CN116403691A - Medical information management system and management method - Google Patents

Abstract

The invention discloses a medical information management system and a management method, which belong to the technical field of medical information processing. By sending broadcast information to each medical terminal, the medical information returned by each medical terminal based on the broadcast information is collected, classified, and processed in the cloud to realize Real-time sharing and transmission of information of each medical terminal, effectively avoiding the situation of isolated islands of medical information; by filtering the medical information in the medical terminal and selecting the data that matches the keyword information for screening, it is possible to select the medical information more accurately. The medical data in the terminal is used as associated medical data, and then the medical information is classified based on the classification model, which improves the accuracy of medical information classification, facilitates the management, query and call of medical data, and improves the efficiency of medical information management.

Description

A medical information management system and management method

technical field

The present invention relates to the technical field of medical information processing, and more specifically relates to a medical information management system and management method.

Background technique

With the rapid development of the medical industry today, with the increase in the number of medical patients, more and more medical data are generated. These medical data are stored in the medical terminal for a short time and will be covered by new medical data; if they are stored all the time, It will take up a lot of memory and reduce the running speed of the medical terminal. Therefore, it is very necessary to effectively manage medical information to improve real-time data sharing and retrieval.

The medical information in the existing medical terminals cannot be shared in real time, so that each medical terminal forms an information island, and each medical terminal cannot carry out information transmission, which greatly reduces the role played by the medical information in each medical terminal and reduces the cost of medical treatment. The efficiency of information utilization and the work efficiency of medical staff.

Moreover, in order to facilitate the management and query of medical data, it is necessary to classify the medical data. However, the current classification of medical information only focuses on the data at the current time, and only uses the data at the current time as the classification standard. The data utilization rate is low because the classification is rough and accurate classification cannot be achieved. Therefore, when it is necessary to call (for example, medical data needs to be called when medical resources are allocated), due to inaccurate classification, it is easy to cause bias in data call, which will adversely affect the final result.

Therefore, it is an urgent problem for those skilled in the art to propose a medical information management system and management method to make medical information classification more accurate and improve medical information management efficiency.

Contents of the invention

In view of this, the present invention provides a medical information management system and management method, which facilitates the management and query of medical data and improves the efficiency of medical information management.

In order to achieve the above object, the present invention adopts the following technical solutions:

On the one hand, the present invention provides a medical information management system, including a cloud and several medical terminals;

The cloud includes a terminal list acquisition module, a broadcast sending module, an information receiving module, an authority configuration module, and a classification processing module;

The terminal list obtaining module is used to obtain a terminal list, the terminal list includes the terminal codes of the plurality of medical terminals, and the terminal codes correspond to the medical terminals one by one;

The broadcast sending module is used to send broadcast information to the medical terminal, and the broadcast information includes the user's identity information and current department information;

The information receiving module is used to receive and store the medical information of the medical terminal corresponding to the terminal code, including the electronic medical record recording the user's disease data;

The authority configuration module is used to configure the access authority of medical terminals in the terminal list;

The classification processing module is preset with a disease classification model, which is used to classify and store the medical information received by the information receiving module and push the classification results to the medical terminal; the disease classification model is composed of the first disease prediction framework, The selection connection layer is sequentially connected with multiple second disease prediction architectures;

The medical terminal includes an access module, a diagnosis and treatment module, and a sending module;

The access module is used to access the medical information stored in the cloud according to the authority assigned by the authority configuration module;

The diagnosis and treatment module is used to prompt the user to perform the diagnosis and treatment process according to the broadcast information, and generate medical information of the user's current diagnosis and treatment process;

The sending module is used to send the medical information of the user's current diagnosis and treatment process to the information receiving module.

Preferably, the terminal list acquisition module initiates a terminal list acquisition request, and each medical terminal sends its own terminal code to the cloud after establishing a channel, and determines the corresponding medical terminal according to each terminal code, and each medical terminal uses an independent channel Transmit information with the cloud to avoid confusion in information transmission.

Preferably, the cloud is provided with a department fit relationship table, and the department fit relationship table is provided with a plurality of departments, and the fit relationship of each department is expressed in the form of connecting lines, and the connection between departments is determined according to the connection mode of the connecting lines. The degree of fit, the higher the degree of fit, the greater the reference value of medical information in the corresponding medical terminal.

Preferably, the information receiving module is also used to screen associated medical data, and the associated medical data is medical information that matches the medical information generated by the current visiting department;

The information receiving module determines the matching department of the current department according to the matching relationship table of departments, and then determines the terminal code of the medical terminal corresponding to the matching department and retrieves the medical information therein, and screens the medical information according to the preset standard matching degree. The medical information whose matching degree with the keyword information is higher than the standard matching degree obtains the associated medical data.

Preferably, the classification processing module includes a specified information acquisition unit, a first predicted disease acquisition unit, a prediction architecture selection unit, a second predicted disease acquisition unit, a disease classification vector mapping unit, a distance threshold judgment unit, and a category division unit;

The specified information obtaining unit is used to obtain specified medical information of the user, including the user's disease data and associated medical data;

The first predicted disease acquisition unit is configured to input the specified medical information into the first disease prediction framework in the preset disease classification model, and obtain the first predicted disease output by the first disease prediction framework;

A prediction architecture selection unit, configured to input the first predicted disease into the selection connection layer, and obtain the designated second disease prediction architecture selected by the selection connection layer according to a preset selection method;

A second predicted disease acquisition unit, configured to input the first predicted disease and the designated medical information into the designated second disease prediction framework, and output a second predicted disease;

A disease classification vector mapping unit, configured to map the specified medical information, the first predicted disease, and the second predicted disease into a disease classification vector according to a predicted classification vector mapping method;

A distance threshold judging unit, configured to call a preset standard classification vector, calculate a distance value between the standard classification vector and the disease classification vector, and judge whether the distance value is smaller than a preset distance threshold, wherein the standard a classification vector is labeled with the first predicted disease and the second predicted disease, and the standard classification vector is labeled with a specified category;

The specified category classification unit is configured to classify the specified medical information into the specified category if the distance value is smaller than a preset distance threshold.

Preferably, the first predicted disease acquisition unit maps the specified medical information into an initial time vector sequence according to a preset time vector mapping method, and the initial time vector sequence includes The first subsequence formed by the associated medical data, and the second subsequence mapped by the associated medical data; the total time involved in the specified medical information, the user's disease data and the associated medical data is divided into n time periods , so that the number of constituent elements of the initial time vector sequence, the first subsequence and the second subsequence is n;

inputting the initial time vector sequence into the first disease prediction framework, and calculating a prediction time vector;

In chronological order, combine the predicted time vectors into a predicted time vector sequence, and interpret the predicted time vector sequence according to the preset vector interpretation method, so as to obtain the predicted disease results and corresponding disease values in different time periods probability;

A predicted disease result whose disease probability is higher than a preset probability threshold is recorded as a first predicted disease, and the first predicted disease is output.

Preferably, the specified second disease prediction framework is trained based on a neural network model, including:

Retrieve sample data from the disease database, and divide the sample data into a training set as a verification set, wherein the sample data consists of the first predicted disease, medical information associated with the first predicted disease, and the first predicted disease. Other disease components associated with the first predicted disease;

Using the stochastic gradient descent method, using the training set to train the preset neural network model, so as to obtain the intermediate model;

Verifying the intermediate model by using the verification set, and judging whether the verification is passed;

If the verification is successful, record the intermediate model as the specified second disease prediction framework.

Preferably, before specifying the second disease prediction architecture to perform neural network training, it includes:

Querying the preset International Classification of Diseases database, so as to obtain the designated International Classification of Diseases code corresponding to the first predicted disease;

Intercept the first three codes of the designated International Classification of Diseases code, and select the second disease prediction framework marked with the first three codes from among the preset multiple second disease prediction frameworks to obtain the designated second disease prediction framework. Disease Prediction Architecture.

On the other hand, the present invention also proposes a medical information management method, comprising the following steps:

Obtain a terminal list through the terminal list acquisition module in the cloud, the terminal list includes the terminal codes of the plurality of medical terminals, and the terminal codes correspond to the medical terminals one by one;

Receive and store the medical information of the medical terminal corresponding to the terminal code through the cloud information receiving module, including the electronic medical record recording the user's disease data;

Configuring the access authority of the medical terminal in the terminal list through the authority configuration module of the cloud;

The access module of the medical terminal accesses the medical information stored in the cloud according to the authority assigned by the authority configuration module;

The broadcast sending module in the cloud sends broadcast information to the medical terminal, and the broadcast information includes the user's identity information and current department information;

The diagnosis and treatment module of the medical terminal prompts the user to perform the diagnosis and treatment process according to the broadcast information, and generates medical information of the user's current diagnosis and treatment process;

Send the medical information of the user's current diagnosis and treatment process to the information receiving module through the sending of the medical terminal;

The classification processing module in the cloud classifies and stores the medical information received by the information receiving module and pushes the classification results to the medical terminal; the classification processing module is preset with a disease classification model, and the disease classification model is determined by the first A disease prediction framework, a selection connection layer and multiple second disease prediction frameworks are sequentially connected.

It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a medical information management system and management method. By sending broadcast information to each medical terminal, the medical information returned by each medical terminal based on the broadcast information is stored in the cloud. The internal summary realizes the sharing and transmission of information of each medical terminal, effectively avoiding the situation of isolated islands of medical information; by filtering the medical information in the medical terminal and selecting the data matching the keyword information K for screening, it can be more Accurately select the medical data in the medical terminal as the associated medical data, and then classify the medical information based on the classification model, which improves the accuracy of medical information classification, facilitates the management and query of medical data, and improves the efficiency of medical information management.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present invention, and those skilled in the art can also obtain other drawings according to the provided drawings without creative work.

FIG. 1 is an architecture diagram of a medical information management system provided by an embodiment of the present invention;

Fig. 2 is a schematic structural diagram of a classification processing module provided by an embodiment of the present invention;

Fig. 3 is a schematic flowchart of a medical information management method provided by an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The embodiment of the present invention discloses a medical information management system, as shown in Figure 1, including a cloud and several medical terminals;

The cloud includes a terminal list acquisition module, a broadcast sending module, an information receiving module, a permission configuration module, and a classification processing module;

The terminal list obtaining module is used to obtain the terminal list, and the terminal list includes terminal codes of several medical terminals, and the terminal codes correspond to the medical terminals one by one;

The broadcast sending module is used to send broadcast information to the medical terminal, and the broadcast information includes the user's identity information and current department information;

The broadcast message is sent from the cloud to each medical terminal through wireless transmission to obtain the terminal list. When obtaining the terminal list, the terminal list acquisition module can initiate an acquisition request, and then each medical terminal will send its own terminal code to the Cloud, the cloud determines the corresponding medical terminal according to each terminal code, so as to realize the transmission of medical information between the cloud and the medical terminal represented by each terminal code;

The information receiving module is used to receive and store the medical information of the medical terminal corresponding to the terminal code, including the electronic medical record recording the user's illness data;

The authority configuration module is used to configure the access authority of the medical terminal in the terminal list;

The classification processing module is preset with a disease classification model, which is used to classify and store the medical information received by the information receiving module and push the classification results to the medical terminal; the disease classification model consists of a first disease prediction architecture, a selection connection layer and multiple second The disease prediction framework is sequentially connected;

The medical terminal includes an access module, a diagnosis and treatment module, and a sending module;

The access module is used to access the medical information stored in the cloud according to the permissions assigned by the permission configuration module;

The diagnosis and treatment module is used to prompt the user to perform the diagnosis and treatment process according to the broadcast information, and generate the medical information of the user's current diagnosis and treatment process;

The sending module is used to send the medical information of the user's current diagnosis and treatment process to the information receiving module to update the user's electronic medical record.

Further, the cloud is provided with a department fit relationship table, and there are multiple departments in the department fit relationship table, and the fit relationship of each department is expressed in the form of connecting lines, and the degree of fit between departments is determined according to the connection mode of the connecting lines, and the higher the degree of fit Department, the greater the reference value of medical information in the corresponding medical terminal.

Specifically, if the relationship between the departments is close, there is a direct connection line for connection. If the relationship between the departments is second, then an indirect connection is made at intervals of one department, and the medical information of the medical terminal corresponding to the close relationship is used as a reference. If the value is large, the value of the medical information of the department that belongs to the first-level connection with the current visiting department is set to 1, and the value of the medical information of the department that belongs to the second-level connection with the current visiting department is set to 2, and so on, the reference value of the medical information is The smaller the value is set, the greater the reference value of the medical information.

Further, the information receiving module is also used to screen associated medical data, and the associated medical data is medical information that matches the medical information generated by the current visiting department;

The information receiving module determines the matching department of the current department according to the department matching relationship table, and then determines the terminal code of the medical terminal corresponding to the matching department and retrieves the medical information in it, and filters the matching with the keyword information according to the preset standard matching degree Medical information with a matching degree higher than the standard is obtained to obtain associated medical data, so that the medical data in the medical terminal can be selected more accurately, the effective medical information in the medical terminal can be extracted, invalid information can be eliminated, and the efficient use of medical information can be improved. , and further improves the processing efficiency of medical information.

As shown in Figure 2, the classification processing module includes a specified information acquisition unit, a first predicted disease acquisition unit, a prediction architecture selection unit, a second predicted disease acquisition unit, a disease classification vector mapping unit, a distance threshold judgment unit, and a category division unit;

The specified information acquisition unit is used to obtain the specified medical information of the user, including the user's disease data and associated medical data, and the two jointly classify the follow-up medical information; for example, if the cloud detects the medical data in the liver, but obviously , the condition of the liver is related to the condition of the gallbladder. Therefore, when classifying, it is necessary to check the medical big data based on the medical data in the liver and the history of the gallbladder in the cloud to obtain accurate classification results. The utilization efficiency of historical medical data is higher, and the utilization efficiency of medical data is improved.

The first predicted disease acquisition unit is configured to input the specified medical information into the first disease prediction framework in the preset disease classification model, and obtain the first predicted disease output by the first disease prediction framework, specifically:

The first predicted disease acquisition unit maps the specified medical information into an initial time vector sequence according to the preset time vector mapping method, and the initial time vector sequence includes the first subsequence mapped from the user's disease data, and the associated medical information The second subsequence formed by data mapping; the total time involved in the specified medical information, user's disease data and associated medical data is divided into n time periods, so that the initial time vector sequence, the first subsequence and the second subsequence The number of constituent elements of the sequence is n;

Input the initial time vector sequence into the first disease prediction framework, and calculate the predicted time vector. The calculation formula is as follows:

e _ij = score(s _i , h _j ), h _j = LSTM _enc (x _j , h _j-1 );

Among them, c _i is the prediction time vector, α _ij is the weight parameter, s _i is the i-th hidden state vector in the first disease prediction framework, score(s _i , h _j ) refers to using the preset score function according to s _i and the score calculated by h _j , h _j is the hidden vector of the jth time period, h _j-1 is the hidden vector of the j-1th time period, x _j is the jth constituent element in the initial time vector sequence, LSTM _enc refers to the use of long short-term memory architecture for computing.

Combine the predicted time vectors into a predicted time vector sequence in chronological order, and interpret the predicted time vector sequence according to the preset vector interpretation method, so as to obtain the predicted disease results and corresponding disease probability in different time periods;

The predicted disease result whose disease probability is higher than the preset probability threshold is recorded as the first predicted disease, and the first predicted disease is output.

A prediction architecture selection unit, configured to input the first predicted disease into the selection connection layer, and obtain the designated second disease prediction architecture selected by the selection connection layer according to a preset selection method;

The second predicted disease acquisition unit is configured to input the first predicted disease and specified medical information into the specified second disease prediction framework, and output the second predicted disease.

The disease classification vector mapping unit is used to map the specified medical information, the first predicted disease and the second predicted disease into disease classification vectors according to the predicted classification vector mapping method, specifically including:

Generate the first subvector (A11,A12,...,A1n; A21,A22,...,A2n; A31,A32,...,A3n), where A11,A12,...,A1n is the first Predict the disease, A21, A22,..., A2n is the predicted onset time period corresponding to A11, A12,..., A1n one by one, A31, A32,..., A3n is the time period corresponding to A11, A12,... , A1n one-to-one predicted incidence probability, there are n kinds of first predicted diseases;

Generate the second subvector (B11,B12,...,B1m; B21,B22,...,B2m; B31,B32,...,B3m), where B11,B12,...,B1m are the second Predict the disease, B21, B22,..., B2m is the predicted onset time period corresponding to B11, B12,..., B1m one by one, B31, B32,..., B3m is the time period corresponding to B11, B12,... , B1m one-to-one predicted incidence probability, there are m kinds of second predicted diseases;

The initial time vector sequence, the first sub-vector and the second sub-vector are sequentially combined to obtain a disease classification vector.

As described above, the method of mapping the specified medical information, the first predicted disease and the second predicted disease into disease classification vectors is implemented according to the predicted classification vector mapping method. The classification vector mapping of the present invention introduces the predicted onset time period and the predicted onset probability; and also introduces the second sub-vector, which is generated by associated medical data; and then introduces the initial time vector reflecting the user's specified medical information sequence, so that the mapped disease classification vector can fully reflect the specified medical information, the first predicted disease and the second predicted disease. The disease classification vector is the basis for medical information classification, that is, the medical information classification is based on the specified medical information, the first predicted disease, and the second predicted disease, thereby improving the precision and accuracy of the medical information classification.

The distance threshold judging unit is used to call the preset standard classification vector, calculate the distance value between the standard classification vector and the disease classification vector, and judge whether the distance value is smaller than the preset distance threshold, wherein the standard classification vector is marked with the first predicted disease and the second predicted disease, the standard classification vectors are annotated for the specified category;

The distance value D between the standard classification vector and the disease classification vector is calculated as follows:

Among them, xi is the i-th sub-vector of the standard classification vector, yi is the i-th sub-vector of the disease classification vector, and both the standard classification vector and the disease classification vector include p sub-vectors. The distance value D not only measures the difference between the vector length of the standard classification vector and the vector length of the disease classification vector, but also measures the angle difference between the standard classification vector and the disease classification vector, so the accuracy of the calculated distance value D is higher. It can better reflect the difference between the standard classification vector and the disease classification vector.

The specified category division unit is used to classify the specified medical information into the specified category if the distance value is less than the preset distance threshold, including:

If the distance value is not less than the preset distance threshold, the review index Qi is calculated according to the following formula:

From the re-examination index Qi, obtain the designated re-examination index with the largest value, and obtain the designated data source corresponding to the designated re-examination index according to the corresponding relationship between the re-examination index-subvector-data source, where the designated data source is the designated medical information, the first Disease prediction framework or designate a second disease prediction framework;

Generate review reminder information, and attach the review order to the review reminder information. The review order is to review the specified data source first.

As mentioned above, the generation of review reminder information is realized, and the review sequence is attached to the review reminder information. The present invention adopts a special disease classification model which is sequentially connected by a first disease prediction framework, a selection connection layer and a plurality of second disease prediction frameworks. The first disease prediction architecture is relatively independent from the multiple second disease prediction architectures, so they can be trained separately, and it is also convenient to check for possible prediction errors. If the distance value is not less than the preset distance threshold, it indicates that the specified medical information cannot be classified, which may be due to an error in the prediction result, so a review is required. Since the parts that can be reviewed include: the specified medical information, the first disease prediction framework or the specified second disease prediction framework, the order of review is particularly important.

The present invention is based on the formula:

Calculate the review index Qi; from the review index Qi, obtain the specified review index with the largest value, and obtain the specified data source corresponding to the specified review index according to the corresponding relationship between the review index-subvector-data source; generate a review reminder message, And attach the review sequence to the review reminder message. The review sequence is to review the specified data source first to find out the most likely source of the error, that is, the specified data source corresponding to the specified review index. Therefore, in the follow-up review process, the efficiency of the review can be improved according to the review sequence, which is conducive to early restoration of the disease classification model.

Further, specify that the second disease prediction framework is trained based on the neural network model, including:

Retrieve sample data from the disease database, and divide the sample data into a training set as a validation set, where the sample data consists of the first predicted disease, medical information associated with the first predicted disease, and other diseases associated with the first predicted disease ; Therefore, each second disease prediction architecture only needs to focus on one first prediction disease, which is highly targeted, requires less training data, improves training efficiency, and has higher prediction accuracy.

Using the stochastic gradient descent method, using the training set to train the preset neural network model, so as to obtain the intermediate model;

Use the verification set to verify the intermediate model and judge whether the verification is passed;

If the verification is passed, record the intermediate model as specifying the second disease prediction framework.

Further, specifying the second disease prediction framework before neural network training includes:

Query the preset International Classification of Diseases database, so as to obtain the designated International Classification of Diseases code corresponding to the first predicted disease;

The first three codes of the specified International Classification of Diseases code are intercepted, and the second disease prediction framework marked with the first three codes is selected from the preset multiple second disease prediction frameworks to obtain the specified second disease prediction framework.

On the other hand, the present invention also proposes a medical information management method, as shown in Figure 3, comprising the following steps:

Obtain the terminal list through the terminal list acquisition module in the cloud, the terminal list includes terminal codes of several medical terminals, and the terminal codes correspond to the medical terminals one by one;

Receive and store the medical information of the medical terminal corresponding to the terminal code through the cloud information receiving module, including the electronic medical record recording the user's disease data;

Configure the access rights of medical terminals in the terminal list through the permission configuration module in the cloud;

The access module of the medical terminal accesses the medical information stored in the cloud according to the authority assigned by the authority configuration module;

The broadcast sending module in the cloud sends broadcast information to the medical terminal, and the broadcast information includes the user's identity information and current department information;

The diagnosis and treatment module of the medical terminal prompts the user to perform the diagnosis and treatment process according to the broadcast information, and generates the medical information of the user's current diagnosis and treatment process;

Send the medical information of the user's current diagnosis and treatment process to the information receiving module through the sending module of the medical terminal, and update the user's electronic medical record;

The classification processing module in the cloud classifies and stores the medical information received by the information receiving module and pushes the classification results to the medical terminal; the classification processing module is preset with a disease classification model. The second disease prediction architecture is sequentially connected; the first disease prediction architecture is used to directly predict the first predicted disease (or conventional predicted disease) based on specified medical information, and the second disease prediction architecture is a small-scale architecture. for predicting other diseases associated with the first predicted disease (ie, the second predicted disease). This is because some diseases have accompanying characteristics, which are determined by the special physiological structure of the human body. Therefore, the second disease prediction framework is used to predict these associated diseases to improve the comprehensiveness of prediction. Wherein, the selection connection layer is used to select which second disease prediction framework to use. Therefore, the first predicted disease is predicted by using the machine learning model (ie, the first disease prediction framework) based on the specified medical information of the specified object; the second predicted disease is based on the first predicted disease, according to the specified object Medical information is obtained by selecting the second disease prediction framework associated with the first predicted disease, wherein since the second disease prediction framework is a more accurate disease prediction framework, it has confirmed the existence of the first predicted disease, so in When performing training and computation in the second disease prediction framework, compared with the first prediction framework, the emphasis on designated medical information will be different, so that different second prediction diseases can be predicted. Furthermore, the medical information input by the second disease prediction framework may also include newly added medical data, so as to further improve the accuracy of the prediction.

Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for relevant details, please refer to the description of the method part.

The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. The medical information management system is characterized by comprising a cloud end and a plurality of medical terminals;

the cloud comprises a terminal list acquisition module, a broadcast sending module, an information receiving module, a permission configuration module and a classification processing module;

the terminal list acquisition module is used for acquiring a terminal list, wherein the terminal list comprises terminal codes of the medical terminals, and the terminal codes are in one-to-one correspondence with the medical terminals;

the broadcast transmitting module is used for transmitting broadcast information to the medical terminal, wherein the broadcast information comprises identity information of a user and current information of a department of medical treatment;

the information receiving module is used for receiving and storing medical information of the medical terminal corresponding to the terminal code, wherein the medical information comprises an electronic medical record for recording user disease data;

the permission configuration module is used for configuring the access permission of the medical terminal in the terminal list;

the classification processing module is preset with a disease classification model and is used for classifying and storing the medical information received by the information receiving module and pushing the classification result to the medical terminal; the disease classification model is formed by sequentially connecting a first disease prediction framework, a selection connecting layer and a plurality of second disease prediction frameworks;

the medical terminal comprises an access module, a diagnosis and treatment module and a sending module;

the access module is used for accessing the medical information stored in the cloud according to the rights allocated by the rights allocation module;

the diagnosis and treatment module is used for prompting a user to execute a diagnosis and treatment process according to the broadcast information and generating medical information of the diagnosis and treatment process of the user;

the sending module is used for sending the medical information of the current diagnosis and treatment process of the user to the information receiving module and updating the electronic medical record of the user.

2. The medical information management system according to claim 1, wherein the terminal list acquisition module initiates a terminal list acquisition request, each medical terminal transmits a respective terminal code to the cloud after establishing a channel, and a corresponding medical terminal is determined according to each terminal code.

3. The medical information management system according to claim 1, wherein the cloud is provided with a department fitting relation table, a plurality of departments are arranged in the department fitting relation table, fitting relations of the departments are represented in a connecting line mode, fitting degrees among the departments are determined according to a connecting mode of the connecting line, and the higher the fitting degree is, the greater the medical information reference value in the corresponding medical terminal is.

4. A medical information management system according to claim 3, wherein said information receiving module is further configured to screen associated medical data, said associated medical data being medical information matching medical information generated by said current department of medical care;

and the information receiving module determines a fitting department of the current visit department according to the department fitting relation table, further determines a terminal code of a medical terminal corresponding to the fitting department, invokes medical information in the terminal code, and screens medical information with the matching degree with the keyword information higher than the standard matching degree according to the preset standard matching degree to obtain the associated medical data.

5. The medical information management system according to claim 1, wherein the classification processing module includes a designation information acquisition unit, a first predicted disease acquisition unit, a prediction architecture selection unit, a second predicted disease acquisition unit, a disease classification vector mapping unit, a distance threshold judgment unit, a category classification unit;

the specified information acquisition unit is used for acquiring specified medical information of a user, including disease data and associated medical data of the user;

the first predicted disease obtaining unit is used for inputting the specified medical information into a first disease prediction framework in a preset disease classification model to obtain a first predicted disease output by the first disease prediction framework;

a prediction architecture selection unit, configured to input the first predicted disease into the selection connection layer, and obtain a specified second disease prediction architecture selected by the selection connection layer according to a preset selection method;

a second predicted disease acquisition unit configured to input the first predicted disease and the specified medical information into the specified second disease prediction framework, and output a second predicted disease;

a disease classification vector mapping unit configured to map the specified medical information, the first predicted disease, and the second predicted disease into disease classification vectors according to a predicted classification vector mapping method;

a distance threshold judging unit, configured to retrieve a preset standard classification vector, calculate a distance value between the standard classification vector and the disease classification vector, and judge whether the distance value is smaller than a preset distance threshold, where the standard classification vector is labeled with the first predicted disease and the second predicted disease, and the standard classification vector is labeled as a specified class;

the specified category classification unit is used for classifying the specified medical information into the specified category if the distance value is smaller than a preset distance threshold value.

6. The medical information management system according to claim 5, wherein the first predicted disease acquisition unit maps the specified medical information into an initial time vector sequence including a first sub-sequence mapped from the user's disease data and a second sub-sequence mapped from the associated medical data according to a preset time vector mapping method; the specified medical information, the diseased data of the user and the total time involved by the associated medical data are all divided into n time periods, so that the number of constituent elements of the initial time vector sequence, the first sub-sequence and the second sub-sequence is n;

inputting the initial time vector sequence into the first disease prediction framework, and calculating a prediction time vector;

combining the predicted time vectors into a predicted time vector sequence according to a time sequence, and reading the predicted time vector sequence according to a preset vector reading method so as to obtain predicted illness results and corresponding illness probabilities in different time periods;

and marking the predicted disease result with the disease probability higher than a preset probability threshold as a first predicted disease, and outputting the first predicted disease.

7. The medical information management system of claim 5, wherein the specified second disease prediction framework is trained based on a neural network model, comprising:

retrieving sample data from a disease database and classifying the sample data into a training set as a validation set, wherein the sample data is comprised of the first predicted disease, medical information associated with the first predicted disease, and other diseases associated with the first predicted disease;

training a preset neural network model by using the training set by adopting a random gradient descent method so as to obtain an intermediate model;

verifying the intermediate model by using the verification set, and judging whether the verification is passed or not;

if the verification is passed, the intermediate model is recorded as the designated second disease prediction architecture.

8. The medical information management system of claim 7, wherein the specifying the second disease prediction framework comprises, prior to neural network training:

inquiring a preset international disease classification library so as to obtain a designated international disease classification number corresponding to the first predicted disease;

and intercepting the first three codes of the specified international disease classification number, and selecting a second disease prediction framework marked with the first three codes from a plurality of preset second disease prediction frameworks to obtain a specified second disease prediction framework.

9. A medical information management method, characterized by comprising the steps of:

acquiring a terminal list through a terminal list acquisition module of a cloud, wherein the terminal list comprises terminal codes of the medical terminals, and the terminal codes are in one-to-one correspondence with the medical terminals;

receiving and storing medical information of a medical terminal corresponding to the terminal code through an information receiving module of the cloud, wherein the medical information comprises an electronic medical record for recording user disease data;

configuring the access rights of the medical terminal in the terminal list through a rights configuration module of the cloud;

the access module of the medical terminal accesses the medical information stored in the cloud according to the rights distributed by the rights configuration module;

the broadcasting sending module of the cloud sends broadcasting information to the medical terminal, wherein the broadcasting information comprises identity information of a user and current medical department information;

the diagnosis and treatment module of the medical terminal prompts the user to execute a diagnosis and treatment process according to the broadcast information, and generates medical information of the diagnosis and treatment process of the user;

the medical information of the current diagnosis and treatment process of the user is sent to the information receiving module through the sending of the medical terminal, and the electronic medical record of the user is updated;

the cloud classification processing module stores the medical information received by the information receiving module in a classified mode and pushes the classification result to the medical terminal; the disease classification model is formed by sequentially connecting a first disease prediction framework, a selection connecting layer and a plurality of second disease prediction frameworks.

Images