JP2008171045A - Support system and method for analyzing cause of variance - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To support effective primary analysis on the cause of variance by properly presenting a phenomenon having strong possibility of the cause of the variance even if there are a small number of cases of the same variance so as to effectively improve a clinical path. <P>SOLUTION: A causal relationship candidate is generated by a cause candidate dictionary construction means 106, and is accumulated in a cause candidate dictionary database 105. When the analysis target variance is selected through an input means 109, execution recording data of a patient wherein the analysis target variance occurs are first acquired from an electronic medical chart system through an electronic medical chart cooperation means 103. Next, in a variance cause candidate extraction means 104, the execution recording data of the patient wherein the analysis target variance occurs and the causal relationship candidate are compared, and the causal relationship candidate according to the execution recording data and having high use frequency is presented on a display means 108 as a cause candidate wherein the variance of an analysis target case occurs. Thereby, a variance cause system is materialized. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to hospital information system technology in the medical field, and more particularly to a system that supports analysis of the cause of occurrence of variance, which is a difference between a standard medical care plan and actual medical care.

  A clinical path (also called a critical path) that represents a standard treatment plan in order to improve the quality of medical care by realizing standardization of medical care in a social situation that promotes the improvement and efficiency of medical care. Is emphasized. In order to improve the quality of medical care using a clinical path, it is necessary to improve the clinical path based on the grounds extracted from the accumulated medical data. In particular, by collecting and analyzing the variance that is the difference between the standard treatment plan described in the clinical path and the actual treatment, it is possible to create a clinical path with low occurrence frequency and high medical effect. It is considered. Specifically, from the viewpoints of length of stay, treatment results, cost, etc., we extract variances from standard treatment plans and treatment practices that are different from the clinical outcomes and outcomes that are clinically desirable outcomes. Perform analysis. As a method of collecting and analyzing variances, a discharge variance method, a gateway variance method, a sentinel method, and an all variance method have been proposed (“Patent Document 1”). Among them, the all variance method is a method that analyzes the difference between all clinical practice and outcomes described in the clinical path in order to analyze the variance in detail, and the improvement effect of the clinical path is considered to be remarkable. It has been. With the spread of electronic medical records, it has become possible to collect a large amount of data, and expectations for realizing all variance analysis are increasing. In particular, there is an increasing expectation for realizing the cause analysis of the occurrence of variance, which is considered to have a high clinical path improvement effect. The reason for this is that, in the method of manually performing the cause analysis of variance that is widely performed at present, there are many cases in which only a superficial cause of occurrence of variance can be found.

  Next, a conventional example related to a system that supports variance analysis and creation of a clinical path with low occurrence frequency and high medical effect will be described. In the method (conventional example 1) described in “Non-Patent Document 1”, first, a specific event such as surgery or movement from an ICU (Intensive Care Unit) to a general ward is set in advance. Next, the occurrence frequency of the variance sliced variously according to the occurrence factor of the variance for the set event is displayed in a graph. The system described in “Patent Document 1” (Conventional Example 2) is a clinically desirable outcome and target outcome for each disease name and postoperative day and criteria for determining whether the outcome has been achieved. This is an electronic medical record system equipped with a file describing a certain assessment as a database.

  Next, a conventional example related to the cause analysis of a certain event other than medical treatment will be shown. The system described in “Patent Document 2” (Conventional Example 3) is a means for classifying disaster cases registered by a user into typical, similar, special, or research cases and registering them in a database in a predetermined data format. And occupational accidents with root cause investigation means for users to investigate the root cause of accidents by classifying factors related to the direct cause of occupational accidents into `` equipment '', `` work method '', `` person '', `` management '' Is a safety design support system for The root cause investigation method includes a list of factors related to the direct cause of occupational accidents and a list of direct causes most relevant to the case when a typical accident case corresponding to the case is selected. It features a direct cause presentation means that outputs in order of importance.

Variance Management System (Bing Net Press) pp.26-27, pp.41-42 JP 2004-86506 A JP 2004-318845 A

  In the variance analysis in the prior art, emphasis was placed on the collection and management of variance. For this reason, the variance analysis method for the purpose of creating and improving a clinical path with low occurrence frequency and high medical effect has not been sufficiently considered. In particular, efficient analysis of the cause of the variance was not considered. Further, in the case of all variance analysis, there are a large number of cause candidates for occurrence of variance, so that even if all variances are acquired, there is a problem that much labor is required for the analysis. Furthermore, when there are few cases where the variance has occurred, in order to analyze the cause of the occurrence, it is necessary to refer to the results of the variance analysis of similar cases, so a lot of experience is required.

  Conventional Example 1 is limited to grasping the occurrence status of variance, and in order to formulate countermeasures for the generated variance, it is necessary to further examine individual cases. Moreover, attention is paid to the frequency of occurrence in grasping the status of variance. Therefore, another approach, such as comparing the impact on treatment outcomes and length of hospital stay, was needed to find a significant variance that was less frequent but could lead to death. Conventional example 2 focuses on the collection of variances for quantitative variance analysis, but the collected variance analysis method has not been sufficiently studied. Also, it does not take into account that the number of objects of variance analysis such as all variance analysis becomes enormous.

  Also, in the conventional example 3 in which the cause analysis of an event other than medical treatment in the prior art is mentioned, the user selects a typical disaster case highly related to the analysis target case and uses a keyword group such as “why”. The root cause of disaster cases is investigated by repeatedly asking questions. However, it is necessary for the user to select typical disaster cases that are highly relevant in advance, and no reduction of analysis load is mentioned.

  As described above, in order to effectively analyze a large amount of collected variances and efficiently analyze the cause of occurrence of variances that have a high clinical path improvement effect, the above-described conventional example can obtain a sufficient effect. It was difficult.

  Therefore, an object of the present invention is to generate a variance that supports the appropriate extraction of candidates for the cause of occurrence of the variance even if there are few cases of the same variance from the implementation information and the history of the cause analysis performed in the past. The purpose is to provide a cause analysis support system.

  In order to achieve the above object, a variance occurrence cause analysis support system according to the present invention is a variance occurrence cause analysis support system for analyzing a cause of occurrence of variance, which is a difference between a clinical path and an actual medical treatment. Means and a processing device, and the processing device cooperates with an electronic medical record system having an electronic medical record database in which execution record data describing a history of medical practice performed on a patient and a progress record relating to a patient state is stored. A causal result obtained by adding a frequency of use of the history data to the history data of the variance occurrence cause analysis composed of a combination of the results of the electronic medical record linking means and the result of the variance taken in through the input means. Cause candidate dictionary construction means for generating a cause candidate dictionary for accumulating relation candidates; and The implementation record data possessed by the patient having the analysis target variance selected through the force means is acquired through the electronic medical record linkage means, and the implementation record data and the cause candidate dictionary are compared, and the implementation record data is obtained. Variance cause candidate extraction means for extracting the causal relationship candidate that matches and uses the frequency of use as a cause candidate evaluation value and that has a high cause candidate evaluation value as a cause candidate in which the variance of the analysis target case has occurred, and the display means Is characterized by displaying the causal relationship candidates.

  In addition, the processing apparatus includes a correlation generation unit that generates a correlation including a variance in a conclusion part from the execution record data by correlation analysis, and the variance cause candidate extraction unit is selected through the input unit. Compared with the implementation record data of the patient having the analysis target variance, the cause candidate dictionary or the correlation, and matches the implementation record data, and causes the use frequency or the certainty of the correlation The causal relationship candidate having a high cause candidate evaluation value as a candidate evaluation value is extracted as a cause candidate in which the variance of the analysis target case has occurred.

  In addition, the processing device, the path similarity that is the similarity of the clinical path that is a standard medical care plan stored in the electronic medical record database,

Path similarity calculation means for calculating from the above, the variance cause candidate extraction means calculates a cause candidate evaluation value from the path similarity and the usage frequency, and the cause of the occurrence of variance using the cause candidate evaluation value It is characterized by extracting as a candidate.

  Further, the variance cause candidate extraction means has a hierarchical structure generation means for sequentially generating a hierarchical structure table describing a hierarchical structure of the causal relationship of variance from the cause candidates extracted by the variance cause candidate extraction means. The hierarchical structure generation means compares the result related to the cause candidate variance and the cause of the result of the hierarchical structure table, and if the result matches the result of the hierarchical structure table, the causal relationship candidate is As a child node of a causal relationship candidate having the result of the hierarchical structure table, a new causal relationship candidate is accumulated in the hierarchical structure table. A new child node of the variance is stored in the hierarchical structure table.

In addition, the processing device generates an arrow for displaying each record of the hierarchical structure stored in the hierarchical structure table at the beginning, and at the end of the generated arrow, the record of the parent node of the record is started. In order to achieve the above object, the method for analyzing the cause of occurrence of variance according to the present invention is obtained from electronic medical chart data. Processing means using a cause candidate dictionary that accumulates causal relationship candidates to which usage frequency, which is frequency information of the history data, is added from history data of variance occurrence cause analysis configured from combinations of causes of the results of variance However, the record data concerning the patient having the analysis target variance selected by the input means is stored in the electronic medical record database. The causal relationship candidate that matches the execution record data and has a high cause candidate evaluation value as the use frequency and the cause candidate evaluation value is compared with the execution record data and the cause candidate dictionary. And a step of extracting as a cause candidate in which the variance of the analysis target case has occurred, and the display means displays the extracted cause candidate.

  Further, using the correlation table in which a correlation including a variance is generated in the conclusion part by correlation analysis from the execution record data, the processing means compares the execution record data with the cause candidate dictionary or the correlation. The causal candidate having a high cause candidate evaluation value with the use frequency or the certainty of correlation as the cause candidate evaluation value that matches the execution record data, and the cause candidate for which the variance of the analysis target case has occurred It has the process of extracting as.

  Further, the processing means calculates a path similarity that is a similarity of clinical paths stored in the electronic medical record data database,

A cause candidate evaluation value is calculated from the path similarity and the use frequency, and extracted as a cause candidate having a variance using the cause candidate evaluation value.

  Further, the processing means has a step of sequentially generating a hierarchical structure table describing a hierarchical structure of causal relationships of variances from the extracted cause candidates, and the results related to the cause candidate variances and the hierarchy When the cause of the result of the structure table is compared with the result of the hierarchical structure table, the causal relationship candidate is set as a child node of the causal relationship candidate having the result of the hierarchical structure table. If the result is stored in the structure table and does not match the result of the hierarchical structure table, the causal relationship candidate is newly stored in the hierarchical structure table as a child node of the variance captured through the input means. It is characterized by.

  Further, the processing means uses the hierarchical structure table to construct the causal relation from the cause candidates, and the display means displays the causal relation together with the cause candidates.

  According to the present invention, variance occurrence cause analysis that supports the appropriate extraction of candidates for occurrence causes of variance even if there are few cases of the same variance from the implementation information and the history of occurrence cause analysis conducted in the past. It becomes possible to provide a support system.

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

  FIG. 1 is a configuration diagram of an electronic medical record system and a variance occurrence cause analysis support system according to the present invention. The electronic medical chart system shown in FIG. 1 includes an electronic medical chart input / output means 100, an electronic medical chart control means 101, and an electronic medical chart database 102. The variance occurrence cause analysis support system includes an electronic medical record linkage unit 103, a variance cause candidate extraction unit 104, a cause candidate dictionary database 105, a cause candidate dictionary construction unit 106, a screen configuration processing unit 107, a display unit 108, It comprises input means 109.

  The hardware configuration of this configuration will be described. FIG. 2 shows a hardware configuration diagram for realizing the variance occurrence cause analysis support system. The electronic medical record database 102 includes an HDD (Hard Disk Drive) device 2014 and the like. Similarly, the cause candidate dictionary database 105 includes an HDD device 2024 and the like. The electronic medical chart control unit 101 can realize various processes by developing and starting a predetermined program in the central processing unit 2013, the memory 2012, and the like. Similarly, the electronic medical record linkage unit 103, the variance cause candidate extraction unit 104, the cause candidate dictionary construction unit 106, and the screen configuration processing unit 107 are expanded and activated by a predetermined program in the central processing unit 2023, the memory 2022, or the like. Various processes can be realized. The display means 108 can be realized by a monitor using a liquid crystal display 2021 or a CRT (Cathode-Ray Tube). The input unit 109 can be realized by a keyboard 2020, a mouse, or a pen tablet. Similarly, the electronic medical record input / output means 100 can be realized by a liquid crystal display 2011, a keyboard 2010, and the like.

  Hereinafter, each component will be described in more detail with a focus on the flow of processing in the variance cause candidate extraction unit 104 which is the most important component of the present invention.

  The variance cause candidate extraction unit 104 extracts a cause candidate in which the noted variance has occurred from the results of variance analysis performed by the user in the past. FIG. 3 shows a flowchart in which the variance cause candidate extraction unit 104 extracts variance cause candidates and displays them on the display unit 108. First, the execution record data relating to the patient in which the analysis target variance selected through the input unit 109 is generated is acquired through the electronic medical record link unit 103 (S301). The execution record data and the electronic medical record link means 103 will be described later. Next, when the user presses the analysis candidate extraction button via the input unit 109 (S302), the cause candidate dictionary database stored in the candidate patient implementation action and outcome acquired in S301 and the cause candidate dictionary database 105 is displayed. Comparison is made and extracted as a candidate group of causes of the analysis target variance (S303). In the extraction, a causal relationship that is frequently used in the cause candidate dictionary database is extracted. The cause candidate dictionary database will be described later. Finally, the constructed causal relationship is displayed on the display unit 108 via the screen configuration processing unit 107 (S304). Among these processes, the extraction of the cause group of the analysis target variance (S303) will be described in detail later.

  Here, the execution record data and the electronic medical record link means 103 will be described. The electronic medical record linkage unit 103 acquires master data and execution record data from the electronic medical record system. FIG. 4 shows an implementation record table representing implementation record data stored in the electronic medical record database 102 and a patient table representing patient basic information. The execution record data is data relating to a history of medical practice performed on a patient, a progress record regarding the patient state, and the like. In the implementation record table, data on the date when the medical practice was performed for each patient and the variances that occurred were recorded.

  Next, the cause candidate dictionary table will be described. The cause candidate dictionary table is a table that describes the frequency of use of the causal relationship between events such as medical practice and patient status based on the results of previous analysis of variance by the user. FIG. 5 shows a causal candidate dictionary table and a causal candidate detail table. The causal candidate detail table describes a causal relationship between events such as medical practice and patient condition. For example, it is shown that the cause of the bleeding is when the removal of the sheath and the insertion of the catheter fail. The causal candidate dictionary table describes the frequency of using the causal relationship described in the causal candidate detail table when the user analyzed the variance in the past. In this example, it is shown that, in various variances that occurred in the past, there were 17 cases in which the causal candidate group in the causal candidate detail table has a causal relationship represented by “bleeding 1”.

  FIG. 6 shows an occurrence cause table that is a table in which the results of analysis of variances by the user are accumulated. In this example, a case where a variance of “bleeding” occurs for a medical practice of “puncture” is analyzed. The node ID represents a causal relationship. For example, it describes that the causes of “bleeding” are “natural removal of sheath” and “catheter insertion failure”.

  Next, extraction of a candidate group of causes for analysis target variance (S303) will be described in detail. FIG. 7 shows a detailed flowchart of the extraction of candidate groups for analysis target variance (S303). In this flowchart, first, the analysis target variance is substituted as the target item array (S701). Next, the next processing is performed until a predetermined number of times (MAX) is reached (S703-S707). First, a record having a result knowledge condition that matches the target item array is acquired from the causal candidate detail table (S703). Next, from the acquired record, a record having a cause knowledge condition that matches the action or outcome of the patient of interest is added to the temporary candidate table having the same data structure as the causal candidate detail table (S704). Next, the record with the highest use frequency is added to the cause candidate group table from the records stored in the temporary candidate table and stored (S705).

  FIG. 8 shows a cause candidate group table. The cause candidate group table describes the cause of occurrence of the extracted analysis target variance. In this example, the cause of the occurrence of the variance “with hematoma” is “catheter insertion failure” and “natural sheath removal”, and the cause of the “catheter insertion failure” is “no real-time US guide” and “decreased deep body temperature” It shows how it is. Finally, the cause knowledge condition of the record stored last in the cause candidate group table is substituted as the target item array (S706). By using the temporary candidate table, it is not necessary to perform an alignment process on the usage frequency for all records in the causal candidate dictionary table when extracting a causal relationship having a high usage frequency in the causal candidate dictionary table. Therefore, it is possible to reduce the amount of calculation related to the extraction of causal relationships that are frequently used. Moreover, it becomes possible to add an appropriate record required for a temporary candidate table from a causal candidate dictionary table by an attention item arrangement | sequence.

  The configuration processing unit 107 configures a screen layout for analyzing the cause of occurrence of the variance, transfers the data to the display unit 108, and acquires the information captured through the input unit 109.

  Next, the screen layout presented on the display means 108 will be described. FIG. 9 is an example of a screen layout. This example includes a variance analysis target unit 901 and a variance occurrence cause presentation unit 902. Here, an example of screen operation will be described. In the variance analysis target unit 901, when a patient to be analyzed and a variance are selected and the analysis button is pressed, an occurrence cause analysis result is constructed in the variance occurrence cause presentation unit 902 according to the flowchart shown in FIG. In FIG. 9, the cause of the occurrence of the variance “had hematoma” is displayed in a list format.

  By automatically constructing and presenting the cause of occurrence of variance in this way, even an unfamiliar user can perform variance analysis. In addition, the results of variance analysis in the past can be effectively reused.

  FIG. 10 is a configuration diagram of a variance occurrence cause analysis support system according to the present invention. In particular, in order to add knowledge about specific medical treatment, patient status, variance, etc. when a variance occurs to a candidate for occurrence of variance, a correlation generation unit 110 is newly added to the configuration diagram shown in FIG. is there. The correlation generation unit 110 can implement various processes by developing and starting a predetermined program in the central processing unit 2023 and the memory 2022 shown in FIG.

  FIG. 11 shows an example of a table indicating knowledge generated by the correlation generation unit 110. In this embodiment, an event having a high correlation with the occurrence of a variance of “bleeding” with respect to the medical practice of “puncture” is recorded as a correlation rule, and two correlation rules are shown. The first one shows that the certainty of the correlation rule that “bleeding” occurs when a patient who is “65 years old or older” and “Balun insertion” is performed is 80%. The second indicates that the certainty of the correlation rule that “bleeding” occurs in a case of “insufficiently fixed sheath” and “many position fluctuation” is 90%.

  Next, processing of the variance occurrence cause candidate extraction unit 104 using the knowledge generated by the correlation generation unit 110 will be described. FIG. 12 is a flowchart in which the extraction of the candidate group of causes for the analysis target variance (S303) in the flowchart shown in FIG. 3 is detailed. In this flowchart, first, the variance to be analyzed is substituted as the target item array (S1201). Next, the next processing is performed until a predetermined number of times (MAX) is reached (S1203 to S1207). First, a record having a result knowledge condition that matches the target item array is acquired from the correlation table (S1203). Next, from the acquired record, a record having a cause knowledge condition that matches the action or outcome of the patient of interest is added to the temporary candidate table having the same data structure as the causal candidate detail table (S1204). Next, the record having the highest certainty factor is added to the cause candidate group table from the records stored in the temporary candidate table and stored (S1205). Finally, the cause knowledge condition of the record stored last in the cause candidate group table is substituted as the target item array (S1206).

  As described above, by using knowledge about a specific medical practice, patient condition, variance, etc. at the time of occurrence of variance, it becomes possible to search for an appropriate occurrence cause candidate even when there is not enough data in the causal candidate dictionary table. .

  FIG. 13 is a configuration diagram of a variance occurrence cause analysis support system according to the present invention. In particular, when the number of cases is small, the path similarity calculation unit 111 is newly added to the configuration diagram shown in FIG. 10 in order to enable the use of variance analysis of similar cases. The path similarity calculation unit 111 can realize various processes by developing and starting a predetermined program in the central processing unit 2023 and the memory 2022 shown in FIG.

  FIG. 14 shows a flowchart in which the variance cause candidate extraction unit 104 extracts the variance cause candidates and displays them on the display unit 108. In particular, in order to calculate a similar case, a process (S1402) of acquiring a record including the path of the patient of interest from the path similarity table is added to the flowchart of FIG. The path similarity table describes the similarity between clinical paths as shown in FIG. Here, the similarity between clinical path P1 and clinical path P2

に示す計算式を用いて算出する。パス類似度テーブルから着目患者のパスを含むレコードを取得する処理（Ｓ１４０２）を追加したため、分析対象バリアンスの原因候補群の抽出（Ｓ１４０４）の詳細なフローも異なる。

It is calculated using the calculation formula shown below. Since a process (S1402) for acquiring a record including the path of the patient of interest from the path similarity table is added, the detailed flow of extracting the candidate group of causes for analysis target variance (S1404) is also different.

  Therefore, extraction of the candidate group of analysis target variance causes (S1404) will be described in detail. FIG. 16 shows a detailed flowchart of extraction of a candidate group for analysis target variance (S1404). In this flowchart, first, the analysis target variance is substituted as the target item array (S1601). Next, the next processing is performed until a predetermined number of times (MAX) is reached (S1603-S1608). First, a record having a result knowledge condition that matches the target item array is acquired from the causal candidate detail table (S1603). Next, from the acquired record, a record having a cause knowledge condition that matches the action and outcome of the patient of interest is added to the temporary candidate table (S1604). Next, the cause candidate evaluation value of the record newly added to the temporary candidate table is calculated from the use frequency and the path similarity (S1605). Specifically, the cause candidate table value is the sum of squares of the usage frequency and the path similarity. Next, the record having the highest cause candidate evaluation value is added to the cause candidate group table from the records stored in the temporary candidate table and stored (S1606). Finally, the cause knowledge condition of the record stored last in the cause candidate group table is substituted as the target item array (S1607). By using the temporary candidate table in this way, it is possible to reduce the cause candidate evaluation value calculation process even when the occurrence cause candidates are extracted in consideration of the path similarity.

  In this way, by extracting candidate causes that take into account the similarity of the path, even if the number of cases is small, it is possible to use the variance analysis of similar cases, so even users with little analysis experience can search for the cause of the occurrence of variance. It becomes possible to do.

  FIG. 17 is a configuration diagram of a variance occurrence cause analysis support system according to the present invention. In particular, in order to construct a causal relationship hierarchical structure in which the analysis target variance has occurred, a hierarchical structure generating means 112 is added to the configuration diagram shown in FIG. The hierarchical structure generation unit 112 can realize various processes by developing and starting a predetermined program in the central processing unit 2023 and the memory 2022 shown in FIG.

  FIG. 18 shows a flowchart in which the variance cause candidate extraction unit 104 extracts the variance cause candidates and displays them on the display unit 108. In particular, in order to construct a causal relationship hierarchical structure, a process (S1805) of constructing a causal relationship hierarchical structure from the cause candidate group has been added to the flowchart of FIG.

  Here, the construction of the causal relationship hierarchical structure (S1805) will be described in detail. FIG. 19 shows a detailed flowchart of the construction of the causal relationship hierarchical structure (S1805). The purpose of this flowchart is to automatically create a hierarchical structure table having the same data structure as the occurrence cause table shown in FIG. In this flowchart, it is determined whether or not the root cause text of the hierarchical structure table that matches the result knowledge condition of the extracted record exists for all the records in the cause candidate group table generated based on the flowchart shown in FIG. . If it exists, the cause knowledge condition of the extracted record is registered in the occurrence cause candidate table as a child node of the record of the root cause text. If it does not exist, the cause knowledge condition of the extracted record is registered in the hierarchical structure table as a child node of the analysis target variance. By this processing, it is possible to generate a hierarchical structure of the causal relationship in which the variance occurs, and to search for the root cause of the variance.

  Here, two examples of the screen layout presented on the display unit 108 will be described.

  FIG. 20 is a first example of a screen layout. This example includes a variance analysis target unit 2001 and a variance occurrence cause analysis construction unit 2002. Here, an example of screen operation will be described. When the patient and the variance to be analyzed are selected in the variance analysis target unit 2001, the cause analysis result is presented to the variance generation cause analysis construction unit 2002 according to the flowchart shown in FIG. In FIG. 20, the same content described in the characteristic factor diagram on the right side of the figure is displayed on the left side of the figure in the form of a tree structure. By automatically constructing and presenting the cause of occurrence of variance in this way, even an unfamiliar user can perform variance analysis.

  FIG. 21 is a second example of the screen layout. This example includes an implementation data presentation unit 2101 and a variance occurrence cause analysis construction unit 2102. Here, an example of screen operation will be described using the flowchart of FIG. The flowchart of FIG. 22 is obtained by adding highlight processing (S2206, S2207) to the flowchart of FIG. When the highlight button in the execution data presentation unit 2201 is pressed, the cause of occurrence of the variance constructed by the variance occurrence cause analysis construction unit 2202 is highlighted in the implementation data of the patient of interest. As a result, it is possible to automatically extract the cause of occurrence from the enormous amount of implementation data of the patient who is paying attention, so that the labor of variance analysis can be reduced.

  As a result, it is possible to efficiently search for the cause of the occurrence of variance from an enormous amount of data. Moreover, the root cause analysis of variance can be effectively performed by the hierarchical structure of causal relationships. By grasping the cause of the occurrence in this way, it is considered that an improvement to a clinical path with low occurrence of variance and high medical effect can be realized.

1 is a first configuration diagram of a variance occurrence cause analysis support system according to the present invention. FIG. It is a hardware block diagram of the variance generation cause analysis support system in this invention. It is a first flowchart regarding a variance occurrence cause analysis support system in the present invention. It is a figure showing the implementation record table in an electronic medical chart system in this invention. It is a figure showing a cause candidate dictionary table in this invention. It is a figure showing the cause table in this invention. It is a 1st flowchart regarding the variance cause candidate extraction means in this invention. It is a figure showing a cause candidate group table in this invention. It is a 1st example which shows the screen in the variance generation cause analysis support system in this invention. It is a 2nd block diagram of the variance generation cause analysis support system in this invention. It is a figure showing a correlation table in this invention. It is a 2nd flowchart regarding the variance cause candidate extraction means in this invention. It is a 3rd block diagram of the variance generation cause analysis support system in this invention. It is a 3rd flowchart regarding a variance generation cause analysis support system in this invention. It is a figure showing a path table and a path similarity table in this invention. It is a 3rd flowchart regarding the variance cause candidate extraction means in this invention. It is a 4th block diagram of the variance generation cause analysis support system in this invention. It is a 4th flowchart regarding a variance generation cause analysis support system in the present invention. It is a flowchart regarding the hierarchical structure production | generation means in this invention. It is a 2nd example which shows the screen in the variance generation cause analysis support system in this invention. It is a 3rd example which shows the screen in the variance generation cause analysis support system in this invention. It is a 5th flowchart regarding a variance generation cause analysis support system in the present invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 ... Electronic medical record input / output means, 101 ... Electronic medical record control means, 102 ... Electronic medical record database, 103 ... Electronic medical record cooperation means, 104 ... Variance cause candidate extraction means, 105 ... Cause candidate dictionary database, 106 ... Cause candidate dictionary construction means 107 ... Screen configuration processing means, 108 ... Display means, 109 ... Input means, 110 ... Correlation generation means, 111 ... Path similarity calculation means, 112 ... Hierarchical structure generation means, 2010 ... Keyboard, 2011 ... Display, 2012 ... Memory, 2013 ... Central processing unit, 2014 ... HDD device, 2020 ... Keyboard, 2021 ... Display, 2022 ... Memory, 2023 ... Central processing unit, 2024 ... HDD device, 901 ... Variance analysis target unit, 902 ... Variance occurrence cause presentation unit , 2001 ... Variance analysis target part 2002 ... variance cause analysis construction unit, 2101 ... implemented data presentation unit, 2102 ... variance cause analysis construction unit.

Claims (10)

A variance occurrence cause analysis support system for analyzing a cause of occurrence of variance that is a difference between a clinical path and an actual medical treatment, comprising an input means, a display means, and a processing device,
The processor is
An electronic medical record linking means that cooperates with an electronic medical record system having an electronic medical record database in which an execution record data describing a history of medical practice performed on a patient and a progress record regarding a patient state is stored;
Causes of accumulating causal relationship candidates to which usage frequency, which is frequency information of the history data, is added from the history data of the variance occurrence cause analysis configured from the combination of the causes of the results as a result of the variance captured through the input means. A cause candidate dictionary construction means for generating a candidate dictionary;
The implementation record data possessed by the patient having the analysis target variance selected through the input means is acquired via the electronic medical record linkage means, the implementation record data is compared with the cause candidate dictionary, and the implementation record is compared. Variance cause candidate extraction means for extracting the causal relationship candidate that matches the data and has a high cause candidate evaluation value as the cause candidate evaluation value as the cause candidate evaluation value as a cause candidate in which the variance of the analysis target case has occurred,
The display means displays the cause-and-effect relationship candidates, and the variance occurrence cause analysis support system. The variance generation cause analysis support system according to claim 1, wherein the processing device includes:
Correlation generating means for generating a correlation including a variance in a conclusion part by correlation analysis from the implementation record data,
The variance cause candidate extraction unit compares the execution record data of the patient having the analysis target variance selected through the input unit with the cause candidate dictionary or the correlation, and matches the execution record data. The causal relationship candidate having a high cause candidate evaluation value with the use frequency or the certainty of correlation as the cause candidate evaluation value is extracted as a cause candidate in which the variance of the analysis target case has occurred. Variance generation cause analysis support system. The variance generation cause analysis support system according to claim 1, wherein the processing device includes:
A path similarity which is a similarity of a clinical path which is a standard medical care plan accumulated in the electronic medical record database,

Path similarity calculation means for calculating from
The variance cause candidate extraction means calculates a cause candidate evaluation value from the path similarity and the usage frequency, and extracts the cause candidate evaluation value as a cause candidate that caused a variance using the cause candidate evaluation value Analysis support system. The variance occurrence cause analysis support system according to any one of claims 1 to 3,
The variance cause candidate extraction means has a hierarchical structure generation means for sequentially generating a hierarchical structure table describing a hierarchical structure of a causal relationship of variance from the cause candidates extracted by the variance cause candidate extraction means,
The hierarchical structure generation means compares the result related to the cause candidate variance and the cause of the result of the hierarchical table,
When the result of the hierarchical structure table matches, the causal relationship candidate is newly accumulated in the hierarchical structure table as a child node of the causal relationship candidate having the result of the hierarchical structure table,
If the result does not match the result of the hierarchical structure table, the cause-cause relationship candidate is newly accumulated in the hierarchical structure table as a child node of the variance captured through the input means. Support system. In the variance occurrence cause analysis support system according to claim 4,
The processing device generates an arrow that displays each record of the hierarchical structure stored in the hierarchical structure table at the beginning, and displays the record of the parent node of the record at the end of the generated arrow. A variation occurrence cause analysis support system comprising a screen for displaying an arrow to be displayed and displayed on the display means. It is a method for analyzing the cause of the occurrence of variance, which is the difference between the clinical path and the actual medical treatment,
Causes of accumulation of causal relationship candidates to which usage frequency, which is frequency information of the history data, is added from history data of variance occurrence cause analysis composed of combinations of the causes of the results as a result of variance captured from electronic medical record data Use candidate dictionary,
Processing means
A step of acquiring from the electronic medical record database execution record data relating to a patient in which the analysis target variance selected by the input means has occurred, comparing the execution record data with the cause candidate dictionary, and matching the execution record data, And the causal relationship candidate having a high cause candidate evaluation value as the use frequency and cause candidate evaluation value is extracted as a cause candidate in which the variance of the analysis target case has occurred,
A cause analysis method of variance occurrence, wherein the display means displays the extracted cause candidates. It is the generation | occurrence | production cause analysis method of the variance of Claim 6, Comprising:
From the implementation record data, using a correlation table that generates a correlation including variance in the conclusion part by correlation analysis,
The processing means compares the execution record data with the cause candidate dictionary or the correlation, matches the execution record data, and uses the frequency of use or the certainty of the correlation as a cause candidate evaluation value. A method for analyzing a cause of occurrence of variance, comprising a step of extracting a cause-and-effect candidate having a high cause candidate evaluation value as a cause candidate for which the variance of the analysis target case has occurred. The variance cause analysis method according to claim 6, wherein the processing means includes:
A path similarity that is a similarity of a clinical path stored in the electronic medical record data database,

A step of calculating from
A cause-of-cause evaluation value is calculated from the path similarity and the use frequency, and is extracted as a cause candidate for occurrence of variance using the cause candidate evaluation value. The variance cause analysis method according to claim 6, wherein the processing means includes:
A step of sequentially generating a hierarchical structure table describing a hierarchical structure of a causal relationship of variance from the extracted cause candidates;
The result related to the variance of the cause candidate is compared with the cause of the result of the hierarchical structure table, and if the result matches the result of the hierarchical structure table, the causal relationship candidate has the result of the hierarchical structure table As a child node of a causal relationship candidate, newly accumulated in the hierarchical structure table, and when the result does not match the result of the hierarchical structure table, the causal relationship candidate is used as a child node of a variance captured through the input unit, A method for analyzing a cause of occurrence of variance, which is newly accumulated in the hierarchical structure table.   10. The variance occurrence cause analysis method according to claim 9, wherein the processing means uses the hierarchical structure table to build the causal relationship from the cause candidates, and the display means displays the causal relationship together with the cause candidates. A method for analyzing the cause of occurrence of variance, characterized by displaying.

Images