JP2005149083A - Electronic medical record input support apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an electronic medical record input support apparatus by which electronic medical records can be efficiently prepared. <P>SOLUTION: The voice of medical information inputted by voice is recognized and converted into character strings, and while referring to a dictionary in which medical terms are recorded correspondingly to items written in electronic medical records, medical terms corresponding to the items written in an electronic medical record are extracted from the character strings. The extracted medical terms are outputted as a report correspondingly to the items written in the electronic medical record. The efficiency of extraction can be improved by the edition of the dictionary, the reference of patient's past reports or the like. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to an electronic medical record input support device used in a medical institution such as a hospital, and more particularly to an electronic medical record input support device using voice recognition.

  In recent years, digitization of medical charts has progressed, and electronic medical chart systems are being introduced in many medical institutions. Such an electronic medical record is generally created manually by medical personnel such as doctors entering texts from the keyboard or by preparing standard texts in advance and selecting text from them. This is a heavy burden for medical professionals.

For this reason, it has been proposed to use speech input and speech recognition technology for recognizing speech and converting it into character data for creating an electronic medical record (see, for example, Patent Document 1 and Patent Document 2).
JP 2003-122849 A JP-A-10-261018

  However, in the conventional techniques as shown in Patent Document 1 and Patent Document 2, voice input and voice recognition are merely used as input means, and whether or not voice input information is necessary for an electronic medical record. Regardless of whether the data is uniformly converted / output or the conversion result needs to be manually edited by a medical staff, it takes time and effort to create an electronic medical record.

  The present invention has been made in view of the above circumstances, and an object thereof is to provide an electronic medical record input support apparatus capable of efficiently creating an electronic medical record.

  In order to achieve the above object, an electronic medical record input support apparatus according to claim 1 includes means for inputting medical information by voice, means for voice recognition of the input voice and converting it into a character string, and medical terms Dictionary data recording means recorded in association with electronic medical record description items, means for extracting medical terms corresponding to the electronic medical record description items from the character string with reference to the dictionary data recording means, and the extracted Means for outputting medical terms in association with the items described in the electronic medical record.

  In the electronic medical record input support apparatus according to the first aspect, the medical term is extracted from the information input by voice and output in association with the items described in the electronic medical record. Therefore, the electronic medical record can be efficiently created based on the output result. Examples of items described in the electronic medical record include a disease name, a symptom, a site, a period, and the like. Medical terms are recorded in association with these items and used as dictionary data.

  The output can be performed by screen display, printing, saving to a recording medium, transmission to another device or system via a communication line, and the like.

  An electronic medical record input support apparatus according to claim 2 is the electronic medical record input support apparatus according to claim 1, further comprising means for editing the dictionary data recorded in the dictionary data recording means.

  In the electronic medical record input support apparatus according to the second aspect, the extraction efficiency can be improved by editing the dictionary data, and the electronic medical record can be created more efficiently. As editing of the dictionary data, addition or deletion of medical terms, setting of association with items described in the electronic medical record, and the like can be performed.

  The electronic medical record input support apparatus according to claim 3 further comprises data storage means for storing the output result for each patient in the electronic medical record input support apparatus according to claim 1 or claim 2, wherein the extraction means includes: Medical terms are extracted with reference to the data storage means.

  Although the contents of the electronic medical chart vary depending on the patient, the electronic medical chart input support apparatus according to claim 3 can create the electronic medical chart more efficiently by referring to the data accumulated for each patient.

  The electronic medical record input support apparatus according to the present invention can efficiently create an electronic medical record.

  Hereinafter, preferred embodiments of an electronic medical record input support apparatus according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 shows a configuration of an electronic medical record input support apparatus 10 according to the present embodiment. The electronic medical record input support apparatus 10 includes a microphone 22 for inputting voice, a voice recognition unit 20 for recognizing the voice inputted by the microphone 22 and converting it into a character string, an analyzer 30 for analyzing the character string, and an analysis result. A report creation unit 40 that creates a report and a display 50 that displays the created report are provided, and the control unit 60 controls these components. The storage unit 70 stores dictionary data (see the example of FIG. 5) used for character string analysis and past reports for each patient.

  Also, as shown in FIG. 2A, the analyzer 30 includes a word conversion unit 32 that converts a speech-recognized character string into words, and a word classification storage unit 34 that classifies and stores conversion results with reference to dictionary data. The report creation unit 40 includes a layout creation unit 42 that creates a report layout, and a word placement unit 44 that places a word analysis result on the created layout and creates a report. As shown in the example of FIG. 2B, the word arrangement unit 44 arranges the result of classification and storage by the word classification storage unit 34 according to the layout generated by the layout generation unit 42.

  The electronic medical record input system 10 includes input / output devices (not shown) such as a keyboard, a mouse, and a printer in addition to the components shown in FIG. 1, and is configured to allow operations such as report printing and dictionary data editing.

  Next, processing in the electronic medical record input support apparatus 10 will be described. FIG. 3 shows the overall processing flow.

  First, in step 100, voice input is performed via the microphone 22. At this time, it is preferable to input identification information such as a patient's name and ID for reference of past reports and electronic medical records, storage of reports, and the like.

  In the next step 110, the speech recognition unit 20 recognizes the input speech and converts it into a word character string. When converted, the process proceeds to step 120, where the analyzer 30 classifies and stores this word character string with reference to the dictionary data and the patient's past report (described later).

  In step 130, the report creation unit 40 creates a report layout according to the items described in the electronic medical record. The report layout includes items to be output, association between items, output order, and the like.

  In the next step 140, the report creation unit 40 creates a report by arranging the words classified and stored in step 120 described above according to the layout created in step 130, and then proceeds to step 150 to display on the display 50. At the same time, it is stored in the storage unit 70.

  Next, the details of the word classification storage process in step 120 will be described. This processing flow is shown in FIG.

  First, in step 200, it is determined whether or not a word included in the word character string converted in step 110 described above corresponds to a disease name. This determination is made with reference to the dictionary data stored in the storage unit 70 and the patient's past reports. If the determination is affirmative, the process proceeds to step 202, the target word is stored in the disease name classification, and the process returns. If the determination is negative, the process proceeds to step 210.

  In step 210, it is determined whether the word to be determined corresponds to the symptom. This determination is made by referring to the dictionary data and the patient's past report as in step 200. If the determination is affirmative, the process proceeds to step 212, the target word is stored in the symptom classification, and then the process returns. If the determination is negative, the process proceeds to the next step 220.

  In step 220, it is determined whether the determination target word corresponds to the symptom. This determination is made by referring to the dictionary data and the patient's past report as in step 200. If the determination is affirmative, the routine proceeds to step 222, where the target word is stored in the symptom classification and then the routine returns.

  Thereafter, it is similarly determined whether or not the target word corresponds to each category. If the target word does not correspond to any category, in step 300, the word is stored unclassified and the process returns.

  In this processing routine, as shown in the example of FIG. 5, dictionary data in which character strings and words are classified corresponding to items described in the electronic medical record is referred to. In the electronic medical record input support apparatus 10 according to the present embodiment, by referring to such dictionary data, words necessary for creating a report or an electronic medical record can be extracted from information input by voice.

  For dictionary data, addition of medical terms, refinement of classification items, association between classification items, and the like may be performed based on reports and items in electronic medical records. Such work may be performed by a medical staff such as a doctor, or may be performed automatically with a learning function in the dictionary itself.

  FIG. 6A shows an example of a conversation between the doctor A and the patient B. Daily conversations that are not directly related to medical information may become a topic in conversations, and patients may not answer symptom or part clearly. Confirming the patient's answer can improve voice recognition and report creation efficiency.

  FIG. 6B is an example of a report created for the conversation shown in FIG. In this example, “symptom” and “time” are connected and output like “Chill from the day before yesterday” and “Cough from yesterday”, but it is output in consideration of the relationship between words and items like this. By doing so, you can create an easy-to-understand report and more efficiently create an electronic medical record. The association between words and items includes “symptom” and “part”, “time”, “numerical value” and “measurement information”.

  As described above, in the electronic medical record input support apparatus 10 according to the present embodiment, medical terms corresponding to the electronic medical record description items are extracted from the voice input information and output as a report. Electronic medical records can be created efficiently.

  In addition, the created report may be used not only for creating an electronic medical record but also for information disclosure to a patient, or may be used as electronic data by another device or system.

  Further, FIG. 6A shows a case where the conversation between the doctor and the patient is input by voice, but the voice input may be performed alone by the doctor reflecting the content of the conversation with the patient.

It is a block diagram of the electronic medical record input assistance apparatus which concerns on one Embodiment of this invention. It is a figure which concerns on one Embodiment of this invention and shows the processing content of an analyzer and a report preparation part. It is a figure which shows the processing flow of report preparation concerning one Embodiment of this invention. It is a figure which shows the detail of word classification memory | storage process concerning one Embodiment of this invention. It is a figure which shows the structural example of dictionary data concerning one Embodiment of this invention. It is a figure which concerns on one Embodiment of this invention, and shows the example of a report creation result corresponding to the example of a doctor's and patient's conversation, and this.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Electronic medical record input assistance apparatus, 20 ... Voice recognition part, 22 ... Microphone, 30 ... Analyzer, 40 ... Report preparation part, 50 ... Display, 60 ... Control unit, 70 ... storage unit

Claims (3)

Means for inputting medical information by voice;
Means for recognizing the input voice and converting it into a character string;
Dictionary data recording means in which medical terms are recorded in association with electronic medical record description items;
Means for extracting medical terms corresponding to the items described in the electronic medical record from the character string with reference to the dictionary data recording means;
Means for outputting the extracted medical terms in association with the items described in the electronic medical record;
An electronic medical record input support device.   2. The electronic medical record input support apparatus according to claim 1, further comprising means for editing dictionary data recorded in the dictionary data recording means. 3. The electronic apparatus according to claim 1, further comprising data storage means for storing the output result for each patient, wherein the extraction means extracts medical terms with reference to the data storage means. Medical chart input support device.

Images