Intelligent decision support system for ear-nose-throat disease nursing

Abstract

The invention discloses an intelligent decision support system for ear-nose-throat disease nursing, relates to the technical field of medical services, and solves the technical problems that effective integration and utilization of a large amount of medical data are lacked, an accurate quantitative risk prediction model is lacked, and targeted prevention and nursing measures cannot be taken in advance. Multi-dimensional information of a patient is comprehensively obtained through the user information collection module, deep integration analysis is conducted through the medical history record analysis module, more accurate disease diagnosis is achieved in combination with symptoms, medical history, examination results and the like, a solid foundation is provided for subsequent nursing decisions, medical big data is utilized, and the medical big data is analyzed. Nursing records are screened and matched according to patient age classification and pathological characteristics, further optimization is performed in combination with living habits, a highly personalized medical history-free nursing decision is generated, the nursing records and patient basic information are comprehensively analyzed according to different risk signals, and comprehensive and highly targeted nursing information is generated.

Description

Technical Field

[0001] The present invention relates to the technical field of medical services, and in particular to an intelligent decision support system for nursing of ear, nose and throat diseases. Background Art

[0002] With the advent of medical technology, clinical decision support systems are increasingly becoming an important factor in patient care delivery. Clinical decision support systems can directly improve patient care outcomes and the performance of healthcare organizations.

[0003] The patent with publication number CN118629620A discloses an intelligent nursing decision support system based on deep learning, which includes: a data acquisition module, a text processing module, an image processing module, and a decision support module. The data acquisition module is used to collect and input the patient's text data and image data respectively; the text processing module is used to read the data acquisition module and train and evaluate the text data through the BiLSTM-CRF model; the image processing module is used to read the data acquisition module and train and evaluate the image data through a convolutional neural network; the decision module is used to read the text processing module and the image processing module respectively, splice the training and evaluation results of the text processing module and the image processing module, and obtain decision support.

[0004] However, some existing intelligent nursing decision-making systems lack effective integration and utilization of large amounts of medical data when in use. It is difficult to quickly obtain nursing experience from similar cases as a reference, and it is difficult to systematically consider the comprehensive impact of multiple factors such as the patient's age, medical history, and living habits on nursing decisions. In addition, the risk assessment of patients with a medical history is mostly qualitative, and there is a lack of accurate and quantitative risk prediction models, which is not conducive to taking targeted prevention and nursing measures in advance. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides an intelligent decision support system for ENT disease care, which solves the problems of lack of effective integration and utilization of large amounts of medical data, lack of accurate and quantitative risk prediction models, and being unfavorable for taking targeted prevention and care measures in advance.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent decision support system for ENT disease nursing, comprising:

[0007] The medical history record analysis module is used to obtain the basic information transmitted by the user information collection module, analyze it, diagnose the disease based on the basic information to obtain diagnostic information, and classify the patients into medical history users and non-medical history users, and then transmit the medical history users to the intelligent decision-making module with medical history, and transmit the non-medical history users to the intelligent decision-making module without medical history;

[0008] The intelligent decision-making module without medical history is used to analyze the acquired users without medical history, select nursing decisions based on the corresponding patient classification information, obtain medical big data, conduct comprehensive analysis based on the patient's living habits, and generate nursing decision information without medical history, which is then transmitted to the decision information output module;

[0009] The intelligent decision-making module with medical history is used to analyze the medical history users, calculate the medical history risk value of the medical history users by analyzing the medical history records of the medical history users, and generate risk prediction information based on the medical history risk value, and transmit the generated risk prediction information to the secondary comprehensive analysis module;

[0010] The secondary comprehensive analysis module is used to analyze the acquired risk prediction information, analyze the different signals corresponding to the risk prediction information, analyze the nursing records and combine them with the basic information of the medical history user to conduct a comprehensive analysis to generate nursing information with medical history, and transmit the nursing information with medical history to the nursing information output module.

[0011] As a further solution of the present invention, it also includes a user information collection module and a nursing information output module;

[0012] The user information collection module is used to obtain the basic information of the patient and transmit the obtained basic information to the medical history record analysis module. The basic information obtained includes the patient's age, medical history and nursing records;

[0013] The nursing information output module is used to display the acquired nursing information without medical history and nursing information with medical history to the corresponding operators.

[0014] As a further solution of the present invention, the specific manner in which the medical history record analysis module analyzes the basic information is as follows:

[0015] Obtain the patient's basic information and diagnose the patient's disease. Analyze the patient's pathological characteristics, determine the patient's disease, and generate diagnostic information. Then obtain the patient's age and classify the patient according to the patient's age to obtain patient classification information. At the same time, determine whether the patient has a medical history. If so, the patient is classified as a medical history user. Otherwise, if no medical history is present, the patient is classified as a non-medical history user.

[0016] As a further solution of the present invention, the specific manner in which the intelligent decision-making module without medical history analyzes users without medical history is:

[0017] Obtain users without medical history, and obtain the patient classification information corresponding to the users without medical history. Then, use the patient classification information as the standard to obtain nursing records of the same classification in the medical big data, and label them as i, where i=1, 2, ..., j, where j represents the number of nursing records. Then, obtain the pathological characteristics of users without medical history, and obtain the pathological characteristics corresponding to nursing record i. Match the pathological characteristics to screen the nursing records to obtain pre-selected records a, where a=1, 2, ..., b, where b represents the number of pre-selected records.

[0018] Then, the living habits of the current user with no medical history are obtained, the pre-selected records a are analyzed, and the pre-selected records that conflict with the living habits are eliminated to obtain secondary screening records. At the same time, the secondary screening records are analyzed, and then the associated features of the pathological features of the current user with no medical history are obtained. The secondary screening records are specifically screened based on the associated features to obtain nursing decisions, and nursing information without medical history is generated, which is then transmitted to the nursing information output module.

[0019] As a further solution of the present invention, the specific manner in which the intelligent decision-making module with medical history analyzes the user with medical history is:

[0020] Get the medical history record of the current medical history user, and get the number of medical history records based on the medical history records, then get the severity corresponding to the number of medical history records, and assign the severity value accordingly based on the severity, and get the time interval corresponding to the number of medical history records, and then substitute the obtained parameters into the formula Calculate the medical history risk value Risk of the current medical history user, where o represents the number of medical histories, and o=1, 2, ..., p, S i is the severity value corresponding to the o-th medical history, T i is the time interval between the o-th medical history and this assessment, F is the correction factor, and compare the calculated medical history risk value with the risk threshold to generate a risk signal or warning signal;

[0021] As a further solution of the present invention, the specific method of generating risk signals and warning signals by the intelligent decision-making module with medical history is:

[0022] The calculated medical history risk value Risk is compared with the risk threshold, and the specific value of the risk threshold is set by the operator. If the medical history risk value Risk is greater than the risk threshold, it means that the disease corresponding to the current medical history user is at risk, and a risk signal is generated. Otherwise, if the medical history risk value Risk is less than the risk threshold, a warning signal is generated, and then the generated risk signal and warning signal are transmitted to the secondary comprehensive analysis module.

[0023] As a further solution of the present invention, the specific method in which the secondary comprehensive analysis module analyzes the risk signal in the risk prediction information is:

[0024] Obtain the nursing record of the current medical history user, and establish a relationship table between pathological characteristics and nursing decisions. Then obtain the real-time pathological characteristics corresponding to the current medical history user, and match the real-time pathological characteristics with the nursing records. If there is a match between the two, select the corresponding nursing record, and generate nursing information with medical history according to the corresponding nursing decision;

[0025] If there is no match between the two, all nursing decisions corresponding to the same classification information are obtained, and then all nursing decisions are matched with the real-time pathological characteristics of the current medical history user as the standard, the pathological characteristics corresponding to the nursing decisions are obtained, and the similarity between the real-time pathological characteristics and the pathological characteristics is calculated. At the same time, the nursing decision corresponding to the largest similarity value is selected as the standard, and nursing information with medical history is generated.

[0026] As a further solution of the present invention, the specific method in which the secondary comprehensive analysis module analyzes the warning signal in the risk prediction information is:

[0027] The real-time nursing situation of the current medical history user is analyzed. If the current medical history user has corresponding nursing decisions, the nursing information with medical history is generated based on the corresponding nursing decisions. If the current medical history user does not have corresponding nursing decisions, the nursing information with medical history is generated in the same way as the risk signal analysis method.

[0028] Beneficial Effects

[0029] The present invention provides an intelligent decision support system for ENT disease nursing. Compared with the prior art, it has the following beneficial effects:

[0030] The present invention obtains comprehensive multi-dimensional information of patients through the user information collection module, and the medical history record analysis module conducts in-depth integrated analysis, combining symptoms, medical history and examination results to achieve more accurate disease diagnosis, providing a solid foundation for subsequent nursing decisions. The intelligent decision-making module without medical history uses medical big data to screen and match nursing records according to the patient's age classification and pathological characteristics, and further optimizes it in combination with living habits to generate highly personalized nursing decisions without medical history. The medical history risk value calculation model constructed by the intelligent decision-making module with medical history comprehensively considers factors such as the number of medical histories, severity and time interval, accurately quantifies the risk of symptoms, and generates risk or early warning signals by comparing with the set threshold. The secondary comprehensive analysis module conducts a comprehensive analysis of nursing records and basic patient information according to different risk signals, generates comprehensive and targeted nursing information, and conveys it to the operator in a timely and accurate manner through the nursing information output module. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a block diagram of the system principle of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] For example, see Figure 1 The present application provides an intelligent decision support system for ENT disease nursing, including: a user information collection module, a medical history record analysis module, an intelligent decision module with medical history, an intelligent decision module without medical history, a secondary comprehensive analysis module and a decision information output module. Figure 1 It can be known that the above functional modules are electrically connected in a unidirectional manner.

[0034] The user information collection module is used to obtain the basic information of the patient and transmit the obtained basic information to the medical history record analysis module. The basic information obtained includes the patient's age, medical history and nursing records.

[0035] The medical history record analysis module is used to analyze the basic information obtained, diagnose the disease based on the basic information to obtain diagnostic information, and classify the patients into users with medical history and users without medical history. The users with medical history are then transferred to the intelligent decision-making module with medical history, and the users without medical history are transferred to the intelligent decision-making module without medical history.

[0036] Obtain the patient's basic information and diagnose the patient's disease at the same time, analyze the patient's pathological characteristics, determine the patient's disease, and generate diagnostic information. Perform a comprehensive analysis based on the patient's symptoms (such as ear pain, nose bleeding, foreign body sensation in the throat, etc.), medical history (previous history of ear infection, history of nasal polyp surgery, etc.) and examination results (such as otoscopy, nasal endoscopy, and laryngoscopy data). For example, when a patient has symptoms of ear pain, hearing loss, and increased ear canal secretions, the system will combine possible causes, such as otitis media, to provide preliminary diagnostic suggestions, including possible types of otitis media (suppurative or non-suppurative), then obtain the patient's age, and classify the patient according to the patient's age to obtain patient classification information. The specific age classification standards are: infancy: 0-3 years old, preschool: 4-6 years old, school age: 7-12 years old, adolescence: 13-19 years old, early adulthood: 20-40 years old, middle adulthood: 41-60 years old, and old age: 61 years old and above. At the same time, it determines whether the patient has a medical history. If so, the patient is classified as a medical history user. Otherwise, if no medical history exists, the patient is classified as a non-medical history user.

[0037] Intelligent decision-making module with no medical history, which is used to analyze the acquired users without medical history, select nursing decisions based on the corresponding patient classification information, obtain medical big data, conduct comprehensive analysis based on the patient's living habits, and generate nursing decision information with no medical history, which is then transmitted to the decision information output module.

[0038] Obtain a user with no medical history, and obtain the patient classification information corresponding to the user with no medical history, then use the patient classification information as a standard to obtain nursing records of the same classification in the medical big data, and the age group of the population corresponding to the nursing records obtained here is the same as the age group of the current user with no medical history, and they are all users with no medical history, and are labeled as i, and i=1, 2, ..., j, where j represents the number of nursing records, then obtain the pathological characteristics of the user with no medical history, and obtain the pathological characteristics corresponding to the nursing record i, match the pathological characteristics to screen the nursing records to obtain the pre-selected record a, and a=1, 2, ..., b, where b represents the number of pre-selected records, and the specific matching method is to obtain the nursing records with the same pathological characteristics as the current user with no medical history;

[0039] Suppose there is a 35-year-old user with no medical history, who is assessed to belong to the patient classification category of "middle adulthood". The nursing records of "middle adulthood" users with no medical history are searched in the medical big data, and a total of 50 records (i.e. j = 50) are found, marked as i = 1 to 50. The pathological characteristics of this user with no medical history are "mild throat discomfort, occasional tinnitus but no hearing loss". By comparing the pathological characteristics of these 50 nursing records one by one, it is found that 10 records (i.e. b = 10) have the same pathological characteristics as this user, such as similar degrees of throat discomfort and tinnitus and no other medical history.

[0040] Then, the living habits of the current user with no medical history are obtained, and the living habits include whether to smoke or drink. The obtained pre-selected record a is analyzed, and the pre-selected records that conflict with the living habits are eliminated to obtain secondary screening records. At the same time, the obtained secondary screening records are analyzed, and then the associated features of the pathological features of the current user with no medical history are obtained. The associated features here are represented by other features that exist on the basis of known pathological features. The secondary screening records are specifically screened based on the associated features to obtain nursing decisions, and at the same time, nursing information without medical history is generated, which is then transmitted to the nursing information output module.

[0041] There is a user with no medical history, aged 40, with no smoking or drinking habits, and his pathological characteristics are intermittent nasal congestion and mild dry throat. In the previous screening process, 8 pre-selected records a (a = 1 to 8) were obtained. Analysis of these pre-selected records found that 3 of the records corresponded to patients with a long history of smoking. Due to conflicts with the current user's living habits, these 3 records were eliminated, and 5 secondary screening records were obtained. Further analysis of the associated characteristics of the user's nasal congestion and dry throat revealed that his working environment was dry and slightly dust-polluted. Therefore, among the 5 secondary screening records, those records with relevant nursing measures for dry environment and dust protection and relatively complete nursing plans for nasal congestion and dry throat symptoms were selected. For example, one of the records mentioned the use of air humidifiers to improve environmental humidity, wearing protective masks to reduce dust inhalation, using mild nasal wash solutions to relieve nasal congestion, and drinking throat tea to relieve dry throat, etc., in order to generate nursing decisions.

[0042] Nursing information output module, which is used to display the acquired nursing information without medical history to the corresponding operator.

[0043] Embodiment 2: This embodiment is implemented on the basis of Embodiment 1, and the difference from Embodiment 1 is as follows:

[0044] There is a medical history intelligent decision-making module, which is used to analyze the medical history of the user, calculate the medical history risk value of the user by analyzing the medical history records of the medical history user, and generate risk prediction information based on the medical history risk value, and transmit the generated risk prediction information to the secondary comprehensive analysis module.

[0045] Get the medical history record of the current medical history user, and then get the number of medical history records based on the medical history records, and then get the severity corresponding to the number of medical history records, and then assign corresponding values ​​based on the severity to obtain the severity value. For example, malignant tumor diseases are assigned a value of 4 (such as nasopharyngeal carcinoma, laryngeal cancer, etc.), because these diseases pose the greatest threat to life and health; chronic complex diseases (such as chronic sinusitis with nasal polyps, chronic suppurative otitis media, etc.) are assigned a value of 3; common mild diseases (such as simple rhinitis, external otitis, etc.) are assigned a value of 1-2, and the time interval corresponding to the number of medical history records is obtained, and then the obtained parameters are substituted into the formula Calculate the medical history risk value Risk of the current medical history user, where o represents the number of medical histories, and o = 1, 2, ..., p, S i is the severity value corresponding to the o-th medical history, T i is the time interval between the o-th medical history and this assessment, and F is the correction factor;

[0046] The calculated medical history risk value Risk is compared with the risk threshold, and the specific value of the risk threshold is set by the operator. If the medical history risk value Risk is greater than the risk threshold, it means that the disease corresponding to the current medical history user is at risk, and a risk signal is generated. Otherwise, if the medical history risk value Risk is less than the risk threshold, a warning signal is generated, and then the generated risk signal and warning signal are transmitted to the secondary comprehensive analysis module.

[0047] The secondary comprehensive analysis module is used to analyze the acquired risk prediction information, analyze the different signals corresponding to the risk prediction information, analyze the nursing records and combine them with the basic information of the medical history user to conduct a comprehensive analysis to generate nursing information with medical history, and transmit the nursing information with medical history to the nursing information output module.

[0048] Analyze the risk signals in the risk prediction information, obtain the nursing records of the current medical history user, and establish a relationship table between pathological characteristics and nursing decisions. Then obtain the real-time pathological characteristics corresponding to the current medical history user, and match the real-time pathological characteristics with the nursing records. If there is a match between the two, select the corresponding nursing records, and generate medical history nursing information according to the corresponding nursing decisions. If there is no match between the two, obtain all nursing decisions corresponding to the same classification information, and the same classification information here is represented as nursing decision information at the same age stage as the current medical history user. Then, use the real-time pathological characteristics of the current medical history user as the standard to match all nursing decisions. The specific matching method is as follows:

[0049] Obtain the pathological features corresponding to the nursing decision, and calculate the similarity between the real-time pathological features and the pathological features. The similarity is calculated by quantifying the two and calculating the cosine similarity of the quantized two for comparison. At the same time, the nursing decision corresponding to the maximum similarity value is selected as the standard, and the nursing information is generated.

[0050] Analyze the warning signals in the risk prediction information, and analyze the real-time nursing situation of the current medical history user. If the current medical history user has corresponding nursing decisions, generate nursing information with medical history based on the corresponding nursing decisions, and the nursing information generated here includes nursing reminders for side effects of the current nursing decision management. If the current medical history user does not have corresponding nursing decisions, the above-mentioned risk signal analysis method is used in the same way, and specifically refers to the analysis method when there is no matching situation, generate nursing information with medical history, and transmit the nursing information with medical history to the nursing information output module.

[0051] Nursing information output module, which is used to display the acquired medical history nursing information to the corresponding operator.

[0052] Embodiment 3, as the embodiment 3 of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2 for implementation.

[0053] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0054] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent decision support system for ENT disease nursing, characterized in that: include: The medical history record analysis module is used to obtain the basic information transmitted by the user information collection module, analyze it, diagnose the disease based on the basic information to obtain diagnostic information, and classify the patients into medical history users and non-medical history users, and then transmit the medical history users to the intelligent decision-making module with medical history, and transmit the non-medical history users to the intelligent decision-making module without medical history; The intelligent decision-making module without medical history is used to analyze the acquired users without medical history, select nursing decisions based on the corresponding patient classification information, obtain medical big data, conduct comprehensive analysis based on the patient's living habits, and generate nursing decision information without medical history, which is then transmitted to the decision information output module; The intelligent decision-making module with medical history is used to analyze the medical history users, calculate the medical history risk value of the medical history users by analyzing the medical history records of the medical history users, and generate risk prediction information based on the medical history risk value, and transmit the generated risk prediction information to the secondary comprehensive analysis module; The secondary comprehensive analysis module is used to analyze the acquired risk prediction information, analyze the different signals corresponding to the risk prediction information, analyze the nursing records and combine them with the basic information of the medical history user to conduct a comprehensive analysis to generate nursing information with medical history, and transmit the nursing information with medical history to the nursing information output module.

2. The intelligent decision support system for ENT disease nursing according to claim 1 is characterized in that: It also includes a user information collection module and a nursing information output module; The user information collection module is used to obtain the basic information of the patient and transmit the obtained basic information to the medical history record analysis module. The basic information obtained includes the patient's age, medical history and nursing records; The nursing information output module is used to display the acquired nursing information without medical history and nursing information with medical history to the corresponding operators.

3. The intelligent decision support system for ENT disease nursing according to claim 1 is characterized in that: The specific method in which the medical history record analysis module analyzes the basic information is as follows: Obtain the patient's basic information and diagnose the patient's disease. Analyze the patient's pathological characteristics, determine the patient's disease, and generate diagnostic information. Then obtain the patient's age and classify the patient according to the patient's age to obtain patient classification information. At the same time, determine whether the patient has a medical history. If so, the patient is classified as a medical history user. Otherwise, if no medical history is present, the patient is classified as a non-medical history user.

4. The intelligent decision support system for ENT disease nursing according to claim 1 is characterized in that: The specific method in which the intelligent decision-making module without medical history analyzes users without medical history is as follows: Obtain users without medical history, and obtain the patient classification information corresponding to the users without medical history. Then, use the patient classification information as the standard to obtain nursing records of the same classification in the medical big data, and label them as i, where i=1, 2, ..., j, where j represents the number of nursing records. Then, obtain the pathological characteristics of users without medical history, and obtain the pathological characteristics corresponding to nursing record i. Match the pathological characteristics to screen the nursing records to obtain pre-selected records a, where a=1, 2, ..., b, where b represents the number of pre-selected records. Then, the living habits of the current user with no medical history are obtained, the pre-selected records a are analyzed, and the pre-selected records that conflict with the living habits are eliminated to obtain secondary screening records. At the same time, the secondary screening records are analyzed, and then the associated features of the pathological features of the current user with no medical history are obtained. The secondary screening records are specifically screened based on the associated features to obtain nursing decisions, and nursing information without medical history is generated, which is then transmitted to the nursing information output module.

5. The intelligent decision support system for ENT disease nursing according to claim 1 is characterized in that: The specific method in which the intelligent decision-making module with medical history analyzes the user with medical history is as follows: Get the medical history record of the current medical history user, and get the number of medical history records based on the medical history records, then get the severity corresponding to the number of medical history records, and assign the severity value accordingly based on the severity, and get the time interval corresponding to the number of medical history records, and then substitute the obtained parameters into the formula The medical history risk value Risk of the current medical history user is calculated, where o represents the number of medical histories, and o = 1, 2, ..., p, Si is the severity value corresponding to the o-th medical history, Ti is the time interval between the o-th medical history and this assessment, F is the correction factor, and the calculated medical history risk value is compared with the risk threshold to generate a risk signal or warning signal.

6. The intelligent decision support system for ENT disease nursing according to claim 5, characterized in that: The specific method for the intelligent decision-making module with medical history to generate risk signals and warning signals is: The calculated medical history risk value Risk is compared with the risk threshold, and the specific value of the risk threshold is set by the operator. If the medical history risk value Risk is greater than the risk threshold, it means that there is a risk for the disease corresponding to the current medical history user, and a risk signal is generated. Otherwise, if the medical history risk value Risk is less than the risk threshold, a warning signal is generated, and then the generated risk signal and warning signal are transmitted to the secondary comprehensive analysis module.

7. The intelligent decision support system for ENT disease nursing according to claim 1 is characterized in that: The specific method in which the secondary comprehensive analysis module analyzes the risk signal in the risk prediction information is as follows: Obtain the nursing record of the current medical history user, and establish a relationship table between pathological characteristics and nursing decisions. Then obtain the real-time pathological characteristics corresponding to the current medical history user, and match the real-time pathological characteristics with the nursing records. If there is a match between the two, select the corresponding nursing record, and generate nursing information with medical history according to the corresponding nursing decision; If there is no match between the two, all nursing decisions corresponding to the same classification information are obtained, and then all nursing decisions are matched with the real-time pathological characteristics of the current medical history user as the standard, the pathological characteristics corresponding to the nursing decisions are obtained, and the similarity between the real-time pathological characteristics and the pathological characteristics is calculated. At the same time, the nursing decision corresponding to the largest similarity value is selected as the standard, and nursing information with medical history is generated.

8. The intelligent decision support system for ENT disease nursing according to claim 1, characterized in that: The specific method in which the secondary comprehensive analysis module analyzes the warning signals in the risk prediction information is as follows: The real-time nursing situation of the current medical history user is analyzed. If the current medical history user has corresponding nursing decisions, the nursing information with medical history is generated based on the corresponding nursing decisions. If the current medical history user does not have corresponding nursing decisions, the nursing information with medical history is generated in the same way as the risk signal analysis method.

Images