JP2011100368A - Clinical path improvement plan presentation system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a clinical path improvement plan presentation system that presents effective improvement plans for a clinical path, in order to improve the clinical path that provides a high treatment effect while the frequency of variances is low. <P>SOLUTION: An individual case analysis result construction means 104 uses data in an electronic medical chart database 102, to construct individual case analysis results hierarchically describing the causes of variances for each case where variance has occurred. A similar case extraction means 107 extracts, focusing on the hierarchical similarities of the individual case analysis results, a previous variance analysis case similar to the current variance. A clinical path improvement history for solving the extracted variance analysis case is extracted and displayed in an output means 109. In this way, the clinical path improvement plan presentation system is provided. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to hospital information system technology in the medical field, and more particularly to a system for presenting a clinical path improvement plan that is a standard medical care plan.

  In a social situation that promotes the improvement and efficiency of medical quality, clinical paths (standard path and path) that represent standard medical care plans to realize standardization of medical care and improve medical quality. Called). 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., analysis was performed by extracting as a variance the treatments that were different from the standard treatment plan and the clinically desirable outcomes and outcomes that were not achieved. I do.

  Here, a conventional example related to general variance analysis is shown. 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.

  Next, a conventional example related to a system that supports the creation of a clinical path with high accuracy of adaptation to a patient will be described. In the method described in “Non-Patent Document 2” (conventional example 2), the variance analysis is regarded as a critical path improvement method, a countermeasure is determined in advance for each cause of variance, and the improvement proposal is shortened. I am trying. In the method described in “Patent Document 1” (Conventional Example 3), a temporary path in which a treatment action set in medical performance data is set as a treatment action schedule, and a treatment action acquired based on a patient identifier are obtained. In this system, a temporary path whose degree of coincidence exceeds a predetermined standard is registered as the critical path.

  Next, a conventional example related to the factor analysis in which the variance is generated will be shown. The method described in “Patent Document 2” (conventional example 4) is a system that presents options for the assumed factor when the medical schedule data deviates from the schedule. The user selects an assumed factor from choices or inputs it as a comment. This eliminates the need to prepare all possible factors as options.

Variance Management System (Bing Net Press) pp.26-27, pp.41-42 Recent Progress in Critical Path 2008 (Jiho) pp.93-102 JP 2007-265080 A JP 2005-182362 A

  The problems of the variance analysis and the clinical path analysis in the prior art will be described. In the conventional variance analysis, although the variance analysis is regarded as a critical path improvement method, there is no mention of a specific method. This is because the points to be improved and the improvement measures differ greatly depending on the contents of the variance and the frequency of occurrence. Therefore, in order to realize improvement of clinical path with high medical effect, abundant experience was necessary.

  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. In Conventional Example 2, about 10 types of countermeasures are determined in advance for each cause of occurrence of variance, but there are about 100 types of clinical paths operated in hospitals, and the contents of variances are even more diverse. Extensive experience was necessary to consider improvement measures.

  In Conventional Example 3, it is possible to create a clinical path with high matching accuracy based on performance data. However, a wealth of experience was required to support treatment methods with better treatment results than results data.

  In Conventional Example 4, it is possible to add an input comment as a new option even if all possible factors of variance are not prepared as options in advance, and it is easy to prepare options considered necessary It is possible. However, the analysis method of variance and clinical path using the input factors has not been sufficiently examined. In addition, it is possible to select the direct cause of the variance, but the analysis of the root cause such as the structural problem in which the variance has occurred has not been sufficiently examined.

  As described above, it is difficult to obtain a sufficient effect in the above-described conventional example in order to realize an improvement to a clinical path with a high medical effect. For example, detailed analysis of variance analysis often cannot be judged by a party, but analysis that considers the entire hospital, such as the use of improvement cases in similar cases of variances that faced and analysis that improves the quality of medical care For that, it was necessary to rely on the experience of health care workers.

  Therefore, an object of the present invention is to improve the clinical path with a low occurrence frequency and a high medical effect, extract the effective clinical path improvement history implemented in the past using the results of the variance analysis, It is to provide a clinical path improvement plan presentation system that supports the improvement of the clinical path.

  In order to achieve the above objective, the clinical path improvement plan presentation system uses the variance, which is the difference between the standard clinical plan and the actual practice, to develop a clinical path improvement plan to prevent the occurrence of variance. A system for presenting a clinical path improvement plan to be presented, comprising an input means, an output means and a processing device, wherein the input means accepts an input of a target variance, and the processing device describes a clinical path describing a standard medical plan Data, variance data recording variance, and clinical path improvement history data, which is a clinical path improvement plan, from the connected electronic medical record database, and the electronic medical record link means acquired by the electronic medical record link means From the clinical path data and the variance data, hierarchically Individual case analysis result construction means for constructing individual case analysis results describing the cause-and-effect relationship for each occurrence of variance, and past variances similar to the cause of occurrence of the target variance selected through the input means Similar case extraction means for extracting the clinical path improvement history that is extracted by focusing on the hierarchical structure similarity and prevents the occurrence of the extracted variance through the electronic medical record cooperation means, and the output means includes the output means, The clinical path improvement history extracted by the similar case extraction means is output as a clinical path improvement plan for the noted variance.

  Also, in the clinical path improvement plan presentation system, the similar case extraction means has a similarity that becomes a criterion for extracting past variances similar to the cause of occurrence of the target variance, and the similarity becomes higher as the cause of occurrence of the variance matches. In order to increase the level of similarity, the higher the proportion of pairs that constitute the cause-and-effect relationship, the higher the degree of similarity. The degree of similarity is calculated to be low, and a variance similar to the cause of occurrence of the noted variance is extracted using the similarity as an evaluation index.

  Further, in the clinical path improvement plan presenting system, the electronic medical record linking means stores a history of medical practice performed on a patient, a history of order attributes describing the type of medical practice, and a history of progress records regarding patient status. The described execution record data is acquired from an electronic medical record database, and the processing device generates a correlation rule including a variance in a conclusion part from the execution record data acquired by the electronic medical record linkage unit by correlation rule mining The individual case analysis result construction means extracts the premise part of the correlation rule generated by the correlation rule generation means as the cause of the occurrence of the variance, and the similar case extraction means extracts the correlation The order attribute in the medical practice that is a component of the premise part of the rule Extracted from Rupasudeta, a similarity which is a reference for extracting a past variance similar to cause the focused variance, and calculates as the similarity higher order attributes match increases.

  Further, in the clinical path improvement plan presenting system, the processing device includes path similarity calculation means for calculating a path similarity that is a similarity of a medical practice pattern from the clinical path data acquired by the electronic medical chart cooperation means. The similar case extraction means extracts the clinical path 1 in which the noted variance has occurred and the clinical path 2 in which the similar past variance has occurred, and serves as a reference for extracting the past variance similar to the cause of the noted variance. The similarity is calculated such that the similarity is higher as the path similarities in the clinical path 1 and the clinical path 2 match.

  Furthermore, in the clinical path improvement plan presenting system, the processing device includes a quality indicator calculating unit that calculates a quality indicator that is a numerical value of medical quality for each version of the clinical path, and the similar case extracting unit includes: The clinical path improvement history having a high quality indicator improvement effect is extracted.

  According to the present invention, aiming to improve a clinical path with low occurrence frequency and high medical effect, using the results of variance analysis, extract an effective clinical path improvement history implemented in the past, It is possible to provide a clinical path improvement plan presentation system that supports the improvement of the clinical path.

  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 clinical path improvement plan presenting 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 clinical path improvement plan presenting system includes an electronic medical record linkage unit 103, an individual case analysis result construction unit 104, an individual case analysis result database 105, a path improvement database 106, a similar case extraction unit 107, and a screen configuration processing unit 108. And an output means 109 and an input means 110.

  The hardware configuration of this configuration will be described. FIG. 2 is a hardware configuration diagram for realizing the electronic medical record system and the clinical path improvement plan presenting system according to the present invention. The electronic medical record database 102 includes an external storage device 2014 represented by an HDD (Hard Disk Drive) device. Similarly, the individual case analysis result database 105 and the path improvement database 106 are configured by an external storage 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 individual case analysis result construction unit 104, the similar case extraction unit 107, and the screen configuration processing unit 108 are expanded and activated by a predetermined program in the central processing unit 2023, the memory 2022, and the like. Various processes can be realized. The output unit 109 can be realized by a monitor using a liquid crystal display 2021 or a CRT (Cathode-Ray Tube). Further, it may be output to a medium such as paper. The input unit 110 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. Here, a diagram is shown in which the electronic medical record system and the clinical path improvement plan presentation system are configured with different hardware, but common hardware such as the keyboard 2010 and the keyboard 2020 may be realized using the same resource. .

  FIG. 3 is a flowchart showing an outline of the clinical path improvement plan presentation system. First, in order to perform root cause analysis in which a target variance, which is a variance that is not focused on, is presented to the output unit 109, an individual case analysis screen is displayed for each case where a variance has occurred via the input unit 110. All the causes of occurrence of variances are constructed as individual case analysis results by the individual case analysis result construction means 104, and the construction results are stored in the individual case analysis result database 105 (S301). Next, when the individual case analysis screen is presented to the output unit 109 in order to perform the root cause analysis of the target variance of interest, the user indicates the cause of occurrence of the variance through the input unit 110 as the individual case analysis result. The analysis result construction means 104 constructs the construction result and accumulates the construction result in the individual case analysis result database 105 (S302). Next, among the target variances analyzed in S301, a variance similar to the target variance analyzed in S302 is extracted by the similar case extraction unit 107 (S303). Next, the path improvement history in the variance extracted in S303 is extracted from the path improvement database 106 and presented to the output unit 109 (S304). The path improvement database 106 stores data related to the path improvement history acquired by the electronic medical record linkage unit 103. Details of the data acquired by the electronic medical record linkage unit 103 will be described later. The user refers to the presented path improvement history and examines the improvement plan of the target variance, and registers the examination result in the path improvement database 106 via the input unit 110 (S305). However, in this embodiment, the examination result is registered in the path improvement database 106 via the input unit 110, but may be stored in the electronic medical record database 102 via the electronic medical record input / output unit 100.

  Next, information acquired by the electronic medical record linkage unit 103 will be described. The electronic medical record linking means 103 acquires clinical path data, variance data, implementation record data, clinical path improvement history data, and patient data from the electronic medical record database 102. The implementation record data is data relating to a history of medical practice performed on a patient, a progress record regarding a patient state, basic information of a patient, and the like. Patient data is data relating to indices such as patient code, applied path name, patient name, gender, age, and length of hospital stay. Details of the execution record data will be described in Example 2, and patient data will be described in Example 4.

  Next, clinical path data will be described. The clinical path data is data in which a standard medical practice to be performed for each clinical path and a scheduled execution date are described. FIG. 4 shows a clinical path data table describing clinical path data. In this embodiment, the first day medical practice of PCI pass (version 001) is orientation with education order attribute, blood pressure confirmation with assessment order attribute, and body temperature confirmation with assessment order attribute Is shown. Next, variance data, which is data relating to variance, will be described. The variance data shown in FIG. 5 includes a variance table and a variance code master table. In the variance code master table, the variance corresponding to the medical practice in the clinical path data table and its code are written. In the variance table, the occurrence variance, the name of the patient, etc. are written for each case where the variance occurred. In the present embodiment, a state where three variances are generated in the patient P0 is shown. It also shows two cases where the fever was 38 degrees or more for the medical practice of checking body temperature. Next, clinical path improvement history data will be described. FIG. 6 shows a clinical path improvement history data table. In the present example, in the TUR-Bt pass version 001, in order to prevent the variance related to hematoma confirmation, when the version is upgraded from 001 to 002, confirmation of body temperature of 38 degrees or less and rest guidance are shown. It also shows how the Midrin P drug was changed to atropine when upgrading from 001 to 002 in the cataract path.

  Here, the analysis of individual cases (S301) (S302) will be described in detail. FIG. 7 shows a detailed processing flow. Here, for the purpose of analyzing the root cause of occurrence of variance, individual case analysis, which is analysis of variance causality, is performed for each individual case where variance occurred (S701) (S701 to S707). Specifically, the screen configured by the screen configuration processing unit 108 that receives the message from the individual case analysis result construction unit 104 is presented to the output unit 109, and the user uses the input unit 110 on the presented individual case analysis screen. The cause of the occurrence of variance is input via (S702-S705). The individual case analysis result construction unit 104 stores the result in the individual case analysis result database 105 based on the input cause of occurrence of variance (S706).

  Here, a process (S702 to S705) in which the user inputs the cause of occurrence of variance will be described. First, the individual case analysis result construction unit 104 acquires a record having a patient code corresponding to the patient index from the variance table (S702). Next, the user inputs the cause of occurrence of variance using the following two methods. In the first method, the user selects and inputs the variance acquired in S702 as the cause of occurrence of the analysis target variance (S703). In the second method, the cause of occurrence of the analysis target variance is input as text in free text (S704). These operations are repeated until all the causes of occurrence of the analysis target variance are input (S705).

  Here, the screen configuration displayed on the output means 109 in the individual case analysis S301 and S302 will be described. FIG. 8 shows the individual case analysis of the target variance in S302. The screen illustrated in FIG. 8 includes a condition setting unit 801, a save button 8011, an improvement plan presentation button 8012, and a variance occurrence cause analysis construction unit 802. First, the target variance is reflected in the condition setting unit 801 in S301 and the target variance in S302. The patient to be analyzed is presented with a patient code corresponding to the patient index set in S701. In this embodiment, a causal relationship in which a patient named P1 causes a variance of bleeding is analyzed by the variance occurrence cause analysis construction unit 802 with respect to a medical practice of confirming bleeding of the PCI path. Here, a state in which a catheter insertion failure or a variance of 38 degrees or more is registered from the variance table as the cause of occurrence of bleeding as the analysis target variance is shown. When the user presses the save button 8011 after inputting the cause of occurrence into the variance occurrence cause analysis construction unit 802 as described above, the variance causal relationship is stored in the individual case analysis result database 105.

  FIG. 9 shows an individual case analysis result table in the individual case analysis result database 105. This example shows a state where the cause of occurrence of variance input in FIG. 8 is registered. The birth flag is set to be 1 when the cause text is acquired from the variance table (S703) and 0 when the user inputs that it is appropriate (S704). In this example, the item whose origin flag is 1 indicates that “bleeding” as the analysis target variance, “catheter insertion failure” acquired from the variance table in S803, and “body temperature of 38 ° C. or higher”. .

  Next, the variance extraction process (S303) similar to the target variance will be described in detail. Use an index (similarity E (Y)) focusing on the structural similarity of the individual case analysis results performed in S301 and S302 in order to extract a variance similar to the target variance from the variances analyzed in the past. It was.

  First, the definition of similarity E (Y) for realizing this method will be described. First, if there are many matching structures that take into account the causal relationship between elements (causes of occurrence) in individual case analysis results, they are considered similar. However, since the individual case analysis is constructed by the user, the structure of the individual case analysis result may be different even for the same phenomenon. For example, the cause of A in some cases may be B, but in another similar case, the cause of A may be C and the cause of C may be B. Therefore, if it is defined that the similarity is high only when the causal partial structures are completely matched, the similarity may be low even for the same phenomenon. Therefore, even if the causal relationship partial structures do not completely match, if the element items in the individual case analysis results match, the similarity is increased. However, in order to lower the similarity as the structure is different, the items of the cause of occurrence match, but when the cause of occurrence is an indirect factor, the degree of similarity is reduced.

  FIG. 10 shows a detailed flowchart of the similar variance extraction process (S303). In this flowchart, first, the structure of the individual case analysis result of the variance of interest and the frequency thereof are registered (S30301-S30304). Then, the structure and frequency of individual case analysis results are registered for all the variances to be extracted (S30306-S30309), and the similarity E (Y) is calculated according to (Equation 1) (S30310). Finally, the target variance whose similarity E (Y) is higher than the threshold is extracted as the similarity variance (S30311). In (Equation 1), the concept of “increase the similarity if the element items in the individual case analysis results match” is a recursive addition focusing on the causal relationship. Even if they do not match completely, if the element items in the individual case analysis result match, the similarity will be increased.``Adding child similarity E (A (Ra)) The concept of “lowering the similarity if is an indirect factor” was reflected in adding 1 / α multiplication.

  Here, each processing will be described in detail with reference to FIGS. 8, 11, 12, 13, and 14. FIG. 8 shows the individual case analysis result regarding the variance of bleeding of the PCI path, which is the noted variance in S302. First, S30301 to S30304 will be described in detail. Here, the structure and frequency of individual case analysis results of the target variance are registered. The registered state is shown in FIG. First, the causal relationship in the individual case analysis result of the target variance is registered in Ri (i is an identifier of the causal relationship) (S30301). Next, the frequency of the causal relationship Ri in the individual case analysis of the target variance is registered in X (Ri) (S30302). In this embodiment, since only one case of the noted variance has occurred, only “0” or “1” is registered. Next, the cause of occurrence of the target variance in the individual case analysis element V is registered in Rc (V) j (j is an identifier of the cause of occurrence and V is a conclusion part) (S30303). In the present embodiment, the cause of occurrence of the variance in FIG. 8 is “sheath natural extraction”, “catheter insertion failure”, and “38 degrees or more”. Therefore, these three items are set as Rc (V) j as the cause of occurrence of the variance V. sign up. Next, the number of occurrences of the noted variance is registered in Nx (S30304). In the present embodiment, since only one case of the noted variance has occurred, “1” is registered.

  Next, S30306 to S30309 will be described in detail. Here, for all variances to be extracted, the structure of individual case analysis results and their frequencies are registered for each variance. FIG. 12 and FIG. 13 show individual case analysis results regarding the variance of the presence of hematoma in the TUR-Bt path as the extraction target variance. For example, in FIG. 12, the direct cause of the occurrence of the variance that the patient P11 has the hematoma is It shows a lot of body position fluctuations and a fever of 38 degrees or more. First, the causal relationship in the individual case analysis result of the target variance is additionally registered in Ri (i is an identifier of the causal relationship) (S30306). Next, the frequency of the causal relationship Ri in the individual case analysis of the target variance is registered in Y (Ri) (S30307). In the present embodiment, only the two cases shown in FIGS. 12 and 13 are generated as the target variance, so only “0”, “1”, or “2” is registered. Next, the cause of occurrence of the target variance in the individual case analysis element V is additionally registered in Rc (V) j (j is the identifier of the cause of occurrence and V is the conclusion part) (S30308). In the present embodiment, the direct factor causing the variance in FIG. 12 is “Many body position fluctuation” “38 degrees or more”, and the direct factor causing the variance in FIG. 13 is “38 degrees or more”. In consideration of the elements registered in this way, “many body posture fluctuation” is newly registered in Rc (V) 0 as a premise part of variance V. Next, the number of occurrences of the target variance is registered in Ny (S30309). In this embodiment, since the target variance occurs in two cases of FIGS. 12 and 13, “2” is registered. When the structure and the frequency of the individual case analysis result are registered in this way, the similarity E (Y) is calculated according to (Equation 1) (S30310), and the variance having a high similarity is extracted (S30311).

  In the present example, the causal relationship that the result of “no suppression” in the target variance of FIG. 8 is “the body position variation is large” has also appeared in the target variance of FIG. Even if they do not agree with each other, it contributes to the improvement of the similarity by the property of the influence that “the similarity is increased if the element items in the individual case analysis result are identical”. On the other hand, since the structure of FIG. 8 and FIG. 12 is different from the viewpoint of whether or not this relationship is a direct factor of variance, the degree of similarity is determined by the nature of the influence level of “reducing similarity when element item is indirect factor” Contributes to the decline.

  Next, the screen configuration displayed on the output means 109 in the presentation of the variance path improvement history extracted in S303 (S304) will be described with reference to FIG. This example includes a path improvement plan basic information display unit 1401 and a path improvement plan presentation unit 1402. In this example, it is determined in S303 that the similarity of the variance indicating that there is hematoma in the TUR-Bt pass is high, and the variance relating to hematoma confirmation is prevented from the variance code master table in FIG. 5 and the clinical path improvement history table in FIG. This shows how the TUR-Bt pass was upgraded from 001 to 002. As a result, it can be seen that it is important to add confirmation of body temperature of 38 degrees or less and guidance for rest in order to prevent variance with hematoma. In this way, by referring to the improvement example of the TUR-Bt pass, the user considers that it is effective to add confirmation and rest guidance of 38 degrees or less to prevent variance in bleeding related to the PCI pass. It becomes possible.

  Thus, it is possible to support the improvement of the clinical path that is faced by extracting similar variances by paying attention to the cause of occurrence of variance and referring to the improvement history of the extracted variance.

  FIG. 15 is a configuration diagram of a clinical path improvement plan presenting system according to the present invention. In particular, a correlation rule generation unit 111 and a correlation rule database 112 have been newly added to the configuration diagram shown in FIG. This is a modification of the method for extracting similar variances in the case extracting means 107. The association rule generation 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. The correlation rule database 112 is configured by the external storage device 2024 shown in FIG.

  In order to realize the system shown in the present embodiment, the flowchart of the data processing is the same as that in FIG. 3, but detailed processing of the individual case analysis processing (S301, S302) and the similar variance extraction processing (S303) is performed. Different. Hereinafter, after describing the association rule generation unit 111, individual case analysis processing will be described, and finally detailed processing of similar variance extraction processing will be described.

  First, the association rule generation unit 111 will be described. The correlation rule generation unit 111 generates a correlation rule having a variance as a conclusion part from an execution record table acquired via the electronic medical record linkage unit 103 using a correlation rule mining technique represented by an a priori algorithm. The generated correlation rules are accumulated in the correlation rule database 112. FIG. 16 shows an example of an implementation record table. In the execution record table, the state in which A1 is performing arterial marking on April 5 is recorded for the patient code P0. FIG. 17 shows an example of a table indicating knowledge generated by the correlation rule generation unit 111. In this embodiment, an event having a high correlation with the occurrence of a variance of “bleeding” is recorded as a correlation rule with respect to the medical practice of “bleeding confirmation”, and three correlation rules are shown. The first indicates that the certainty of the correlation rule that “bleeding” occurs when a fever of “38 degrees or more” occurs is 90%. The second indicates that the certainty of the correlation rule that “bleeding” occurs when “catheter insertion failure” occurs is 85%. The third indicates that the certainty of the association rule that “bleeding” occurs when “SpO2” decreases is 80%.

  Next, detailed processing of individual case analysis (S301, S302) will be described using the flowchart of FIG. Here, for the purpose of analyzing the root cause of occurrence of variance, individual case analysis, which is analysis of variance causality, is performed for each individual case where variance occurred (S1801) (S1801-S1808). Specifically, the screen configured by the screen configuration processing unit 108 that receives the message from the individual case analysis result construction unit 104 is presented to the output unit 109, and the user uses the input unit 110 on the presented individual case analysis screen. The cause of the occurrence of variance is input via (S1802-S1806). The individual case analysis result construction means 104 stores the result in the individual case analysis result database 105 based on the input variance occurrence cause data (S1807). 7 is different from the flowchart of FIG. 7 in that a process for inputting a cause of occurrence of variance is performed by adding “cause knowledge condition of an association rule having a certainty level equal to or higher than a threshold set by the user” (S1803). There are three ways to input the cause of occurrence. Thereby, the user can input the cause of occurrence of variance more easily.

  Next, the screen configuration displayed on the output unit 109 in the analysis of individual cases (S301, S302) will be described by focusing on the addition of the correlation rule generation unit 111. FIG. 19 shows a screen configuration displayed on the output means 109. A rule capture button 8013 is added to the screen configuration example shown in FIG. Also in the present embodiment, for the medical practice of confirming PCI path bleeding, the cause of the occurrence of the variance of bleeding for the patient P1 is analyzed by the variance generation cause analysis construction unit 802. In this example, when the user presses the rule capture button 8013, the correlation table stored in the correlation rule database 112 indicates that the cause knowledge condition of the correlation rule having a certainty factor of 85% or higher is “38 degrees or higher”. The “catheter insertion failure” is reflected in the variance occurrence cause analysis construction unit 802.

  Next, detailed processing of the similar variance extraction processing (S303) will be described with reference to the flowchart of FIG. The difference from FIG. 10 is that S30302 is changed to S303021, S30307 is changed to S303071, and S30310 is changed to S303101 for the purpose of dealing with the case where the expression of the individual case analysis result is different even for the same phenomenon. First, I will briefly describe the changed points. Since the element of the individual case analysis constructed using the association rule is the cause knowledge condition (S1803), it is a premise part of the association rule. Furthermore, since it is a premise part of the correlation rule, it can be seen from the variance code master table and the clinical path data table that the elements constructed using the correlation rule are related to the order attribute. Since the order attribute describes the type of medical practice, if the element order attributes match even if the element expression is different, the expression of the individual case analysis results will be somewhat similar Judgment can be made. Therefore, in S303021 and S303071, it is added that the frequency of the causal relationship of the individual case analysis results is counted in units of order attributes (Xo (Ri), Yo (Ri)). Further, in S303101, even if the expression of the element in the individual case analysis result is different, if the order attribute is the same, the similarity is changed to (Equation 2) so that the similarity is increased to some extent. However, since the similarity should be higher when the element representation is the same, the coefficient β (<1) is multiplied.

  In order to explain the difference from FIG. 10, specific values of Xo (Ri) and Yo (Ri) will be described with reference to FIGS. 8, 12, 13, 21, and 22. FIG. 8 shows the analysis result of the target variance, and FIGS. 12, 13, and 21 show the analysis results of the target variance. Focusing on R1, the premise part is “38 degrees or more” and the conclusion part is “variance”, but the order attribute of “38 degrees or more” is “assessment” from the variance code master table and the clinical path data table. I understand. 12 and 13, there is a causal relationship in which the premise part is “38 degrees or more” and the conclusion part is “variance”, but it does not exist in FIG. 21. However, in the causal relationship in FIG. 21, the premise part is “assessment” and the conclusion part is “variance” from the viewpoint of the order attribute. Therefore, it can be understood that Xo (R1) exists in any of FIGS. 12, 13, and 21, and “3” is registered. Therefore, the value of Si (R1) in (Equation 2) is larger than that in (Equation 1), and it is more similar by using (Equation 2).

  By paying attention to the order attribute in the element of the individual case analysis result based on the association rule in this way, it is possible to extract similar variances even in the case where the expression of the individual case analysis result is different even for the same phenomenon, It is possible to extract the clinical path improvement history more effectively.

  FIG. 23 is a block diagram of a clinical path improvement plan presenting system according to the present invention. In particular, we thought that the clinical path improvement history should be referenced if the medical practice patterns are similar. FIG. 23 is a diagram in which a path similarity calculation unit 113 is newly added to the configuration diagram shown in FIG. 1 and the extraction method in the similar case extraction unit 107 is changed. The path similarity calculation unit 113 can implement various processes by developing and starting a predetermined program in the central processing unit 2023 and the memory 2022 shown in FIG.

  In order to realize the system as shown in the present embodiment, the flowchart of the data processing is the same as that in FIG. 3, but the detailed processing of the similar variance extraction processing (S303) is different. Accordingly, the similar variance extraction process (S303) will be described with reference to the flowchart of FIG. The difference from FIG. 10 is that S30310 is changed to S303102 in order to introduce the concept of path similarity in similarity calculation. In (Equation 3), path similarity D (X, Y) is calculated by quantifying whether or not the clinical path where variance X occurred and the clinical path where variance Y occurred are similar, and path similarity If the value of degree D (X, Y) is large, the degree of similarity is also increased. The path similarity D (X, Y) is calculated by paying attention to the number of times of the medical practice i to be performed on the tth day, for example, as in (Equation 4). A calculation example may be stored as shown in FIG.

  By paying attention to the path similarity in this way, it is possible to refer to a clinical path improvement history having a similar medical practice pattern even if the individual case analysis results performed by the user do not completely match.

  FIG. 26 is a configuration diagram of a clinical path improvement plan presenting system according to the present invention. In particular, in order to make it possible to refer to a clinical path improvement history having a higher improvement effect, a quality indicator calculation means 114 is newly added to the configuration diagram shown in FIG. The quality indicator calculation unit 114 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. 27 shows a data processing flowchart for realizing the system as shown in the present embodiment. The difference from the flowchart shown in FIG. 3 is that a process (S2704) for extracting a past variance having a high quality indicator improvement value before and after the path improvement is added among the extracted past variances. Therefore, this process will be described in detail. Quality Indicator is a numerical value that measures the quality of medical care and is also called a clinical indicator, and includes the average length of hospital stay, readmission rate, pressure ulcer incidence, and the like. FIG. 28 shows a quality indicator table storing quality indicators and a patient data table on which the quality indicators are based. In the patient data table, the quality indicator calculation means 114 calculates the quality indicators such as the average hospital stay and the readmission rate based on the information acquired from the electronic medical record database 102 via the electronic medical chart linkage means 103. Is stored. Further, an average value of the Quality Indicator is calculated by the Quality Indicator calculating means 114 for each pass from the patient data table and stored in the Quality Indicator table.

  FIG. 29 shows a state in which the value calculated in this way is output via the output means 109. In this screen example, a quality indicator improvement display unit 803 is added to the screen configuration example shown in FIG. Based on the Quality Indicator table shown in FIG. 28, the quality indicator improvement value is displayed on the quality indicator improvement display unit 803. In this example, the TUR-Bt pass is upgraded so that the improvement in hospital stay and readmission rate is high, but the cataract upgrade does not show any improvement. When the user selects a TUR-Bt path by referring to this result and presses an improvement plan presentation button 8012, a TUR-Bt path improvement history is displayed as shown in FIG.

  Thus, by calculating the Quality Indicator in each version of the clinical path and considering the improvement effect, it is possible to refer to the clinical path improvement history having a higher improvement effect.

The first block diagram of the clinical path improvement plan presentation system in the present invention Hardware configuration diagram of clinical path improvement plan presentation system in the present invention First flowchart related to a clinical path improvement plan presenting system in the present invention The figure showing the clinical path data table in an electronic medical chart system in this invention The figure showing the variance table and variance code master table in an electronic medical record system in this invention The figure showing the clinical path improvement log | history table in an electronic medical chart system in this invention First flowchart regarding the analysis processing of individual cases in the present invention The first example showing a screen in the analysis processing of individual cases in the noted variance in the present invention The figure showing the individual case analysis result table in the clinical path improvement plan presentation system in this invention First flowchart regarding similar variance extraction processing in the present invention The first example showing the memory image in the similarity calculation process in the clinical path improvement plan presenting system in the present invention First example showing a screen in the analysis processing of individual cases in the target variance in the present invention Second example showing screen in analysis processing of individual case in target variance in the present invention First example showing screen of clinical path improvement plan presenting system in the present invention The second block diagram of the clinical path improvement plan presentation system in the present invention The figure showing the implementation record table in an electronic medical chart system in this invention The figure showing the correlation table in the clinical path improvement plan presentation system in this invention Second flowchart regarding the analysis processing of individual cases in the present invention Second example showing screen in analysis processing of individual case in target variance in the present invention 2nd flowchart regarding similar variance extraction processing in the present invention Third example showing screen in analysis processing of individual case in target variance in the present invention A second example representing a memory image in the similarity calculation process in the clinical path improvement plan presenting system in the present invention The third block diagram of the clinical path improvement plan presentation system in the present invention 3rd flowchart regarding similar variance extraction processing in the present invention The figure showing a path | pass similarity table in this invention. 4th block diagram of the clinical path improvement plan presentation system in this invention The second flowchart regarding the clinical path improvement plan presenting system in the present invention. The figure showing a patient data table and a Quality Indicator table in this invention Second example showing screen in analysis processing of individual case in target variance in the present invention Figure representing number 1 Figure representing the number 2 Figure representing the number 3 Figure representing the number 4

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 ... Individual case analysis result construction means, 105 ... Individual case analysis result database, 106 ... Path improvement database 107 ... Similar case extraction means, 108 ... Screen configuration processing means, 109 ... Output means, 110 ... Input means, 111 ... Correlation rule generation means, 112 ... Correlation rule database, 113 ... Path similarity calculation means, 114 ... Quality Indicator 2010, keyboard, 2011 ... display, 2012, memory, 2013 ... central processing unit, 2014 ... external storage device, 2020 ... keyboard, 2021 ... display, 2022, memory, 2023 ... central processing unit, 2024 ... external storage device , 801 ... Condition setting , 8011 ... save button, 8012 ... improvement plan presentation button, 8013 ... rules capture button, 802 ... variance cause analysis construction unit, 1401 ... path improvement proposal basic information display unit, 1402 ... path improvement plan presentation section

Claims (5)

A clinical path improvement plan presenting system for presenting a clinical path improvement plan for preventing the occurrence of variance by utilizing a variance that is a difference between a clinical path that is a standard medical plan and an actual medical treatment. An output means and a processing device;
The input means accepts input of the variance of interest,
The processor is
Electronic medical record linkage means for acquiring clinical path data describing a standard medical treatment plan, variance data recording variance, and clinical path improvement history data that is a clinical path improvement plan from a connected electronic medical record database ,
From the clinical path data and the variance data acquired by the electronic medical record linkage means, an individual case analysis result construction means for constructing an individual case analysis result describing the variance causal relationship for each variance occurrence case in a hierarchical structure;
Extract past past variances similar to the cause of occurrence of the target variance selected through the input means, focusing on the hierarchical structure similarity of the individual case analysis results, and a clinical path improvement history for preventing the occurrence of the extracted variance, Similar case extraction means for extracting via the electronic medical record linkage means,
The said output means outputs the said clinical path improvement log | history extracted by the said similar case extraction means as a clinical path improvement plan of the said attention variance, The clinical path improvement plan presentation system characterized by the above-mentioned. In the clinical path improvement plan presentation system according to claim 1,
With similar case extraction means,
The similarity that is the standard for extracting past variances that are similar to the cause of the occurrence of
The cause of the occurrence is further matched so that the similarity is higher as the cause of occurrence of the variance matches, and the degree of similarity is higher as the proportion of the causal relations of the cause of occurrence is higher. However, if the cause is an indirect factor, calculate the similarity to be low,
A clinical path improvement plan presenting system that extracts a variance similar to a cause of occurrence of a noted variance by using the similarity as an evaluation index. In the clinical path improvement plan presentation system according to claim 2,
In the electronic medical record linking means, the history of the medical practice performed on the patient, the order attribute history describing the type of the medical practice, and the implementation record data describing the history of the history of the patient status are stored in the electronic medical record database. Retrieve data from
The processor is
Correlation rule generating means for generating a correlation rule including a variance in a conclusion part by correlation rule mining from the execution record data acquired by the electronic medical record cooperation means,
In the individual case analysis result construction means,
Extracting the premise part of the correlation rule generated by the correlation rule generation means as the cause of occurrence of variance,
In the similar case extraction means,
Extracting from the clinical path data the order attribute in the medical practice that is a component of the premise part of the association rule,
A clinical path improvement plan presenting system characterized in that a similarity as a reference for extracting past variances similar to the cause of occurrence of a noted variance is calculated such that the similarity increases as the order attributes match. In the clinical path improvement plan presentation system according to claim 2,
The processor is
Path similarity calculation means for calculating a path similarity that is a similarity of a medical practice pattern from the clinical path data acquired by the electronic medical record linkage means,
In the similar case extraction means,
Extract the clinical path 1 where the noted variance occurred and the clinical path 2 where similar past variances occurred,
The similarity that is the standard for extracting past variances that are similar to the cause of the occurrence of
A clinical path improvement plan presentation system characterized in that the degree of similarity increases as the path similarity between the clinical path 1 and the clinical path 2 matches. In the clinical path improvement plan presentation system according to claim 1,
The processor is
A quality indicator calculation means for calculating a quality indicator, which is a numerical value of medical quality, for each version of the clinical path is provided.
The clinical path improvement plan presenting system characterized in that the similar case extraction means extracts the clinical path improvement history having a high effect of improving the quality indicator.

Images