CN115662562A - Medical record diagnosis and treatment data management method, device, equipment and storage medium - Google Patents
Medical record diagnosis and treatment data management method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115662562A CN115662562A CN202211394232.0A CN202211394232A CN115662562A CN 115662562 A CN115662562 A CN 115662562A CN 202211394232 A CN202211394232 A CN 202211394232A CN 115662562 A CN115662562 A CN 115662562A
- Authority
- CN
- China
- Prior art keywords
- medical record
- target disease
- patient
- data management
- medical
- 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.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 100
- 238000013523 data management Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 53
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 167
- 201000010099 disease Diseases 0.000 claims abstract description 159
- 208000024891 symptom Diseases 0.000 claims abstract description 61
- 238000012549 training Methods 0.000 claims abstract description 59
- 238000013145 classification model Methods 0.000 claims abstract description 35
- 238000004590 computer program Methods 0.000 claims description 14
- 239000003814 drug Substances 0.000 claims description 11
- 229940079593 drug Drugs 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000036541 health Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 abstract description 12
- 238000010586 diagram Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 206010020772 Hypertension Diseases 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 102100032202 Cornulin Human genes 0.000 description 2
- 101000920981 Homo sapiens Cornulin Proteins 0.000 description 2
- 201000001421 hyperglycemia Diseases 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013518 transcription Methods 0.000 description 2
- 230000035897 transcription Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 208000013016 Hypoglycemia Diseases 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002218 hypoglycaemic effect Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a medical record diagnosis and treatment data management method, device, equipment and storage medium, and belongs to the technical field of data management. According to the method, through acquiring historical patient medical record data uploaded by different network application nodes, diagnosis and treatment data of different regions and different users can be acquired; target disease information in the patient history medical record is extracted through a preset training model and symptom keywords, the preset training model can extract the symptom keywords in the patient history medical record and extract the key information in the patient history medical record, and the interference of redundant information is avoided; then, the target disease information is identified and classified through a preset classification model, and the target disease information can be divided into corresponding disease categories, so that the target disease information is accurately input into the medical record diagnosis and treatment data management system, and diagnosis and treatment data of the medical record diagnosis and treatment data management system are perfected.
Description
Technical Field
The present application relates to the field of data management technologies, and in particular, to a method, an apparatus, a device, and a storage medium for managing medical record diagnosis and treatment data.
Background
The medical record diagnosis and treatment data of the patient have important reference and guidance functions for disease diagnosis and medical research.
However, at present, the medical record diagnosis and treatment data of the patient is lack of unified management, the source and the management of the medical record diagnosis and treatment data of the patient are disordered, for example, the medical record diagnosis and treatment data of the patient may be stored in a patient, a hospital or a local medical service center and other parties, the management means of the medical record diagnosis and treatment data of the parties are different, and the data cannot be shared, so that the medical record diagnosis and treatment data may be easily lost and incomplete.
Therefore, how to achieve consistency of medical record diagnosis and treatment data management becomes a technical problem to be solved urgently at present.
Disclosure of Invention
The application provides a method, a device, equipment and a storage medium for medical record diagnosis and treatment data management, which can realize unified management of medical record diagnosis and treatment data.
In a first aspect, the present application provides a medical record diagnosis and treatment data management method, including the following steps:
acquiring a patient history medical record uploaded by a network application node;
extracting target disease information in the patient history medical record based on a preset training model and a symptom keyword;
classifying and identifying the target disease information based on a preset classification model, and determining a target disease category corresponding to the target disease information;
and inputting the target disease information into the medical record diagnosis and treatment data management system based on the target disease category so as to enrich medical record diagnosis and treatment data of the medical record diagnosis and treatment database.
Further, the network application node comprises a hospital application end, a basic health service center application end and a patient application end.
Further, the target disorder information includes a disorder name, a symptom description, a treatment course, medication information, and a treatment result.
Further, the extracting target disease information in the patient history medical record based on the preset training model and the symptom keyword comprises:
when the patient history medical records uploaded by the network application nodes are received and the patient history medical records correspond to the same patient, combining the patient history medical records belonging to the same patient;
when a plurality of patient history medical records corresponding to the same patient have disease conflict, searching a disease name corresponding to the disease description in the medical record diagnosis and treatment database as a target disease of the patient based on the disease description in the patient history medical records;
combining the unrepeated information in the history medical records of a plurality of patients corresponding to the same patient to obtain combined information, and obtaining the target disease information based on the combined information and the target disease.
Further, the extracting target disease information in the patient history medical record based on the preset training model and the symptom keyword further includes:
extracting text contents in the historical patient medical record based on the preset training model;
and matching corresponding target keywords in the text content based on the symptom keywords to obtain the target disease information.
Further, before acquiring the patient history medical record uploaded by the network application node, the method further includes:
acquiring symptom corpus data;
and pre-training a language model based on the symptom prediction base data to obtain the preset training model.
Further, before acquiring the patient history medical record uploaded by the network application node, the method further includes:
acquiring disease classification data;
training the classification model based on a preset recognition algorithm and the disease classification data to obtain the preset classification model.
In a second aspect, the present application further provides a medical record diagnosis and treatment data management device, where the medical record diagnosis and treatment data management device includes:
the patient history medical record acquisition module is used for acquiring the patient history medical record uploaded by the network application node;
the target disease information extraction module is used for extracting target disease information in the historical patient medical record based on a preset training model and the symptom keywords;
the target disease category determining module is used for classifying and identifying the target disease information based on a preset classification model and determining a target disease category corresponding to the target disease information;
and the target disease information input module is used for inputting the target disease information into the medical record diagnosis and treatment data management system based on the target disease category so as to enrich medical record diagnosis and treatment data of the medical record diagnosis and treatment database.
In a third aspect, the present application further provides a computer device, where the computer device includes a processor, a memory, and a computer program stored on the memory and executable by the processor, where the computer program, when executed by the processor, implements the steps of the medical record medical data management method as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program, when executed by a processor, implements the steps of the medical record diagnosis and treatment data management method as described above.
The application provides a method, a device, equipment and a storage medium for managing medical record diagnosis and treatment data, wherein the method comprises the steps of acquiring a patient history medical record uploaded by a network application node; extracting target disease information in the patient history medical record based on a preset training model and a symptom keyword; classifying and identifying the target disease information based on a preset classification model, and determining a target disease category corresponding to the target disease information; and inputting the target disease information into the medical record diagnosis and treatment data management system based on the target disease category so as to enrich medical record diagnosis and treatment data of the medical record diagnosis and treatment database. According to the method and the system, historical medical record data of the patient uploaded by different network application nodes can be obtained, so that diagnosis and treatment data of different regions and different users can be obtained; target disease information in the patient history medical record is extracted through a preset training model and symptom keywords, the preset training model can extract the symptom keywords in the patient history medical record and extract the key information in the patient history medical record, and the interference of redundant information is avoided; then, the target disease information is identified and classified through a preset classification model, and the target disease information can be divided into corresponding disease categories, so that the target disease information is accurately input into the medical record diagnosis and treatment data management system, and diagnosis and treatment data of the medical record diagnosis and treatment data management system are perfected.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a medical record diagnosis and treatment data management system according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a medical record diagnosis and treatment data management method according to a first embodiment of the present application;
fig. 3 is a schematic flowchart of a medical record diagnosis and treatment data management method according to a second embodiment of the present application;
fig. 4 is a schematic flow chart of a preset training model training method according to an embodiment of the present application;
fig. 5 is a schematic flowchart of a preset classification model training method provided in the embodiment of the present application;
fig. 6 is a schematic block diagram of a medical record diagnosis and treatment data management device provided by an embodiment of the present application;
fig. 7 is a schematic block diagram of a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flowcharts shown in the figures are illustrative only and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
The embodiment of the application provides a medical record diagnosis and treatment data management method, a medical record diagnosis and treatment data management device, a computer device and a storage medium, which are used for acquiring disease information of different user application ends and classifying the disease information so as to perfect diagnosis and treatment data of a medical record diagnosis and treatment data system and realize unified management of the medical record diagnosis and treatment data.
As shown in fig. 1, fig. 1 is a medical record diagnosis and treatment data management system provided by an embodiment of the present application, and the system includes a terminal and a server, where the terminal and the server are in communication connection, and the server is in communication connection with a medical record diagnosis and treatment database.
The terminal comprises electronic equipment such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant and wearable equipment.
The server comprises an independent server or a server cluster.
Hereinafter, a medical record diagnosis and treatment data management method provided by an embodiment of the present application will be described in detail based on the medical record diagnosis and treatment data management system.
Referring to fig. 2, fig. 2 is a flowchart illustrating a medical record diagnosis and treatment data management method according to a first embodiment of the present application. The medical record diagnosis and treatment data management method can be used in a terminal of a medical record diagnosis and treatment data management system.
As shown in fig. 2, the medical record medical data management method includes steps S101 to S104.
S101, acquiring a patient history medical record uploaded by a network application node;
in this embodiment, the user can upload the historical patient medical records by logging in the medical record diagnosis and treatment data management system, and extract the key information in the historical patient medical records by data analysis of the historical patient medical records by the system, so as to complete classification and identification of the historical patient medical records.
In one embodiment, the network application nodes comprise a hospital application, a primary health service center application and a patient application.
In one embodiment, the system may provide corresponding control pages and functions for users according to user identities, such as patients, physician assistants, doctors, or medical researchers, where different user identities have different system permissions.
S102, extracting target disease information in the historical patient medical record based on a preset training model and a symptom keyword;
in this embodiment, the preset training model may match corresponding keywords in the historical patient medical records according to the symptom keywords, and extract the keywords, that is, the target disease information in the historical patient medical records.
In one embodiment, according to medical textbooks, scientific literature, expert prior knowledge and the like, medical academic words or terms and the like can be extracted, and a set of symptom keywords for identifying target disease information is established.
In one embodiment, the target condition information includes condition name, symptom description, treatment course, medication information, and treatment result.
In one embodiment, the disease name is the diagnosis result of a doctor in the history medical record of the patient, and the disease category of the patient can be preliminarily determined; the symptom description is convenient for knowing the symptoms corresponding to the diseases of the patient, is convenient for verifying the names of the symptoms and further limits the category of the symptoms; the treatment process, the medication information and the treatment result can provide treatment reference for medical workers and research reference for medical researchers.
In one embodiment, based on the preset training model, extracting text content in the patient history medical record; and matching corresponding target keywords in the text content based on the symptom keywords to obtain the target disease information.
In an embodiment, a user uploads an electronic medical record of a patient history medical record through a network application node, a preset training model can extract text contents in the electronic medical record, and corresponding keywords are matched in the extracted text contents according to preset symptom keywords, wherein the keywords can be medical special nouns and the like.
In an embodiment, the preset training model may be a text recognition model, for recognizing and extracting text contained in the target region, such as a CRNN text recognition model. CRNN is based on convolutional neural networks for text recognition, including convolutional layers, cyclic layers, and transcription layers. The convolutional layer is composed of CNN, and its role is to extract features from the input image. The extracted feature map is input into the next loop layer, which consists of RNNs, that output a prediction for each frame of the feature sequence. Finally, the transcription layer converts the obtained prediction probability distribution into a marker sequence to obtain a final recognition result, which is actually a loss function in the model. The network consisting of CNN and RNN is trained by minimizing the loss function.
Step S103, classifying and identifying the target disease information based on a preset classification model, and determining a target disease category corresponding to the target disease information;
in this embodiment, the preset classification model may identify the target disorder information according to the symptom keyword extracted from the preset training model, and match the target disorder information according to the preset category to determine the target disorder category of each target disorder information.
In one embodiment, the preset categories may be classified according to existing medical categories, and may be classified in a hierarchical manner, for example, the first-level categories may be classified into a basic medical category, a clinical medical category, an oral medical category, a public health and preventive medical category, a traditional Chinese medical category, and the like; human immunology, medical genetics, medical biology, human anatomy and the like can be further subdivided under the basic medicine category, or image diagnostics, radiology diagnostics, clinical diagnostics, neurology, pediatrics and the like can be subdivided under the clinical medicine category as the second-level category, and by analogy, the classification of medical symptoms is realized.
And step S104, inputting the target disease information into the medical record diagnosis and treatment data management system based on the target disease category so as to enrich medical record diagnosis and treatment data of a medical record diagnosis and treatment database.
In this embodiment, the medical record diagnosis and treatment data management system is configured to store and manage all medical record diagnosis and treatment data, and fill the extracted symptom keywords into corresponding categories after completing classification and identification of medical record of a patient.
In an embodiment, when the target disease information is entered, the disease information corresponding to the same patient may be saved as a medical use case, and the saving format may be a table format or an independent file format. For example, the storage can be performed according to the form of the disease name, symptom description, treatment process, medication information and treatment result.
The embodiment provides a medical record diagnosis and treatment data management method, which can acquire historical medical record data of patients uploaded by different network application nodes, so that diagnosis and treatment data of different regions and different users can be acquired; target disease information in the patient history medical record is extracted through a preset training model and symptom keywords, the preset training model can extract the symptom keywords in the patient history medical record and extract the key information in the patient history medical record, and the interference of redundant information is avoided; then, the target disease information is identified and classified through a preset classification model, and the target disease information can be divided into corresponding disease categories, so that the target disease information is accurately input into the medical record diagnosis and treatment data management system, and diagnosis and treatment data of the medical record diagnosis and treatment data management system are perfected.
Referring to fig. 3, fig. 3 is a flowchart illustrating a medical record diagnosis and treatment data management method according to a second embodiment of the present application.
As shown in fig. 3, based on the embodiment shown in fig. 2, in this embodiment, the step S102 specifically includes:
step S201, when the patient history medical records uploaded by the network application nodes are received and a plurality of patient history medical records corresponding to the same patient exist, combining the patient history medical records belonging to the same patient;
in this embodiment, since the sources of the patient history medical records are various and the patient history medical records are from hospitals, community health service centers and patients themselves, the patient history medical records corresponding to the same patient inevitably appear therein.
In an embodiment, when there are multiple patient history medical histories corresponding to the same patient, the medical condition information corresponding to the same medical condition in the multiple patient history medical histories can be merged, for example, when all of the medical conditions correspond to hypertension, the descriptions of the symptoms of hypertension and the like can be merged together, and one of the medical conditions is repeatedly retained.
In one embodiment, when a plurality of patient historical disease durations corresponding to the same patient exist, if different diseases correspond to a plurality of patient historical cases, whether the different diseases are different can be further determined according to information such as symptom description, and if the different diseases are different, the diseases can be separately recorded.
Step S202, when disease conflicts exist in a plurality of patient history medical records corresponding to the same patient, based on the symptom description in the patient history medical records, searching a disease name corresponding to the symptom description in a medical record diagnosis and treatment database as a target disease of the patient;
in one embodiment, when there is a conflict between medical conditions in a plurality of patient history medical records corresponding to the same patient, such as one patient history medical condition showing hypoglycemia and another patient history medical condition showing hyperglycemia, the diagnosis time of the two is determined first, if the time interval is longer, and the medical condition is changed, the medical condition corresponding to the diagnosis time closest to the current time is the latest medical condition, but other medical conditions can be input as history medical conditions.
In an embodiment, if the diagnosis time of the conflicting disease is short and one of the conflicting diseases has a suspected misdiagnosis, the corresponding information such as symptom description and the like can be searched in the medical record diagnosis and treatment database according to the symptom description, the treatment process, the medication information, the medication reaction and the like of the conflicting disease, the disease name corresponding to the information such as the symptom description and the like in the medical record diagnosis and treatment database is determined and used as the real disease of the patient, and the misdiagnosis information is marked.
Step S203, combining the unrepeated information in the plurality of patient history medical records corresponding to the same patient to obtain combined information, and obtaining the target disease information based on the combined information and the target disease.
In this embodiment, when the same disease of the same patient corresponds to a plurality of patient history medical histories, the disease information in the plurality of patient history medical histories may be merged, and the merged information of the disease may be obtained by deleting the repeated content and supplementing the non-repeated content.
Referring to fig. 4, fig. 4 is a schematic flow chart of a training method for a preset training model according to an embodiment of the present disclosure.
As shown in fig. 4, the preset training model training method includes steps S301 to S302.
Step S301, obtaining symptom corpus data;
and S302, pre-training a language model based on the symptom prediction base data to obtain the preset training model.
In this embodiment, a large-scale text in the medical diagnosis field may be used as the symptom corpus data to perform model learning training on the language model, thereby generating the preset training model.
In one embodiment, the symptom corpus data may be a text data set formed from books, papers, guidelines, etc. in the medical field.
In one embodiment, the learning training of the model refers to a process of estimating model parameters according to a given sample set/corpus database, and through these corpus data, the model can learn a better language representation and can improve the downstream task effect.
In an embodiment, the language pre-training model may include a model that Word2Vec, CBOW, glove, and the like are trained from a non-labeled corpus to obtain Word vectors, or may be a model that an ELMO model and the like can extract context-related Word vectors, or a model that a trimming pre-training model is used to classify texts, such as an ulmmit model and the like.
Referring to fig. 5, fig. 5 is a schematic flow chart of a preset classification model training method according to an embodiment of the present disclosure.
As shown in fig. 5, the method for training the predetermined classification model includes steps S401 to S402.
Step S401, acquiring disease classification data;
step S402, training the classification model based on a preset recognition algorithm and the disease classification data to obtain the preset classification model.
In this embodiment, the disease classification of the small-batch data may be performed manually to obtain disease classification data, and then the disease classification data is used as sample data, the disease information therein is identified by the preset identification algorithm, and the classification model is trained, so as to obtain a preset classification model capable of classifying the disease information.
In one embodiment, the preset classification model may be a multi-label classification model. The multi-label classification model can realize a multi-label classification task, wherein the multi-label classification task refers to that one piece of data has one or more labels, such as a physical examination report of a patient, which can be marked with a plurality of labels, such as hypertension, hyperglycemia and the like. The multi-label classification model can be suitable for the situation that a plurality of diseases exist in one patient.
In an embodiment, the preset classification model may also be a multi-classification model, and the multi-classification model may predict the category to which the target feature belongs by analyzing the features of the disorders, and is suitable for classification prediction between different disorders with similar symptoms.
Referring to fig. 6, fig. 6 is a schematic block diagram of a medical record medical data management apparatus according to an embodiment of the present application, where the medical record medical data management apparatus is configured to execute the medical record medical data management method. The medical record diagnosis and treatment data management device can be configured in a terminal.
As shown in fig. 6, the medical record medical data management apparatus 100 includes: a patient history medical record acquisition module 101, a target disease information extraction module 102, a target disease category determination module 103 and a target disease information entry module 104.
A patient history medical record obtaining module 101, configured to obtain a patient history medical record uploaded by a network application node;
the target disease information extraction module 102 is configured to extract target disease information in the patient history medical record based on a preset training model and a symptom keyword;
the target disease category determining module 103 is configured to classify and identify the target disease information based on a preset classification model, and determine a target disease category corresponding to the target disease information;
and the target disease information entry module 104 is configured to enter the target disease information into the medical record diagnosis and treatment data management system based on the target disease category, so as to enrich medical record diagnosis and treatment data of the medical record diagnosis and treatment database.
In one embodiment, the network application nodes comprise a hospital application, a primary health service center application and a patient application.
In one embodiment, the target condition information includes condition name, symptom description, treatment course, medication information, and treatment result.
In an embodiment, the target medical condition information extraction module 102 is further configured to merge the patient history medical records belonging to the same patient when the patient history medical records uploaded by a plurality of network application nodes are received and a plurality of patient history medical records correspond to the same patient; when a plurality of patient history medical records corresponding to the same patient have disease conflict, searching a disease name corresponding to the disease description in the medical record diagnosis and treatment database as a target disease of the patient based on the disease description in the patient history medical records; combining the unrepeated information in the plurality of patient history medical records corresponding to the same patient to obtain combined information, and obtaining the target disease information based on the combined information and the target disease.
In an embodiment, the target medical condition information extraction module 102 is further configured to extract text content in the patient history medical record based on the preset training model; and matching corresponding target keywords in the text content based on the symptom keywords to obtain the target disease information.
In an embodiment, the medical record diagnosis and treatment data management apparatus 100 further includes a preset training model obtaining module, configured to obtain data of a symptom corpus; and pre-training a language model based on the symptom prediction base data to obtain the preset training model.
In an embodiment, the medical record diagnosis and treatment data management apparatus 100 further includes a preset classification model obtaining module, configured to obtain disease classification data; training the classification model based on a preset recognition algorithm and the disease classification data to obtain the preset classification model.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the apparatus and the modules described above may refer to corresponding processes in the embodiment of the medical record diagnosis and treatment data management method, and are not described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 7.
Referring to fig. 7, fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present disclosure. The computer device may be a terminal.
Referring to fig. 7, the computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any one of the medical record clinical data management methods.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for running a computer program in the nonvolatile storage medium, and the computer program can enable the processor to execute any medical record diagnosis and treatment data management method when being executed by the processor.
The network interface is used for network communication, such as sending assigned tasks and the like. It will be appreciated by those skilled in the art that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
acquiring a patient history medical record uploaded by a network application node;
extracting target disease information in the patient history medical record based on a preset training model and a symptom keyword;
classifying and identifying the target disease information based on a preset classification model, and determining a target disease category corresponding to the target disease information;
and inputting the target disease information into the medical record diagnosis and treatment data management system based on the target disease category so as to enrich medical record diagnosis and treatment data of the medical record diagnosis and treatment database.
In one embodiment, the network application nodes comprise a hospital application, a primary health service center application and a patient application.
In one embodiment, the target condition information includes condition name, symptom description, treatment course, medication information, and treatment result.
In an embodiment, when the processor extracts the target medical condition information in the patient history medical record based on the preset training model and the symptom keyword, the processor is configured to:
when the patient history medical records uploaded by the network application nodes are received and the patient history medical records correspond to the same patient, combining the patient history medical records belonging to the same patient;
when a plurality of patient history medical records corresponding to the same patient have disease conflict, searching a disease name corresponding to the disease description in the medical record diagnosis and treatment database as a target disease of the patient based on the disease description in the patient history medical records;
combining the unrepeated information in the plurality of patient history medical records corresponding to the same patient to obtain combined information, and obtaining the target disease information based on the combined information and the target disease.
In an embodiment, when the processor extracts target medical condition information in the patient history medical record based on the preset training model and the symptom keyword, the processor is further configured to:
extracting text contents in the historical patient medical record based on the preset training model;
and matching corresponding target keywords in the text content based on the symptom keywords to obtain the target disease information.
In an embodiment, before implementing the acquiring of the patient history medical record uploaded by the network application node, the processor is further configured to implement:
acquiring symptom corpus data;
and pre-training a language model based on the symptom prediction base data to obtain the preset training model.
In an embodiment, before implementing the acquiring of the patient history medical record uploaded by the network application node, the processor further includes:
acquiring disease classification data;
training the classification model based on a preset recognition algorithm and the disease classification data to obtain the preset classification model.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A medical record diagnosis and treatment data management method is characterized in that the medical record diagnosis and treatment data management method is applied to a medical record diagnosis and treatment data management system, and the method comprises the following steps:
acquiring a patient history medical record uploaded by a network application node;
extracting target disease information in the patient history medical record based on a preset training model and a symptom keyword;
classifying and identifying the target disease information based on a preset classification model, and determining a target disease category corresponding to the target disease information;
and inputting the target disease information into the medical record diagnosis and treatment data management system based on the target disease category so as to enrich medical record diagnosis and treatment data of the medical record diagnosis and treatment database.
2. The medical record medical data management method according to claim 1, wherein the network application nodes comprise a hospital application, a grass-roots health service center application and a patient application.
3. The medical record diagnosis and treatment data management method according to claim 1, wherein the target disease information includes disease name, symptom description, treatment process, medication information and treatment result.
4. The medical record diagnosis and treatment data management method according to claims 2 and 3, wherein the extracting target disease information in the patient history medical record based on the preset training model and the symptom keyword comprises:
when the patient history medical records uploaded by the network application nodes are received and the patient history medical records correspond to the same patient, combining the patient history medical records belonging to the same patient;
when a plurality of patient history medical records corresponding to the same patient have disease conflict, searching a disease name corresponding to the disease description in the medical record diagnosis and treatment database as a target disease of the patient based on the disease description in the patient history medical records;
combining the unrepeated information in the history medical records of a plurality of patients corresponding to the same patient to obtain combined information, and obtaining the target disease information based on the combined information and the target disease.
5. The medical record diagnosis and treatment data management method according to claim 1, wherein the extracting target disease information in the patient history medical record based on a preset training model and a symptom keyword further comprises:
extracting text contents in the historical patient medical record based on the preset training model;
and matching corresponding target keywords in the text content based on the symptom keywords to obtain the target disease information.
6. The medical record medical data management method according to claim 1, wherein before acquiring the historical medical records of the patient uploaded by the network application node, the method further comprises:
acquiring symptom corpus data;
and pre-training a language model based on the symptom prediction base data to obtain the preset training model.
7. The medical record medical data management method according to claim 1, wherein before acquiring the historical medical records of the patient uploaded by the network application node, the method further comprises:
acquiring disease classification data;
training the classification model based on a preset recognition algorithm and the disease classification data to obtain the preset classification model.
8. The medical record diagnosis and treatment data management device is characterized by comprising the following components:
the patient history medical record acquisition module is used for acquiring the patient history medical record uploaded by the network application node;
the target disease information extraction module is used for extracting target disease information in the historical patient medical record based on a preset training model and the symptom keywords;
the target disease category determining module is used for classifying and identifying the target disease information based on a preset classification model and determining a target disease category corresponding to the target disease information;
and the target disease information input module is used for inputting the target disease information into the medical record diagnosis and treatment data management system based on the target disease category so as to enrich medical record diagnosis and treatment data of the medical record diagnosis and treatment database.
9. A computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, performs the steps of the medical record data management method as recited in any one of claims 1 to 7.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the medical record medical data management method according to any one of claims 1 to 7 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211394232.0A CN115662562A (en) | 2022-11-08 | 2022-11-08 | Medical record diagnosis and treatment data management method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211394232.0A CN115662562A (en) | 2022-11-08 | 2022-11-08 | Medical record diagnosis and treatment data management method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115662562A true CN115662562A (en) | 2023-01-31 |
Family
ID=85016821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211394232.0A Pending CN115662562A (en) | 2022-11-08 | 2022-11-08 | Medical record diagnosis and treatment data management method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115662562A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116646044A (en) * | 2023-05-16 | 2023-08-25 | 上海景栗信息科技有限公司 | Active management method and system for tumor patients based on WeChat ecological cycle |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220918A (en) * | 2017-06-30 | 2017-09-29 | 王中显 | Patient medical history management method, device and server |
| CN110706774A (en) * | 2019-09-29 | 2020-01-17 | 广州达美智能科技有限公司 | Medical record generation method, terminal device and computer readable storage medium |
| CN113345577A (en) * | 2021-06-18 | 2021-09-03 | 北京百度网讯科技有限公司 | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium |
| CN114065756A (en) * | 2021-10-19 | 2022-02-18 | 深圳市联影医疗数据服务有限公司 | Method and device for extracting positive symptoms of electronic medical record |
| CN114117053A (en) * | 2021-12-09 | 2022-03-01 | 深圳云知声信息技术有限公司 | Disease classification model training method and device, storage medium and electronic device |
| CN114708976A (en) * | 2022-03-11 | 2022-07-05 | 中国医学科学院阜外医院深圳医院(深圳市孙逸仙心血管医院) | Method, device, equipment and storage medium for assisting diagnosis technology |
| CN114927179A (en) * | 2021-02-02 | 2022-08-19 | 阿里巴巴集团控股有限公司 | Information and medical diagnosis classification method, computing device and storage medium |
-
2022
- 2022-11-08 CN CN202211394232.0A patent/CN115662562A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220918A (en) * | 2017-06-30 | 2017-09-29 | 王中显 | Patient medical history management method, device and server |
| CN110706774A (en) * | 2019-09-29 | 2020-01-17 | 广州达美智能科技有限公司 | Medical record generation method, terminal device and computer readable storage medium |
| CN114927179A (en) * | 2021-02-02 | 2022-08-19 | 阿里巴巴集团控股有限公司 | Information and medical diagnosis classification method, computing device and storage medium |
| CN113345577A (en) * | 2021-06-18 | 2021-09-03 | 北京百度网讯科技有限公司 | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium |
| CN114065756A (en) * | 2021-10-19 | 2022-02-18 | 深圳市联影医疗数据服务有限公司 | Method and device for extracting positive symptoms of electronic medical record |
| CN114117053A (en) * | 2021-12-09 | 2022-03-01 | 深圳云知声信息技术有限公司 | Disease classification model training method and device, storage medium and electronic device |
| CN114708976A (en) * | 2022-03-11 | 2022-07-05 | 中国医学科学院阜外医院深圳医院(深圳市孙逸仙心血管医院) | Method, device, equipment and storage medium for assisting diagnosis technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116646044A (en) * | 2023-05-16 | 2023-08-25 | 上海景栗信息科技有限公司 | Active management method and system for tumor patients based on WeChat ecological cycle |
| CN116646044B (en) * | 2023-05-16 | 2024-03-26 | 上海景栗信息科技有限公司 | Active management method and system for tumor patients based on WeChat ecological cycle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11810671B2 (en) | System and method for providing health information | |
| US11790171B2 (en) | Computer-implemented natural language understanding of medical reports | |
| CN106682397B (en) | Knowledge-based electronic medical record quality control method | |
| US20200265931A1 (en) | Systems and methods for coding health records using weighted belief networks | |
| US11481411B2 (en) | Systems and methods for automated generation classifiers | |
| US20220044812A1 (en) | Automated generation of structured patient data record | |
| CA3137096A1 (en) | Computer-implemented natural language understanding of medical reports | |
| CN112329964B (en) | Method, device, equipment and storage medium for pushing information | |
| CN108899064A (en) | Electronic health record generation method, device, computer equipment and storage medium | |
| US20180011974A1 (en) | Systems and methods for improved optical character recognition of health records | |
| US20160110502A1 (en) | Human and Machine Assisted Data Curation for Producing High Quality Data Sets from Medical Records | |
| EP3748640A1 (en) | Anonymization of heterogenous clinical reports | |
| WO2021169101A1 (en) | Method and apparatus for generating medical image recognition model, computer device and medium | |
| CN112655047A (en) | Method for classifying medical records | |
| US20230282322A1 (en) | System and method for anonymizing medical records | |
| CN115662562A (en) | Medical record diagnosis and treatment data management method, device, equipment and storage medium | |
| CN113450905A (en) | Medical auxiliary diagnosis system, method and computer readable storage medium | |
| CN113111660A (en) | Data processing method, device, equipment and storage medium | |
| CN116719840A (en) | Medical information pushing method based on post-medical-record structured processing | |
| CN116469526A (en) | Training method, device, equipment and storage medium for traditional Chinese medicine diagnosis model | |
| US20210133627A1 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| Cui et al. | Intelligent recommendation for departments based on medical knowledge graph | |
| CN114676258A (en) | Disease classification intelligent service method based on patient symptom description text | |
| US20230077056A1 (en) | Systems and methods for automated generation of classifiers | |
| CN113343680B (en) | Structured information extraction method based on multi-type medical record text |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230131 |
|
| RJ01 | Rejection of invention patent application after publication |