JP7008939B2 - Medical document management system - Google Patents

Description

The present invention is a medical document management system that efficiently creates and searches medical documents by using a knowledge management means that efficiently accumulates and searches knowledge required for inference, judgment, recognition, and the like. Regarding.

If a computer can make judgments and inferences that humans make on a daily basis, it will be possible to process or simplify daily tasks at high speed in large quantities. Development for this has been carried out conventionally.
Initially, judgment rules such as "if A is B" and "if B is C" are accumulated, and when the proposition "D is A" is given in advance. An expert system has been developed that infers that "D is C" by sequentially applying the accumulated judgment rules. "MYCIN" is known to infer the optimal antibiotic for infectious diseases.

In the age of the Internet, more flexible searches have been needed. For example, "Is E a musician?" Using web records and declarations such as "E is a fiddler", "a violin player is a musician", "a conductor is a musician", etc. (Semantic web: semantic web).
Here, under the superordinate concept of "musician", subordinate concepts such as "violin player", "conductor", and "composer" are developed. In this way, when the concept is described structurally (ontology), even if there is no direct description that "E is a musician" on the web, "E is a violin player, so he is also a musician." Is inferred, and the above question can be answered correctly.
Here, it is necessary to describe individual concepts and relationships in a unified format using a format such as XML so that concepts in multiple fields can be searched across. RDF (Resource Description Framework) has been proposed as an example of this unified format. The method of describing concepts and relationships in individual fragments is compatible with programming languages such as Prolog, and is easy to be familiar with relational databases.

In the medical field as well, attempts are being made to construct a disease ontology as shown in Non-Patent Document 1 below. Further, Patent Document 1 and the like have been proposed in the general industrial field as well.
In the medical field, the introduction of so-called electronic medical records, which create medical records electronically, is progressing. Medical documents can be easily created by searching or duplicating the stored electronic documents, which is becoming more widespread.

Ontology expression and utilization of clinical medical knowledge (https://www.jstage.jst.go.jp/article/johokanri/52/12/52_12_701/_pdf)

Japanese Patent Laid-Open No. 2012-119004

In the early expert system, it is difficult to accumulate a large amount of judgment rules necessary for practical level operation. Further, since the condition part A of "if A then B" is applied only when it exactly matches, it is applicable when the search for "musician" is performed for "violin player" as in the above example. It will be none.
In the Semantic Web, it is ambiguous to some extent by utilizing the common sense that "violin player", "conductor", "composer", etc. are also included in the subconcept of "musician" by structural description such as ontology. It has become possible to support searches. However, when actually constructing a concrete ontology, the degree of freedom of the description format is so great that multiple description formats are possible even with the same content, and the structure described by the builder fluctuates. Therefore, even if the contents are the same, the description styles are often different. For this reason, when a plurality of ontology is constructed by a plurality of people in parallel work, confusion occurs due to the inconsistency of the description format. In addition, since various description methods are mixed, it is often difficult to understand even when looking at the expanded ontology, and the readability is often poor.

On the other hand, even when knowledge fragments such as individual knowledge areas, knowledge items, attribute descriptions, and parent-child relationship descriptions are described in a format such as RDF, fluctuations in the same description format are inevitable, and in the first place, a large number of knowledge fragments are listed. Yes, the whole picture of knowledge cannot be listed, and the readability is extremely poor.
In order to efficiently describe a large amount of knowledge, it goes without saying that it is in a format that can be understood by a computer, but it also needs to be readable so that it can be easily understood by humans. As recommended by WEB 2.0, it is possible to easily describe knowledge without any special knowledge or skills, and to be able to easily point out contradictions by looking at it. It is an indispensable characteristic for many non-experts to build ontology etc. in parallel while cooperating via the web.

In the creation of medical documents, the vocabulary and expressions used are left to the discretion of medical professionals including doctors, so the range of content to be described varies, and when collecting statistical data, There is a large amount of missing data, which causes incomplete analysis.
In addition, even if the contents are the same, the vocabulary and expressions fluctuate greatly, so that it is difficult to perform unified processing, and it is necessary to manually judge the same contents.
Due to these factors, medical documents are merely a description of the situation, and from the contents described, a list of disease names with high probability can be estimated, and tests useful for distinguishing between diseases and diseases can be performed. The current situation is far from being intelligent, such as recommending findings.

The present invention has been made to solve such a conventional problem, and an object thereof is to clearly separate and organize knowledge in a certain area into a plurality of knowledge trees, and each knowledge tree. Then, the knowledge entries constituting the tree are expanded in a hierarchical structure of parent-child relationship, each knowledge entry is a set of entry attribute descriptions related to the knowledge entry, and the entry attribute description is to another knowledge entry or entry attribute description. By including the reference link, it is possible to describe the systematic knowledge without fluctuation of the notation.
Furthermore, the child knowledge entry inherits the entry attribute description of the parent knowledge entry, eliminating the need to duplicate the attribute description. For other areas, by enabling management as another independent knowledge tree group separated by namespace, the area of interest can be managed without worrying about duplication of knowledge trees and knowledge entry names in other areas. It is possible to concentrate on building a knowledge system. By establishing such a knowledge management framework, we have built a knowledge management system that not only enables machine processing, but also has good readability that allows people to view the contents, and that no matter who creates it, the description does not fluctuate. It is to provide a foundation for knowledge processing that enables flexible and advanced search and inference. In addition, by making it possible to reconfigure the knowledge management system by extracting part or all of the above knowledge management system and integrating it into another knowledge management system, it is possible to flexibly operate the knowledge management system. Is.
In addition, it is possible to make inquiries to the knowledge management system and respond from the knowledge management system, enabling effective utilization in the real world. Furthermore, by managing the execution authority of the user and making it possible to set the scope of the search, security against destruction and confusion is ensured.

On the other hand, in the creation of medical documents, by using the reference links to the knowledge entries and attribute descriptions defined by the knowledge management means as vocabulary, fluctuations in expressions are suppressed and standardized to withstand subsequent statistical analysis. It is to enable description.
In addition, by incorporating judgment logic into the reference link, it is possible to eliminate omissions in description and checks, and to enable highly complete document description and safe medical instruction document issuance.
In addition, tests that are useful for estimating a list of possible diseases and for advancing disease differentiation using the frequency of occurrence of disease-specific symptoms and findings efficiently accumulated in knowledge management means. By recommending the acquisition of findings, it is possible to provide accurate and efficient medical care.

As a means for achieving the above object, the medical document management system according to claim 1 is provided with a knowledge entry management means for recording knowledge entries and a knowledge entry attribute description management means for recording attribute descriptions related to knowledge entries. The vocabulary described in the entry attribute description management means has a link to another knowledge entry or the attribute description of another knowledge entry, and is described in the knowledge entry attribute description management means in the preparation of the medical document. It is characterized by being provided with a knowledge management reference link usage means that enables the vocabulary to be described as a reference link in a medical document, and a knowledge entry attribute category management means that manages the knowledge entry attribute description by dividing it into categories.

In the medical document management system according to claim 2, in the medical document management system according to claim 1, the knowledge entry management means includes a knowledge tree group management means for managing at least one knowledge tree and at least each knowledge tree. It has a function to manage one existing knowledge entry and manage the data structure on the premise of the knowledge tree structure. Each knowledge entry has a knowledge entry attribute description that describes an attribute related to the knowledge entry and a knowledge tree attribute description. It consists of a knowledge entry parent-child relationship link that describes a parent-child relationship with another knowledge entry, and the knowledge entry attribute description is a knowledge entry that belongs to a different or the same knowledge tree, or the knowledge entry attribute category of the knowledge entry, or the knowledge. Entry knowledge It is characterized by including a link to the entry attribute description.

In the medical document management system according to claim 3, in the knowledge management system according to any one of claims 1 and 2, an external document reference means for referencing an external document or a group of external documents related to the knowledge entry attribute description is provided. It is characterized by being prepared.

In the medical document management system according to claim 4, in the medical document management system according to any one of claims 1 to 3 , when the vocabulary described in the knowledge entry attribute description management means is described as a reference link in the medical document. It is characterized by having a script execution means for managing the script to be executed.

In the medical document management system according to claim 5, in the medical document management system according to any one of claims 1 to 4 , when the vocabulary described in the knowledge entry attribute description management means is described as a reference link in the medical document. , It is characterized by having a reference strength management means that sets the strength of the reference and changes the strength according to the observation frequency of symptoms / findings.

In the medical document management system according to claim 6, in the medical document management system according to claim 2, the knowledge entry attribute that inherits the knowledge entry attribute description of the parent knowledge entry to the knowledge entry attribute description of the child knowledge entry in the parent-child relationship. It is characterized by having a description inheritance means.

The medical document management system according to claim 7 is characterized in that the medical document management system according to any one of claims 1 to 6 has a case link creating means for creating a case link for a medical document referring to a vocabulary. do.

In the medical document management system according to claim 8, in the medical document management system according to claim 7, each of the symptoms / findings observed in the case or a combination of the symptoms / findings observed simultaneously in the case link creating means. The pair is characterized by being provided with a means for creating a case link for each symptom / finding that creates a case link with the symptom / finding for each knowledge entry of the observed symptom / finding.

The medical document management system according to claim 9 is characterized in that the medical document management system according to claim 8 is provided with a function of classifying and aggregating case links according to symptoms / findings .

In the medical document management system according to claim 10, in the medical document management system according to any one of claims 8 to 9, simultaneous observation is performed when the disease name of the case is confirmed and input in the case link creating means for each symptom / finding . It is characterized by providing a means for creating a definite disease symptom / finding case link for creating a case link for each symptom / finding for the knowledge entry of the disease name.

In the medical document management system according to claim 11, in the medical document management system according to any one of claims 8 to 10, in a case whose disease name is uncertain, the symptom / finding or symptom / symptom observed in the medical document of the case. It is characterized by providing a similar case search means for obtaining a list of cases similar to the case by obtaining a product set of a set of case links already created for each of the findings pairs.

In the medical document management system according to claim 12, in the medical document management system according to claim 11, the confirmed disease names in the case list obtained by the similar case search means are aggregated and displayed in order of frequency. It is characterized by having an estimation means.

In the medical document management system according to claim 13, in the medical document management system according to claim 9, in the case where the disease name is uncertain, the case is classified by symptom / finding with respect to the symptom / finding observed in the medical document of the case . It is highly possible to use the disease name-specific symptom / findings observation frequency aggregated using the function for classifying and aggregating links, the disease name frequency distribution for each of the observed symptoms / findings, or both. It is characterized by being provided with a disease name list estimation means for estimating a list of disease names of the case.

In the medical document management system according to claim 14, in the medical document management system according to claim 13, the symptoms by disease name of the plurality of disease names aggregated by using the function of classifying and aggregating case links by symptom / finding , It is equipped with a medical examination recommendation means to obtain a list of symptoms and findings with a large difference in frequency distribution depending on the disease name using the observation frequency of findings, and to estimate a list of symptom findings to be obtained next, which is effective for differentiating the disease name. It is characterized by that.

In the medical document management system according to claim 15, in the medical document management system according to claim 14, when creating a medical document, the symptoms and findings to be obtained by a medical examination and a recommended list of tests to be performed are automatically displayed. It is characterized by being provided with a medical examination inspection recommendation display means for displaying and facilitating the smooth creation of medical examination records and examination orders.

The medical document management system according to claim 16 has, in the medical document management system according to claim 2, a namespace management means for managing a plurality of knowledge tree groups by dividing them into namespaces in the knowledge tree group management means. It is characterized by that.

In the medical document management system according to claim 17, in the medical document management system according to claim 2 , any part of a namespace, a knowledge tree, a knowledge entry, an entry attribute description, and a parent-child relationship link is extracted and a knowledge management subset. It is characterized by having a knowledge export means for creating and exporting.

In the medical document management system according to claim 18, in the medical document management system according to claim 17, the knowledge management subset extracted by the knowledge export means or the knowledge management from a separately constructed knowledge management system. It is characterized by having knowledge import means for importing subsets and reconstructing namespaces, knowledge trees, knowledge entries, entry attribute descriptions, and parent-child relationship links.

In the medical document management system according to claim 19, in the medical document management system according to any one of claims 17 to 18, each of the namespace, knowledge tree, knowledge entry, knowledge entry attribute category, knowledge entry attribute description, and parent-child relationship link. It is characterized in that it is provided with a user authority management means for managing the execution authority of the function for each user for the functions of creating, editing, deleting, and referencing.

In the medical document management system according to claim 20, in the medical document management system according to any one of claims 1 to 19, the knowledge browsing means for browsing the parent-child relationship between the knowledge entries and the content of the knowledge attribute description of the knowledge entry. It is characterized by being equipped with.

In the medical document management system according to claim 21, in the medical document management system according to any one of claims 1 to 20, (i) a knowledge inquiry receiving means for receiving inquiries about records and managed knowledge contents, and inquiries. Knowledge inquiry response means for responding to, and (ii) Medical document content inquiry reception means for accepting inquiries about the contents of recorded and managed medical documents in the creation of medical documents, for the contents of inquiries It is characterized by having at least one of the above (i) and (ii) as a means for responding to an inquiry about the contents of a medical document.

In the medical document management system according to claim 22, in the medical document management system according to claim 20 , each of the namespace, the knowledge tree, the knowledge entry, the entry attribute description, and the parent-child relationship link is created and edited, and the user is managed. , Exclude medical documents created by a specific user or user group from the search target range of the knowledge browsing means , knowledge inquiry receiving means, medical document content inquiry receiving means, or conversely, create a specific user or user group. It is characterized in that it is provided with a search scope management means that covers only the part of the knowledge management means and the medical document as the search target range of the knowledge browsing means , the knowledge inquiry receiving means, and the medical document content inquiry receiving means.

Since the medical document management system according to claim 1 is provided with knowledge entry management means, an information classification system for each knowledge entry is constructed.
Since the knowledge entry attribute description management means is provided, the information belonging to each knowledge entry is stored.
Since it is equipped with knowledge management means including reference links, a wide information collection system via reference links is constructed.
Since the knowledge management reference link is provided, the reference link in the knowledge management means can be used as a descriptive vocabulary of the medical document contents.

Since the medical document management system according to claim 1 is provided with the knowledge entry attribute category management means, the knowledge entry attribute description is managed by dividing it into categories.

Since the medical document management system according to claim 2 is provided with knowledge entry management means extended on the premise of a knowledge tree structure, there is at least one knowledge tree group management means for managing the knowledge tree and at least one for each knowledge tree. An extended information management system is constructed on the premise of a knowledge tree structure that manages knowledge entries.
Since it has a knowledge entry parent-child relationship link, the knowledge entry attribute description that describes the attributes related to the knowledge entry and the parent-child relationship with other knowledge entries in the knowledge tree are described and recorded.
The knowledge entry attribute description contains a reference link to a knowledge entry that belongs to a different or identical knowledge tree, or to the knowledge entry attribute category of the knowledge entry, or to the knowledge entry attribute description of the knowledge entry, so via the reference link. A wide information gathering system is constructed.

Since the medical document management system according to claim 3 is provided with an external document reference means, the document is created while referring to the external document or external document group related to the knowledge entry attribute description, or the in-document description of the document. Can be done.

Since the medical document management system according to claim 4 is provided with a script execution means, it is possible to select and execute an appropriate script according to the type of reference link and the like.

Since the medical document management system according to claim 5 is provided with a reference strength management means, the priority of the reference link is managed by setting the strength of the reference or changing the strength according to the observation. Can be done.

Since the medical document management system according to claim 6 is provided with the knowledge entry attribute description inheritance means, the knowledge entry attribute description of the parent knowledge entry can be inherited to the entry attribute description of the child knowledge entry.

Since the medical document management system according to claim 7 has a case link creation means, a case link is made from a medical document that refers to a vocabulary to a knowledge entry of a reference source or a knowledge entry attribute description of the knowledge entry. Can be created.

The medical document management system according to claim 8 is provided with a means for creating a case link for each symptom / finding. A case link with the symptom / finding can be created for each knowledge entry of the symptom / finding.

Since the medical document management system according to claim 9 is provided with the case link aggregation means for each symptom / finding, the case link can be classified and aggregated for each symptom / finding.

Since the medical document management system according to claim 10 is provided with a definite disease symptom / finding case link creation means, when the disease name of the case is determined, the observed symptom / finding or symptom / finding pair is said to be relevant. A case link by symptom / finding can be created for the knowledge entry of the disease name.

Since the medical document management system according to claim 11 is provided with a similar case search means, a set of case links already created for each symptom / finding or symptom / finding pair observed in the medical document of the case. By obtaining the intersection of, a list of cases similar to the case can be obtained.

Since the medical document management system according to claim 12 is provided with a means for estimating a similar case disease name, the confirmed disease names in the case list obtained in claim 12 can be aggregated and displayed in order of frequency.

Since the medical document management system according to claim 13 is provided with a disease name list estimation means, the symptoms / findings observed in the medical document of the case are tabulated using the case link tabulation means by symptom / finding. A list of likely disease names in the case can be estimated using the disease name-specific symptom / findings observation frequency, the disease name frequency distribution for each of the observed symptoms / findings, or both. can.

Since the medical document management system according to claim 14 is provided with a medical examination and examination recommendation means, the symptom by disease name and the frequency of observation of the findings of the plurality of disease names aggregated by using the case link aggregation means by symptom and finding are used. Therefore, it is possible to obtain a list of symptoms and findings having a large difference in frequency distribution depending on the disease name, and to estimate a recommended list of symptom findings to be obtained next, which is effective for differentiating the disease name.

Since the medical document management system according to claim 15 is provided with a medical examination recommendation display means, when creating a medical document, the symptoms and findings to be obtained by the medical examination and the recommendation list of the examination to be performed are automatically displayed. It also facilitates the creation of smooth medical examination records and examination orders.

Since the medical document management system according to claim 16 has a namespace management means, a plurality of knowledge tree groups can be divided and managed in the namespace.

Since the medical document management system according to claim 17 is provided with knowledge export means, knowledge can be extracted by extracting any part of the knowledge space, knowledge tree, knowledge entry, entry attribute description, and parent-child relationship link constituting the knowledge management system. You can create a management subset and export it to another Knowledge Management System.

Since the medical document management system according to claim 18 is provided with knowledge import means, the knowledge management subset extracted by the knowledge export means or the knowledge management subset from a separately constructed knowledge management system is imported. You can then reconstruct namespaces, knowledge trees, knowledge entries, entry attribute descriptions, and parent-child relationship links.

Since the medical document management system according to claim 19 is provided with user authority management means, each of the namespace, knowledge tree, knowledge entry, knowledge entry attribute category, knowledge entry attribute description, and parent-child relationship link is created, edited, and deleted. As for the reference function, in the medical creation means, it is possible to manage the execution authority of the function for each user for the function of creating, editing, deleting, and referencing a medical document.

Since the medical document management system according to claim 20 is provided with knowledge browsing means, it is possible to browse the parent-child relationship between knowledge entries and the content of the knowledge attribute description of the knowledge entry.

Since the medical document management system according to claim 21 is provided with a knowledge inquiry receiving means, it is possible to receive inquiries about the recorded and managed knowledge contents.
In addition, the content of the inquiry can be answered by the knowledge inquiry response means.
In addition, since it is equipped with a means for receiving medical document content inquiries and a means for responding to medical document content inquiries, it is possible to make inquiries about the contents of recorded and managed medical documents and respond to the contents of inquiries.

The medical document management system according to claim 22 is provided with a search scope management means, so that it manages each of a namespace, a knowledge tree, a knowledge entry, an entry attribute description, a parent-child relationship link, and an editing user, and also manages the user. In the medical document creation means, the user who creates and edits the medical document is managed, and the knowledge management means or the medical document created by a specific user or a user group can be viewed, the knowledge inquiry reception means, and the medical document content inquiry reception. Exclude from the search target range of means, or conversely, search only the knowledge management means and medical documents created by a specific user or user group, the knowledge browsing, knowledge inquiry receiving means, and medical document content inquiry receiving means. It can be a target range.

It is a figure which shows an example of the simplest medical document management system. It is a figure which shows an example of the knowledge entry management master in the knowledge entry management means. It is a figure which shows an example in which the knowledge entry attribute description is performed using the knowledge entry attribute category in the knowledge entry attribute description management means. It is a figure which shows an example of the knowledge entry attribute category master in the knowledge entry attribute category management means. An example of a group of knowledge entries structured in a tree shape. It illustrates some of the knowledge entries that make up the knowledge tree. It is a figure which shows the example of the knowledge tree of (a) "symptom / laboratory findings", (b) "disease name". It is a figure which shows the knowledge tree group management master as a knowledge tree group management means. An example of the knowledge entry management master in the knowledge entry management method extended on the premise of the knowledge tree structure. It is a figure which adds the knowledge tree ID to the 1st column. This is an example of the knowledge entry attribute category management method extended on the premise of the knowledge tree structure. It is a figure which adds the knowledge tree ID to the 1st column. It is a figure which shows the content of the knowledge entry attribute description of "type I diabetes" and "type II diabetes". Taking the knowledge entry of "diabetes", which is one of the container-type knowledge entries corresponding to the branches, and the "type I diabetes" and "type II diabetes" corresponding to the leaves as examples, the parent-child relationship link and the attribute description are illustrated. It is a figure which shows various embodiments of a reference link. It is a figure which shows an example of the reference link which has a reference strength. It is a figure which shows an example of the script which should be executed with a reference link. It is a figure which shows an example of the case link making means. It is a figure which shows an example of the registration process of the case link and the diagnosis name after the diagnosis name is confirmed. It is a figure which shows an example which manages not only a symptom / finding but also a list of a pair of symptom / finding observed at the same time. It is a figure which shows an example of the total of the number of cases, the observation frequency for each symptom / finding, the frequency of a disease name, and the like. It is explanatory drawing of namespace management. It is explanatory drawing of the namespace management means. It is a figure which shows the screen composition example of the knowledge browsing means.

FIG. 2 shows a master file of a knowledge entry ID in the knowledge management means shown in FIG. 1 (knowledge entry management means).
The attribute description of each knowledge entry may be recorded in any database such as a relational database or mongodb in the form of text, XML, JSON, or an object in association with the knowledge entry ID (knowledge entry attribute description management means).

As the amount of knowledge entry attribute description increases, the outlook becomes worse. Therefore, as shown in FIG. 3, it is useful to record and manage the knowledge entry attribute description by dividing it into categories.
FIG. 4 shows a master file that manages the ID of the knowledge entry attribute category.
The knowledge entry attribute description may be recorded and managed in an arbitrary database in the form of being linked to the knowledge entry ID and the knowledge entry attribute category ID in FIG. 4 (knowledge entry attribute category management means).

As shown in FIGS. 1 to 4, even a simple example in which knowledge entries are listed in parallel has a certain effect such as vocabulary standardization, but there is a limit to covering the vocabulary of medical documents, and Fig. 5 and below. As shown in, the knowledge entry itself needs to be structured in a tree.
In FIG. 5, the structured knowledge management means of the present invention will be outlined by taking medical knowledge as an example.
As a knowledge tree, FIG. 5 (a) “symptoms and laboratory findings” and FIG. 5 (b) “disease name” are illustrated.
In addition, a knowledge tree such as "drug", "treatment", "insurance claim", etc. can be considered. Each knowledge tree consists of a set of knowledge entries connected by a parent-child relationship.
FIG. 6 is an example of the knowledge tree group management means, and manages the knowledge tree ID and the knowledge tree name in the knowledge tree group in the form of a master table.

FIG. 5B illustrates a group of knowledge entries constituting the “disease name” knowledge tree as an example of the knowledge tree.
The knowledge entry group of "disease name" is first divided into major categories such as "metabolic system", "digestive system", "musculoskeletal system", and "circulatory system". Each major classification is divided into middle categories such as "sugar metabolism system", "lipid metabolism system", and "amino acid metabolism system" in "metabolic system".
The "sugar metabolism system" in the middle category is further divided into sub-categories such as "diabetes" and "glycogen storage disease". The sub-category "diabetes" includes "type I diabetes" and "type II diabetes".
Here, "type I diabetes" and "type II diabetes", which correspond to the ends and leaves of the knowledge tree, are specific disease names. Knowledge entries such as minor classification, middle classification, and major classification, which correspond to branches, are composed by grouping out these common attributes, and these function as container-type knowledge entries containing the lower classification and leaf disease names.
Here, the classification hierarchy is large, medium, and small, but depending on the area, a deeper hierarchy may be used, or a shallow hierarchy may be sufficient. Here, the classification criteria based on the pathological condition were used, but in addition, the criteria for classification by site such as "neck", "cervical", "upper limb", "inflammatory system", "tumor system", etc. There are also criteria for classification by etiology such as "infectious system" and "genetic system". The administrator of the knowledge management system may set the classification criteria according to the purpose. In some cases, multiple knowledge trees with different classification criteria may coexist.

FIG. 7 is an example of the knowledge entry management means extended on the premise of the knowledge tree structure.
In the format of the master table, the ID of the knowledge entry in the knowledge tree (knowledge tree ID = 1 knowledge tree name "symptom / finding") is managed in the knowledge tree group.
In this example, the knowledge entry name is unique within the knowledge tree to which it belongs, but in some cases it may be something like "test findings / physical findings / chest / swelling" and "test findings / physical findings / abdomen / swelling". You may also define an intermediate route on the knowledge tree (route-dependent knowledge tree name). In this case, the knowledge entry name itself corresponding to the leaf may be duplicated because it is distinguished by the intermediate route. Further, if the knowledge trees to which they belong are different, they are distinguished from each other by the knowledge tree ID defined as shown in FIG. 6, so that the same knowledge entry name is allowed.
In this figure, the knowledge entries in the knowledge tree group are centrally managed regardless of the knowledge tree to which they belong, but in some cases, a master table is created separately for each knowledge tree to manage the knowledge entries. Is also good.
If the knowledge entry name is unique throughout the knowledge tree group regardless of the knowledge tree to which it belongs, the knowledge tree ID in the first column of FIG. 7 is unnecessary.
When changing the structure such as changing the parent-child relationship of the knowledge tree, if the knowledge entry name is unique, the change work can be minimized, but if the knowledge entry name is defined depending on the route, the route is rearranged. Knowledge entry names need to be redefined, which can be difficult to deal with.

FIG. 8 is an example of the knowledge entry attribute category management means extended on the premise of the knowledge tree structure.
In the format of the master table, the knowledge entry attribute category ID in the knowledge tree (knowledge tree ID = 2 knowledge tree name "disease name") is managed in the knowledge tree group.
The knowledge entry attribute category name must be unique within the knowledge tree to which it belongs, but if the knowledge tree to which it belongs is different, it is the same because it is distinguished from each other by the knowledge tree ID defined as shown in FIG. Knowledge entry attribute category names are also allowed.
In this figure, the knowledge entry attribute category in the knowledge tree group is centrally managed regardless of the knowledge tree to which it belongs, but in some cases, a master table is created separately for each knowledge tree, and the knowledge entry attribute category. May be managed.
If the knowledge entry attribute category name is unique throughout the knowledge tree group regardless of the knowledge tree to which it belongs, the knowledge tree ID in the first column of FIG. 8 is unnecessary.

9 (a) and 9 (b) show the contents of the knowledge entry attribute description of "type I diabetes" and "type II diabetes". It corresponds to the leaf at the end of the "disease name" knowledge tree in FIG. 5 (b). It can be seen that both knowledge entry attribute descriptions are common in many parts.
In order to avoid duplication of knowledge entry attribute description, if "diabetes", which is the upper knowledge entry of both, is set and the overlapping part is grouped out, the duplication of knowledge entry attribute description will be eliminated, the storage capacity will be reduced, and the visibility will be good. can get.

FIG. 10 illustrates the parent-child relationship link and attribute description by taking the knowledge entry of "diabetes", which is one of the container-type knowledge entries corresponding to the branches, and the "type I diabetes" and "type II diabetes" corresponding to the leaves as examples. It is a thing.
"Diabetes" has a link to "metabolic system" as a parent knowledge entry, and further has links to "type I diabetes" and "type II diabetes" as child knowledge entries.

Knowledge entry attribute categories of "diabetes" include <pathology> and <complications>.
<Pathological conditions> include decreased insulin secretion, hyperglycemia, and excretion of sugar in urine.
Each <pathology> item consists of a reference link to the relevant knowledge entry in another knowledge tree, the "symptoms / findings" knowledge tree.
By doing so, the attribute description is performed using the controlled vocabulary like a thesaurus, and the fluctuation of the expression can be suppressed.
Of course, here, the attribute description may be performed directly using the character string as in the conventional case, but it is not preferable because the fluctuation cannot be suppressed and the reference link function described later cannot be utilized.
<Complications> include "renal failure" and "arteriosclerosis obliterans".
The reference links to these complications are the reference links to the knowledge entry in the same "disease name" knowledge tree.

The etiology of "type I diabetes" is the rapid necrosis of beta cells in the pancreas, so the only treatment is insulin injection supplementation.
On the other hand, the etiology of "type II diabetes" is due to obesity and sugar overeating, and treatment is dietary restriction, oral administration of hypoglycemic agents, and finally injection of insulin.
In this way, "type I diabetes" and "type II diabetes" have different <cause> and <treatment>, but other <pathology> and <complications> are common to both, and are parental knowledge entries. It is described in a certain "diabetes".
In "type I diabetes" and "type II diabetes", which correspond to the leaves, even if only <cause> and <treatment> are described, the attribute description of <pathology> and <complication> of "diabetes", which corresponds to the parental knowledge entry, Furthermore, attribute descriptions such as higher metabolic diseases are inherited.
In this way, by grouping the common attribute description into the parent knowledge entry, the child knowledge entry can be completed with the minimum attribute description.
The attribute description of the knowledge entry may be individually viewed and configured in the mind while tracing the parent-child relationship, but the attribute description of the knowledge entry that is the parent rather than the knowledge entry can be created by the knowledge entry attribute description inheritance means. If all are inherited and collectively displayed as shown in FIGS. 9 (a) and 9 (b), the list of attribute descriptions becomes easy.

The attribute description inherited from the parent for each knowledge entry attribute category may be the knowledge entry attribute description of the child knowledge entry as it is, but what is the attribute description inherited to the knowledge entry attribute category of the child knowledge entry? If a different knowledge entry attribute description exists, the knowledge entry attribute description of the child knowledge entry overwrites or adds to the knowledge entry attribute description inherited from the parent.
This overwritten or added knowledge entry attribute description will be inherited further for the knowledge entries below the grandchild. The proper use of this overwrite or additional writing may be appropriately set by the knowledge entry attribute description inheritance means.

Although it is possible to describe attributes without using the knowledge entry attribute category as shown in Fig. 1, using the knowledge entry attribute category facilitates parent-child inheritance for each attribute category by the knowledge entry attribute description inheritance means. Can be done.
In addition, it can be said that it is more useful because the attribute description can be easily overwritten and added.
The parent-child inheritance of the knowledge entry attribute description has an inclusive relationship between the parent-child knowledge entries (in this example, "type I diabetes" and "type II diabetes" are included in the parent knowledge entry "diabetes"). In some cases, it is just an enumeration like the table of contents and chapters of a book, or the inclusion of content between parent and child knowledge entries, such as a car body and four tires that are in parallel as components of an automobile. If irrelevant, knowledge entry attribute description is not inherited.

<Case> In the knowledge entry attribute category, a case link to a medical record of a case having the disease name is recorded (case link creation means).
This makes it possible to directly refer to the patient record of the disease.
The case link to the case chart may be in any format as long as it enables access to the case information such as medical institution ID + patient ID, patient chart URL, patient chart file name, and the like. In addition, a knowledge entry attribute category such as <literature> may be provided to describe links to related books, files, and documents on the Web (external document reference means).

FIG. 11 shows various embodiments of the reference link.
FIG. 11A is an example showing the structure of {hyperglycemia}, which is a reference link in the <pathology> of "diabetes" in FIG.
It consists of a link to "hyperglycemia", which is a text used when displaying on a label, and "hyperglycemia", which is a knowledge entry in the "symptoms / findings" knowledge tree.
In some cases, it may be linked to <definition> which is a knowledge entry attribute category in "hyperglycemia" as shown in FIG. 11 (b).
The link here is "knowledge tree name / knowledge entry / (knowledge entry attribute category)", but it may be expressed directly in the URL format of the link destination.
The label is the display content when browsing.
As in this example, the linked knowledge entry name may be used as it is, but for easy viewing, “hyperglycemia blood glucose level> 140 mg / dl” may be used as shown in FIG. 11 (c).
By doing so, it is possible to easily list and grasp the outline without the process of individually referencing the link destination.

FIG. 12 shows a reference link for the <side effects and incidence> knowledge entry attribute category within the "furosemide" knowledge entry in the "drug" knowledge tree.
The first line consists of a "hyperkalemia" label, a reference intensity of "5%", and a reference link to the "hyperkalemia" knowledge entry in the "symptoms / findings" knowledge tree.
The second line consists of a "dehydration" label, a "1%" reference intensity, and a reference link to the "dehydration" knowledge entry in the "symptoms / findings" knowledge tree. The incidence is not uniform even with various side effects.
Having information on the frequency of occurrence as the reference strength clarifies the order of side effects to be considered. In addition, this frequency of occurrence is a prior probability in terms of Bayesian probability, and is useful for Bayesian estimation to estimate the causative drug when side effects occur due to administration of a plurality of drugs.
Further, by making the reference intensity variable according to the observation frequency in the case, it is possible to perform Bayesian estimation more suitable for the situation (reference intensity management means).

FIG. 13 shows the "herniated disk" knowledge entry in the disease name knowledge tree, along with the "MRI" label in the <examination> knowledge entry attribute category and the link to the "MRI" knowledge entry in the "examination" knowledge tree. The following is a flow chart of a script that performs a preliminary check when performing MRI. This script may be written directly in the reference link to "MRI", or a link to the recording location of the script may be written (script execution means).
In this way, by having a reference characteristic management means that includes reference strength and manages the script that is executed for reference, Bayesian inference can be used for response, and check mistakes can be eliminated to improve medical safety. do.

FIG. 14 is a case link creating means for creating a case link to a medical document in the referenced knowledge entry when the vocabulary used in the medical document is composed of reference links from the “symptoms / findings” tree. (Means for creating case links by symptom / finding).
From the case link group for each knowledge entry accumulated by this case link creating means, it is possible to easily obtain a list of medical documents or cases in which symptoms / findings such as "fever" are observed. Here, if not only the cases with positive findings in which fever is observed but also the cases with negative findings in which fever is not observed are managed by establishing a knowledge entry attribute category such as <negative cases>. It is even more useful in advancing the diagnosis of disease names.

FIG. 15 shows the treatment after the disease name of the patient is confirmed (here, “gastric ulcer”).
First, a case link to the patient is registered in the <case>, which is the knowledge entry attribute category of the knowledge entry "gastric ulcer" in the "disease name" knowledge tree.
Here, the patient ID is registered, not the individual medical document of the patient, which is the basis of the diagnosis. This is because symptoms / findings occur in individual medical documents, but the disease name is patient-based.
Here, registration of the case link in the <case> in the knowledge entry of symptoms / findings at the stage where the disease name is undecided, and registration of the case link in the <case> in the knowledge entry of symptoms / findings at the time when the disease name is confirmed. It is less confusing to register separately, for example, <cases with unconfirmed disease name> and <cases with confirmed disease name>.

For each of the lists of symptoms and findings observed in the patient, the disease name "stomach ulcer" is registered in the <disease name> of the knowledge entry attribute category.
This makes it possible to obtain a list of possible diagnostic names for each symptom and finding.
In addition, for each of the lists of symptoms / findings observed in the patient, the case ID is registered in the <case> knowledge entry attribute category of the knowledge entry of the symptoms / findings.
This makes it possible to easily obtain a list of cases in which each symptom or finding is observed (means for creating a case link by confirmed disease symptom / finding).
Here, it is more useful to register a list of diagnostic names not only for positive findings but also for negative findings.
Similarly, in the knowledge entry "stomach ulcer" itself, a list of symptoms / findings observed in the case is registered in the knowledge entry attribute category <symptoms / findings>.
This provides a list of symptoms / findings by disease. Here, it is more useful to register a list of symptoms / findings not only for positive findings but also for negative findings.
In addition, if the ID of the observed case is attached to each line of the list of symptoms / findings, the case having the symptom / finding can be easily searched.

In FIG. 16, not only the symptoms / findings observed in each case but also a list of pairs of symptoms / findings observed at the same time are managed.
Symptoms / findings are not necessarily independent and may be interrelated. In this case, when one symptom / finding is observed, another symptom / finding is often observed or not observed at the same time.
In this case, even if the correlated symptoms / findings are repeated, little new information can be obtained. Therefore, when proceeding with diagnosis, correlated symptoms / findings should be treated with lower priority.
In such cases, it is difficult to proceed with the above-mentioned differentiation with a simple list of observed symptoms / findings, and it is essential to aggregate pairs of simultaneously observed symptoms / findings.
Here, it is more useful to register a list of simultaneous observation symptoms / findings not only for positive findings but also for negative findings.

FIG. 17 is a compilation of the number of cases, the frequency of observation for each symptom / finding, the frequency of disease names, etc. from the list of cases, the list of symptoms / findings, the list of disease names, etc. obtained in FIGS. 15 and 16. It is a thing.
Although not shown, the frequency of simultaneously observed symptoms / findings is also tabulated from the list of simultaneously observed symptoms / findings. By using these frequency tabulations, conversely, in cases with unknown diagnosis names, it is possible to estimate the disease name from the observed symptoms and findings, and to recommend the next useful test to confirm the diagnosis. It becomes.

In daily clinical practice, the diagnosis name is often inferred by remembering patients with similar symptoms / findings in the past.
However, the number of cases is limited and the memory is ambiguous within the range of individual experience, so the accuracy is also limited.
In the knowledge entry of the observed symptoms / findings, as shown in FIG. 15, a list of case IDs of the past cases in which the findings were observed is managed in the <case> of the knowledge entry attribute category.
If the intersection of the list of case IDs having the symptoms / findings is obtained from the symptoms / findings that are sequentially observed during the examination, a set of cases that satisfy all the symptoms / findings at that time can be obtained (similar cases). Search method).
By aggregating the confirmed disease names of each case and arranging them in order of frequency, a list of disease name candidates of the case can be obtained (similar case disease name estimation means).

Another method for obtaining a list of disease name candidates is a method using the summary table shown in FIG.
Knowledge for each symptom / finding The list of disease names in which the symptom / finding was observed is managed in <disease name>, which is an entry attribute category.
The frequency distribution of disease names obtained by aggregation corresponds to the prior probability of disease names in Bayesian probabilities.
The posterior probabilities should be updated each time new symptoms / findings are observed (disease name list estimation method).
If multiple candidates for the disease name are obtained, the next question is what symptoms / findings should be sought in order to obtain a definitive diagnosis.

As shown in FIG. 17, the frequency distribution of symptoms and findings is obtained for each of the obtained disease name candidates.
Symptoms / findings with large frequency differences are useful for confirming the diagnosis by comparing disease name candidates.
As mentioned above, lower priority should be given to symptoms / findings that are likely to be observed simultaneously. You should proceed with medical examinations and tests to obtain the symptoms / findings, and update the posterior probabilities in the previous section with the obtained observation results. The magnitude of the posterior probability that will change if the observation result is obtained is the degree of contribution to the confirmation of the diagnosis of the symptom / finding (examination test recommendation means).
At this time, if the degree of contribution is the same, it is more practical to have less labor and cost. Efforts and costs (costs) should be quantified and displayed in descending order of contribution to confirmation of diagnosis per cost, and medical examinations and tests should proceed (medical examination test recommendation display method). When the posterior probability reaches a certain level, the purpose is achieved. It goes without saying that what is obtained here is to meet by probabilistic reasoning and to be used as a suggestion or an aid for a diagnosis by a doctor or the like, and is not a diagnosis itself with responsibility.

In FIG. 16, the frequency distribution for each disease name and symptom / finding is shown, but if the absolute number is small and the processing in the previous section cannot be performed sufficiently, the parent-child relationship link of each knowledge entry is used to rank higher. You can use the knowledge entry that corresponds to the parent. This is because the frequency distributions of other child knowledge entries of the parent's knowledge entry can also be aggregated and added up.

In this way, it is possible to obtain candidates for disease names and recommend candidates for the next examination or test to be performed in order to distinguish the disease names through a list of symptoms / findings, disease names, cases, etc. Will be.
It should be noted that what is provided in the present invention is a candidate for a disease name, a recommendation for a medical examination or a test, and is a probabilistic one. In other words, it provides the judgment material to the doctor who is responsible for the judgment, not the judgment itself.

The knowledge tree group shown in FIG. 5 is related to medical treatment, but there are innumerable other areas where knowledge should be described, such as art and industry.
It is essential that the knowledge tree name is unique and unique, but if the same knowledge tree name is used in other areas that are not known, it causes a troublesome problem.
In order to avoid this problem, a namespace is set for each area as shown in FIG. As a result, the knowledge tree name becomes the namespace + the knowledge tree name, so that the knowledge tree names in other areas can be considered completely separated.
FIG. 19 is an example in which the namespace ID and the namespace name are managed in the form of a master table (namespace management means). By adding the namespace ID to the first column of FIGS. 2, 4, 6, 7, and 8 as needed, large-scale knowledge management becomes possible without confusion.

FIG. 20 is an example of knowledge browsing means.
First, from the left, "medical" is selected here from the list of namespaces in the first column.
As a result, the second column lists the names of the knowledge trees that belong to the "medical" namespace. If you select the "disease name" knowledge tree here, a list of major categories such as metabolic system and circulatory system is first shown.
When "Metabolism system" is selected, a list of "sugar metabolism system", "lipid metabolism system", etc., which are the lower taxa, is displayed.
When "sugar metabolism system" is selected, the sub-categories such as "diabetes" and "glycogen storage disease" are listed.
When "diabetes" is selected, knowledge entry attribute categories such as <pathology> and <complications> are displayed.
When <pathological condition> is selected, reference links such as "hyperglycemia" and "HbA1c high value", which are attribute descriptions constituting <pathological condition>, are shown.
When "Hyperglycemia" is selected, the attribute categories of "Hyperglycemia" knowledge entry in the "Symptoms / Findings" knowledge tree, which is the reference link destination, such as <Definition> and <Test method> are displayed.
If you select <Definition>, the contents of the relevant knowledge entry attribute category will be displayed.

As shown in FIG. 20, it is useful to proceed with browsing manually, but it is also useful to make inquiries such as searches to the knowledge management system, perform processing such as set operations and logical operations on the search results, and display the results. Or downloading to a file is even more useful.
It would be efficient if a series of inquiry procedures could be described in a script or the like and automatically processed in order (knowledge inquiry receiving means and knowledge inquiry replying means).
Similarly, it is also useful to make inquiries such as searches for medical documents, perform processes such as set operations and logical operations on the search results, and display the results or download them to a file (). Medical document content inquiry receiving means, medical document content inquiry replying means to respond to the inquiry content)

The knowledge management system of the present invention is assumed to be constructed on the cloud. However, some companies and hospitals operate on-premises without connecting to the Web for security reasons.
In such a case, extract any part of the knowledge management system, knowledge tree, knowledge entry, entry attribute description, parent-child relationship link, create a knowledge management subset, and export it to another knowledge management system. The knowledge export means, the knowledge management subset extracted by the knowledge export means, or the knowledge management subset from a separately constructed knowledge management system can be imported into the name space, knowledge tree, knowledge entry, etc. By providing a knowledge import means that integrates and reconstructs entry attribute descriptions and parent-child relationship links into the knowledge management system, some or all of the knowledge management system maintained on the cloud will be incorporated into the company's internal knowledge management system. Can be done.
In addition, if an excellent knowledge management system can be constructed in-house and there are other purchase applicants, a part or all of the knowledge management system can be transplanted to another by the same procedure.

Since the amount of information handled by the knowledge management system is enormous, the cooperation of many people is required to create it.
Set permissions for namespaces, knowledge trees, knowledge entries, knowledge entry attribute categories, knowledge entry attribute descriptions, creating, editing, deleting, and referencing functions for each of the parent-child relationship links, depending on the permissions and skills of the people involved. Is indispensable (user authority management means).
This makes it possible to prevent the knowledge management system from being damaged by a user with poor understanding. In addition, by limiting the reference range by the user, it is possible to retain knowledge that should be kept secret.

To implement the knowledge management system of the present invention in a database, there are a graph database, a relational database (RDB) that has been widely used in the past, and a key-value store (KVS) that has recently attracted attention as a processing method for big data. .. It is possible to use any implementation, but each has its own advantages / disadvantages.
First of all, the graph database is good at setting and displaying network-like graph relationships, but it cannot be said that the processing speed is fast in large-scale processing, and it is not suitable for large-scale knowledge management systems. In RDB, the knowledge management system of the present invention is implemented by describing parent-child relationship links and knowledge entry attributes for each row of relations under master table management such as namespace, knowledge tree, knowledge entry, and knowledge entry attribute category. Can be done. Since the degree of freedom of search is high, the inquiry language such as SQL is complete, and there are many software assets from the past, implementation using RDB will be realistic.

KVS consists of one to several items of data (columns) and a set of key data.
A wide variety of free searches are inferior to RDBs. However, even with a large amount of data, distributed processing such as Map processing and Reduce processing is possible.
The case list in <cases> in FIG. 5 and the <cases> of "hyperglycemia" in the "symptoms / findings" knowledge tree will soon become a huge case list if an electronic medical record or the like is actually used.
The frequency distribution of one attribute can be easily obtained by any method, but there are multiple cases such as "What is the frequency of diabetic patients with HbA1c exceeding 10 and urinary protein 2+ or more?" When determining the frequency of factors from large-scale case data, it sometimes exceeds the processing capacity of RDB. In such cases, it is necessary to perform a set operation between the diabetic patient list, the HbA1c> 10 patient list, and the urinary protein> 2+ patient list. In such a case, distributed processing by Map / Reduce of KVS is extremely effective.

Further, in the knowledge management system of the present invention, the knowledge entries have a hierarchical structure. Therefore, for example, when searching a patient list of "fever", "remittent fever" or "remittent fever" which is a subconcept of "fever" is desired. It is possible to expand the search range to the patient list such as "" as needed.
As described above, the knowledge management system of the present invention may be most effective in combination such that the basic part is RDB and the processing such as the case list is performed by KVS, regardless of the database implementation method.

The user authority management means sets the authority for each user regarding access to the knowledge management system, but this alone is not sufficient.
There are examples of followers of conflicting theories repeatedly overwriting each other to deny each other's writing.
As a solution to such a case, a peaceful solution can be achieved by using a search scope management means that excludes the writing of another specific user from the search target from the viewpoint of a certain user.
Even if the same "chest pain" occurs, there is a high possibility of myocardial infarction if it occurs at a hospital specializing in heart disease, but there is a high possibility of rib fracture in the outpatient department of orthopedics.
In this way, the prior distribution of the frequency of occurrence of symptoms / findings often differs depending on the clinical department.
In such a case, it is useful to set the search scope in a place that matches similar clinical departments, medical institution types, and regions.

Although the embodiments have been described above, the specific configuration of the present invention is not limited to the above embodiments, and the present invention includes design changes and the like within a range that does not deviate from the gist of the invention.
For example, in this application, medical care is taken as an example, but other similar discussions such as education and personnel affairs are possible. The knowledge tree name, knowledge entry name, knowledge entry attribute category name, etc. shown in the figure are merely examples and may be changed according to the actual situation.
Experienced designers need to carefully define classification criteria such as knowledge trees and knowledge entries, and setting of knowledge entry attribute categories.
The classification criteria for this patent application are just one example. Once the classification criteria have been defined, subsequent fluctuations in the description will be minimal.

Claims (22)

Knowledge entry management means to record knowledge entries,
Equipped with a knowledge entry attribute description management means to record attribute descriptions related to knowledge entries
The vocabulary described in the knowledge entry attribute description management means has a link to another knowledge entry or the attribute description of another knowledge entry.
In the creation of a medical document, a knowledge management reference link utilization means that enables the vocabulary described in the knowledge entry attribute description management means to be described as a reference link in the medical document is provided.
A medical document management system characterized by having a knowledge entry attribute category management means for managing knowledge entry attribute descriptions by dividing them into categories. The knowledge entry management means manages a knowledge tree group management means that manages at least one knowledge tree, and data structure management that manages at least one knowledge entry that exists in each knowledge tree on the premise of a knowledge tree structure. Equipped with functions
Each knowledge entry consists of a knowledge entry attribute description that describes the attributes related to the knowledge entry and a knowledge entry parent-child relationship link that describes the parent-child relationship with other knowledge entries in the knowledge tree.
The claim is characterized in that the knowledge entry attribute description comprises a link to a knowledge entry belonging to a different or identical knowledge tree, or a knowledge entry attribute category of the knowledge entry, or a knowledge entry attribute description of the knowledge entry. 1 The medical document management system described. The medical document management system according to any one of claims 1 to 2, further comprising an external document reference means for referencing an external document or a group of external documents related to the knowledge entry attribute description . Any of claims 1 to 3 provided with a script execution means for managing a script to be executed when the vocabulary described in the knowledge entry attribute description management means is described as a reference link in a medical document. Described medical document management system. When describing a vocabulary described in a knowledge entry attribute description management means as a reference link in a medical document, the strength of the reference is set, or the strength is variable according to the observation frequency of symptoms / findings. The medical document management system according to any one of claims 1 to 4, wherein the medical document management system is provided with a strength control means. In the parent-child relationship
The medical document management system according to claim 2, wherein the knowledge entry attribute description of the parent knowledge entry is inherited to the knowledge entry attribute description of the child knowledge entry, and the knowledge entry attribute description is inherited. The medical document management system according to any one of claims 1 to 6, further comprising a case link creating means for creating a case link for a medical document with reference to a vocabulary. In the case link creating means,
Create a case link with symptoms / findings for each knowledge entry of observed symptoms / findings for each of the symptoms / findings observed in the case, or for a combination pair of symptoms / findings observed at the same time. The medical document management system according to claim 7, further comprising a means for creating another case link. The medical document management system according to claim 8, further comprising a function of classifying and aggregating case links according to symptoms / findings . In the above-mentioned means for creating a case link by symptom / finding ,
When the disease name of the case is confirmed and entered, for the symptoms / findings observed at the same time, a definite disease symptom / finding case link creation means is provided to create a case link by symptom / finding for the knowledge entry of the disease name. The medical document management system according to any one of claims 8 to 9. In cases where the disease name is uncertain
For each symptom / finding or symptom / finding pair observed in the medical document of the case, the intersection of the set of case links already created is obtained to obtain a list of cases similar to the case. The medical document management system according to any one of claims 8 to 10, further comprising a case search means. In the similar case search means,
The medical document management system according to claim 11, further comprising a similar case disease name estimation means that aggregates the confirmed disease names in the obtained case list and displays them in order of frequency. In cases where the disease name is uncertain
For the symptoms / findings observed in the medical document of the case, the symptoms / findings by disease name aggregated using the function to classify and aggregate the case links by symptoms / findings, or the observed symptoms / findings. 9. The medical document according to claim 9, further comprising a disease name list estimation means for estimating a list of likely disease names of the case using the disease name frequency distribution for each individual or both. Management system. Using the disease name-specific symptoms and findings observation frequency of the multiple disease names aggregated using the function to classify and aggregate case links by symptoms / findings , a list of symptoms and findings with a large difference in frequency distribution depending on the disease name can be obtained. The medical document management system according to claim 13, further comprising a medical examination recommendation means for estimating a list of symptom findings to be obtained next, which is effective for differentiating a disease name. When creating a medical document, the symptoms and findings that should be obtained by the examination and the recommendation list of the examination to be performed are automatically displayed, and the examination examination recommendation display that facilitates the creation of smooth examination records and examination orders. The medical document management system according to claim 14, further comprising means. In the knowledge tree group management means,
The medical document management system according to claim 2 , further comprising a namespace management means for managing a plurality of knowledge trees by dividing them into namespaces. The second aspect of claim 2 , wherein the knowledge export means for extracting an arbitrary part of a namespace, a knowledge tree, a knowledge entry, an entry attribute description, and a parent-child relationship link to create and export a knowledge management subset is provided. Medical document management system. The knowledge management subset extracted by the knowledge export means, or the knowledge management subset from a separately constructed knowledge management system is imported, and the namespace, knowledge tree, knowledge entry, entry attribute description, parent-child relationship link are imported. 17. The medical document management system according to claim 17, wherein the medical document management system is provided with a knowledge import means for reconstructing the above. User permission management that manages the execution authority of each user for the functions of namespace, knowledge tree, knowledge entry, knowledge entry attribute category, knowledge entry attribute description, and parent-child relationship link creation, editing, deletion, and reference. The medical document management system according to any one of claims 17 to 18, characterized in that the means is provided. The medical document management system according to any one of claims 1 to 19, further comprising a knowledge browsing means for browsing the parent-child relationship between the knowledge entries and the content of the knowledge attribute description of the knowledge entry. (I) Knowledge inquiry receiving means for accepting inquiries about recorded and managed knowledge contents, knowledge inquiry replying means for responding to inquiries,
In addition, (ii) medical document content inquiry receiving means for receiving inquiries about the contents of recorded and managed medical documents, medical document content inquiry replying means for responding to the contents of inquiries,
The medical document management system according to any one of claims 1 to 20, wherein the medical document management system includes at least one of the above (i) and (ii). Manages users by creating and editing namespaces, knowledge trees, knowledge entries, entry attribute descriptions, and parent-child relationship links, and accepts medical documents created by specific users or user groups as the above-mentioned knowledge viewing means and knowledge inquiries. Means, medical document content Inquiry reception means exclude from the search target range, or conversely, only the knowledge management means or medical documents created by a specific user or user group are excluded from the knowledge viewing means or knowledge inquiry reception means. The medical document management system according to claim 20 , further comprising a search scope management means which is a search target range of the medical document content inquiry receiving means.

Images