KR102484681B1 - Method and system for clinical decision-making - Google Patents

Abstract

As a clinical decision-making method, the present invention may comprise: a step of inputting prescription information after diagnosing a patient, on an electronic chart; a step of transmitting the prescription information to a cloud server; a step of searching prescription information received from the cloud server and a rule inputted in advance by a manager to create and reply a content of a related rule; and a step of displaying the content reply-received from the electronic chart on a CDSS-only viewer screen. Therefore, the present invention is capable of providing a differentiated service.

Description

Method and system of clinical decision making {METHOD AND SYSTEM FOR CLINICAL DECISION-MAKING}

The present invention relates to methods and systems for clinical decision-making and, more particularly, to methods and systems for clinical decision-making for assisting decision-making in diagnosing and treating patients.

Clinical decision-making must be diagnosed through patient information and evidence (knowledge information), and since the subject of judgment is a human, there may be unintentional cognitive errors, and there may be misdiagnosis due to prejudice based on the culture of patients or doctors. there is.

In the case of large hospitals, CDSS (Clinical Decision Support System) is being built around university hospitals to reduce cases of diagnosis errors and overprescription, even though medical treatment is carried out through consultation and cooperation with specialists in various parts. CDSS is urgently needed in clinics, not large hospitals, where one or two doctors perform medical treatment, and are burdened with medical errors.

CDSS includes correlations and rules for accumulated data and uses non-knowledge-based CDSS (Knowledge-based CDSS) that mainly uses IF-THEN rules and non-knowledge that provides information by learning patterns found in clinical medical information through artificial intelligence It can be divided into non-knowledge-based CDSS (CDSS).

However, CDSS in existing clinics has limitations in informing the risk of taking medications. Therefore, it is necessary to introduce the same CDSS as in a large hospital even at a clinic level, not a large hospital.

Republic of Korea Patent Registration No. 10-1066246 Republic of Korea Patent Registration No. 10-1295613 Republic of Korea Patent Registration No. 10-1612635

The present invention is to solve the above problems, and an object of the present invention is to provide a method and system for clinical decision making.

There are many difficulties in the process (clinical) of doctors examining and treating patients, and to alleviate them, technology is needed to reduce the possibility of misdiagnosis by providing various information and notification functions, and to increase patient safety by improving the quality of medical care.

For example, if a doctor prescribes drug A to a patient and the amount exceeds the standard value, it can be fatal to the patient's life, and it is to provide a warning system. In addition, a patient may have an allergy to a specific ingredient, and if prior information on such allergy is not confirmed, the patient's life may be endangered by the ingredient of the prescribed medicine.

According to an embodiment of the present invention, when a doctor examines a patient and inputs a disease, a prescription, etc., the prescription information is delivered to the cloud server in real time, and then clinical decision support information processed by the server is returned, thereby essentially necessary clinical information. When occurs, it communicates with the chart, receives the value, calculates the stability of the prescription with patient-specific data, and provides information in real time.

The above and other objects and advantages of the present invention will become apparent from the following description of preferred embodiments.

A clinical decision-making method according to an embodiment of the present invention for achieving the above object is a method comprising: inputting prescription information into an electronic chart through an order reception application programming interface (API); Transmitting the prescription information to a cloud server; Retrieving prescription information received from the cloud server and a rule input in advance by a manager, creating content of a related rule, and returning the content; and displaying the contents returned from the electronic chart on a CDSS viewer screen.

According to one embodiment, prior to the step of inputting prescription information into the electronic chart, the step of inputting reception information about the patient; Further comprising the step of inputting disease information about the patient, wherein the step of inputting the reception information about the patient includes the step of extracting symptom keywords from the reception information, and the step of extracting the symptom keywords comprises: A step of extracting a keyword related to a selected check box among a plurality of symptom check boxes may be included.

According to one embodiment, determining whether prescription information exists in the database; If there is no previous record of health CDSS report (Hp_cdss_report) on prescription information, entering a health CDSS report (Hp_cdss_report); If there is a previous record of health CDSS report (Hp_cdss_report) on prescription information, not performing additional calculation based on re-prescription; determining whether an element list (Element_list) column value exists; If there is an element list (Element_list) column value, search the health element (Hp_element) and if there is a corresponding result, copy the result data. If there is an element with the same condition, in order to reuse the data Retrieving an element already entered in (Hp_element); and if it is determined that the input element exists, inputting a health element (Hp_element) - the health element (Hp_element) includes a patient number (hosp_no), a receipt number (receipt_no), an item number (item_no), and clinical copying result data, including - including a decision-making element (element_cd); generating a card list of Result 1, which is a conventional result, when an element list (Element_list) column value does not exist; And after copying the result data, as a step of determining whether there is even one necessary data of the element list (Element_list), if there is not even one necessary data, return items of result 1 (Result1) are returned. generate If there is even one necessary data, generating a card list of result 1 (Result 1), which is a conventional result; and if there is a previous record of the health CDSS report (Hp_cdss_report), generating a card list of Result 1, which is a conventional result, determining whether there is even one piece of necessary data in the element list (Element_list). Further comprising the step of doing, terminating with result 1 (Result 1), or terminating with result 2 (Result2) if there is no item due to not generating a card; Step of determining an item type (item type), if the item type (item_type) is '00', generating JSON including URL; and when the item type (item_type) is '02', inquiring a CDS element description (cds_element_description) and generating a JSON element (Element JSON), including: determining an item type; Retrieving the CDS description (cds_description) and generating a description JSON (Description JSON); and generating a card list JSON.

According to one embodiment, inputting a health element (Hp_element) - the health element (Hp_element) includes patient's reception information (Hp_receipt), patient's disease information, and symptom keyword (hp_symp_keyword) -; Generating a card list of result 1 (Result1); Retrieving data on a health factor (Hp_element); A step of inquiring and calculating a card result (Cds_result), not generating a card if the card result (Cds_result) is inquired; and if the card result (Cds_result) is not inquired, calculating the clinical decision-making result; Determining an item type (item_type), if the item type (item_type) is '00', generating JSON including a URL; and when the item type (item_type) is '02', determining the item type (item_type) including the step of inquiring the CDS element description (cds_element_description) and generating the JSON element (Element JSON); And querying the CDS description (cds_description) and generating a description JSON (Description JSON); A step of generating card list JSON may be further included.

According to one embodiment, providing the patient's CR, EGFR result values when prescribing losartan tablets on an electronic chart; and if there is no test result, outputting a message recommending test execution; Further, the electronic chart is configured to display a color mark and a comment message if the test result is out of tolerance, and the comment message is: (1) Creatinine clearance 20-50mL/min: initial dose adjustment is required don't (2) Patients on dialysis with creatinine clearance < 20 mL/min: The initial dose may include a message recommending 25 mg once a day as this drug.

According to an embodiment of the present invention, first of all, the patient's clinical information (vital, sample test, reading result, history, allergy, family history, etc.) Differentiated services can be provided by providing non-knowledge-based information through analysis and learning based on medical data and examination records.

When a patient is examined and a disease, prescription, etc. is entered, the prescription information is delivered to the cloud server in real time and the clinical decision support information processed by the server is returned. When necessary clinical information occurs, it communicates with the chart and receives the value By calculating the stability of prescription with patient-specific data and providing information in real time, it is possible to prepare a safety device in prescription.

1 is a schematic diagram of a clinical decision-making system according to an embodiment of the present invention.
2 is a diagram related to rule management according to an embodiment of the present invention.
3 is a diagram briefly illustrating the basic concept of an artificial neural network.
4 is a diagram relating to code master management.
5 is a diagram related to management of necessary clinical information.
6 is a diagram related to management of descriptions related to optional prescriptions.
7 is a block diagram of a clinical decision-making method.
8 is a diagram related to a method for application in medical treatment.
9 is a diagram of a method for storing prescription information.
10 is a diagram of a method for calculating CDSS.
11 is a diagram of a method for transmitting clinical information.

Hereinafter, the present invention will be described in detail with reference to embodiments and drawings of the present invention. These examples are only presented as examples to explain the present invention in more detail, and it will be apparent to those skilled in the art that the scope of the present invention is not limited by these examples. .

In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and in case of conflict, including definitions The description herein will take precedence.

In order to clearly explain the proposed invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification. And, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated. Also, a “unit” described in the specification means one unit or block that performs a specific function.

In each step, the identification code (first, second, etc.) is used for convenience of description, and the identification code does not describe the order of each step, and each step does not clearly describe a specific order in context. It may be performed differently from the order specified above. That is, each step may be performed in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

1 is a schematic diagram of a clinical decision-making system according to an embodiment of the present invention.

The clinical decision-making system according to an embodiment of the present invention relates to an electronic chart 110 communicatively connected in a clinic, a medical cloud server 120, a CDSS rule management tool 130, and a CDSS rule management tool 130. It may include a manager 140.

The communicatively connected electronic chart 110 in the clinic may be a computing device that is communicatively connected, examines the patient toward the medical cloud server 120, transmits diseases, prescriptions, etc. as input values, and in response The prescription information may be received and the information may be transmitted to the doctor of the clinic. For example, it may be a personal computer, notebook, tablet, smartphone, electronic chart, and the like.

The medical cloud server 120 is a server device, receives information about the disease, prescription, etc. of patients examined by doctors, and makes clinical decisions according to the rules of the CDSS rule management tool 130 implemented as a computer-readable program (software). Supporting information may be returned to the electronic chart (110).

The CDSS rule management tool 130 is configured to manage CDSS rules, and rules may be adjusted by the administrator 140 or rules may be automatically modified or changed through artificial intelligence.

When a doctor examines a patient at a clinic and inputs a disease or prescription, the prescription information is delivered to the cloud in real time, and then the clinical decision-making support information processed by the server is returned. When necessary clinical information occurs, it communicates with the chart and receives the value, calculates the stability of prescription with patient-specific data, and provides information in real time.

2 is a diagram related to rule management according to an embodiment of the present invention.

Rules in the clinical decision-making system are rules made based on patient clinical data and standard treatments, and items (risk notification, information retrieval, prescription decision support information, etc.) provided according to the set rules are stored.

The result type of the item (item) can be divided into Web, big data, clinical information utilization, and special.

The CDSS rule management tool 130 can manage target prescriptions and disease codes.

The CDSS rule management tool 130 is a program that can be accessed by a rule manager, and can manage items subject to provision of information for clinical decision-making.

By pre-registering data such as gender, age, prescription code, disease code, etc. and providing related data, it is possible to increase rule accuracy and reduce server overload.

For example, Astin tablets are antihistamine and anti-allergic drugs, and are composed of azelastine hydrochloride, and Sudafed tablets are rhinitis drugs, and are composed of pseudoephedrine hydrochloride.

KCD is the Korean Standard Classification of Causes of Disease, which systematically categorizes disease morbidity and death data, such as medical records and cause-cause statistics, according to their similarities in nature. As of 2022, it follows the 8th revised Korea Standard Classification of Diseases, which took effect on January 1, 2021, and is called the "KCD 8th Disease Code". For example, a C code can classify a malignant tumor (cancer), a D code a benign tumor, an S code an injury, a Q code a congenital disease, and a P code a perinatal disease.

For example, the target data is as follows.

- number code

- Drug price code

- Ingredient Code

- Material cost code

- KCD 8th corporal code

- gender

- age

FIG. 3 is a schematic diagram showing the basic concept of an artificial neural network for artificial intelligence applied to a clinical decision-making system. As shown in FIG. 3, an artificial neural network (ANN) includes an input layer, an output layer, and It may be composed of a hierarchical structure including at least one intermediate layer (or hidden layer) between the input layer and the output layer. The deep learning algorithm, based on such a multi-layered structure, can derive highly reliable results through learning to optimize the weight of an activation function between layers.

Deep learning algorithms applicable to the present invention may include a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), and the like.

A deep neural network (DNN) is basically characterized by improving the result of learning by increasing a lot of intermediate layers (or hidden layers) in an existing ANN model. As an example, the above DNN is characterized by performing a learning process using two or more intermediate layers.

Accordingly, the computer can derive an optimal output value by repeating the process of generating classification labels, distorting space, and classifying data by itself.

A convolutional neural network (CNN) is characterized by having a structure in which a pattern of features is identified by extracting features of data, unlike existing techniques in which a learning process is performed by extracting knowledge from data. The above CNN may be performed through a convolution process and a pooling process. In other words, the above CNN may include an algorithm complexly composed of a convolution layer and a pooling layer. Here, in the convolution layer, a process of extracting features of data (aka convolution process) is performed. The above convolution process is a process of examining the adjacent components of each component in the data, identifying characteristics, and deriving the identified characteristics into a single sheet. As a single compression process, the number of parameters can be effectively reduced. In the pooling layer, a process of reducing the size of the layer that has undergone the convolution process (aka pooling process) is performed. The above pooling process can reduce the size of data, cancel noise, and provide consistent features in fine parts. For example, the above CNN can be used in various fields such as information extraction, sentence classification, and face recognition.

A recurrent neural network (RNN) is a type of artificial neural network specialized in learning repetitive and sequential data and is characterized by having a recurrent structure therein. The above RNN uses the above circular structure to apply weights to past learning contents and reflect them to current learning, enabling a connection between current learning and past learning, and has the characteristic of being dependent on time. The above RNN is an algorithm that solves the limitations of existing continuous, iterative, and sequential data learning, and can be used to identify speech waveforms or to identify the front and back components of text.

However, these are only examples of specific deep learning techniques applicable to the present invention, and other deep learning techniques may be applied to the present invention according to embodiments.

4 is a diagram relating to code master management.

In FIG. 4 , the code master management can be grouped to enable collective management by designating the same prescription group or the same drug group for management convenience.

For example, it is possible to manage bundles of fee codes for acts, management of drug codes and ingredient codes, management of bundles for ingredients, and bundle management of KCD 8th disease codes.

5 is a diagram related to management of necessary clinical information.

Clinical information required when prescribing the selected target code can be registered.

<Body data>

*physical measurement

- weight

- blood sugar

-BMI

- kidney

- Blood pressure

- age

* Specimen test

-AST

-ALT

-HbA1C

-CR

Can be added if needed

*allergy

- NSAIDs

Can be added if necessary

*Other calculations

- EGFR (Epidermal growth factor receptor)

- CCR (creatinine clearance; creatinine clearance)

If the value exceeds the reference value by using a formula, a comment message may be transmitted and the comment message may be displayed on the electronic chart 110. 6 is a diagram related to management of descriptions related to optional prescriptions.

In the case of managing prescription-related explanations applicable to all cases, medication information, reference thesis, etc. can be provided. In case of managing names corresponding to specific conditions, precautions, etc. can be provided.

It is possible to input a prescription guide appropriate for the patient according to test results or gender, age, and body measurements. It can be designed to be used under any condition by using a calculation formula. It may be possible to provide doctors with customized data such as medication information, reference papers, and precautions so that they can make appropriate clinical decisions.

For example, in the case of administering losartan tablets, a comment message indicating that a reduction in dose to 25 mg once a day is recommended may be displayed.

7 is a diagram of a clinical decision-making method.

Data can be transmitted to the API server at the same time as prescription input in the clinic room.

If necessary clinical information exists after going through the CDSS process, the content is created, the data is returned, and expressed on the electronic chart in CARD format, so that the patient's individual clinical information and related data for the prescribed items can be provided to the doctor in real time.

The detailed screen of the clinic can be expressed in the form of a card (CARD) by generating necessary clinical information and prescription notes at the same time as prescription. The detailed screen of the treatment room can secure appropriateness and convenience with a response time of 1000 ms or less.

For example, as necessary clinical information, the patient's CCR and EGFR result values can be provided when prescribing losartan tablet, and if there is no test result, a message recommending test execution is generated, and if the test result is out of tolerance, color marking and comment message

can provide As a prescription-related explanation, for example, it can provide academic information to be aware of when prescribing losartan tablets.

Precautions for use
1. Warning
Administration of drugs that act directly on the renin-angiotensin-aldosterone system (RAAS) to pregnant women can cause damage and even death to the fetus and newborn. The occurrence of oligohydramnios may be associated with fetal pulmonary hypoplasia and skeletal malformations. Possible side effects in neonates include cranial hypoplasia, anuria, hypotension, renal failure and death. If pregnancy is confirmed, this drug should be discontinued as soon as possible (see section 7. 'Administration to pregnant and lactating women').
2. Do not administer to the following patients.
1) Patients with hypersensitivity to this drug or its components
2) Women who are pregnant or may be pregnant
3) Patients with severe hepatic impairment
4) Patients with hereditary angioedema or a history of angioedema during treatment with ACE inhibitors or angiotensin II receptor blockers
5) Patients with primary hyperaldosteronism
6) Since this drug contains lactose, it should be administered to patients with genetic problems such as galactose intolerance, Lapp lactase deficiency or glucose-galactose malabsorption. (Limited to products containing lactose)
7) Concomitant use with aliskiren-containing agents in patients with diabetes or moderate to severe renal impairment (glomerular filtration rate <60mL/min/1.73m2)

Convenience can be secured by automatically exposing essential clinical information related to prescriptions, and treatment stability can be secured by providing customized data for each patient and using a judgment function. It can provide a higher level of drug interaction, side effects, treatment, and medication precautions by utilizing allergy, medical history, and family history. Various statistical data can be provided by accumulating medical information excluding personal information and deep learning. , It can suggest and support the decision of treatment method by providing information such as frequent prescription according to disease, possible side effects, and treatment cases. In addition, charts can be learned through natural language analysis to determine frequent diseases according to patient expressions, and statistics can be provided from various angles by combining data with regional, seasonal, and seasonal variables.

It is possible to provide highly reliable expected reading results by adding result data such as endoscopy, ultrasound, and image reading as clinical variables and learning them in a complex way.

Through Hello100 (a medical application related to medical treatment), patients can be provided with a standard treatment plan for a group of patients with the same disease as themselves, enabling smooth communication with doctors.

8 is a diagram related to a method for application in medical treatment.

In step S810, if a patient is diagnosed and a prescription is entered, prescription information may be transmitted to the cloud in real time.

In step S820, the prescription information received from the cloud and the rule entered in advance by the manager may be searched for, and the contents of the related rule may be prepared and returned.

In step S830, the electronic chart may provide the returned content as a viewer screen dedicated to CDSS. If additional information is required, it is possible to execute step S810 after receiving the input in the content and retransmitting it to the cloud.

9 is a diagram of a method for storing prescription information.

In step S910, data may be received.

Prior to the step of inputting prescription information into the electronic chart, the step of inputting reception information about the patient and the step of inputting disease information about the patient may be further included.

In step S920, patient reception information (Hp_recept) may be input.

During the secondary operation, the step of inputting registration information about the patient may include extracting symptom keywords from the registration information, and extracting the symptom keywords may include checking a plurality of symptom checkboxes related to the patient's symptoms. and extracting keywords related to the selected checkboxes.

In step S930, disease information (Hp_diag) of the patient may be input.

In step S940, prescription information (Hp_order) may be input. Prescribing information can be referred to as primary prescribing information before CDSS, which is determined by a doctor based on his/her knowledge of the patient, is applied. Prescriptions can be modified with the help of the CDSS described below.

10 is a diagram of a method for calculating CDSS.

In step S1010, it may be determined whether corresponding prescription information exists in the database (Query1).

In step S1020, it ends and outputs result 2 (Result2).

In step S1021, if there is no previous record of the health CDSS report (Hp_cdss_report), in step S1022, the health CDSS report (Hp_cdss_report) is input. In this case, re-prescription is not counted.

In step S1023, it is determined whether an element list (Element_list) column value exists.

If the element list (Element_list) column value exists, in step S1024, the health element (Hp_element) is searched, and if there is a desired result (Result), the corresponding result data is copied. If the element list (Element_list) column value does not exist, in step S1027, a card list of result 1 (Result 1), which is a conventional result, is generated.

In step S1024, after copying the data, in step S1025, it is determined whether there is even one piece of necessary data in the element list (Element_list).

Looking at step S1024 in detail, in step S1024-1, an element already entered in the health element (Hp_element) is queried (Query2). This is to reuse if there is an element with the same condition. In step S1024-2, it may be determined that the input element exists. In step S1024-3, a health factor (Hp_element) may be input. For example, the health element (Hp_element) may include a patient number (hosp_no), a receipt number (receipt_no), an item number (item_no), and a clinical decision-making element (element_cd).

If there is not even one required data, in step S1026, return items of result 1 (Result1) are generated. If there is even one necessary data, in step S1027, a card list of result 1 (Result 1), which is a conventional result, is generated.

In step S1021, if there is a previous record of the health CDSS report (Hp_cdss_report), in step S1027, a card list of Result 1, which is a conventional result, is generated.

In step S1030, it ends with result 1 (Result 1), or if there is no item due to not generating a card, it ends with result 2 (Result2).

Looking at step S1027 in detail, at step S1052, element data can be retrieved (Query3). In step S1052, the clinical decision-making result may be inquired and calculated (Query4). When the clinical decision-making result is inquired, a card is not generated in step S1056. If the clinical decision-making result is not queried, the clinical decision-making result is calculated. In step S1058, an item type may be determined.

In step S1060, if the item type (item_type) is '00' (S1150), JSON including URL may be generated. Here, JSON (JavaScript Object Notation) is data consisting of attribute-value pairs, array data types, or any other serializable value or “key-value pair”. It is an open standard format that uses human readable text to convey objects.

If the item type (item_type) is '02' (S1070), a CDS element description (cds_element_description) may be retrieved and a JSON element (Element JSON) may be created (S1072), and then the CDS description (cds_description) may be retrieved. And, description JSON (Description JSON) can be generated (S1074). Content to be displayed on the electronic chart may include a card list and description JSON of result 1 (Result1).

After step S1060 or step S1074, card list JSON may be generated in step S1080.

11 is a diagram of a method for transmitting clinical information.

In step S1110, input data may be received. For example, the input data may be necessary clinical information management data. For example, weight, blood sugar, BMI, height, blood pressure, and age may be included as body measurements, AST, ALT, HbA1C, and CR may be included as sample tests, and NSAID (nonsteroidal antiinflammatory) as allergy drugs) may be included. Meanwhile, other calculated values may include EGFR, CCR, and the like.

In step S1120, a health element (Hp_element) may be input.

Here, the health element (Hp_element) may include the patient's reception information (Hp_receipt) in step S920 in FIG. 9, the patient's disease information in step S930, and the symptom keyword (hp_symp_keyword) in step S925.

In step S1130, a card list of Result1 may be generated.

Step S1130 is a step of inquiring data about the health factor (Hp_element), inquiring and calculating the card result (Cds_result), that is, if the card result (Cds_result) is inquired, no card is generated (step S1146), and the card result If (Cds_result) is not queried, the clinical decision-making result is calculated. It may include determining an item type (item_type).

When the item type (item_type) is '00' (S1150), JSON including URL may be generated.

When the item type (item_type) is '02' (S1160), a CDS element description (cds_element_description) may be retrieved and a JSON element (Element JSON) may be created (S1162). Then, the CDS description (cds_description) may be retrieved and description JSON (Description JSON) may be generated (S1164).

In step S1170, card list JSON may be generated.

12 is an embodiment related to the display of the electronic chart 110.

The CDSS screen 1210 of the electronic chart 110 of FIG. 12 may include necessary clinical information 1220 and prescription related description 1230.

For example, the necessary clinical information 1220 may provide the patient's CR and EGFR result values when prescribing Losartan tablets, and output a message recommending test execution if there is no test result, and the electronic chart 110 may If the result is out of tolerance, color marking and comment message can be displayed. As an example, 100 mg of losartan tablet is (1) creatinine clearance 20-50 mL/min: initial dose adjustment is not required. (2) Patients on dialysis with creatinine clearance < 20mL/min: A message may be displayed on the electronic chart 110 stating that 25mg once a day is recommended as the initial dose of this drug.

For example, the prescription-related description 1230 may provide academic information to be noted when prescribing Losartan tablets.

Additionally, the computer program according to the present invention, combined with a computer, may be stored in a computer readable recording medium in order to execute the various methods described above.

The above-mentioned program is a computer language such as C, C++, JAVA, machine language, etc. It may include a code coded as . These codes may include functional codes related to functions defining necessary functions for executing the above methods, and include control codes related to execution procedures necessary for the processor of the above computer to execute the above functions according to a predetermined procedure. can do. In addition, these codes may further include memory reference related code for additional information or media required to execute the above functions by the processor of the above computer from which location (address address) of the computer's internal or external memory should be referenced. there is. In addition, if the processor of the above computer needs to communicate with any other remote computer or server in order to execute the above functions, the code can use the communication module of the above computer to communicate with any other remote computer or server. It may further include communication-related codes for whether to communicate, what kind of information or media to transmit/receive during communication, and the like.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand

Therefore, the embodiments disclosed in this document are not intended to limit the technical idea disclosed in this document, but to explain, and the scope of the technical idea disclosed in this document is not limited by these embodiments. The scope of protection of technical ideas disclosed in this document should be interpreted according to the scope of the following claims, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of this document.

110: electronic chart
120: medical cloud server
130: CDSS rule management tool

Claims (5)

An electronic chart 110, which is a computing device in a clinic, a medical cloud server 120 communicatively connected to the electronic chart 110, and implemented as a computer readable program communicatively connected to the medical cloud server 120 A clinical decision-making method performed by a clinical decision-making system including a CDSS rule management tool 130, comprising:
Obtaining reception information about the patient input by a doctor through the electronic chart 110 - The reception information about the patient includes disease information, prescription information, allergy information, and history information of the patient examined by the doctor , family history information, the patient includes a check box selected from among a plurality of symptom check boxes relating to symptoms -;
transmitting reception information about the patient to the medical cloud server 120 by means of the electronic chart;
Extracting a symptom keyword from the reception information by the medical cloud server 120 - Extracting the symptom keyword includes extracting a keyword related to the selected check box among the plurality of symptom check boxes. -;
Retrieving, by the medical cloud server 120, the reception information about the patient including the prescription information received from the medical cloud server 120 and the rule entered in advance by the manager, creating and replying the content of the associated rule ; and
In the electronic chart 110, displaying the returned content on a CDSS-only viewer screen
including,
The content of the related rule includes the patient's CCR (creatinine clearance; creatinine clearance rate) and EGFR (Epidermal growth factor receptor; epidermal growth factor receptor) result values when the prescription is losartan tablet,
The medical cloud server 120 of the clinical decision-making system may provide the result values including the patient's CCR and EGFR to the electronic chart 110, and if the prescription has no test result, the test is performed. Sending a message recommending to the electronic chart 110,
In the electronic chart 110, if the patient has a CCR (creatinine clearance rate) of less than 20mL/min and is on dialysis, the initial dose is 25mg once a day as this drug. Configured to display a message, Clinical decision-making methods. delete delete delete delete

Images