KR102597133B1 - Clinical decision support methods and device based on phr and medical records - Google Patents

Abstract

A clinical decision support method and device based on PHR and medical records are disclosed. According to an embodiment of the present invention, the clinical decision support method based on PHR and medical records is, as the patient's patient information is received from the EMR system, the EMR maintained in association with the patient in each of the EMR database and the PHR database. collecting data and PHR data; Analyzing the EMR data and the PHR data to generate analysis results related to clinical decision making; And it may include transmitting the analysis results to the EMR system.

Description

Clinical decision support method and device based on PHR and medical records {CLINICAL DECISION SUPPORT METHODS AND DEVICE BASED ON PHR AND MEDICAL RECORDS}

The present invention provides a PHR and a PHR that provide notifications so that doctors can make clinically meaningful decisions by analyzing medical records stored in the patient's PHR (Personal Health Record) and EMR (Electronic Medical Record) when treating patients. This relates to clinical decision support methods and devices based on medical records.

Typically, the reality of treatment at domestic hospitals and clinics is often expressed as ‘1 hour waiting and 3 minutes of treatment’.

This may be an expression that patients are not guaranteed time to talk with their doctors to fully understand their disease.

Additionally, in order to provide an accurate diagnosis to a patient in a short period of time, doctors are under pressure to obtain a lot of information from the EMR system in a short period of time and prescribe prescriptions.

For some diseases, it may be necessary to obtain detailed information on past medical records and make a new diagnosis. For example, if a specific diagnosis, prescription drug, test, treatment, etc. is performed within a specific period, the practitioner can select a new disease and make a related prescription based on the relevant medical record.

However, this requires time to search and review past medical records.

Therefore, there is an urgent need for a new clinical decision support model that allows accurate diagnosis and prescription for patients in a short time using the patient's medical records and various PHR information.

Embodiments of the present invention allow the conditions for determining a new disease to be defined in advance based on the clinical experience of the treating doctor, thereby enabling the doctor to make more accurate diagnosis and prescription even during a short treatment time, and PHR and medical treatment. The purpose is to provide record-based clinical decision support methods and devices.

Additionally, the purpose of an embodiment of the present invention is to provide an alarm that a new disease rather than an existing disease is suspected when treating a patient in an EMR system based on predefined conditions.

In addition, the embodiment of the present invention defines conditions under which a disease can be inferred by combining not only the patient's medical record in the hospital but also various PHR information recorded by the patient outside the hospital, thereby allowing the doctor to rely on the medical record in the hospital. The purpose is to be able to define more precise conditions than one condition.

According to an embodiment of the present invention, the clinical decision support method based on PHR and medical records is, as the patient's patient information is received from the EMR system, the EMR maintained in association with the patient in each of the EMR database and the PHR database. collecting data and PHR data; Analyzing the EMR data and the PHR data to generate analysis results related to clinical decision making; And it may include transmitting the analysis results to the EMR system.

In addition, the clinical decision support device based on PHR and medical records according to an embodiment of the present invention is maintained in association with the patient in each of the EMR database and PHR database as the patient's patient information is received from the EMR system. A collection department that collects EMR data and PHR data; a processing unit that analyzes the EMR data and the PHR data to generate analysis results related to clinical decision-making; and an interface unit that transmits the analysis results to the EMR system.

According to one embodiment of the present invention, the PHR allows the conditions for determining a new disease to be defined in advance based on the clinical experience of the treating doctor, allowing the doctor to make a more accurate diagnosis and prescription even in a short treatment time. It is possible to provide clinical decision support methods and devices based on medical records.

In addition, according to the present invention, the EMR system can provide an alarm that a new disease rather than an existing disease is suspected during patient treatment based on predefined conditions.

In addition, the present invention defines conditions under which a disease can be inferred by combining not only the patient's medical record in the hospital but also various PHR information recorded by the patient outside the hospital, allowing the doctor to rely on the in-hospital medical record. You can define more precise conditions than conditions.

Figure 1 is a block diagram showing the configuration of a clinical decision support device based on PHR and medical records according to an embodiment of the present invention.
Figure 2 is a diagram to explain the disease inference system.
Figure 3 is a diagram illustrating registering disease inference conditions for new disease inference based on EMR data.
Figure 4 is a diagram illustrating detailed registration for EMR search conditions.
Figure 5 is a diagram illustrating items of EMR search conditions.
Figure 6 is a diagram showing an example of a notification message and recommended prescription displayed on the EMR system when the EMR search conditions are satisfied.
Figure 7 is a diagram illustrating a screen for registering a disease name when registering detailed conditions in EMR search conditions.
Figure 8 is a diagram illustrating a screen for registering a drug when registering detailed conditions in EMR search conditions.
Figure 9 is a diagram illustrating a screen for registering an examination when registering detailed conditions in EMR search conditions.
Figure 10 is a diagram illustrating a screen for registering a questionnaire when registering detailed conditions in EMR search conditions.
Figure 11 is a diagram illustrating registering disease inference conditions for new disease inference based on PHR data.
Figure 12 is a diagram illustrating the items and measurement period of PHR data.
Figure 13 is a diagram illustrating the EMR system.
Figure 14 is an example of a past medical record screen in the EMR system.
Figure 15 is a diagram illustrating a notification of a disease inference system in an EMR system.
Figure 16 is an example of PHR Data.
Figure 17 is an example of an alarm displayed on the EMR when the PHR search conditions are met.
Figure 18 is an example of a notification message when both EMR search conditions and PHR search conditions are met.
Figure 19 is a flowchart showing a clinical decision support method based on PHR and medical records, according to an embodiment of the present invention.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, various changes can be made to the embodiments, so the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes for the embodiments are included in the scope of rights.

The terms used in the examples are for descriptive purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the embodiments belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In addition, when describing with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiments, if it is determined that detailed descriptions of related known technologies may unnecessarily obscure the gist of the embodiments, the detailed descriptions are omitted.

Figure 1 is a block diagram showing the configuration of a clinical decision support device based on PHR and medical records according to an embodiment of the present invention.

Referring to Figure 1, the clinical decision support device 100 (hereinafter abbreviated as 'clinical decision support device') based on PHR and medical records, according to an embodiment of the present invention, includes a collection unit 110. , a processing unit 120, and an interface unit 130. Additionally, the clinical decision support device 100 may be configured by selectively adding a condition register 140, depending on the embodiment.

First, as the patient's patient information is received from the EMR system, the collection unit 110 collects EMR data and PHR data maintained in association with the patient from each of the EMR database and the PHR database. That is, the collection unit 110 is linked to patient information transmitted from the EMR system, and collects EMR data about the patient's medical treatment/prescription history and PHR data about the patient's lifestyle habits/habits, respectively. It can play a role in searching and extracting data from the database.

Reception of the patient information from the EMR system can be performed at a hospital or clinic where the EMR system is running and actual diagnosis/treatment of the patient is performed, as a disease inference command for the patient is generated in the EMR system.

The patient information may be received by the interface unit 130, which will be described later.

When a patient's name is clicked in the EMR system, the interface unit 130 can receive the patient's chart number and PHR User Key as the patient information from the EMR system.

The PHR User Key is a user identification key for accessing the PHR data, and may be a key value converted to a Hash function by combining the patient's resident registration number, name, and gender.

Here, EMR data is data generated by the EMR system, which is a computer system that manages and searches all medical records, and can refer to mandatory computerized medical data of all information that has been recorded in existing paper charts. This mandated computerized EMR data can be shared even in different healthcare environments.

PHR data is a health record that users can view and manage on their own by compiling information on medical treatment and examinations scattered across various medical institutions, activity data collected through smartphones, etc., and information such as weight and blood sugar levels measured by patients themselves. It can refer to data.

The processing unit 120 analyzes the EMR data and the PHR data to generate analysis results related to clinical decision making. In other words, the processing unit 120 can examine EMR data and PHR data to derive clinical decisions that can specify the patient's disease.

In generating analysis results, the clinical decision support device 100 determines whether the EMR data and the PHR data satisfy disease inference conditions set through items input from the treating physician, and generates analysis results. can do.

To this end, the clinical decision support device 100 may be configured to further include a condition register 140.

That is, the condition register 140 can register disease inference conditions by receiving items from the treating physician through the EMR system.

Items may be exemplified by category/code/name/search period/conditional search criteria/required or not, etc., as shown in FIG. 4, which will be described later.

The item ‘classification’ may be a medical record that can be registered as a disease inference condition. The item 'classification' may be a category as a range to be registered as a disease inference condition, and Figure 4 illustrates that the disease name is entered as the item 'classification' among the 'allergic rhinitis patient detection conditions'.

The item 'code' may be a code value to be used as a search key when searching medical records. Figure 4 illustrates that a code value specified as 'J00' among 'disease names' is entered as an item 'code'.

The item 'name' may be the name of a code registered as a search condition. Figure 4 illustrates that 'acute nasopharyngeal [cold]' searched by searching 'J00' among 'disease names' is entered as the item 'name'.

The item ‘search period’ may be the scope of the search for past medical records. Figure 4 illustrates that 'last 6 months' is entered as the item 'search period'.

The item 'condition search standard' is the search condition value that serves as the standard for disease inference. Figure 4 illustrates that 'two or more times' is entered as the item 'condition search criteria'.

The item 'required' may be an item that must be detected when inferring a disease if the condition is essential. Figure 4 illustrates that what is checked as 'required' is entered as an item 'whether it is required'.

According to the input of these items, the condition register 140 registers the disease inference condition of 'disease name/J00/acute nasopharyngitis [cold]/last 6 months/2 or more times/required' for 'allergic rhinitis patient detection conditions'. can do.

Thereafter, through the analysis, the processing unit 120 estimates the patient's disease as a new disease defined in response to the disease inference conditions, as the EMR data and the PHR data satisfy the disease inference conditions. You can.

In the above example, if the information and values described in the EMR data all match 'Disease name/J00/Acute nasopharyngitis [cold]/Last 6 months/2 or more times/Required', the processing unit 120 processes the received patient information. For the patient, a new disease can be assumed as an ‘allergic rhinitis patient’.

In registering disease inference conditions, the condition register 140 allows EMR search conditions and PHR search conditions to be separately registered.

That is, the condition registering unit 140 receives EMR items for registering EMR search conditions, including at least a 'name' automatically selected by 'classification' and 'code' search.

The condition registration unit 140 can register EMR search conditions by entering the item 'classification' and item 'code' and then using the item 'name' output through the search (see FIG. 4).

Additionally, the condition register 140 receives PHR items for registering PHR search conditions, including at least 'category' and 'measurement period'.

The condition register 140 can register PHR search conditions using information and values limited through selection of the item 'category' and the item 'measurement period' (see FIG. 11).

Additionally, the condition register 140 may register the EMR search condition and the PHR search condition, which are registered according to input of the EMR item and the PHR item, as the disease inference condition.

The condition register 140 can distinguish between EMR search conditions and PHR search conditions through tabs and register each of them as disease inference conditions. This tab division is intended to determine whether the EMR search conditions or PHR search conditions are independently satisfied through tab selection depending on the type of data to be analyzed when generating analysis results by the processing unit 120 later.

In one embodiment, the condition registering unit 140 further receives a 'condition range' when the sleep time is input as the 'category', and when analyzing the PHR data by the processing unit, during the 'measurement period', It is possible to analyze whether the sleep time is within the above ‘condition range’.

Here, the item 'condition range' may be an inequality such as <, =, >.

In other words, the condition register 140 may determine whether the sleep time entered as an item 'category' satisfies the additionally entered 'condition range' during the item 'measurement period' and generate an analysis result.

For example, as the sleep time is input, the condition register 140 further receives 'condition range '>= 7 (7 hours or more)' and '<=9 (9 hours or less)', and accordingly, the processing unit ( 120), when analyzing the PHR data, may generate an analysis result by analyzing whether the sleep time is within the 'condition range' of 7 hours or more and 9 hours or less during the 'measurement period' (see FIG. 11).

Additionally, the interface unit 130 transmits the analysis results to the EMR system. In other words, the interface unit 130 returns a determined clinical decision to the EMR system, allowing the clinician who diagnoses and treats the patient using the EMR system to quickly determine what disease the patient came to the hospital for. It can play a helping role.

Depending on the embodiment, the clinical decision support device 100 may notify a determined clinical decision and provide recommended prescriptions related to the clinical decision.

To this end, the condition register 140 can receive and register a recommended prescription for the new disease from the treating physician through the EMR system.

Recommended prescriptions may include tests, treatment methods, and drug prescriptions that the treating physician deems appropriate in treating the presumed new disease.

For example, the condition register 140 can receive 'test/treatment, EY853000, allergen skin reaction test' as input and register it as a recommended prescription.

Thereafter, the interface unit 130 may transmit an EMR notification message notifying the estimated new disease and the recommended prescription to the EMR system as the analysis result.

That is, when the interface unit 130 transmits the generated analysis results to the EMR system, it can analyze them and provide notification of the patient's disease, which is a clinical decision, and recommend a prescription to treat the disease.

For example, in Figure 3, it is shown that the EMR notification message "~The patient is likely to be a candidate for allergic rhinitis~" and the recommended prescription "Questionnaire, Allegy1, Allergy History Questionnaire" are transmitted to the EMR system as analysis results. .

Additionally, depending on the embodiment, the clinical decision support device 100 may automatically replace an existing disease with a presumed new disease in the EMR system.

To this end, the interface unit 130 can transmit a command for correction to the estimated new disease to the EMR system, thereby allowing the EMR system to correct the disease name for the patient to the new disease.

For example, in Figure 14, by sending a command to modify the new disease to 'allergic rhinitis patient', the disease name 'J00 acute nasopharyngitis [cold]' in the EMR system of the patient is modified to the presumed new disease 'allergic rhinitis patient'. This is an example.

According to one embodiment of the present invention, the PHR allows the conditions for determining a new disease to be defined in advance based on the clinical experience of the treating doctor, allowing the doctor to make a more accurate diagnosis and prescription even in a short treatment time. It is possible to provide clinical decision support methods and devices based on medical records.

In addition, according to the present invention, the EMR system can provide an alarm that a new disease rather than an existing disease is suspected during patient treatment based on predefined conditions.

In addition, the present invention defines conditions under which a disease can be inferred by combining not only the patient's medical record in the hospital but also various PHR information recorded by the patient outside the hospital, allowing the doctor to rely on the in-hospital medical record. You can define more precise conditions than conditions.

The clinical decision support device 100 of the present invention includes a 'condition registration system' that registers disease inference conditions so that the disease can be inferred based on the clinician's clinical experience, and receives patient information from the EMR system during patient treatment. , Based on the registered disease inference conditions, it can be configured as a 'disease inference system' that analyzes the patient's PHR data and EMR data (medical records) and displays the results of the disease inference algorithm as a message.

Figure 2 is a diagram to explain the disease inference system.

As shown in Figure 2, the disease inference system can be linked to the EMR system, analyze the patient's PHR data and EMR data (medical records), and transmit the disease inference results to the EMR system.

The disease inference system can be implemented in the form of an algorithm, and in step 1 of Figure 2, patient information is transmitted from the EMR system.

The disease inference system searches the EMR data of the patient in step 2 of Figure 2.

The disease inference system searches the PHR data of the patient in step 3 of Figure 2.

The disease inference system analyzes EMR data and PHR data in step 4 of Figure 2 and delivers the analyzed results to the EMR system.

Below, we will describe a condition registration system that registers disease inferred conditions based on medical records.

The condition registration system allows you to register disease inference conditions that make up medical records, such as disease names, drugs, tests/treatments, and questionnaires that can infer a specific disease based on your medical experience from a doctor.

Figure 3 is a diagram illustrating registering disease inference conditions for new disease inference based on EMR data.

Figure 3 illustrates a registration method for disease inference conditions that can suspect a new disease called allergic rhinitis for a patient who has received multiple prescriptions for colds in the past.

As shown in Figure 3, the condition registration screen is largely comprised of a condition name for entering the name of the condition to be registered, an EMR search condition for registering the condition based on EMR medical records, and a PHR for registering the condition based on PHR data. It can be divided into search conditions.

EMR search conditions and PHR search conditions include registering conditions, EMR notification messages that create a message to be displayed in the EMR system when the conditions are met, and recommendations that recommend prescriptions by displaying them in the EMR notification message. It may consist of a prescription.

The following items are required to register conditions for inferring a new disease based on the EMR data in Figure 3.

The condition name is where you register the name that will define the condition.

Condition registration is the part where conditions that can be inferred from a disease based on the practitioner's clinical experience are registered in past medical records.

Conditions may include medical information that can cause the disease to be inferred from medical records, such as disease name, medication, examination/treatment, height, weight, abdominal circumference, blood pressure, and blood sugar.

In Figure 3, after clinically confirming the new disease allergic rhinitis, the doctor enters 'allergic rhinitis patient detection conditions' as the condition name to register it, and the EMR search condition is 'disease name/J00/acute nasopharyngitis. This example shows an additional button along with registration of pre-registered conditions such as ‘[cold]/last 6 months/more than twice’.

Conditions are newly registered by a doctor, and thereafter, for patients whose EMR data satisfies the EMR search conditions, the clinical decision support device 100 may provide an EMR notification message and a recommended prescription.

Figure 4 is a diagram illustrating detailed registration for EMR search conditions.

Figure 4 is a detailed screen for registering conditions in the EMR search conditions tab.

EMR search conditions can be registered in detail by pressing the Add button in the condition registration of FIG. 3.

The detailed field values of condition registration in FIG. 4 are as follows.

The category may be a medical record item that can be registered as a condition.

The code may be a code value used as a search key when searching medical records.

The name may be the name of a code registered as a search condition.

The search period may be the range of past medical records search.

The condition search standard may be a search condition value that serves as a standard for disease inference.

Necessity may be an item that must be detected when inferring a disease if the condition is essential. If there is no satisfactory value even though it is required, the disease inference notification does not occur.

Detailed field values in condition registration can be modified or deleted at any time depending on the clinical experience of the treating physician.

Figure 4 illustrates that, as EMR search conditions, 'Disease name/J00/Acute nasopharyngitis [cold]/Last 6 months/2 or more times/Required' is entered and saved as condition registration.

Figure 5 is a diagram illustrating items of EMR search conditions.

Figure 5 is a screen showing an example of past medical record items that classify conditions on the condition registration screen of Figure 4.

Figure 5 illustrates that among past medical record items, examination/treatment is selected and conditions are searched.

In addition to the example in FIG. 5, there may be multiple medical records that can be included in the conditions.

Figure 6 is a diagram showing an example of a notification message and recommended prescription displayed on the EMR system when the EMR search conditions are satisfied.

The EMR notification message may be a message that automatically displays the inferred disease to the physician through the EMR system when the physician treats the patient and the patient's medical records meet the conditions.

Practitioners can write content to be expressed in the disease inference notification message.

The EMR notification message in FIG. 6 illustrates a disease inference message for allergic rhinitis.

The notification may be displayed in the EMR system if there is data that meets the EMR search criteria.

The recommended prescription may be a function that registers a recommended prescription to be included in the EMR order on a screen where an EMR notification message is displayed when a medical record that meets the EMR search conditions exists.

As shown in FIG. 6, the EMR notification message may be a disease inference notification message displayed when a record that satisfies the EMR search conditions exists in the patient's past medical records during patient treatment in the EMR system.

The recommended prescription in Figure 6 shows a list of recommended prescriptions provided along with the EMR notification message. The recommended prescription list can be automatically registered in the EMR prescription order area by clicking the ‘Apply Recommended Prescription EMR’ button. Additionally, only some prescriptions from the recommended prescription list may be entered into the EMR prescription order area depending on the practitioner's selection.

Figure 7 is a diagram illustrating a screen for registering a disease name when registering detailed conditions in EMR search conditions.

Figure 7 is an example screen for registering the name of the disease on the condition registration details screen of the EMR search conditions. The international disease name code in Figure 7 can register codes and names based on KCD.

Figure 7 illustrates clicking the search button on the condition registration details screen to search for the disease name code J00 and then registering acute nasopharyngitis [cold].

Figure 8 is a diagram illustrating a screen for registering a drug when registering detailed conditions in EMR search conditions.

Figure 8 is an example screen for searching and registering a drug on the detailed conditions registration screen.

Figure 8 illustrates a list of drugs searched by entering 'sin' in the drug search box to search for Singulair 10mg, which can be prescribed for allergic rhinitis.

The clinical decision support device 100 performs a search based on a drug code when searching for conditions in the medical record, and the drug code may be a drug billing code or drug active ingredient code provided by the Health Insurance Review and Assessment Service.

Figure 9 is a diagram illustrating a screen for registering an examination when registering detailed conditions in EMR search conditions.

Figure 9 is an example screen for searching and registering an inspection on the detailed condition registration screen.

Figure 9 illustrates a search by entering 'allergen' in the test search field to search for conditions to check whether an allergen skin reaction test has been performed within the last 6 months.

If the test code is covered, you can use the fee code provided by the HIRA, and if it is a non-covered test/treatment, you can use the user code registered in the EMR.

Figure 9 illustrates a screen for registering an allergen skin test (claim code: EY853000).

If the allerken skin test does not have a billing code, the registration code can be registered as a search code.

Figure 10 is a diagram illustrating a screen for registering a questionnaire when registering detailed conditions in EMR search conditions.

Figure 10 illustrates a screen for searching and registering a medical questionnaire on the detailed conditions registration screen.

In Figure 10, it is exemplified to search for the type of medical examination by entering 'allergen' in the medical examination search field.

Below, we will describe a condition registration system that registers disease inference conditions based on PHR data.

The condition registration system can register disease inference conditions from doctors that infer diseases based on PHR data recorded by patients outside the hospital through a PHR app.

Figure 11 is a diagram illustrating registering disease inference conditions for new disease inference based on PHR data.

Figure 11 is an example screen for setting disease inference conditions to infer a disease based on PHR data.

As shown in Figure 11, the PHR search conditions, similar to the EMR search conditions, are an area that defines items that meet the conditions in the PHR record, and are displayed as a notification message to the EMR system when there is a PHR record that meets the conditions. It consists of an area where information and recommended prescriptions are registered.

PHR data may be data that the patient directly enters through the PHR app.

PHR data may be sleep, heart rate, electrocardiogram, step count, calorie consumption, etc. collected through a PHR app linked to a wearable device, or may be blood pressure, blood sugar, etc. collected through home healthcare equipment.

Additionally, PHR data may include temperature, humidity, air pollution, etc. in the house.

In order to monitor the patient's daily lifestyle or disease status, the doctor can transmit the questionnaire information to the PHR app and have it entered as PHR data.

The PHR search conditions in Figure 11 show examples of conditions for inferring diseases among items collected through the PHR app.

PHR search conditions for disease inference include columns indicating items, conditions, values, measurement periods, and whether search is required.

The items categorize data collected through the PHR app. Examples of items include sleep time, meal calories, or questionnaire information entered by the user.

Figure 11 illustrates registration of allergy questionnaire, sleep time, meal calories, residential environment questionnaire, etc. as PHR data for inferring allergic rhinitis.

In conditions, you can set a specific value or range using >, <, and =.

The measurement period can determine the search range of the entered PHR data.

In Figure 11, the item sleep time is condition >= 7 and condition <= 9, and the measurement period is 'last 10 days (average)', so among the sleep times recorded in the PHR app, the sleep time is the sleep time within the last 10 days based on the search date. If the average value is >=7 or <=9, it can be considered to meet the search conditions.

Required sets whether or not the value of the item is required if it meets the conditions.

Figure 11 illustrates that allergic rhinitis disease inference is searched using allergy questionnaire, sleep time, meal calories, and residential environment questionnaire based on PHR data.

At this time, allergy questionnaires and residential environment questionnaires are mandatory and must meet the set values. However, sleep time and meal calories are conditioned on whether they meet the set values only when data exists.

Figure 12 is a diagram illustrating the items and measurement period of PHR data.

Figure 12 illustrates a UI for selecting 'key' and the measurement period 'last 20 days (average)' among the items of PHR data.

The disease inference system can operate in conjunction with the EMR system.

When a physician selects a patient to see the patient, the EMR system provides the disease inference system with the patient's chart number (information that can distinguish the patient in the EMR system) and PHR User Key (key value that can distinguish the patient in the PHR data). can be delivered.

The disease inference system searches the patient's past medical records based on the search period for predefined conditions and checks whether the conditions are met. If the conditions are met, the disease inference system also checks whether it is essential.

The disease inference system uses the PHR User Key to search PHR data based on items registered in the PHR search conditions.

The disease inference system searches the patient's medical records and PHR data based on the registered conditions, and when results matching the conditions are found, it delivers the exposure message registered for the conditions to the EMR system.

Figure 13 is a diagram illustrating the EMR system.

Figure 13 shows an example of changing the disease from 'acute nasopharyngitis [cold]' to 'other allergic rhinitis' by analyzing the past medical records of a 3-year-old child named 'Hong Gil-dong'.

When the patient “Hong Gil-dong” is selected in the EMR system, the EMR system transmits the chart number “43084” and the PHR User Key “2aca1d770381b55f2a9fdb25cb9977984273c7c6f49cbdfe5f67924fc9b40456” to the disease inference system.

The PHR User Key used in the example is a user identification key for accessing PHR data, and may be a key value converted to a Hash function by combining the patient's resident registration number + name + gender.

The disease inference system, which receives the chart number and PHR User Key from the EMR system, loads the “EMR search conditions” and “PHR search conditions” registered in advance by the treating physician and then sequentially searches the patient’s past medical records and PHR data. and check whether the results meet the registered conditions.

Figure 14 is an example of a past medical record screen in the EMR system.

Figure 14 is an example screen showing the past medical records of patient “Hong Gil-dong” in the EMR system. Patient Hong Gil-dong has three days of medical records on May 17, May 20, and May 24, 2021, and was diagnosed with "J00 acute nasopharyngitis [cold]."

Additionally, patient Hong Gil-dong was prescribed “Singulair Tablet 10mg” on both days of visit and underwent an “allergen skin reaction test” on May 20th. On May 24th, an allergy history questionnaire was conducted, and 3 out of 6 questions were answered “yes”.

Questions answered with “yes” are measured by the value of “whether or not the questionnaire is applicable” in “EMR search conditions.”

The EMR search condition items registered as “Allergic Rhinitis Patient Detection Conditions” are as follows.

Disease name: J00 Acute nasopharyngeal cold/Diagnosed more than twice in the past 6 months/Required conditions

Drug: 65500200 Singulair tablets 10mg/Prescribed more than 2 times in the last 6 months/Required conditions

Test: EY853000 Allergen skin reaction test/Prescribed more than once in the last 6 months/Not a required condition

The medical record search results for patient 'Hong Gil-dong' match the conditions registered in "Allergic Rhinitis Patient Detection Conditions", so the disease inference system sends a notification message "As a result of EMR medical record analysis, the patient is likely to be a candidate for allergic rhinitis. Please refer to your past medical records.” and the recommended prescription are sent to the EMR system.

Figure 15 is a diagram illustrating a notification of a disease inference system in an EMR system.

Figure 15 is an example screen that displays a disease inference system notification in the EMR system.

In Figure 15, an example of “EMR notification message” and “recommended prescription” registered in “EMR search conditions” displayed on the “disease inference system notification” screen.

Practitioners can select the prescription they want to register as an EMR prescription order among the recommended prescriptions displayed on the “Disease Inference System Notification” screen and register them in the EMR by clicking the “Apply Recommended Prescription EMR” button.

At this time, the disease inference system can register prescriptions by searching the prescription library registered in the EMR system using the delivered patient's chart number and the code of each recommended prescription as key values.

PHR search conditions can operate in the same way as EMR search conditions.

Figure 16 is an example of PHR Data.

Figure 16 is a screen showing an example of PHR Data.

The PHR search condition items registered as “Allergic Rhinitis Patient Detection Conditions” are as follows.

Allergy questionnaire/average of 2 or more in the last 3 months/required

Sleep time/ 7=<Average sleep time in the last 10 days<=9/Not required

Meal calories/average over 2000 for the past month/not required

Residential environment questionnaire/average of 1 or more questions in the last 3 months/required

Items measured as “Yes” in the “Allergic Rhinitis Questionnaire” or “Residential Environment Questionnaire” in FIG. 16 are measured as the value of “PHR Search Conditions.”

The PHR Data in FIG. 16 meets the criteria for the PHR search condition item among “Allergic Rhinitis Patient Detection Conditions.”

Therefore, the disease inference system transmits the exposure message registered in the “allergic rhinitis patient detection conditions” to the EMR system.

Figure 17 is an example of an alarm displayed on the EMR when the PHR search conditions are met.

Figure 17 illustrates that “EMR notification message” and “recommended prescription” registered in “PHR search conditions” are displayed on the “disease inference system notification” screen.

Practitioners can select the prescription they want to register as an EMR prescription order among the recommended prescriptions displayed on the “Disease Inference System Notification” screen and register them in the EMR by clicking the “Apply Recommended Prescription EMR” button.

At this time, the disease inference system can register the prescription by searching the prescription library registered in the EMR system using the delivered patient's PHR Key and the code of each recommended prescription as key values.

Figure 18 is an example of a notification message when EMR search conditions and PHR search conditions meet.

If the "EMR search conditions" and "PHR search conditions" meet simultaneously, the contents registered in each "EMR notification message" are displayed sequentially, as shown in Figure 18, and the "recommended prescriptions" are displayed sequentially excluding duplicate prescriptions. give.

According to the present invention, domestic treatment called '1 hour waiting 3 minutes treatment' is provided through a disease inference system that proposes a new diagnosis by analyzing the patient's past medical records and PHR data under conditions predefined by the practitioner through clinical experience. In reality, a more accurate diagnosis can be made in a limited amount of time.

According to the present invention, it is possible to register preconditions that can infer a disease through the clinical experience of a treating physician.

According to the present invention, by linking the EMR system and the disease inference system, a notification can be sent to the EMR system when conditions are met during patient treatment.

Hereinafter, in FIG. 19, the work flow of the clinical decision support device 100 according to embodiments of the present invention will be described in detail.

Figure 19 is a flowchart showing a clinical decision support method based on PHR and medical records, according to an embodiment of the present invention.

The clinical decision support method according to this embodiment may be performed by the clinical decision support device 100.

First, as the clinical decision support device 100 receives the patient's patient information from the EMR system, it collects EMR data and PHR data maintained in association with the patient from each of the EMR database and the PHR database (1910). Step 1910 is linked to the transmission of patient information from the EMR system, and searches for EMR data on the patient's medical treatment/prescription history and PHR data on the patient's lifestyle habits/habits from each corresponding database. This may be an extraction process.

Reception of the patient information from the EMR system can be performed at a hospital or clinic where the EMR system is running and actual diagnosis/treatment of the patient is performed, as a disease inference command for the patient is generated in the EMR system.

In receiving the patient information, the clinical decision support device 100 can receive the patient's chart number and PHR User Key from the EMR system as the patient information when the patient's name is clicked in the EMR system. there is.

The PHR User Key is a user identification key for accessing the PHR data, and may be a key value converted to a Hash function by combining the patient's resident registration number, name, and gender.

Here, EMR data is data generated by the EMR system, which is a computer system that manages and searches all medical records, and can refer to mandatory computerized medical data of all information that has been recorded in existing paper charts. This mandatory computerized EMR data can be shared even in different healthcare environments.

PHR data is a health record that users can view and manage on their own by compiling information on medical treatment and examinations scattered across various medical institutions, activity data collected through smartphones, etc., and information such as weight and blood sugar levels measured by patients themselves. It can refer to data.

Additionally, the clinical decision support device 100 analyzes the EMR data and the PHR data to generate analysis results related to clinical decision making (1920). Step 1920 may be a process of examining EMR data and PHR data to derive a clinical decision that can specify the patient's disease.

In generating analysis results, the clinical decision support device 100 determines whether the EMR data and the PHR data satisfy disease inference conditions set through items input from the treating physician, and generates analysis results. can do.

To this end, the clinical decision support device 100 can receive items from a treating physician through the EMR system and register disease inference conditions.

As shown in Figure 4, items may be exemplified by category/code/name/search period/conditional search criteria/required or not, etc.

The item ‘classification’ may be a medical record that can be registered as a disease inference condition. The item 'classification' may be a category as a range to be registered as a disease inference condition, and Figure 4 illustrates that the disease name is entered as the item 'classification' among the 'allergic rhinitis patient detection conditions'.

The item 'code' may be a code value to be used as a search key when searching medical records. Figure 4 illustrates that a code value specified as 'J00' among 'disease names' is entered as an item 'code'.

The item 'name' may be the name of a code registered as a search condition. Figure 4 illustrates that 'acute nasopharyngeal [cold]' searched by searching 'J00' among 'disease names' is entered as the item 'name'.

The item ‘search period’ may be the scope of the search for past medical records. Figure 4 illustrates that 'last 6 months' is entered as the item 'search period'.

The item 'condition search standard' is the search condition value that serves as the standard for disease inference. Figure 4 illustrates that 'two or more times' is entered as the item 'condition search criteria'.

The item 'required' may be an item that must be detected when inferring a disease if the condition is essential. Figure 4 illustrates that what is checked as 'required' is entered as an item 'whether it is required'.

According to the input of these items, the clinical decision support device 100 makes a disease inference of 'disease name/J00/acute nasopharyngitis [cold]/last 6 months/2 or more times/required' for 'allergic rhinitis patient detection conditions'. Conditions can be registered.

Thereafter, the clinical decision support device 100, through the analysis, determines that the EMR data and the PHR data satisfy the disease inference conditions, thereby defining the patient's disease in response to the disease inference conditions. It can be assumed to be a disease.

In the above example, if the information and values described in the EMR data all match 'Disease name/J00/Acute nasopharyngitis [cold]/Last 6 months/2 or more times/Required', the clinical decision support device 100 receives the information. For patients whose patient information is available, a new disease can be estimated as an ‘allergic rhinitis patient’.

In registering disease inference conditions, the clinical decision support device 100 distinguishes between EMR search conditions and PHR search conditions and allows them to be registered independently.

That is, the clinical decision support device 100 receives EMR items for registering EMR search conditions, including at least a 'name' automatically selected by 'classification' and 'code' search.

The clinical decision support device 100 can register EMR search conditions by entering the item 'classification' and item 'code' and then using the item 'name' output through the search (see FIG. 4).

Additionally, the clinical decision support device 100 receives PHR items for registering PHR search conditions, including at least 'category' and 'measurement period'.

The clinical decision support device 100 can register PHR search conditions using information and values limited by selecting the item 'category' and the item 'measurement period' (see FIG. 11).

Additionally, the clinical decision support device 100 may register the EMR search condition and the PHR search condition, which are registered according to input of the EMR item and the PHR item, as the disease inference condition.

The clinical decision support device 100 can distinguish between EMR search conditions and PHR search conditions through tabs and register each of them as disease inference conditions. This tab division is used to determine whether the EMR search conditions or PHR search conditions are independently satisfied through tab selection depending on the type of data to be analyzed when generating analysis results by the clinical decision support device 100 later. .

In one embodiment, the clinical decision support device 100 further receives a 'condition range' when the sleep time is input as the 'category', and when analyzing the PHR data by the processor, the 'measurement period' ', it is possible to analyze whether the sleep time is within the above 'condition range'.

Here, the item 'condition range' may be an inequality such as <, =, >.

In other words, the clinical decision support device 100 determines whether the sleep time entered as an item 'category' satisfies the additionally entered 'condition range' during the item 'measurement period', and generates an analysis result. .

For example, as the sleep time is input, the clinical decision support device 100 further receives 'condition range '>= 7 (more than 7 hours)' and '<=9 (less than 9 hours)' as input, and accordingly When analyzing the PHR data, the clinical decision support device 100 may generate an analysis result by analyzing whether the sleep time is within the 'condition range' of 7 hours or more and 9 hours or less during the 'measurement period'. There is (see Figure 11).

Subsequently, the clinical decision support device 100 transmits the analysis results to the EMR system (1930). Step 1930 returns the determined clinical decision to the EMR system, helping the clinician who diagnoses and treats the patient using the EMR system to quickly determine what disease the patient came to the hospital for. It can be a process.

Depending on the embodiment, the clinical decision support device 100 may notify a determined clinical decision and provide recommended prescriptions related to the clinical decision.

To this end, the clinical decision support device 100 may receive and register a recommended prescription for the new disease from the physician through the EMR system.

Recommended prescriptions may include tests, treatment methods, and drug prescriptions that the treating physician deems appropriate in treating the presumed new disease.

For example, the clinical decision support device 100 can receive input of 'test/treatment, EY853000, allergen skin reaction test' and register it as a recommended prescription.

Thereafter, the clinical decision support device 100 may transmit an EMR notification message notifying the estimated new disease and the recommended prescription to the EMR system as the analysis result.

In other words, when the clinical decision support device 100 transmits the generated analysis results to the EMR system, it can analyze and provide notification of the patient's disease, which is the clinical decision maker, and recommend a prescription to treat the disease. there is.

For example, in Figure 3, the EMR notification message "~The patient is likely to be a candidate for allergic rhinitis~" and the recommended prescription "Questionnaire, Allegy1, Allergy history questionnaire" are shown as analysis results and are transmitted to the EMR system. .

Additionally, depending on the embodiment, the clinical decision support device 100 may automatically replace an existing disease with a presumed new disease in the EMR system.

To this end, the clinical decision support device 100 transmits a command for modification to the estimated new disease to the EMR system, so that the disease name for the patient is modified to the new disease in the EMR system. You can.

For example, in Figure 14, by sending a command to modify the new disease to 'allergic rhinitis patient', the disease name 'J00 acute nasopharyngitis [cold]' in the EMR system of the patient is modified to the presumed new disease 'allergic rhinitis patient'. This is an example.

According to one embodiment of the present invention, the PHR allows the conditions for determining a new disease to be defined in advance based on the clinical experience of the treating doctor, allowing the doctor to make a more accurate diagnosis and prescription even in a short treatment time. It is possible to provide clinical decision support methods and devices based on medical records.

In addition, according to the present invention, the EMR system can provide an alarm that a new disease rather than an existing disease is suspected during patient treatment based on predefined conditions.

In addition, the present invention defines conditions under which a disease can be inferred by combining not only the patient's medical record in the hospital but also various PHR information recorded by the patient outside the hospital, allowing the doctor to rely on the in-hospital medical record. You can define more precise conditions than the conditions

The clinical decision support method based on PHR and medical records according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed on networked computer systems to store and execute clinical decision support methods based on distributed PHRs and medical records. Software and data may be stored on one or more computer-readable recording media.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in a different order than the described PHR and clinical decision support method based on medical records, and/or components of the described system, structure, device, circuit, etc. may be used in the described PHR and medical treatment. Appropriate results can be achieved even if it is combined or combined in a different form with the record-based clinical decision support method, or is replaced or substituted by other components or equivalents.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the following claims.

100: Clinical decision support device
110: collection unit 120: processing unit
130: Interface unit 140: Condition register

Claims (15)

Receiving EMR items from a practitioner through the EMR system and registering EMR search conditions; receiving PHR items and registering PHR search conditions;
As the patient's patient information is received from the EMR system, collecting EMR data and PHR data maintained in association with the patient from each of the EMR database and the PHR database;
Analyzing the EMR data and the PHR data to generate analysis results related to clinical decision making; and
Transferring the analysis results to the EMR system
Including,
If the EMR data meets the EMR search conditions and, at the same time, the PHR data meets the PHR search conditions,
The step of generating the analysis results is,
As a result of the analysis, the 'EMR notification message' registered in association with the EMR search conditions and the 'PHR notification message' registered in association with the PHR search conditions are sequentially displayed, excluding duplicate prescriptions, and the EMR A step of generating analysis results sequentially showing the 'recommended prescription' registered in association with the search conditions and the 'recommended prescription' registered in association with the PHR search conditions.
Clinical decision support method based on PHR and medical records, including. According to paragraph 1,
The above clinical decision support method is,
If the EMR data meets the EMR search conditions, or the PHR data meets the PHR search conditions,
Step of estimating the patient's disease as a new disease defined in response to the EMR search conditions or the PHR search conditions
A clinical decision support method based on PHR and medical records that further includes. According to paragraph 1,
The registration step is,
Receiving EMR items for registering EMR search conditions, including at least a 'name' automatically selected by 'classification' and 'code'search; and
Step of entering PHR items to register PHR search conditions, including at least 'category' and 'measurement period'
Clinical decision support method based on PHR and medical records, including. According to paragraph 3,
The step of entering the PHR item is,
When the sleep time is input as the 'category', a 'condition range' is further input, and when analyzing the PHR data, analyzing whether the sleep time is within the 'condition range' during the 'measurement period'.
Clinical decision support method based on PHR and medical records, including. According to paragraph 2,
The above clinical decision support method is,
receiving and registering a recommended prescription for the new disease from the practitioner through the EMR system; and
A step of transmitting an EMR notification message notifying the estimated new disease and the recommended prescription to the EMR system as a result of the analysis.
A clinical decision support method based on PHR and medical records that further includes. According to paragraph 2,
The above clinical decision support method is,
A step of modifying the disease name for the patient to the new disease in the EMR system by sending a command for modification to the estimated new disease to the EMR system.
A clinical decision support method based on PHR and medical records that further includes. According to paragraph 1,
The above clinical decision support method is,
When the patient's name is clicked in the EMR system, receiving the patient's chart number and PHR User Key as the patient information from the EMR system
It further includes,
The PHR User Key is,
A user identification key for accessing the PHR data, which is a key value converted to a Hash function by combining the patient's resident registration number, name, and gender,
Clinical decision support method based on PHR and medical records. A condition register that receives EMR items from a practitioner through the EMR system and registers EMR search conditions, and receives PHR items and registers PHR search conditions;
As the patient's patient information is received from the EMR system, a collection unit that collects EMR data and PHR data maintained in association with the patient from each of the EMR database and the PHR database;
a processing unit that analyzes the EMR data and the PHR data to generate analysis results related to clinical decision-making; and
An interface unit that transmits the analysis results to the EMR system
Including,
If the EMR data meets the EMR search conditions and, at the same time, the PHR data meets the PHR search conditions,
The processing unit,
As a result of the analysis, the 'EMR notification message' registered in association with the EMR search conditions and the 'PHR notification message' registered in association with the PHR search conditions are sequentially displayed, excluding duplicate prescriptions, and the EMR Generates analysis results that sequentially show 'recommended prescriptions' registered in relation to the search conditions and 'recommended prescriptions' registered in relation to the PHR search conditions.
Clinical decision support device based on PHR and medical records. According to clause 8,
The processing unit,
If the EMR data meets the EMR search conditions, or the PHR data meets the PHR search conditions,
Presuming that the patient's disease is a new disease defined in accordance with the EMR search conditions or the PHR search conditions
Clinical decision support device based on PHR and medical records. According to clause 8,
The condition register is,
Enter EMR items to register EMR search conditions, including at least 'Name' automatically selected by 'Classification' and 'Code' search,
Enter PHR items to register PHR search conditions, including at least 'category' and 'measurement period'
Clinical decision support device based on PHR and medical records. According to clause 10,
The condition register is,
When the sleep time is entered as the 'category', the 'condition range' is further input, and when the PHR data is analyzed by the processor, it is analyzed whether the sleep time is within the 'condition range' during the 'measurement period'. to do
Clinical decision support device based on PHR and medical records. According to clause 9,
The condition register is,
Receive and register a recommended prescription for the new disease from the practitioner through the EMR system,
The interface unit,
An EMR notification message notifying the estimated new disease and the recommended prescription are delivered to the EMR system as a result of the analysis.
Clinical decision support device based on PHR and medical records. According to clause 9,
The interface unit,
By sending a command for modification to the estimated new disease to the EMR system, the disease name for the patient is modified to the new disease in the EMR system.
Clinical decision support device based on PHR and medical records. According to clause 8,
The interface unit,
When a patient's name is clicked in the EMR system, the patient's chart number and PHR User Key are received as patient information from the EMR system,
The PHR User Key is,
A user identification key for accessing the PHR data, which is a key value converted to a Hash function by combining the patient's resident registration number, name, and gender,
Clinical decision support device based on PHR and medical records. A computer-readable recording medium recording a program for executing the method of any one of claims 1 to 7.

Images