that accumulate and manage test results as electronic data have become widespread. With the spread of clinical inspection systems, the logic for determining whether re-examination is necessary (re-examination necessity means) has been incorporated into clinical examination systems. As such re-examination necessity determination means, a single item check, a previous value check, and an inter-item check are known as typical methods. As a single item check, for example, a technique disclosed in Japanese Patent Application Laid-Open No. HEI 5-151282 is known. This technology sets a reference range for each test item according to gender, age, and pregnant woman, and if the test value exceeds this reference range, Report as a result. Further, Japanese Patent Application Laid-Open No. 7-271873 describes a method of providing two types of reference ranges for each inspection item, an abnormal value range and a panic value range.

 As the previous value check, for example, a delta check described in Japanese Patent Application Laid-Open No. 5-151282 and a cumulative delta check described in Japanese Patent Application Laid-Open No. 11-92665 are known. Have been. In the delta check, a reference value is set for the difference between the previous value and the current value for each inspection item, and an error is reported for ^^ where the difference between the previous value and the current value exceeds the reference value. In addition, in the cumulative delta check, the standard deviation within an individual (the standard deviation of the test value for each test item for the same patient and examinee) is determined for each test item, and the difference between the previous value and the current value is calculated. Calculate the ratio to the standard deviation. An abnormality is detected by providing a reference value to the value obtained by adding the above ratio obtained for each inspection item.

 As an inter-item check, for example, as described in Japanese Patent Application Laid-Open No. 11-92665, a reference value is set for a ratio between items, and a method of judging abnormality or a plurality of inspection items are used. A method is known in which a logical operation expression is defined and an abnormality is determined based on the truth of the logical operation expression. Disclosure of the invention

By applying the technology as described above, labor saving and efficiency of retest necessity determination are being realized. However, the results of the test that the technician determines that a retest is necessary do not completely match the results of the automatic retest necessity determination, and further improvement in accuracy is desired. Since it is difficult for the inspection side to have an error in the inspection result, the determination of the necessity of automatic re-inspection is generally carried out by using a reference value or a judgment logic so that there is no oversight of the inspection result to be re-inspected (missing detection). In many cases, a detection result that does not actually need to be re-examined is used as a criterion for judging the necessity of re-examination. Therefore, a laboratory technician checks again the test results determined to be necessary by the automatic retest necessity judgment, and extracts the test results that really need to be retested. Work is required. In order to save labor for inspection technicians, a more accurate method for determining whether reexamination is necessary is needed.

 In addition, when applying the automatic reexamination necessity judgment, it is not only necessary to set a large number of reference values or logical expressions in advance, but also the composition of patients (disease, age, etc.) who visit each facility (hospital) for consultation. And the criteria for technicians to conduct retests are also different, making it difficult to set optimal reference values and logical formulas. As a result, the standard values and logical expressions cannot be easily optimized, and the automatic retest necessity judgment cannot be applied effectively.

 The present invention has been made in view of the above circumstances, and realizes a more accurate automatic retest necessity determination, and can easily optimize a reference value and a logic used in the retest necessity determination. It aims to provide a system.

 In a clinical test system that has a retest necessity determination unit that determines whether a retest is necessary for a test result, a sample that has already been obtained from a Perform all re-examinations. The result of this re-examination is compared with the result of the previous inspection, and the re-examination necessity determination logic is corrected using this result. BRIEF DESCRIPTION OF THE FIGURES

 FIG. 1 is a diagram showing one configuration example of a clinical test system to which the present invention can be applied.

 FIG. 2 is a diagram showing another example of the configuration of the clinical test system to which the present invention can be applied.

 FIG. 3 is a diagram showing still another example of the configuration of the clinical test system to which the present invention can be applied.

FIG. 4 is a diagram showing a basic block configuration of the inspection server according to the present invention. FIG. 5 is a diagram for explaining one embodiment of the principle of optimization of the retest necessity determination logic according to the present invention. FIG. 6 is a diagram for explaining another embodiment of the principle of optimality of the retest necessity determination logic according to the present invention.

 FIG. 7 is a diagram showing a flowchart of a process of optimizing the retest necessity determination logic according to FIG.

 FIG. 8 is a diagram showing a flowchart of the process of optimizing the retest necessity determination logic according to FIG.

 FIG. 9 is a diagram illustrating an example of a parameter such as a reference value used in the retest necessity determination logic according to the present invention and a logical expression describing the determination logic.

 FIG. 10 is a diagram showing one example of a screen configuration for displaying the inspection result and the result of the necessity of re-inspection on the display of the inspection client according to the present invention.

 FIG. 11 is a diagram showing another example of the screen configuration for displaying the inspection result and the re-examination necessity determination result on the display of the inspection client according to the present invention. BEST MODE FOR CARRYING OUT THE INVENTION

 Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

1 to 3 are diagrams showing a configuration example of a clinical test system to which the present invention can be applied. In FIG. 1, an analyzer server 20, an inspection server 30, and an inspection client 40 are connected to a LAN 50 installed in a hospital or an inspection room. As each of the servers 20 and 30 and the inspection client 40, for example, a personal computer or the like can be used. The first inspection device 11, the second inspection device 12, and the third inspection device 13 are further connected to the LAN 50. The analysis device server 20 controls each inspection device, performs necessary processing such as analysis on the inspection result output from each inspection device, and transmits information to the inspection server 30 via the LAN 50. send. The inspection server 30 accumulates information such as the obtained inspection result, and determines whether or not the inspection result requires re-examination. The inspection client 40 receives the inspection results accumulated in the inspection server 30 and the inspection server 30. It is possible to refer to information such as the necessity of the determined retest. In addition, the inspection result for the inspection that is not automated can be input using the inspection client 40. In this case, the input data such as inspection results

It is sent from 40 to the inspection server 30 and stored in the inspection server 30.

 Figure 2 shows the hospital 500 and the decision logic learning facility where the system described in Figure 1 was built.

550 is an example of a system configuration that enables data transmission / reception via a communication line 540. A learning server 60 is installed in the court learning facility 550, and the learning server 60 is connected to a communication line 540 via a first communication means 610. The inspection server 30 is connected to the communication line 540 via the second communication means 620. The inspection server 30 and the learning server 60 can transmit and receive data via the communication line 540. As the communication line 540, various lines capable of data communication can be used, and for example, a telephone line can be used. Further, as the first communication means 6 10 and the second communication means 6 20, appropriate communication means according to the type of line is used. For example, when a telephone line is used as the communication line 540, a modem can be used as the first communication means 610 and the second communication means 6200. According to this example, in the example of FIG. 1, it is possible to leave to the learning server 60 the optimization of the criterion for judging the necessity of the retest for the test result performed by the test server 30. Therefore, since the learning server 60 can perform the optimization using the data of other hospitals connected to the communication line 540, a more complete optimization can be expected than the system of FIG.

 FIG. 3 is an example of a form in which each of the hospitals 5200 and 5300 connected via a communication line 5400 uses the inspection center 5100 in which the system described in FIG. Each hospital is provided with a test result reference terminal 70, which allows the user to know the test results for the requested test object. According to this example, each hospital can perform a test including a more sophisticated retest while reducing capital investment.

The present invention can be applied to any of the embodiments, The retest necessity determination by the test server 30 can be further improved.

 FIG. 4 shows a basic block diagram of the configuration of the inspection server 30 according to the present invention. 100 is a system path. 101 is CPU. Numeral 102 is a database, which is data such as initial test results 1 1 1, re-test necessity judgment results 1 1 4 or re-test results 1 1 5, re-test execution information 1 1 2, diagnostic information 1 2 1, Various information such as contract information 1 2 2, request information 1 2 3 or re-examination necessity determination logic 1 16, re-examination necessity judgment reference value 1 18, and re-examination necessity judgment processing 1 1 3 Execution programs for re-test necessity determination logic optimization processing 117, disease candidate estimation processing 124, and the like are stored. Reference numeral 103 denotes a RAM, which is a memory area used as a work area for executing various processes. Reference numeral 104 denotes an input / output interface for inputting various information such as test result input, diagnostic information input, retest execution information input, contract information input, and various information such as test result output and retest results. Is output.

 This embodiment enumerates data and processing programs as functions that the inspection server 30 should have, and does not cover all of them. In the system configuration shown in FIG. 2, the re-examination necessity determination logic optimization processing and the like are executed by the decision logic learning facility 550, and the inspection server 30 cooperates with the re-examination logic. Will be promoted.

 Specific processing for optimizing the retest necessity determination logic according to the present invention in a system having such a configuration will be described.

 Here, as an example, optimization of a check between two items using a linear discriminant will be described. Specifically, in the re-examination necessity determination process 1 1 3 using two test values x, y,

Calculate the value of t according to equation (1). If t≥0, it is determined that reinspection is necessary, and if t <0, it is determined that reinspection is unnecessary.

 t = a x + b y + c (1)

Here, a, b, and c are constants, which are recorded together with the expression (1) in the database re-examination necessity determination logic 116 of FIG. The initial value of this value uses data collected in advance. Use the power to set the optimal value, or set the value based on the engineer's past experience. In this case, since the optimal value differs depending on the characteristics of the patient at each hospital (what kind of disease is most common) and the conditions of the test method, test equipment, reagents, etc., it is not possible to optimize for each hospital. Of course.

 The principle of the optimality of the retest necessity determination logic at this time will be described with reference to FIG. In FIG. 5 (a), the test value x and the test value y are set on the horizontal axis and the vertical axis, respectively, and the distribution of the test values is indicated by a data group 920 indicated by X and a data group 940 indicated by 〇. A straight line 950 indicates a straight line ax + by + c = 0, and the data on the upper side of this straight line is determined to require retesting, and the data on the lower side is determined to be unnecessary. Therefore, for the data group 920 indicated by X, the retest necessity judgment result 1 14 is recorded as “retest required”, and for the data group 940 indicated by 4, the retest necessity judgment result 1 1 4 records "No need to retest". In the present invention, for the data group 920 indicated by X, a retest is performed on each sample of the data group 920. In general, the specimen will be unsuitable as a specimen after a long period of time, so this retest should be performed as soon as the first test result is obtained. Of course, the technician may review whether or not reexamination is actually necessary, and omit those that are judged to be unnecessary.

 The results of the retest are shown in Fig. 5 (b). The data group indicated by a thick X in FIG. 5 (b) indicates a data group in which the results of the retest did not differ significantly from the results of the initial test. In other words, the same result is obtained even if the retest is performed, that is, the retest is useless. These data will be recorded again in the Judgment of Necessity of Re-examination. On the other hand, the specimens in the data group indicated by X surrounded by a broken line with the original thickness indicate that the test value changed to the position of △ indicating the corresponding relationship by the broken line with an arrow as a result of the retest. In other words, the initial inspection of these specimens was unreliable due to some abnormalities and was confirmed by re-inspection, resulting in data within the range of the inspection value, and it can be evaluated that the determination that re-inspection was necessary was appropriate.

Therefore, the re-test necessity determination logic optimization process 1 17 includes the re-test necessity judgment result 1 1 4 From the distribution, it is possible to change the straight line 950, which is the threshold of the necessity of retest, to the straight line 960 shown by the equation (2). The content of the expression (2) is adopted as a correction of the judgment recorded in the judgment 1 16 of the necessity of reexamination.

 a 'x + b' y + c '= 0 (2)

 The retest according to the present invention and the evaluation of the results may not exactly correspond to the results obtained by the technician reviewing whether or not the retest is actually necessary, but the present invention The burden on the operator and the burden on the technician can be reduced, and more reasonable reexamination necessity determination logic can be obtained.

 The major reasons for the change in the evaluation of test results for such specimens are mostly due to measuring instruments or reagents. Of course, facilities that perform this type of testing routinely perform certain preliminary tasks to check for measurements or reagents, but in practice this type of useless retesting is being evaluated. Is a fact. Therefore, in Fig. 5 (a) and (b), an example was described in which a more reasonable optimization of the re-test necessity determination logic was pursued by re-examination of those determined to be re-requested. Even for the data group 940 indicated by ①, for which reexamination is not necessary, there is a possibility that there is something that needs to be judged as reexamination.

With reference to FIGS. 6 (a) and 6 (b), an example will be described in which the retest is determined to be necessary from the data group for which retest is unnecessary. FIG. 6 (a) is data showing the same initial inspection results as FIG. 5 (a). In this example, reexamination is performed on data existing near the straight line ax + by + c = 0 in the data group 940 once determined to be unnecessary for reexamination as indicated by 〇. First, the specimens in the data group indicated by X are retested because they are judged to be necessary for retesting. In this case, too, the specimen will be unsuitable as a specimen after a long period of time, so this retest should be performed as soon as the first result is obtained. In the comparison between the result of the reexamination and the result of the first initial inspection, it is assumed that most of the X-marks have changed the inspection values and have changed to below the threshold value of 950. In other words, it is evaluated that the reinspection is necessary. Then, from this distribution, it was once judged that re-examination indicated by 〇 in It can be said that the determined data is also suspicious whether the test value is correct. Therefore, in the present invention, in the data group indicated by the thick line 群 in FIG. 6 (b), the threshold value indicated by the triangle 內 surrounded by the broken line is close to the threshold value. Is corrected and judged to be a re-examination. In other words, it is recorded again as the necessity of reinspection in the reinspection necessity determination result 114.

 Specifically, in the re-test necessity determination logic optimization process 1 17, the re-test necessity judgment result 1 14 is re-examined from the change in the value obtained by comparing the re-test result with the first result among the data of the re-test necessity judgment result 1 14 Was evaluated to be appropriate, and the straight line 950 that was judged to be necessary for retesting from the distribution of the original test values that were evaluated to be appropriate for retesting was corrected to the straight line 970 shown in equation (3), It is determined again whether or not it is necessary to re-examine the past data with a straight line that has been corrected to a predetermined range. The content of the expression (3) is adopted as a modification of the judgment necessity logic recorded in the retest necessity judgment logic 116.

 a "x + b" y + c "= 0 (3)

 Again, the retest according to the present invention and the evaluation of the results may not exactly match the results obtained by the technician reviewing whether or not the original test results actually require a retest. According to the present invention, the burden on the subject and the burden on the technician can be reduced, and a more reasonable retest necessity determination logic can be obtained. Although this example is not advantageous in terms of reducing the cost of re-examination, it can be said that it is possible to realize re-examination evaluation without oversight.

 If most of the evaluation results indicate that retesting was appropriate, instead of modifying the retesting necessity determination logic and re-determining past data as described above, simply The same effect can be obtained by issuing a warning that the result of the determination that the inspection is unnecessary is suspicious.

FIG. 7 is a flowchart showing the above-described processing and the optimization processing of FIG. 5 in an organized manner. First, a test is performed on all specimens for predetermined items (step 201). This inspection result is input via the input / output interface 104 and stored in the initial inspection result 111 of the database 102 (step 202). Mochi Of course, some of these data are automatically input from the analyzer 20 and some are input manually by a laboratory technician. The necessity judgment reference value 118 and the retest necessity judgment logic 116 are read into the RAMI 03 (steps 203 and 204), and the retest necessity judgment is executed for each sample according to the retest necessity judgment logic (step 205). For the sample judged to be retested here, “retest required” is recorded in the retest necessity judgment result 114 (step 206). On the other hand, with respect to the sample determined to be unnecessary for retest, "retest not performed" is recorded in the retest execution information 112 (step 207). For the sample determined to require retesting in step 205, a retest is performed (step 208), and “retest execution” is recorded in the retest information 112 (step 209). Further, a retest result is input (step 210). Based on the magnitude of the difference between the input retest result and the initial test result, it is determined whether or not the sample really needs to be retested (step 211). Here, for the sample determined not to require retest, “retest unnecessary” is recorded in the retest necessity determination result 114 (step 213). Next, the reexamination necessity determination logic optimization processing 117 is executed with reference to the record of the reexamination necessity determination result 114 and the reexamination execution information 112 (step 214). The retest necessity logic is modified according to the result (step 215).

FIG. 8 is a flowchart showing the above-described processing and the optimization processing of FIG. 6 in an organized manner. In this case as well, the processing up to step 205 for executing the determination of the necessity of retest for each sample according to the retest necessity determination logic is the same. Here, for the sample judged to be retested, “retest required” is recorded in the retest necessity result 114 (step 206), and the retest is performed (step 208). On the other hand, for specimens that are determined to be unnecessary for retesting, the data that has been judged to be unnecessary for retesting is evaluated for how far away from the identification boundary that separates the samples that need to be retested from those that do not. (Step 220). For example, using t in Eq. (1), it is evaluated whether t ≥ 1 0.1, and if t ≥ --0.1, the determination of the necessity of retest described in Fig. 7 is executed. It is handled in the same way as the determination of "retest required" in step 205. If it is sufficiently away from the discrimination boundary, for example, t is smaller than _0.1, the processing when it is determined that "retest is unnecessary" in the processing of step 205 described in FIG. 7 is performed.

 For the sample judged as t≥10.1 in step 220, “retest required” is recorded in the retest necessity judgment result 114 (step 206). On the other hand, for the sample determined to be 0.1 times 0.1, “retest not performed” is recorded in the retest execution information 112 (step 207). For the sample determined as t≥—0.1 in step 220, retest is performed (step 208), and “retest performed” is recorded in the retest information 112 (step 209). In addition, the retest result is input (Step 210). Based on the magnitude of the difference between the input retest result and the initial test result, it is determined whether a retest is necessary (step 211). Here, for the sample determined not to require retest, “retest unnecessary” is recorded in the retest necessity judgment result 114 (step 211). Next, the reexamination necessity determination logic optimization processing 117 is executed with reference to the record of the reexamination necessity determination result 114 and the reexamination execution information 112 (step 214). The reexamination necessity determination logic is modified according to the result. (Steps 2 15). The embodiment described in FIG. 6 and FIG. 8 increases the number of retesting targets compared with the embodiment described in FIG. 5 and FIG. 7, and thus is disadvantageous in terms of simply narrowing down to those requiring retesting. However, it is advantageous from the viewpoint of preventing accidental overlooking of the retest target.

 Although an example using a linear discriminant has been described here, other retest determination methods are also applicable. For example, the same optimization can be performed for retest determination using a neural network.

Uses a network with multiple input elements for inputting test results, diagnostic information, etc., and one output element for determining the necessity of retesting. Outputs when test results and diagnostic information that require retesting are input. It is learned in advance that s is 1 and the output s is 0 when the inspection result of unnecessary data is input. And the unknown data It is determined that ^ for output S ≥ V requires retesting when input, and retesting is unnecessary when S < _V .

 V is the darkness value of the judgment, and 0.5 is set as the initial value.

 ^ 8, which is equivalent to Fig. 5 and Fig. 7, is optimized by learning the neural network using the data of re-requiring and re-requiring recorded in step 2 Can be In addition, in the case corresponding to FIG. 6 and FIG. 8, in step 220, instead of the condition of t≥—0.1, for example, s≥0.4. In this way, the detection near the discrimination boundary can be performed by detecting the inspection value when the neuura network outputs a value slightly lower than the initial value of V (0.5 in this case) (here, 0.4). The value can be determined to be a retest.

When a linear discriminant is used, as shown in Figs. 5 and 6, the boundary for determining whether or not reexamination is necessary on a plane with _X and y as axes is a straight line. In the neural network, since the discrimination boundary is a curve, more accurate retest determination can be performed.

 At present, computerization of information related to diagnosis handled in hospitals is progressing, and such computerized information is being accumulated in various hospital information systems. However, various information can be referred to in optimizing the re-test necessity logic. For example, the diagnostic information 122 records the results of a doctor's diagnosis, information on medication, and the like, and can be used to determine whether a retest is necessary. For example, even if a patient's blood glucose level is higher than normal, if the patient has already been diagnosed with diabetes, it is judged that the possibility of a measurement error is low. be able to. In addition, when the diagnosis of hyperlipidemia is made, the tendency of the test value peculiar to the type of the disease is shown, such as a high value of cholesterol and triglyceride. Therefore, by using the information on the diagnosis, it is possible to appropriately judge the possibility of measurement error.

Further, although the disease is exemplified as the information regarding the diagnosis, information other than the disease name may be used. For example, taking certain medications may result in high test values, Alternatively, for ^^ which is known to show a low value, the accuracy of the re-test necessity determination can be increased by using the medication information as the information regarding the diagnosis. Information about the stage of medical treatment, such as whether the disease name has not yet been determined, whether the disease name has been determined and the patient is undergoing treatment, and how much power has passed since the operation, may be used. Laboratory values may fluctuate significantly before the disease name is determined or immediately after surgery, etc., but after the disease name is determined and treatment is started, or after a long time has passed since surgery, After the condition is stabilized, the fluctuation of the inspection value becomes small. By using such information, it is possible to increase the accuracy of the retest necessity determination using the change from the previous value.

 In Fig. 5 and Fig. 6, for the sake of simplicity, the determination of the necessity of retesting was described as an example of a linear evaluation between two items.However, various items such as single item check, previous value check, item check, etc. Method can be extended and used. Furthermore, reference values or logical formulas for judgment were set for each gender and age, but as in the above example, when using disease names as information on diagnosis, In addition, reference values and logical expressions may be set for each disease name. The age, gender, and disease name of the examinee are read from the diagnosis information 121 as the information related to the diagnosis, and the corresponding reference values and logical formulas are used to determine whether reexamination is necessary. It can be read from the value 1 18 to determine whether a retest is necessary. In this case, the re-examination necessity logic 1 16 or the re-examination necessity reference value 1 18 is, for example, a standard value and a logical expression for each gender, age, and disease name in the format shown in Fig. 9. Record it. As described above, the re-examination necessity determination logic 1 16 and the re-examination necessity determination reference value 1 18 are represented by parameters such as reference values used for re-examination necessity determination and logical expressions describing the determination logic. Recording each time can improve the accuracy of the retest necessity determination.

If the patient's disease name is not available at the initial stage of medical treatment, for example, when the doctor's diagnosis has not been determined, as shown in Fig. 9, the retest reference value and the retest logic for `` diagnostic name undetermined '' in advance The retest necessity determination process may be performed using the retest reference value and the retest logic. In addition to the above methods, the retest reference values for all A determination using retest logic may be performed, and a retest reference value for at least one type of disease may be determined. If retest is not required in the determination using retest logic, retest may be determined to be unnecessary. In this case, the patient is likely to be a disease corresponding to the retest reference value and retest logic when it is determined that retest is unnecessary, and as a result, the retest grave value for this disease and retest logic are judged to be unnecessary. It can be considered that it was done.

 Also, when the disease name is not available, the disease candidate estimating process 124 shown in FIG. 4 is used to estimate the patient's disease name from the input test results and the like, and then correspond to the estimated disease name. The retest necessity judgment processing may be performed using the retest reference value and the retest judgment logic. In this case, if no disease candidate is output, the input test value is considered to be incorrect, and it can be determined that the sample requires retesting.

 When using medication information, record reference values and logical expressions for each type of drug, and select and use different reference values and logical expressions according to the type of drug administered to the patient. This makes it possible to judge the necessity of reexamination with high accuracy. Furthermore, it is also possible to record different reference values and logical expressions according to the operating power and the number of days elapsed, and select and use different reference values and logical expressions according to the number of days elapsed since the patient's operation. The accuracy of the retest necessity determination can be improved.

 Also, a re-test necessity judgment: As a process, a neural network that inputs the current test values, past test values, diagnostic information, etc., and outputs whether re-test is necessary or not may be used. In this case, the reexamination necessity determination logic 1 16 records parameters describing the network structure such as the number of layers of the neural network, the number of elements in each layer, etc., the connection weight value between the elements, and the like. The network is configured based on the recorded information when the necessity of reexamination is determined. When fuzzy inference is used as the reexamination necessity determination logic, the membership function used for fuzzy inference is recorded in the reexamination necessity determination logic 1 16.

Judgment of reexamination necessity ^ The result of the judgment (step 2 05) is recorded in the reexamination necessity result 1 14, but information that is the basis of the reexamination necessity result is also recorded here. Good to keep. The reason for the retest necessity judgment result is as follows: if it is determined that retest is necessary, why it was determined to be necessary, and if it was determined that retest was unnecessary, why it was determined to be unnecessary Is the information that is the basis for explaining. Reasons for determining that retesting is necessary include, for example, inspection items and values that exceeded the reference value in the single item check, inspection items and values that exceeded the reference value in the previous value check, and inter-item check. These include the logical expression that was determined to be abnormal, the test values used for the logical operation, and information on diagnosis such as the name of the disease. The basis for determining that retesting is unnecessary is based on the information that there is no abnormal value if there is no abnormal value (test value exceeding the reference value) in a single item check, for example. In addition, in the case where there is an abnormal value and a retest is unnecessary, the previous value for the test item indicating the abnormal value, or information on diagnosis such as a disease name can be used as a basis for the determination.

FIGS. 10 and 11 show screen configuration examples of displaying the inspection result and the re-examination necessity determination result on the display of the inspection client 40. In Fig. 10, on the screen 800 of the inspection client 40, the reception date and time 810, inspection order number 815, patient name 820, patient age 825, patient gender 830, An example is shown in which the patient's consultation department 835, examination status 840, presence / absence of abnormal values 845, necessity of reexamination 850, etc. is displayed in a list format. Of these, the test status 840 shows the progress of the tests by type of test: biochemical immunoassay (described as “bioimmune” in the figure) and general test (described as “general” in the figure). Is shown. In the figure, “complete” indicates that the inspection has been completed and the inspection result has been reported, and “not yet” indicates that the inspection has not been completed. A “one” indicates that no order has been placed for that type of inspection. The presence / absence of an abnormal value 8 4 5 indicates that “no J” indicates that there was no abnormal value, and “present” indicates that there was an abnormal value. If no test result has been issued yet, “one” is displayed. The necessity of reexamination 850 indicates the necessity of reexamination determined by the reexamination necessity determination processing 1 13 .If “no” indicates that there is no necessity of reexamination, "Necessary" indicates that a retest is necessary. You. If no test result is given, “one” is displayed.

 Here, the above information is displayed as a list in order of the order number, but it is also possible to extract the information according to conditions. For example, by setting conditions for specific medical departments, patient names, presence / absence of abnormal values, necessity of re-examination, and extracting only rows that satisfy the conditions, it is possible to refer to the target information efficiently. .

 In the example of the screen configuration shown in FIG. 10, by operating a mouse or a keyboard attached to the inspection client 40 and selecting one of the lines, more detailed information on the line is displayed. Fig. 11 shows a configuration example of the screen displayed at this time.

 FIG. 11 shows an example of a screen configuration on the display 800 of the inspection client 40. The screen consists of a basic patient information display area 860, an examination result display area 865, a re-examination necessity result display area 870, and a re-examination information input area 875.

 In the basic patient information display area 860, information about the patient, such as the patient ID, name, age, and gender, is displayed. In the inspection result display area 865, the current value, previous value, and previous values for each inspection item such as TP and Alb are displayed in a table format along with the inspection date. In the re-examination necessity judgment result display area 870, the judgment result on the necessity of the re-examination by the re-examination necessity judgment processing 113 is displayed, and the information as the basis for the judgment is displayed. In the reinspection execution information input area 8 7 5, the operator of the system uses the mouse, keyboard, etc. attached to the inspection client 40 to perform the reinspection (whether it was done or not). ) Can be selected and input.

The laboratory technician may refer to the test results for the sample that the system determines to need to be retested, and make a final decision as to whether the test is really necessary. If the necessary reexamination is automatically performed according to the necessity judgment result, the judgment made by the inspection technician can be omitted in many cases. In order for the inspection technician to make a decision, a re-examination necessity record that records the basis of the re-examination necessity is set. Result table By displaying the retest necessity judgment result and the basis of the retest necessity judgment in the display area 870, the technician determines which test value to focus on when making the final judgment. This allows the technician to make quick decisions.

The re-examination information entered in the re-examination information input area 875 is recorded in the re-examination information 112. The re-test necessity determination logic optimization processing 1 1 7 is the test result recorded in the initial test result 1 1 1, the re-test execution information and the re-test result 1 1 5 recorded in the re-test execution information 1 1 2 By using the rejection determination result 1 14 and the re-examination necessity determination logic 1 16 used in the re-examination necessity determination process 1 13, information is output to optimize the re-examination necessity determination logic 1 16. For example, optimize the reference values used in the conventional single-item check, previous value check, item-to-item check, etc .: ^, create a histogram of the inspection value distribution using the past inspection results recorded in the inspection result recording means. A well-known optimization method is to use a range that includes 95% of the total value around the average value as a reference range. As another method, there is a method in which the average value μ and the standard deviation σ of the inspection values are obtained, and the range (α-1ισ, + kσ) is used as a reference range. Where k is an appropriate constant. However, such a method of setting a reference range does not use information as to what kind of test value the specimen that needs to be retested is. Therefore, when re-testing is required using the reference range set by this method, samples that have been re-tested in the past are determined to be unnecessary, or samples that do not need to be re-tested need to be re-tested. In many cases. Therefore, when setting the reference range, in addition to the past inspection results, the re-test necessity judgment result indicating whether the inspection result is a force that should be re-inspected is used, and the內 It is possible to set the maximum reference range where all the test results that really needed to be retested are judged to need to be retested. By setting the reference range in this way, oversight of the test results to be re-tested is reduced, and cases where test results that do not actually need to be re-tested are judged to be re-tested are reduced. It is possible to increase the accuracy of the rejection determination. In the re-examination necessity determination process 113, when using a method other than the above, various optimal riding methods and learning methods corresponding to the respective methods may be used. For example, using the neural network as the re-test necessity judgment processing 1 1 3 ^ This is the test result 1 1 1 output The past test value to be read is used as learning data, and the re-test read from the re-test necessity judgment result 1 1 4 The information on whether or not the specimen is to be subjected to power is used as teacher data, and neural network learning can be performed. For example, when a feed-forward type network is used as a neural network, a pack propagation method can be used as a learning method.

 The retest necessity determination can be considered as a pattern recognition problem in which a pattern using a test value as a feature quantity is classified into two types, a pattern that requires retest and a pattern that does not require retest. For this reason, as the re-examination necessity determination logic 1 16, various known pattern recognition methods can be used as the re-examination necessity determination method. A variety of pattern recognition logic construction methods can be used. Therefore, for example, even when using fuzzy inference in the retest necessity decision 1 16, it is possible to optimize the inference method by using the test result and the corresponding retest necessity result. it can. In addition, by using a known pattern recognition logic construction method, it is possible to obtain an optimal logical expression by learning. In this way, by providing the initial inspection result 11 1 and the re-inspection result 1 15 and the re-inspection execution information 1 12, it is possible to optimize the re-inspection necessity determination logic as described above, The necessity determination accuracy can be improved.

 Although it has been described in FIGS. 7 and 8 that the optimal logic of the reexamination logic is always executed in the flow of the reexamination, the user of the present system inputs the reexamination necessity determination logic change. It may be executed.

Also, of course, the system operator can change the retest necessity determination logic regardless of the retest result. For example, the retest reference value or the retest logic in Fig. 9 is updated using an input device. Optimizing the retest necessity determination logic using accumulated retest execution information and test results such as retest results for samples judged to be retested or retest results for some of the samples judged not to be retested As a result, the accuracy of the retest can be improved.

Claims

The scope of the claims  1. It has a re-test necessity judgment to judge the necessity of re-test for the results of clinical laboratory test of the subject's sample (1). The specimen of the subject re-examined by the above-mentioned judgment of re-examination is re-examined, and the re-examination execution information indicating whether or not the re-examination is necessary and the result of the first examination are provided. A clinical test system, wherein a parameter of the retest necessity determination logic is corrected with reference to a retest result.  2. It has a re-test necessity determination logic for judging the necessity of a re-test with respect to a clinical test result of a subject's sample, and the re-test necessity determination logic has predetermined parameters. Means for saving, and comparing the results of each re-inspection of the plurality of specimens determined to be re-inspection by the re-inspection necessity determination logic with the corresponding saved initial inspection results. According to the means for determining whether the inspection is appropriate or not, and the distribution of the inspection results determined to be appropriate for the re-inspection, it is determined that the re-inspection is unnecessary and the re-inspection is unnecessary according to the re-inspection necessity determination theory. A clinical test system that requires re-testing of the specimens that have been used and means for giving correction instructions.  3. The means for instructing the correction instructs the correction by correcting the parameters of the retest necessity determination logic, and determining again the stored initial test result by the corrected retest necessity determination logic. 3. The clinical test system according to claim 2, wherein: 4. The clinical test system according to claim 1, wherein a different retest necessity determination logic is used depending on the type of the disease of the subject.  5. The clinical testing system according to claim 1, wherein different re-test necessity determination logics are used depending on the type of medicine the subject is taking. 6. The clinical test system according to claim 1, further comprising: a disease candidate extracting unit configured to extract a suspected disease name from the clinical test result, wherein a different retest is performed according to a type of the disease output by the disease candidate extracting unit. A clinical test system characterized by using necessity logic.