CN109817297B - Medical report generation method, device, computer equipment and computer storage medium - Google Patents
Medical report generation method, device, computer equipment and computer storage medium Download PDFInfo
- Publication number
- CN109817297B CN109817297B CN201811553950.1A CN201811553950A CN109817297B CN 109817297 B CN109817297 B CN 109817297B CN 201811553950 A CN201811553950 A CN 201811553950A CN 109817297 B CN109817297 B CN 109817297B
- Authority
- CN
- China
- Prior art keywords
- medical
- data
- medical data
- analysis model
- medical information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application discloses a medical report generation method, a medical report generation device, a medical report generation computer device and a medical report generation computer storage medium, which relate to the technical field of artificial intelligence, and can improve the readability of medical report generation and save the medical report generation time. The method comprises the following steps: acquiring medical data uploaded by each data source; storing the medical data uploaded by each data source into a blockchain network, wherein a medical information analysis model for analyzing the medical data is pre-packaged in the blockchain network; analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for confirmation of doctors; and filling the medical information for doctor confirmation into a preset report template to generate a medical report.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a method and apparatus for generating a medical report, a computer device, and a computer storage medium.
Background
Medical treatment has become an important research and application field in the artificial intelligence industry, and medical report has been widely paid attention to as an important basis for doctors in recording the health of patients.
In the early medical field, doctors often need to manually complete the writing of medical reports, such as examination reports, operation reports and the like, while in the medical field under artificial intelligence, doctors can input electronic medical records through machines, and the writing speed of the medical reports is improved by utilizing electronic medical histories. With the continuous development of artificial intelligence, most common important doctors input electronic medical records through voice, can carry out basic record on the forehead basic information and the operation condition of patients by utilizing a voice recognition mode to obtain unstructured text data on the medical records, and then convert the unstructured text data on the medical records into structured text data by utilizing natural language processing, so as to generate medical reports.
However, because the requirements of voice recognition on the surroundings are high, a doctor is required to enter a language expression of a report, the result of recognizing characters is inaccurate easily, and the generated medical report has poor readability. In addition, some of the text in the medical report may be directly retrieved from the examination result data or from a template of the specification, and generating the medical report by speech recognition may take more time for the physician.
Disclosure of Invention
In view of the above, the present invention provides a method, apparatus, computer device and computer storage medium for generating medical reports, which mainly aims to solve the problem of poor readability of medical reports generated in the related art at present.
According to one aspect of the present invention, there is provided a method of generating a medical report, the method comprising:
acquiring medical data uploaded by each data source;
storing the medical data uploaded by each data source into a blockchain network, wherein a medical information analysis model for analyzing the medical data is pre-packaged in the blockchain network;
analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for confirmation of doctors;
and filling the medical information for doctor confirmation into a preset report template to generate a medical report.
Further, the storing the medical data uploaded by the respective data sources into the blockchain network includes:
extracting sequence identifiers for recording medical data from the medical data uploaded by each data source;
and recording medical data belonging to the same sequence identifier to the same block in the block chain network according to the sequence identifier.
Further, before the recording of medical data belonging to the same order identifier onto the same block in the blockchain network according to the order identifier, the method further includes:
and carrying out consistency verification on the medical data belonging to the same sequence identifier by utilizing a consensus mechanism of the blockchain network to obtain the medical data with the same sequence identifier consensus.
Further, before analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for doctor confirmation, the method further includes:
medical data of each disease type is collected in advance, and the medical data is marked according to the disease type corresponding to the medical data, so that medical data carrying a disease type label is obtained;
inputting the medical data carrying the disease type label into a neural network model for training to obtain a medical information analysis model, wherein the medical information analysis model records the disease type matched with the medical data;
encrypting and registering the medical information analysis model in a blockchain network.
Further, the neural network model is a multi-layer structure, and the step of inputting the medical data carrying the disease type label into the neural network model for training to obtain the medical information analysis model includes:
Extracting local information features corresponding to medical data of each disease through a first layer structure of the neural network model;
summarizing local data features corresponding to medical data of each disease type through a second layer structure of the neural network model to obtain multidimensional local data features;
performing dimension reduction processing on the multidimensional local data features through a third layer structure of the neural network model to obtain data features corresponding to each disease type;
and classifying the data features corresponding to each disease type through a fourth layer structure of the neural network model to obtain a medical information analysis model for identifying each disease type.
Further, the analyzing the medical data uploaded by each data source according to the medical information analysis model, and obtaining medical information for confirming by a doctor includes:
identifying a disease type matched with the medical data by inputting the medical data uploaded by each data source into the medical information analysis model;
and searching medical information corresponding to the medical data according to the disease type to obtain medical information for confirmation of doctors.
Further, after the medical information for doctor confirmation is filled into a preset report template to generate a medical report, the method further comprises:
Extracting a plurality of processor information from the medical report, and respectively sending the medical report to the plurality of processor information so that a plurality of processors can make medical feedback information for the medical report.
According to another aspect of the present invention, there is provided a medical report generating apparatus, the apparatus comprising:
the acquisition unit is used for acquiring the medical data uploaded by each data source;
the storage unit is used for storing the medical data uploaded by each data source into a blockchain network, and a medical information analysis model for analyzing the medical data is packaged in the blockchain network in advance;
the analysis unit is used for analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for a doctor to confirm;
and the generation unit is used for filling the medical information for the confirmation of the doctor into a preset report template and generating a medical report.
Further, the storage unit includes:
the extraction module is used for extracting the sequence identifier for recording the medical data from the medical data uploaded by each data source;
and the storage module is used for recording the medical data belonging to the same sequence identifier to the same block in the block chain network according to the sequence identifier.
Further, the memory cell further includes:
and the verification module is used for carrying out consistency verification on the medical data belonging to the same sequence identifier by utilizing a consensus mechanism of the blockchain network before the medical data belonging to the same sequence identifier is recorded on the same block in the blockchain network according to the sequence identifier, so as to obtain the medical data with the same sequence identifier agreed.
Further, the apparatus further comprises:
the marking unit is used for collecting the medical data of each disease type in advance before analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for a doctor to confirm, and marking the medical data according to the disease type corresponding to the medical data to obtain medical data carrying a disease type label;
the training unit is used for inputting the medical data carrying the disease type label into a neural network model for training to obtain a medical information analysis model, wherein the medical information analysis model records the disease type matched with the medical data;
and the encryption unit is used for encrypting the medical information analysis model and registering the medical information analysis model into a blockchain network.
Further, the neural network model is a multi-layer structure, and the training unit includes:
the extraction module is used for extracting local information features corresponding to medical data of each disease through the first layer structure of the neural network model;
the summarizing module is used for summarizing local data characteristics corresponding to the medical data of each disease type through a second layer structure of the neural network model to obtain multidimensional local data characteristics;
the processing module is used for performing dimension reduction processing on the multi-dimensional local data features through a third layer structure of the neural network model to obtain data features corresponding to each disease type;
and the classification module is used for classifying the data features corresponding to each disease type through a fourth layer structure of the neural network model to obtain a medical information analysis model for identifying each disease type.
Further, the analysis unit includes:
the identification module is used for identifying the disease type matched with the medical data by inputting the medical data uploaded by each data source into the medical information analysis model;
and the searching module is used for searching the medical information corresponding to the medical data according to the disease type to obtain the medical information for the confirmation of doctors.
Further, the apparatus further comprises:
and the sending unit is used for extracting a plurality of pieces of processor information from the medical report after the medical information for confirming the doctor is filled into a preset report template to generate the medical report, and respectively sending the medical report to the plurality of pieces of processor information so that a plurality of processors can make medical feedback information for the medical report.
According to a further aspect of the present invention there is provided a computer device comprising a memory storing a computer program and a processor implementing the steps of the method of generating a medical report when the computer program is executed by the processor.
According to a further aspect of the present invention, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a method of generating a medical report.
By means of the technical scheme, compared with the mode of generating the medical report in the text form by using the voice recognition mode in the prior art, the medical data uploaded by each data source are stored in the blockchain network, so that the blockchain network has more comprehensive medical data, the medical data are further analyzed by using the medical information analysis model stored in the blockchain network to obtain medical information for a doctor to confirm, the medical analysis model can analyze the medical data characteristics of different disease types, more accurate medical information data can be obtained by using the medical information analysis model, voice input and text description of the doctor are not needed, and the doctor can conveniently operate, so that the generation time of the medical report is saved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a schematic flow chart of a method for generating a medical report according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for generating a medical report according to an embodiment of the present invention;
FIG. 3 is a flow chart of constructing a medical information analysis model according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a medical report generating device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of another medical report generating apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the invention provides a method for generating a medical report, which can improve the readability of the generated medical report, as shown in fig. 1, and comprises the following steps:
101. medical data uploaded by each data source is acquired.
When a doctor completes a treatment process or an operation, etc., a medical report in the form of text needs to be generated, where the medical data is typically data related to the medical report, such as doctor diagnosis data, doctor examination data, doctor advice data, etc., and the medical data may include, but is not limited to, text, voice, or picture, etc.
The different data sources can be shooting equipment, a printing machine, a voice recorder and the like, the medical data can be pictures shot by the shooting equipment, characters printed by the machine, voices recorded by the voice recorder and the like.
For the embodiment of the invention, after the medical data is recorded in a certain data source, the data of the data source can be uploaded to a system, the system gathers the medical data uploaded by each data source, the data source can be set to automatically upload the medical data, or a professional can be set to take charge of each data source, and after the medical data of the data source is recorded, the medical data is uploaded through manual operation.
102. And storing the medical data uploaded by each data source into a blockchain network, wherein a medical information analysis model for analyzing the medical data is pre-packaged in the blockchain network.
Since corpus data uploaded by different data sources may relate to data generated by different diagnostic approaches, accurate diagnostic results applicable to a patient's condition may not be obtained if the patient's condition is determined from only a single data source. For example, machine-generated medical data may more record index data and whether the index data is within a normal range, while medical data recorded by a voice recorder may more record analysis of the index data by a doctor, a treatment mode, and the like.
For the embodiment of the invention, the blockchain is a chain type data structure which is formed by combining data blocks in a sequential connection mode according to a time sequence, medical data uploaded by different data sources are collected through a blockchain network, and more perfect and comprehensive medical data are obtained, so that the disease type of a patient is accurately judged, and a follow-up doctor can provide accurate medical diagnosis and advice for the patient.
In order to more accurately judge and process the disease types of the patients, the embodiment of the invention packages the medical information analysis model for analyzing the medical data in the blockchain network in advance, wherein the medical information analysis model records the disease types of the patients matched with the medical data, and the disease types of the patients matched with the medical data can be identified through the medical information analysis model.
103. And analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for confirmation of doctors.
Since the medical information analysis model records the disease types matched with the medical data, for example, the disease types caused by lymphadenitis, lymphoma and other lymphatics, the medical information analysis model analyzes the medical data to find the disease types matched with the medical data, and in general, the number of the disease types may be multiple, and a doctor needs to further confirm or further check, and the multiple disease types are used as medical information to generate medical information for the doctor to confirm.
For the embodiment of the invention, as the medical data uploaded by each data source can record the patient disease data in different aspects, the patient disease data can record disease performance characteristics, disease inspection data and the like, the patient disease data in different aspects can be analyzed through the medical information analysis model, the accuracy of the patient medical data is verified comprehensively in multiple aspects, the medical information for doctor confirmation is generated, the doctor does not need to expend effort to summarize the patient medical information, and only needs to further confirm the patient medical information and provide accurate advice for the patient, so that the time of the doctor and the patient is saved.
104. And filling the medical information for doctor confirmation into a preset report template to generate a medical report.
The whole medical treatment process of the patient can be recorded in the preset report template, and the medical treatment process at least comprises but is not limited to the steps of inquiry, diagnosis, examination, treatment and the like, each step can be corresponding to respective medical information, and the medical information for doctor confirmation is further filled in the preset report template to generate a medical report.
Compared with the mode of generating the text-form medical report by utilizing the voice recognition mode in the prior art, the medical data uploaded by each data source is stored in the blockchain network, so that the blockchain network has more comprehensive medical data, the medical data is further analyzed by utilizing the medical information analysis model stored in the blockchain network to obtain medical information for a doctor to confirm, the medical analysis model can analyze the medical data characteristics of different disease types, more accurate medical information data can be obtained through the medical information analysis model, the voice input and the word arrangement description of the doctor are not needed, the doctor can conveniently operate, and the generation time of the medical report is saved.
The embodiment of the invention provides another method for generating a medical report, which can save the generation time of the medical report, as shown in fig. 2, and comprises the following steps:
201. medical data uploaded by each data source is acquired.
The different data sources can be equipment with data acquisition functions, such as a voice recorder, printing equipment, shooting equipment and the like, which are arranged in each department in the patient diagnosis process. The voice recorder can collect data such as voice dialogue between doctors and patients, the printing equipment can collect data such as indexes of patient examination, the shooting equipment can collect data such as pictures of patient examination organs, each data source has a data collection function and a data transmission function, the collected medical data can be uploaded in each period of time through the automatic uploading function, and the medical data can be uploaded through manual operation of course, and the medical data are not limited.
For the embodiment of the invention, when a patient visits a hospital, each data source can collect the medical data of each step in the whole medical treatment process of the patient, and the medical data of the whole aspect of the patient is obtained by summarizing the medical data uploaded by each data source, so that doctors can accurately diagnose the illness state of the patient and provide more effective advice.
202. And extracting the sequence identification of the recorded medical data from the medical data uploaded by each data source.
For the embodiment of the invention, each data source may relate to different stages of the patient during medical treatment, and medical data is generally collected by voice recording during doctor consultation, some medical data about disease symptoms of the patient is collected, medical data is collected by medical equipment during patient examination, and some medical data about disease indexes of the patient is collected. So according to the characteristics of the medical data of each data source in different medical treatment stages, the sequence identification for recording the medical data can be extracted from the medical data uploaded by each data source.
According to the embodiment of the invention, the sequence identification for recording the medical data is extracted from the medical data uploaded by each data source, and the medical data related to the patient in the medical treatment process can be connected in series through the sequence identification, so that a doctor can diagnose the patient conveniently.
203. And carrying out consistency verification on the medical data belonging to the same sequence identifier by utilizing a consensus mechanism of the blockchain network to obtain the medical data with the same sequence identifier consensus.
For the embodiment of the invention, before the medical data is uploaded to the block, the consistency verification is carried out on the medical data to be uploaded to each block by utilizing the consensus mechanism of the block chain network, the medical data passing verification can be uploaded to the block, once the medical data is recorded into the block and cannot be deleted or changed, the consistency of the medical data of each data source or each characteristic information is ensured, and the same data cannot appear in a plurality of blocks.
The blockchain technology is a novel distributed architecture and calculation paradigm, and uses a chained data structure to verify and store data, a distributed node consensus algorithm to generate and update data, cryptography and other modes to ensure the safety of data transmission and access. Medical data uploaded by different data sources are summarized and verified through the blockchain network, so that the safety of the medical data is ensured.
The consensus mechanism is used for verifying the consistency of data in the blocks in the block chain network, and as each block records medical data with the same sequence identification, when different medical data with the same sequence identification are received, the consistency of the medical data with the sequence identification is verified through the consensus mechanism, so that the medical data with the sequence identification are consensus, and the consistency among the medical data with the same sequence identification is ensured.
It should be noted that different consensus mechanisms have different implementation manners, for example, the consensus mechanism of workload certification relies on a machine to perform data operation to certify the workload of a node; the node rights allocation is carried out according to the amount and time of the held data by the consensus mechanism of the rights evidence.
204. And recording medical data belonging to the same sequence identifier to the same block in the block chain network according to the sequence identifier.
For the embodiment of the present invention, the blockchain network structure includes a plurality of block files, each block file records the medical data which is identified in the same order and is agreed with the same block file, and the medical data which is identified in the same order and is agreed with the same block file is further recorded on the same block according to the order identification without being recorded by other previous blocks, and once the medical data is recorded in the block, the medical data cannot be changed or deleted.
Each block is composed of a block chain head and a block body, wherein each block chain head contains block meta information such as a version number, a hash value of a previous block, a time stamp and the like, and also contains a pointer pointing to the hash value of the previous block chain head, the pointer is key information for preventing the block chain network from being tampered, and the block body contains medical data uploaded by each data source.
It should be noted that the block header plays a decisive role in the whole blockchain network, and in the process of data transmission between the block and other blocks, each block in the blockchain network is combined by the pointer in the block chain header to form a medical data record book which is easy to verify and cannot be changed.
In the process of recording medical data to the blockchain network, firstly, a data layer of the blockchain network records the medical data uploaded by each data source on different blocks, each block is identified according to characteristic information corresponding to the medical data, a sequence rule among the blocks is established through the identification, the medical data uploaded by each data source is stored in the blockchain network by utilizing the sequence rule among the blocks, for example, patient characteristics are stored in one block, patient examination information is stored in one block, doctor diagnosis information is stored in one block, and a sequence rule exists among the blocks.
205. And identifying the disease type matched with the medical data by inputting the medical data uploaded by the data sources into the medical information analysis model.
For the embodiment of the invention, as the disease types matched with the medical data are recorded in the medical information analysis model, the disease types corresponding to the data characteristics of the medical data can be identified through the medical information analysis model, diagnosis is carried out without the need of a doctor to gather each data, pre-analysis of the illness state of a patient can be realized, and the disease diagnosis speed of the doctor is improved.
206. And searching medical information corresponding to the medical data according to the disease type to obtain medical information for confirmation of doctors.
In addition, as the medical data with different order rules are recorded in each block, in the process of specifically generating the medical information for the doctor to determine, the medical data stored in each block according to the order rules is imported into a pre-trained medical information analysis model, the pre-trained medical information analysis model has characteristic information of disease types corresponding to the medical data recorded in the block, the disease types corresponding to each block are output and obtained, the medical information corresponding to the medical data is further searched according to the disease types, and the medical data uploaded by each data source can be summarized by the medical information, so that the accuracy is higher.
207. And filling the medical information for doctor confirmation into a preset report template to generate a medical report.
Here, the medical information for doctor confirmation is not a final diagnosis result, and the doctor is required to further confirm the accuracy of the new medical country, and a medical report is generated by filling the medical information for doctor confirmation into a preset report template in which various information of the patient, such as patient disease symptoms, examination indexes, and medication information, etc., are recorded.
In order to further record more medical information, user information, time of medical treatment, hospital information, and the like may be added to a preset report destination, which is not limited herein.
208. Extracting a plurality of processor information from the medical report, and respectively sending the medical report to the plurality of processor information so that a plurality of processors can make medical feedback information for the medical report.
The medical feedback information is a process that the processing party confirms the generated medical information, so that if the processing party has problems on the content recorded in the medical information, the processing party can timely feed back the content, for example, the disease symptoms of a patient in the medical information are wrongly described, the disease diagnosis result can be influenced, and the patient is required to feed back the content in time, thereby ensuring the accuracy of the medical report.
Compared with the mode of generating the text-form medical report by using the voice recognition mode in the prior art, the medical data uploaded by each data source is stored in the blockchain network, so that the blockchain network has more comprehensive medical data, the medical data is further analyzed by using the medical information analysis model stored in the blockchain network to obtain medical information for a doctor to confirm, the medical analysis model can analyze the medical data characteristics of different disease types, more accurate medical information data can be obtained by the medical information analysis model, the voice input and the word arrangement description of the doctor are not needed, the doctor can operate conveniently, and the generation time of the medical report is saved.
It should be noted that, before step S206 is performed, the medical information analysis model needs to be built, which may be specifically implemented by following steps S209 to S211, and the process of building the medical information analysis model is not limited to be performed after steps S201 to S205, and as shown in fig. 3, the specific process of building the medical information analysis model includes the following steps:
209. medical data of each disease type is collected in advance, and the medical data is marked according to the disease type corresponding to the medical data, so that the medical data carrying the disease type label is obtained.
According to the embodiment of the invention, in order to improve the accuracy of the medical information analysis model, medical data samples of all disease types which are collected in advance are as large as possible and data are as diverse as possible, so that the output medical information analysis result is ensured to contain more disease types and is closer to the actual situation.
The medical data of each disease type may be collected in advance by medical sample data recorded in each hospital, and the disease type corresponding to the medical data may be a disease type related to a large class of different organs, for example, gastrointestinal type disease, liver disease, eye disease, or a disease type related to a certain organ refinement, for example, glaucoma, keratitis, cataract, etc., without limitation.
210. And inputting the medical data carrying the disease type label into a neural network model for training to obtain a medical information analysis model.
The medical information analysis model records the disease type matched with the medical data, specifically adopts a network training model to train the medical data carrying the disease type label, can adopt a supervised learning algorithm or an unsupervised learning algorithm, and can also adopt a deep neural network learning algorithm.
For the embodiment of the present invention, the neural network model is a multi-layer structure, and the specific process of inputting the medical data carrying the disease type label as the sample data into the neural network model for training may be: extracting local information features corresponding to medical data of each disease through a first layer structure of the neural network model; summarizing local data features corresponding to medical data of each disease type through a second layer structure of the neural network model to obtain multidimensional local data features; performing dimension reduction processing on the multidimensional local data features through a third layer structure of the neural network model to obtain data features corresponding to each disease type; and classifying the data features corresponding to each disease type through a fourth layer structure of the neural network model to obtain a medical information analysis model for identifying each disease type.
Because the mapping relation between the data characteristics of each disease type and the medical data is recorded in the medical information analysis model, the disease type matched with the medical data can be identified through the medical information analysis model.
211. Encrypting and registering the medical information analysis model in a blockchain network.
For the embodiment of the invention, the medical information analysis model can be trained through the network model, and as the medical information analysis model is constructed for medical data aiming at different disease types, not all clients have the authority of using the medical information analysis model to analyze the medical data, in order to ensure the safety of the medical information analysis model, the medical information analysis model needs to be encrypted before being packaged and registered in a blockchain network, and only the clients which are subjected to decryption verification can analyze the uploaded medical data, but other clients cannot analyze the medical data.
Specifically, before the medical information analysis model is used for analyzing the medical data, the decryption key is sent to the uploading client with the use authority in advance, the uploading client with the use authority decrypts the medical information analysis model according to the decryption key, then the medical information analysis model is used for analyzing the medical data, and when the client without the use authority cannot acquire the decryption key, the medical information analysis model cannot be used for analyzing the medical data.
Further, as a specific implementation of the method shown in fig. 1, an embodiment of the present invention provides a medical report generating apparatus, as shown in fig. 4, where the apparatus includes: an acquisition unit 31, a storage unit 32, an analysis unit 33, and a generation unit 34.
An acquisition unit 31, which may be configured to acquire medical data uploaded by each data source;
a storage unit 32, configured to store the medical data uploaded by the respective data sources into a blockchain network, where a medical information analysis model for analyzing the medical data is pre-packaged;
the analysis unit 33 may be configured to analyze the medical data uploaded by each data source according to the medical information analysis model, to obtain medical information for confirmation by a doctor;
the generating unit 34 may be configured to fill the medical information for doctor confirmation into a preset report template, and generate a medical report.
Compared with the mode of generating the text-form medical report by utilizing the voice recognition mode in the prior art, the medical data uploaded by each data source is stored in the blockchain network, so that the blockchain network has more comprehensive medical data, the medical data is further analyzed by utilizing the medical information analysis model stored in the blockchain network to obtain medical information for a doctor to confirm, the medical analysis model can analyze the medical data characteristics of different disease types, more accurate medical information data can be obtained through the medical information analysis model, the voice input and the word arrangement description of the doctor are not needed, the doctor can conveniently operate, and the generation time of the medical report is saved.
As a further illustration of the medical report generating apparatus shown in fig. 4, fig. 5 is a schematic structural view of another medical report generating apparatus according to an embodiment of the present invention, as shown in fig. 5, the apparatus further includes:
the marking unit 35 may be configured to collect, in advance, medical data of each disease type before the medical data uploaded by each data source is analyzed according to the medical information analysis model to obtain medical information for confirmation by a doctor, and mark the medical data according to a disease type corresponding to the medical data to obtain medical data carrying a disease type tag;
the training unit 36 may be configured to input the medical data carrying the disease type tag into a neural network model for training, to obtain a medical information analysis model, where a disease type matched with the medical data is recorded in the medical information analysis model;
an encryption unit 37 operable to encrypt the medical information analysis model and register it into a blockchain network;
the sending unit 38 may be configured to extract a plurality of pieces of processor information from the medical report after the medical information for doctor confirmation is filled into a preset report template to generate the medical report, and send the medical report to the plurality of pieces of processor information, respectively, so that a plurality of processors make medical feedback information for the medical report.
Further, the storage unit 32 includes:
the extracting module 321 may be configured to extract a sequence identifier of the recorded medical data from the medical data uploaded by the data sources;
the storage module 322 may be configured to record medical data belonging to the same order identifier onto the same block in the blockchain network according to the order identifier.
Further, the storage unit 32 further includes:
the verification module 323 may be configured to perform consistency verification on the medical data belonging to the same order identifier by using a consensus mechanism of the blockchain network before the medical data belonging to the same order identifier is recorded on the same block in the blockchain network according to the order identifier, so as to obtain medical data having the same order identifier agreed.
Further, the neural network model is a multi-layer structure, and the training unit 36 includes:
the extraction module 361 may be configured to extract local information features corresponding to medical data of each disease through a first layer structure of the neural network model;
the summarizing module 362 may be configured to summarize local data features corresponding to medical data of each disease type through a second layer structure of the neural network model, to obtain multidimensional local data features;
The processing module 363 can be used for performing dimension reduction processing on the multi-dimensional local data features through a third layer structure of the neural network model to obtain data features corresponding to each disease type;
the classification module 364 may be configured to classify the data features corresponding to the disease types through a fourth layer structure of the neural network model, so as to obtain a medical information analysis model for identifying the disease types.
Further, the analysis unit 33 includes:
the identifying module 331 may be configured to identify a disease type matched with the medical data by inputting the medical data uploaded by the respective data sources into the medical information analysis model;
the searching module 332 may be configured to search for medical information corresponding to the medical data according to the disease type, and obtain medical information for a doctor to confirm.
It should be noted that, for other corresponding descriptions of each functional unit related to the medical report generating apparatus provided in this embodiment, reference may be made to corresponding descriptions in fig. 1, fig. 2 and fig. 3, and no further description is given here.
Based on the above-described methods shown in fig. 1, 2 and 3, correspondingly, the present embodiment further provides a storage medium having a computer program stored thereon, which when executed by a processor, implements the above-described medical report generating method shown in fig. 1, 2 and 3.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to perform the methods described in various implementation scenarios of the present application.
Based on the methods shown in fig. 1, fig. 2 and fig. 3 and the virtual device embodiments shown in fig. 4 and fig. 5, in order to achieve the above objects, the embodiments of the present application further provide a computer device, which may specifically be a personal computer, a server, a network device, etc., where the entity device includes a storage medium and a processor; a storage medium storing a computer program; a processor for executing a computer program to implement the above-described medical report generation method as shown in fig. 1, 2 and 3.
Optionally, the computer device may also include a user interface, a network interface, a camera, radio Frequency (RF) circuitry, sensors, audio circuitry, WI-FI modules, and the like. The user interface may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., bluetooth interface, WI-FI interface), etc.
It will be appreciated by those skilled in the art that the physical device structure for generating a medical report provided in this embodiment is not limited to this physical device, and may include more or fewer components, or may combine certain components, or may be a different arrangement of components.
The storage medium may also include an operating system, a network communication module. An operating system is a program that manages the computer device hardware and software resources described above, supporting the execution of information handling programs and other software and/or programs. The network communication module is used for realizing communication among all components in the storage medium and communication with other hardware and software in the entity equipment.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware. Through applying the technical scheme of this application, compare with current prior art, through the medical data storage to the blockchain network that uploads each data source for have more comprehensive medical data in the blockchain network, further utilize the medical information analysis model that stores in the blockchain network to carry out the analysis to medical data, obtain the medical information that is used for doctor to confirm, here medical analysis model can analyze the medical data characteristic of different disease types, can obtain more accurate medical information data through medical information analysis model, need not doctor's voice input and arrangement word description, make things convenient for doctor's operation, thereby save the generation time of medical report.
Those skilled in the art will appreciate that the drawings are merely schematic illustrations of one preferred implementation scenario, and that the modules or flows in the drawings are not necessarily required to practice the present application. Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The foregoing application serial numbers are merely for description, and do not represent advantages or disadvantages of the implementation scenario. The foregoing disclosure is merely a few specific implementations of the present application, but the present application is not limited thereto and any variations that can be considered by a person skilled in the art shall fall within the protection scope of the present application.
Claims (8)
1. A method of generating a medical report, the method comprising:
acquiring medical data uploaded by each data source;
storing the medical data uploaded by each data source into a blockchain network, wherein a medical information analysis model for analyzing the medical data is pre-packaged in the blockchain network;
Analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for confirmation of doctors;
filling the medical information for doctor confirmation into a preset report template to generate a medical report;
before analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for doctor confirmation, the method further comprises: medical data of each disease type is collected in advance, and the medical data is marked according to the disease type corresponding to the medical data, so that medical data carrying a disease type label is obtained; inputting the medical data carrying the disease type label into a neural network model for training to obtain a medical information analysis model, wherein the medical information analysis model records the disease type matched with the medical data; encrypting the medical information analysis model and registering the medical information analysis model into a blockchain network;
the neural network model is of a multi-layer structure, the medical data carrying the disease type label is input into the neural network model for training, and the obtaining of the medical information analysis model comprises the following steps: extracting local information features corresponding to medical data of each disease through a first layer structure of the neural network model; summarizing local data features corresponding to medical data of each disease type through a second layer structure of the neural network model to obtain multidimensional local data features; performing dimension reduction processing on the multidimensional local data features through a third layer structure of the neural network model to obtain data features corresponding to each disease type; and classifying the data features corresponding to each disease type through a fourth layer structure of the neural network model to obtain a medical information analysis model for identifying each disease type.
2. The method of claim 1, wherein storing the medical data uploaded by the respective data sources into a blockchain network comprises:
extracting sequence identifiers for recording medical data from the medical data uploaded by each data source;
and recording medical data belonging to the same sequence identifier to the same block in the block chain network according to the sequence identifier.
3. The method of claim 2, wherein prior to said recording medical data belonging to a same order identifier onto a same tile in the blockchain network in the order identifier, the method further comprises:
and carrying out consistency verification on the medical data belonging to the same sequence identifier by utilizing a consensus mechanism of the blockchain network to obtain the medical data with the same sequence identifier consensus.
4. The method of claim 1, wherein analyzing the medical data uploaded by the respective data sources according to the medical information analysis model to obtain medical information for physician confirmation comprises:
identifying a disease type matched with the medical data by inputting the medical data uploaded by each data source into the medical information analysis model;
And searching medical information corresponding to the medical data according to the disease type to obtain medical information for confirmation of doctors.
5. The method of any one of claims 1-4, wherein after the filling of the medical information for physician confirmation into a preset report template, generating a medical report, the method further comprises:
extracting a plurality of processor information from the medical report, and respectively sending the medical report to the plurality of processor information so that a plurality of processors can make medical feedback information for the medical report.
6. A medical report generating apparatus, the apparatus comprising:
the acquisition unit is used for acquiring the medical data uploaded by each data source;
the storage unit is used for storing the medical data uploaded by each data source into a blockchain network, and a medical information analysis model for analyzing the medical data is packaged in the blockchain network in advance;
the analysis unit is used for analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for a doctor to confirm;
the generation unit is used for filling the medical information for the doctor to confirm into a preset report template and generating a medical report;
The apparatus further comprises:
the marking unit is used for collecting the medical data of each disease type in advance before analyzing the medical data uploaded by each data source according to the medical information analysis model to obtain medical information for a doctor to confirm, and marking the medical data according to the disease type corresponding to the medical data to obtain medical data carrying a disease type label;
the training unit is used for inputting the medical data carrying the disease type label into a neural network model for training to obtain a medical information analysis model, wherein the medical information analysis model records the disease type matched with the medical data;
the encryption unit is used for encrypting the medical information analysis model and registering the medical information analysis model into a blockchain network;
the neural network model is a multi-layer structure, and the training unit comprises:
the extraction module is used for extracting local information features corresponding to medical data of each disease through the first layer structure of the neural network model;
the summarizing module is used for summarizing local data characteristics corresponding to the medical data of each disease type through a second layer structure of the neural network model to obtain multidimensional local data characteristics;
The processing module is used for performing dimension reduction processing on the multi-dimensional local data features through a third layer structure of the neural network model to obtain data features corresponding to each disease type;
and the classification module is used for classifying the data features corresponding to each disease type through a fourth layer structure of the neural network model to obtain a medical information analysis model for identifying each disease type.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer storage medium having stored thereon a computer program, which when executed by a processor realizes the steps of the method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811553950.1A CN109817297B (en) | 2018-12-19 | 2018-12-19 | Medical report generation method, device, computer equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811553950.1A CN109817297B (en) | 2018-12-19 | 2018-12-19 | Medical report generation method, device, computer equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109817297A CN109817297A (en) | 2019-05-28 |
| CN109817297B true CN109817297B (en) | 2023-08-08 |
Family
ID=66602132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811553950.1A Active CN109817297B (en) | 2018-12-19 | 2018-12-19 | Medical report generation method, device, computer equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109817297B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335676A (en) * | 2019-07-09 | 2019-10-15 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN111696675B (en) * | 2020-05-22 | 2023-09-19 | 深圳赛安特技术服务有限公司 | User data classification method and device based on Internet of things data and computer equipment |
| CN113890755B (en) * | 2021-09-26 | 2023-05-16 | 天津大学 | Patient family remote confirmation system and authorization method based on blockchain |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101203170A (en) * | 2005-06-02 | 2008-06-18 | 美的派特恩公司 | System and method of computer-aided detection |
| CN102651055A (en) * | 2012-04-11 | 2012-08-29 | 华中科技大学 | Method and system for generating file based on medical image |
| CN106156530A (en) * | 2016-08-03 | 2016-11-23 | 北京好运到信息科技有限公司 | Health check-up data analysing method based on stack own coding device and device |
| CN106446574A (en) * | 2016-10-10 | 2017-02-22 | 重庆市中迪医疗信息科技股份有限公司 | Image report system |
| CN108198620A (en) * | 2018-01-12 | 2018-06-22 | 洛阳飞来石软件开发有限公司 | A kind of skin disease intelligent auxiliary diagnosis system based on deep learning |
| CN108320781A (en) * | 2018-03-15 | 2018-07-24 | 安徽科大讯飞医疗信息技术有限公司 | A kind of voice-based medical report generation method and device |
| CN109036553A (en) * | 2018-08-01 | 2018-12-18 | 北京理工大学 | A kind of disease forecasting method based on automatic extraction Medical Technologist's knowledge |
-
2018
- 2018-12-19 CN CN201811553950.1A patent/CN109817297B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101203170A (en) * | 2005-06-02 | 2008-06-18 | 美的派特恩公司 | System and method of computer-aided detection |
| CN102651055A (en) * | 2012-04-11 | 2012-08-29 | 华中科技大学 | Method and system for generating file based on medical image |
| CN106156530A (en) * | 2016-08-03 | 2016-11-23 | 北京好运到信息科技有限公司 | Health check-up data analysing method based on stack own coding device and device |
| CN106446574A (en) * | 2016-10-10 | 2017-02-22 | 重庆市中迪医疗信息科技股份有限公司 | Image report system |
| CN108198620A (en) * | 2018-01-12 | 2018-06-22 | 洛阳飞来石软件开发有限公司 | A kind of skin disease intelligent auxiliary diagnosis system based on deep learning |
| CN108320781A (en) * | 2018-03-15 | 2018-07-24 | 安徽科大讯飞医疗信息技术有限公司 | A kind of voice-based medical report generation method and device |
| CN109036553A (en) * | 2018-08-01 | 2018-12-18 | 北京理工大学 | A kind of disease forecasting method based on automatic extraction Medical Technologist's knowledge |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109817297A (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shen et al. | Privacy-preserving image retrieval for medical IoT systems: A blockchain-based approach | |
| CN107239666B (en) | Method and system for desensitizing medical image data | |
| CN111316281B (en) | Semantic classification method and system for numerical data in natural language context based on machine learning | |
| CN117238458B (en) | Critical care cross-mechanism collaboration platform system based on cloud computing | |
| US11080423B1 (en) | System for simulating a de-identified healthcare data set and creating simulated personal data while retaining profile of authentic data | |
| CN109817297B (en) | Medical report generation method, device, computer equipment and computer storage medium | |
| CN107273698B (en) | Processing and detecting method and system for artificial intelligence training standard library | |
| CN112015917A (en) | Data processing method and device based on knowledge graph and computer equipment | |
| CN101944154A (en) | The shadow system is read in medical imaging | |
| CN110210234B (en) | Medical information migration method and device during referral, computer equipment and storage medium | |
| US11164309B2 (en) | Image analysis and annotation | |
| JP2022541588A (en) | A deep learning architecture for analyzing unstructured data | |
| CN107451391A (en) | A kind of network medical history information storage circulation method and system | |
| CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
| CN106201857A (en) | The choosing method of test case and device | |
| CN117095799A (en) | Health medical big data sharing system and method | |
| CN113724878B (en) | Medical risk information pushing method and device based on machine learning | |
| Pagad et al. | Clinical text data categorization and feature extraction using medical‐fissure algorithm and neg‐seq algorithm | |
| CA2873819C (en) | Systems and methods for authenticating and aiding in indexing of and searching for electronic files | |
| CN113961609A (en) | Data query method, device, server and storage medium | |
| CN111724873B (en) | Data processing method and device | |
| CN114360671A (en) | Electronic medical record generation method and device, storage medium and electronic device | |
| CN115985506A (en) | Information extraction method and device, storage medium and computer equipment | |
| CN114783557A (en) | Method and device for processing tumor patient data, storage medium and processor | |
| Song et al. | Catching up faster data in digital crime using mobile devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |