JP3707738B2 - Medical remuneration statement examination support apparatus and method and program thereof - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
  The present inventionMedical remuneration statement examination support apparatus and method and program thereofAbout.
[0002]
[Prior art]
The insured of the public medical insurance pays a partial contribution to the hospital, clinics, pharmacies, medical institutions such as dental clinics (hereinafter referred to as medical institutions, etc.), treatment, prescription of drugs, hospitalization You can receive medical services such as In addition, even when a doctor's prescription is received, the insurance pharmacy can prescribe the drug by paying a partial contribution.
A medical institution or the like is required to request an insurer of public medical insurance to pay a contribution to be paid by the insurer as a medical fee.
[0003]
Here, a medical fee payment request to an insurer from a medical institution or the like is made via a bill called a medical fee statement (hereinafter referred to as a receipt). The receipt describes in detail matters relating to the contents of the medical practice and the dispensing, such as the number of treatments for the insured person and the type and number of medications, and payment is made in accordance with the description.
[0004]
An examination / payment institution is interposed between the medical institution and the insurer as an institution for conducting the examination of the receipt in order to confirm the appropriateness of the receipt and realize a smooth payment of the medical fee.
Therefore, receipts created by medical institutions etc. are collected at the examination and payment institution, and first the administrative assistant is inspected for doubts, followed by doctors who have sufficient technical and technical knowledge (hereinafter referred to as “subjects”). Is referred to by the person in charge of review). As a result, a receipt with a basic error is returned to a medical institution, etc., and a receipt that is appropriate or that has become appropriate after examination is sent to each insurer.
Most of these processes have been performed by paper reception.
[0005]
However, since most of the receipts currently handled in the medical fee claim office are paper, the administrative assistant and the examiner must inspect and examine each of these huge paper receipts one by one. The work is becoming unscientific and inefficient. Therefore, despite the fact that the level of errors and the level to be focused on correspondingly differ considerably, it is the situation that the same human resources are being allocated, and sufficient administrative assistance and It is in a situation where the effect of the examination cannot be obtained.
[0006]
Conventionally, as a system and method related to such a receipt and insurance procedure, when an insurer receives a receipt, the claim for the receipt is settled or returned to a medical institution (see Patent Document 1), medical information The insurance card data for each insured person is stored in the database of the medical information storage management company that is stored, and the insurance card at the time of medical examination is confirmed and billed to the insurer through this management company. There are those that reduce the burden (see Patent Document 2), and those that confirm the existence of the insured person's qualification with the qualification authority to prevent loss of medical expenses for the insurer (see Patent Document 3) .
[0007]
[Patent Document 1]
JP 2001-344337 A ([0012], FIG. 1)
[Patent Document 2]
JP 2002-41649 A ([0034], FIG. 7)
[Patent Document 3]
Japanese Patent Laid-Open No. 2002-109069 ([0020] to [0028], FIG. 1)
[0008]
[Problems to be solved by the invention]
  However, all of the conventional technologies are only intended to solve the problems of ensuring efficient office work and reducing the processing burden in insurers and insured persons of public medical institutions, medical institutions, etc. However, it does not attempt to solve the issues of ensuring efficient office work and reducing processing burdens at examination and payment institutions.
  The present invention has been made in view of the problems of ensuring efficient office work and reducing the processing burden in the examination and payment organization, and can sufficiently improve the efficiency of office assistance work and review the load of examination work. In this way, it is possible to easily find errors for each receipt, and to appropriately allocate human resources according to the degree of improperness and the degree to which each receipt should be focused. NaMedical remuneration statement examination support apparatus and method and program thereofThe purpose is to provide.
[0009]
[Means for Solving the Problems]
In order to solve the above-mentioned problems, the present invention aims to improve the work efficiency by converting the paper receipt into text data, in particular, processing the portion that could not be converted into text data completely by the conventional technology and using it for examination. . That is, a character string (keyword) that has a high possibility of being described in the receipt is prepared as a dictionary, and if there is a keyword that matches this dictionary in the combination of parts cut out from the imaged paper receipt, it is Registered as text data to enable machine processing. Conventionally, it has been done manually with information on paper, so the effect of reducing the burden obtained is great.
[0010]
Also, data mining processing is performed for the item of receipt information that has been converted to text. A large amount of receipt data is used to extract highly credible sorting rules based on the know-how obtained from past examinations, and the receipts are sorted using these rules. Divide into a group of receipts where there are few receipts. As a result, it is possible to extract a receipt that does not need to be examined and perform an efficient examination.
Furthermore, if new know-how can be obtained from those that have been examined, the data mining perspective can be changed and new rules can be generated, which is useful information for subsequent examination support.
In addition, applying judgment rules that consist of keywords extracted at the time of reading to a group of receptors with many errors in error makes it possible to further narrow down the highly error-recepts at various angles. From the point of view and prioritized examinations, the work of the person in charge of the examination can be made more efficient.
As a result, it is possible to sufficiently improve the efficiency of the work and reduce the burden of examination processing, facilitate the discovery of errors for each receptor, and cope with the level of errors that each receptor has and the level to be focused on. It is possible to accurately allocate human resources.
[0011]
DETAILED DESCRIPTION OF THE INVENTION
FIG. 1 is a diagram cited for explaining a relationship between a model for realizing a medical fee description information reading method and a medical fee statement examination support method according to an embodiment of the present invention, and its user.
In FIG. 1, reference numeral 1 denotes a medical institution, reference numeral 2 denotes a screening / payment institution, and reference numeral 3 denotes an insurer. Here, a mechanism is also described in which a reward (medical fee) is charged to the insurer according to a medical care performed on a patient such as an insured.
The medical institution 1 such as a hospital or a pharmacy makes a request for the medical treatment fee to the examination / payment institution 2, and the examination / payment institution 2 examines the medical treatment invoice request from the medical institution 1 and is appropriate if necessary. After the assessment, the insurance fee is counted for each insurer, and the medical fee is charged to the insurer 3 to whom the patient is enrolled as an insured person. The insurer pays a medical fee to the examination / payment institution, conducts an examination / inspection by the insurer, and makes a re-examination request to the examination / payment institution.
[0012]
The medical institution 1 charges the medical institution 1 with respect to the examination and payment institution 2 based on a receipt created for each patient and for each month. Most of the receipts provided by the medical institution 1 are based on paper based on handwriting or printed by a personal computer or the like, but recently, text based on a magnetic recording medium or code base is also seen.
In view of this, in the present embodiment, it is considered that the information described in the paper-based receipt is converted into text data because the efficiency of the business cannot be obtained with the paper-based one.
[0013]
In other words, the receipt includes information on the prefecture number, medical institution code, date of birth of the patient, etc., all of which can be read by OCR. However, there are cases where characters are small in the description part relating to the medical practice, such as the injury / illness name column and the summary column, and when there is an overlap with a ruled line, misreading increases.
Therefore, the character read by OCR or the like is recognized as a part, and a combination of them is considered. At that time, keywords that are highly likely to be described in a receipt are extracted from medical insurance-related materials (S01) and stored as a receipt dictionary, so that there is a keyword that matches the receipt dictionary in the combination of read parts. It is recognized and stored as text (keyword information).
[0014]
At the present stage, most of the receipts submitted by medical institutions are paper (shown as “handwritten receipt” and “paper receipt” in the figure), but they are billed for magnetic recording media such as flexible disks. As described above, there are also receptors. Some of the claims for magnetic recording media are in the text format shown as "printing receipt" in the figure, or are partially encoded as shown in the figure as "magnetic receipt". Can be considered.
Therefore, the paper-based receipt data (keyword information) obtained from the OCR and keyword extraction and the receipt requested from the magnetic recording medium are encoded (S02) and registered in the database. As a result, the examination / payment institution 2 can handle the receipts accepted in various forms in the transitional period during the transition to computerization, and improve the work efficiency.
[0015]
Further, as described above, the examination / payment institution 2 obtains the receipt data and conducts the administrative check of the receipt by the computer, and then performs the examination support process (S03). The examination support processing work means that the receipts after the administrative inspection are sorted into a group of receptors having many errors and a group of receptors having few errors in accordance with the sorting rules.
Based on the know-how obtained from the results of previous examinations through data mining, rules with high credibility are found, and the receipts are sorted based on this. Data mining processing is processing of a large amount of various data using statistical and mathematical methods. Here, association extraction that searches for a combination pattern of highly relevant data is used.
[0016]
If you sort the receipts using the rules and the know-how of the judges, you can sort them into a group of receipts with many erroneous receipts and a group of receipts with few erroneous receipts. This will reduce the burden on the examiner. Furthermore, it is possible to realize an efficient examination by conducting a more focused examination with respect to a group of receptors having many erroneous receipts. In addition, if new know-how can be obtained from what was actually examined, it is possible to change the viewpoint of data mining and generate new rules, which will be useful information for subsequent examination support. .
In addition, applying judgment rules composed of keywords extracted at the time of reading to a group of receptors with many errors in error makes it possible to further narrow down the highly error-prone receptions at various angles. From the point of view and prioritized examinations, the work of the person in charge of the examination can be made more efficient.
[0017]
Further, if the above is executed as examination support, when a receipt substantive examination is performed (S04), a receipt as intended can be extracted under various conditions. In addition, since past receipts are stored as data, it is possible to easily search and inspect even when conducting a general inspection, and to perform an efficient examination. For example, search for a disease name that causes a lot of errors, which is noticed when a person conducts a paper review, screening that focuses on high-cost medical expenses, or a prescription such as a cold that is unlikely to make a mistake. It is also possible to extract.
[0018]
FIG. 2 is a block diagram showing a functional development of the internal configuration of the receipt management system 4 in which the medical remuneration statement information reading device according to this embodiment is mounted.
In FIG. 2, the medical fee detailed statement information reading device includes an image file 201, a character reading unit 202, a text file 203, a virtual character reading file 204, a receipt data capturing unit 205, a receipt dictionary 206, a keyword file. 207, a recording medium file 208, a code conversion unit 209, a code table 210, a code file 211, and a receipt dictionary generation unit 212.
[0019]
The image file 201 stores an image when a paper-based receipt is read by OCR. The character reading unit 202 has a function of reading information such as a basic information column of a receipt from the image file 201, and further has a function of extracting character line candidates such as a summary column and cutting out a character string as a part. Information in the basic information column and the like is stored in the text file 203, and parts cut out from the character line candidates are stored in the virtual character reading file 204.
The receipt data capturing unit 205 compares any combination of character string components stored in the virtual character reading file 204 with a receipt dictionary 206 in which a frequently used character string described in the receipt is described in advance, When there is a character string that matches the receipt dictionary 206, it has a function of extracting the character string as text data, and the extracted character string is stored in the keyword file 207.
[0020]
Further, the code conversion unit 209 receives the text data captured by the character reading unit 202 and the receipt data capturing unit 205, and the text data of the receipt information requested by the magnetic recording medium captured in the recording medium file 208. The code table 210 is coded and stored in the code file 211.
Note that the receipt dictionary generation unit 212 has a function of extracting a keyword that is highly likely to be described in a receipt from medical insurance related materials in advance and generating a file as the receipt dictionary 206.
[0021]
FIG. 4 is a flowchart cited for explaining the operation of the medical fee detailed statement information reading apparatus in the present embodiment, and specifically shows the processing procedure of the medical fee detailed statement information reading program of the present embodiment.
Hereinafter, the operation of the medical remuneration statement information reading device of this embodiment will be described in detail with reference to the flowchart shown in FIG.
[0022]
First, the examination / payment institution 2 receives a paper-based receipt from the medical institution 1 and a receipt recorded on a recording medium (S50).
In the case of a paper-based receipt, characters of the receipt information described in the receipt are read (S51). As shown in FIG. 7, the receipt includes a prefecture number, a medical institution code, and the date of birth of the patient. There is an OCR readable area A such as, and a summary column B with a description part of a medical practice. The former is supplied to the code conversion unit immediately after character reading, while the latter takes the image and then converts it into text-based information by performing the following processing.
[0023]
The reading of printed characters described in the summary column B will be briefly described below.
First, the character reading unit 202 extracts character line candidates and character extraction candidates from the input image accumulated in the image file 201 (S52), and stores them in the virtual character reading file 204 (S53). The character line candidates are the vertex coordinates of the circumscribed rectangle in the up, down, left, and right directions.
[0024]
Next, the receipt data capturing unit 205 reads out character string cutout data stored in the virtual character reading file 204 in any combination, and a receipt dictionary 206 in which character strings frequently used described in the reception are registered in advance. Is compared (S54). Here, when there is a character string that matches the receipt dictionary 206, the character string is taken into the keyword file 207 as text data (S55). Thereafter, the code is converted together with the read data of the OCR readable area A and the receipt data requested by the magnetic medium (S56), and stored in the code file (S57).
In this way, a character string that is captured from an input image is recognized as part information, and all combinations of the part information and keywords that are likely to be described in the receipt from medical insurance related materials are registered. If there is a matching character string in the data of the dictionary 206, it can be extracted as text data. By reading as many parts as necessary to realize the examination support of the receipt, it is possible to efficiently obtain the information in the summary column, which was conventionally impossible to read completely by OCR and often misread. It is possible to carry out extraction much more efficiently.
[0025]
Also, paper-based receipt data previously obtained from OCR and keyword extraction, receipt data (image file 201, text file 203, keyword file 207) extracted from the summary column, etc., and receipt data requested by the recording medium ( The magnetic medium file 208) and data obtained by encoding the respective text data are collectively managed by the receipt management system 4 as a receipt DB. As a result, the examination / payment institution 2 can handle the receipts received in various forms in the transitional period during the transition to computerization in the same manner in the same system, thereby improving the work efficiency.
[0026]
FIG. 3 is a block diagram showing the functional expansion of the internal configuration of the medical fee description examination support apparatus according to this embodiment.
In FIG. 3, the medical remuneration statement review support device includes a receipt DB 213, a sorting rule selection unit 214, a reception sorting unit 215, a sorting rule DB 216, a determination rule selection unit 217, a receipt extraction unit 218, and a determination rule. The DB 219 includes a rule / error receipt image display unit 220, a sorting condition capture unit 221, a sorting rule update unit 222, a determination condition capture unit 223, and a determination rule update unit 224.
[0027]
  The sorting rule selection unit 214 has a function of displaying a sorting rule from the sorting rule DB 216 and selecting a sorting rule to be applied from among these as required.Specifically, the sorting rule selection unit 214 displays a sorting rule that is stored in the sorting rule DB 216 and is generated by data mining from past examination results, or a pre-defined sorting rule, and is selectively input. The sorting rule is read from the sorting rule DB.
[0028]
  The reception sorting unit 215 is a sorting rule selection unit.214By applying the rule selected in (1), the function is to divide the receipt DB 213 that is collectively managed by the receipt management system 4 into a reception group that includes many erroneous receptions and a reception group that includes few erroneous receptions.Specifically, the receipt sorting unit 215 determines whether or not the medical fee description matches the condition indicated by the previously selected sorting rule, and when there is a medical fee specification that matches the condition, The medical fee remuneration statement is determined as a medical fee remuneration statement that requires examination.
[0029]
  The sorting condition fetching unit 221 has a function of determining a sorting rule from an evaluation of an association rule analysis using a large amount of past receipt data. As an application condition of this sorting rule, a support level indicating the generality of the rule and a reliability level indicating the reliability of the rule are used. For example, “support level 2.0% or higher, confidence level 99.9% or higher” To be determined. These rules are evaluated as needed from the result of data mining newly performed using the latest receipt data, and the sorting rule update unit 222 updates the sorting rule DB 216.The classification rule update unit 222 performs a predetermined calculation defined for evaluation from the result of data mining performed using the latest medical fee description, and performs a classification when the calculation result indicates a predetermined value. It has a function of updating the sorting rules stored in the rule DB 216.
[0030]
The determination rule selection unit 217 has a function of displaying a determination rule from the determination rule DB 219 and selecting a determination rule to be applied from among the determination rules as necessary.
[0031]
The receipt extraction unit 218 has a function of extracting a receipt corresponding to the rule selected by the determination rule selection unit 217.
[0032]
Further, the determination condition capturing unit 223 inputs a determination rule determined from past examination results and know-how. As these rules, a rule generated from the examination result of new receipt data is input, and registration / modification is performed in the judgment rule update unit 224, and the judgment rule DB 219 is updated.
[0033]
On the other hand, in the rule / error receipt image display unit 216, a receipt including an error extracted by applying the sorting rule, the determination rule, and the selected determination rule is displayed as an image.
In addition, here, the item that has been determined as a receipt containing an error is highlighted with a red line or the like, and the determination rule applied at this time is displayed in a sticky note. A message is displayed.
[0034]
FIG. 5 and FIG. 6 are flowcharts cited for explaining the operation of the medical fee specification examination support apparatus in the present embodiment. Specifically, the processing procedure of the medical fee specification examination support program of the present embodiment Indicates.
Hereinafter, the operation of the medical remuneration statement examination support device of the present embodiment will be described in detail with reference to the flowcharts shown in FIGS.
[0035]
Here, the sorting rule selection unit 214 selects a rule to be applied as necessary from the rules obtained by analyzing the correlation rules of the past receipt data (S60). At this time, the contents of the sorting rule DB 216 are displayed on the rule / error receipt image display unit 220, and a rule to be applied can be selected. By pressing the “Apply Rule” button on the screen (S61 “ON”), the selected rule is applied, and the receptor group 215 is likely to contain an error, and the receipt is less likely to contain an error. Sorted into groups (S63). The following determination rule is applied to a group of receptors that are determined to have a large number of receipts that contain errors.
[0036]
The person in charge of screening extracts a receptor from a group of receptors that are likely to contain classified errors by further applying a determination rule by the receptor extraction unit 218 and performs screening.
First, the rule stored in the determination rule DB 219 is displayed, and a condition for selecting or extracting the determination rule is input (S64 “with input”). By pressing the “apply rule” button (S65 “ON”), the selected rule is applied (S66), and only the receipts that meet the conditions are extracted from the group of receipts and displayed in a list (S67). When a receipt to be viewed from this list is selected and the “image display” button is pressed (S68 “ON”), the receipt can be displayed as an image (S69). At this time, the parts that violate the rules are marked.
Further, the name of the determination rule applied at that time is displayed as a sticky note, and when the sticky note is clicked (“Yes” in S70), the reason for determining that the receipt contains an error is displayed as a message (S71).
[0037]
FIG. 8 shows an example of a description item of a receipt used when creating the sorting rule described above. Here, from the basic information column, the medical care month, the number of medical days, age, gender, etc., from the injury and sickness name column, the number of disease names and disease classification, from the score column, the presence or absence of each medical practice, from the decision column, the presence or absence of decision points Is read.
[0038]
9, 10, and 11 show examples of screens of the rule / error receipt image display unit 220 when applying the sorting rule and the determination rule.
FIG. 9 shows a selection screen for selecting a sorting rule, FIG. 10 shows a selection screen for selecting a determination rule, and FIG. 11 shows a screen on which the extracted receipt is displayed as an image.
In the screen for selecting a sorting rule in FIG. 9, the sorting rule read from the sorting rule DB 216 is displayed as the rule (a) used for sorting. This rule can be selected as required.
The screen displayed when using the determination rule in FIG. 10 displays the determination rule list (b) used in rule application and the keyword list (c) in the receipt extracted by the receipt data capturing unit 205, and is also in the screen Includes a “rule application execution” button that is clicked by the examiner when applying a judgment rule to narrow down the receipts, and a “screen display” that is executed by the examiner in order to output the filtered receipt as an image. The button is assigned. On the other hand, FIG. 11 shows a state after the “rule application execution” button in FIG. 10 is pressed, and a receipt according to the selected rule is extracted and displayed on the screen. The received rule application result list (d), the applied rule name (e) used for narrowing down the displayed on-screen receipt, and the narrowed-down receipt image (f) are displayed.
[0039]
As described above, according to the present invention, a character string (keyword) that is highly likely to be described in a receipt is prepared as a dictionary, and a keyword that matches the dictionary is selected from combinations of component information read as images from the receipt. If there is, register it as text data, and read the summary column, which was impossible with OCR in the past, by reading as many parts as necessary to realize the review support of the receipt. It has a function that can obtain important data.
Also, sorting rules are created based on the classification criteria based on past examination results obtained by data mining and the know-how possessed by the judges, and are classified into those receiving a group with many errors and those with few errors. . Further, by applying a determination rule from a keyword to a group of receipts with many errors in error, it becomes possible to extract a screening that requires intensive screening and perform screening.
In addition, if new know-how can be obtained from those that have been examined, it is possible to change the viewpoint of data mining and generate new rules, which will be useful information for subsequent examination support.
[0040]
【The invention's effect】
As described above, according to the present invention, it is possible to easily find an error for each medical fee statement due to the improvement of the efficiency of the office support work and the reduction / review effect of the examination processing load, and each receipt has. It is possible to accurately allocate human resources according to the level of inaccuracy and the level of focus.
[Brief description of the drawings]
BRIEF DESCRIPTION OF DRAWINGS FIG. 1 is a diagram cited for explaining the relationship between a model for realizing a method for reading medical remuneration statement information and a screening support method in the present embodiment, and its use subject.
FIG. 2 is a block diagram showing a functional development of an internal configuration of a receipt management system 4 in which a medical fee detailed statement information reading device according to the present embodiment is mounted.
FIG. 3 is a block diagram showing a functional development of the internal configuration of a receipt management system 4 in which the medical fee description examination support apparatus according to the present embodiment is installed.
FIG. 4 is a flowchart cited for explaining the operation of the medical remuneration statement information reading device in the present embodiment.
FIG. 5 is a flowchart cited for explaining the operation of the medical fee description examination support device in the present embodiment.
FIG. 6 is a flowchart cited for explaining the operation of the medical fee description examination support device in the present embodiment.
FIG. 7 is a diagram cited for explaining regions constituting a medical fee remuneration statement used in the present embodiment.
FIG. 8 is a diagram illustrating an example of description items of a medical fee remuneration statement used for association rule analysis used in the present embodiment.
FIG. 9 is a diagram illustrating an example of a screen configuration used by the medical fee description examination support device according to the present embodiment.
FIG. 10 is a diagram showing an example of a screen configuration used by the medical fee description examination support device in the present embodiment.
FIG. 11 is a diagram showing an example of a screen configuration used by the medical fee description examination support device in the present embodiment.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 4 ... Receipt management system, 201 ... Image file, 202 ... Character reading part, 203 ... Text file, 204 ... Virtual character reading file, 205 ... Receipt data taking-in part, 206 ... Receipt dictionary, 207 ... Keyword file, 208 ... Recording medium File, 209 ... Code conversion unit, 210 ... Code table, 211 ... Code file, 212 ... Recept dictionary generation unit, 213 ... Receive DB, 214 ... Sorting rule selection unit, 215 ... Receive sorting unit, 216 ... Sorting rule DB, 217 ... Determination rule selection unit, 218 ... Receive extraction unit, 219 ... Determination rule DB, 220 ... Rule / error receipt image display unit, 221 ... Classification condition acquisition unit, 222 ... Classification rule update unit, 223 ... Determination condition acquisition unit, 224 ... judgment rule update unit

Claims (9)

A medical fee statement examination support apparatus having an input unit, a display unit, and a processing unit for supporting examination when examining the items described in the medical fee statement,
The processor is
A character reading unit that takes the medical fee description as an image, reads a character line candidate with respect to a character string described in an item field of the medical fee specification, and cuts out the character string as a component;
The combination of the parts of the character string cut out by the character reading unit is compared with the medical fee description dictionary in which the frequently used character string described in the medical fee description is described in advance. When the combination of character strings that match the book dictionary matches, the medical fee statement data capturing unit that captures the character string as keyword data;
A keyword list display unit for displaying the keywords extracted from at least one item of the medical remuneration statement by the character reading unit on the display unit;
A determination rule list display unit that displays a determination rule generated by data mining from the past examination results and stored in the database on the display unit, and prompts the user to input a determination rule to be applied;
It is determined whether or not the extracted keyword matches the condition indicated by the input determination rule, and when there is a keyword that matches the condition, a medical remuneration statement including the keyword is extracted and the A medical statement display unit for displaying an image on the display unit;
A medical remuneration statement examination support device characterized by comprising: The character reader is
Character line candidates and character extraction candidates are extracted from the captured image, and further, the character extraction candidates are stored as virtual character reading files. Then, combinations of character strings that match the medical fee description dictionary are used as keyword files. The medical remuneration statement examination support apparatus according to claim 1 , wherein the medical remuneration statement examination support apparatus is stored. The code further includes a code conversion unit that encodes the text data of the item, the medical fee description data requested by the recording medium, and the text data of the basic information column and stores the encoded data in a code file. The medical fee remuneration statement examination support device according to 1 or 2 . The processor is
Based on the result of the data mining performed using the latest medical remuneration statement, a predetermined calculation defined for evaluation is performed, and the determination stored in the database when the calculation result indicates a predetermined value The medical remuneration statement examination support device according to claim 1 , further comprising a rule update unit for updating a rule. The processor is
The medical reward specification display unit, medical specification examination support apparatus according to claim 1, characterized in that to highlight items of medical fees specification that matches the conditions. The processor is
The applied determination rule is displayed as a sticky note on the medical remuneration statement display unit, and when the sticky note is selected by input from the input unit, a medical remuneration statement item that matches the condition is displayed as a message. The medical statement examination support device according to claim 1 . The processor is
The medical remuneration statement that matches the condition is displayed as an image on the medical remuneration statement display unit when a determination rule that is an extraction condition is specified by an input from the input unit. 1. A medical statement examination support device according to 1. A method for supporting the examination of a medical fee statement, in which examination of items described in the medical fee statement is performed by a computer,
The computing means of the computer is
Capture the medical fee description as an image, read out the character line candidate for the character string described in the item column of the medical fee description, and cut out the character string as a part,
And combinations of parts of the cut-out character string, the medical fees higher string of how often used as described in the specification is compared with the prewritten reimbursement specification dictionary, to the medical fee specification Dictionary When the combination of matching character strings matches, the character string is imported as keyword data.
The keyword extracted from at least one item of the read medical remuneration statement is displayed, and the determination rule generated by data mining from the past examination results and stored in the database is displayed and applied to the user. Prompts input of a determination rule to be determined, determines whether the extracted keyword matches a condition indicated by the input determination rule, and when there is a keyword that matches the condition, Extracting and displaying the medical remuneration statement including images,
A method for supporting examination of medical remuneration statements, characterized by A program used in a medical fee statement examination support apparatus for examining items described in a medical fee statement,
Capturing the medical fee description as an image, reading out character line candidates for the character string described in the item field of the medical fee description, and cutting out the character string as a component;
The combination of the extracted character string components is compared with the medical fee description dictionary in which the frequently used character string described in the medical fee description is described in advance, and the result matches the medical fee description dictionary When the combination of character strings to be matched matches the step of taking the character string as keyword data,
The keyword extracted from at least one item of the read medical remuneration statement is displayed, and the determination rule generated by data mining from the past examination results and stored in the database is displayed and applied to the user. Prompts input of a determination rule to be determined, determines whether the extracted keyword matches a condition indicated by the input determination rule, and when there is a keyword that matches the condition, Extracting a medical remuneration statement including the image and displaying the image;
A medical fee statement review support program that allows a computer to execute

Images