CN114639456A - Medical evaluation generation method and device, computer equipment and storage medium - Google Patents
Medical evaluation generation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114639456A CN114639456A CN202210253344.8A CN202210253344A CN114639456A CN 114639456 A CN114639456 A CN 114639456A CN 202210253344 A CN202210253344 A CN 202210253344A CN 114639456 A CN114639456 A CN 114639456A
- Authority
- CN
- China
- Prior art keywords
- key information
- evaluation
- medical
- correlation
- report
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 244
- 238000000034 method Methods 0.000 title claims abstract description 69
- 239000003814 drug Substances 0.000 claims abstract description 137
- 229940079593 drug Drugs 0.000 claims abstract description 130
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 claims abstract description 104
- 206010061623 Adverse drug reaction Diseases 0.000 claims abstract description 98
- 238000010219 correlation analysis Methods 0.000 claims abstract description 70
- 238000012098 association analyses Methods 0.000 claims abstract description 38
- 206010067484 Adverse reaction Diseases 0.000 claims description 72
- 230000006838 adverse reaction Effects 0.000 claims description 72
- 230000008569 process Effects 0.000 claims description 25
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000012552 review Methods 0.000 claims description 13
- 230000002411 adverse Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 238000011160 research Methods 0.000 claims description 10
- 238000003745 diagnosis Methods 0.000 claims description 8
- 201000010099 disease Diseases 0.000 claims description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 230000000144 pharmacologic effect Effects 0.000 claims description 3
- 230000001988 toxicity Effects 0.000 claims description 3
- 231100000419 toxicity Toxicity 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 43
- 230000011218 segmentation Effects 0.000 description 22
- 206010047700 Vomiting Diseases 0.000 description 16
- 230000008673 vomiting Effects 0.000 description 16
- 206010012735 Diarrhoea Diseases 0.000 description 13
- 206010028813 Nausea Diseases 0.000 description 11
- 230000008693 nausea Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000002347 injection Methods 0.000 description 10
- 239000007924 injection Substances 0.000 description 10
- 150000001413 amino acids Chemical class 0.000 description 9
- -1 compound amino acid Chemical class 0.000 description 9
- 229940063517 omeprazole sodium Drugs 0.000 description 9
- KNVABRFVZVESIL-UHFFFAOYSA-N sodium;6-methoxy-2-[(4-methoxy-3,5-dimethylpyridin-2-yl)methylsulfinyl]-1h-benzimidazole Chemical compound [Na+].N=1C2=CC(OC)=CC=C2NC=1S(=O)CC1=NC=C(C)C(OC)=C1C KNVABRFVZVESIL-UHFFFAOYSA-N 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 208000024891 symptom Diseases 0.000 description 7
- 206010026673 Malignant Pleural Effusion Diseases 0.000 description 6
- 201000011510 cancer Diseases 0.000 description 6
- 206010006187 Breast cancer Diseases 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 229960003674 tropisetron hydrochloride Drugs 0.000 description 3
- XIEGSJAEZIGKSA-LUNMCBQDSA-N tropisetron hydrochloride Chemical compound Cl.C1=CC=C2C(C(=O)O[C@H]3C[C@H]4CC[C@@H](C3)N4C)=CNC2=C1 XIEGSJAEZIGKSA-LUNMCBQDSA-N 0.000 description 3
- BSYNRYMUTXBXSQ-UHFFFAOYSA-N Aspirin Chemical compound CC(=O)OC1=CC=CC=C1C(O)=O BSYNRYMUTXBXSQ-UHFFFAOYSA-N 0.000 description 2
- 208000026310 Breast neoplasm Diseases 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 2
- 229930182555 Penicillin Natural products 0.000 description 2
- JGSARLDLIJGVTE-MBNYWOFBSA-N Penicillin G Chemical compound N([C@H]1[C@H]2SC([C@@H](N2C1=O)C(O)=O)(C)C)C(=O)CC1=CC=CC=C1 JGSARLDLIJGVTE-MBNYWOFBSA-N 0.000 description 2
- 229960001138 acetylsalicylic acid Drugs 0.000 description 2
- 210000000481 breast Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 230000036210 malignancy Effects 0.000 description 2
- 229940049954 penicillin Drugs 0.000 description 2
- 238000002636 symptomatic treatment Methods 0.000 description 2
- SUBDBMMJDZJVOS-UHFFFAOYSA-N 5-methoxy-2-{[(4-methoxy-3,5-dimethylpyridin-2-yl)methyl]sulfinyl}-1H-benzimidazole Chemical compound N=1C2=CC(OC)=CC=C2NC=1S(=O)CC1=NC=C(C)C(OC)=C1C SUBDBMMJDZJVOS-UHFFFAOYSA-N 0.000 description 1
- 206010027476 Metastases Diseases 0.000 description 1
- 239000002775 capsule Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 238000003255 drug test Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013332 literature search Methods 0.000 description 1
- 210000001165 lymph node Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000009401 metastasis Effects 0.000 description 1
- 229960000381 omeprazole Drugs 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- QYSPLQLAKJAUJT-UHFFFAOYSA-N piroxicam Chemical compound OC=1C2=CC=CC=C2S(=O)(=O)N(C)C=1C(=O)NC1=CC=CC=N1 QYSPLQLAKJAUJT-UHFFFAOYSA-N 0.000 description 1
- 229960002702 piroxicam Drugs 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000002626 targeted therapy Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 210000004916 vomit Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the specification provides a medical evaluation generation method, a medical evaluation generation device, computer equipment and a storage medium. The method comprises the following steps: extracting key information including primary key information and secondary key information in a medical report text aiming at a target drug; performing association analysis on the primary key information and the secondary key information based on the evaluation dimensions to obtain association analysis results between the primary key information and the secondary key information in different evaluation dimensions; generating a correlation evaluation result between the target drug and the adverse drug reaction event based on the correlation analysis result and a preset correlation evaluation rule; and generating a medical evaluation report according to the correlation evaluation result. The medical evaluation report is generated by extracting key information in the medical report text and combining a preset medical evaluation knowledge base and a correlation evaluation rule, so that the quality and the standardization degree of the medical evaluation report are improved.
Description
Technical Field
The embodiment of the specification relates to the field of drug alert, in particular to a method and a device for generating medical examination and comment, a computer device and a storage medium.
Background
Medical evaluation of safety reports of clinical study cases has an important role in risk management of drugs and medication safety of the public. The existing medical examination and evaluation report is mainly manually written by medical examiners based on clinical research individual safety reports and assisted by a mode of referring to related medical documents. However, due to differences in professional levels among different persons, written medical reviews are different and cannot be guaranteed in quality, a large number of medical documents need to be consulted in the writing process, and common knowledge existing among medical reviews of safety reports of different clinical research cases may need to be searched for the same document for many times, so that the efficiency is low.
Disclosure of Invention
In view of the above, embodiments of the present disclosure are directed to a method, an apparatus, a computer device, and a storage medium for generating a medical evaluation, so as to improve the standardization of a medical evaluation report and the work efficiency of a medical evaluation staff.
The embodiment of the specification provides a generation method of medical examination and evaluation, which is applied to a first terminal and comprises the following steps: receiving a medical report text aiming at the target medicine sent by the second terminal; extracting key information in the medical report text; the key information comprises main key information for expressing the adverse drug reaction event and secondary key information for expressing the reason for causing the adverse drug reaction event; wherein the secondary key information corresponds to different evaluation dimensions; performing correlation analysis on the primary key information and the secondary key information based on the evaluation dimensions to obtain correlation analysis results between the primary key information and the secondary key information in different evaluation dimensions; wherein the correlation analysis result comprises the existence of correlation or the nonexistence of correlation; generating a correlation evaluation result between the target drug and the adverse drug reaction event based on the correlation analysis result and a preset correlation evaluation rule; and generating a medical evaluation report according to the correlation evaluation result.
An embodiment of the present specification provides a medical review generation apparatus, which is applied to a first terminal, and includes: the medical report text receiving module is used for receiving a medical report text which is sent by the second terminal and aims at the target medicine; the key information acquisition module is used for extracting key information in the medical report text; the key information comprises main key information for expressing the adverse drug reaction event and secondary key information for expressing the reason for causing the adverse drug reaction event; the secondary key information corresponds to different evaluation dimensions; the association analysis module is used for performing association analysis on the primary key information and the secondary key information based on the evaluation dimensions to obtain association analysis results between the primary key information and the secondary key information in different evaluation dimensions; wherein the correlation analysis result comprises the existence of correlation or the nonexistence of correlation; a correlation evaluation module for generating a correlation evaluation result between the target drug and the adverse drug reaction event based on the correlation analysis result and a preset correlation evaluation rule; and the medical evaluation report generating module is used for generating a medical evaluation report according to the correlation evaluation result.
The embodiment of the specification provides a computer device which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the method of the embodiment when executing the computer program.
The present specification embodiments propose a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the embodiments.
According to the implementation mode of the specification, the key information required for filling the template and analyzing the correlation is extracted from the safety report of the clinical research individual case, and the final medical examination and evaluation report is generated by combining the preset medical examination and evaluation knowledge base and the correlation evaluation rule, so that the automatic filling of the medical examination and evaluation report is realized, and the standardization degree of the medical examination and evaluation report is improved. Relevant documents of the adverse drug reaction events are determined by a keyword search method, and adverse drug reaction reasons corresponding to the adverse drug reaction events in the relevant documents are added into a preset medical examination and evaluation knowledge base, so that the quality and the interpretability of a medical examination and evaluation report are improved, repeated document data can be prevented from being searched, and the working efficiency of medical examiners is improved.
Drawings
FIG. 1 is a diagram illustrating different peer interactions in an example scenario provided by an embodiment.
FIG. 2 is a diagram illustrating different peer interactions in an example scenario provided by an embodiment.
Fig. 3 is a flowchart illustrating a method for generating a medical evaluation report according to an embodiment.
Fig. 4 is a schematic diagram illustrating a correlation evaluation rule according to an embodiment.
Fig. 5 is a schematic diagram of a medical evaluation report generation apparatus according to an embodiment.
FIG. 6 is a diagram illustrating a computer device according to an embodiment.
Detailed Description
In order to make the technical solutions in the present specification better understood, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, but not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art without any inventive work based on the embodiments in the present specification belong to the protection scope of the present specification.
Please refer to fig. 1 and fig. 2. The present specification provides an example scenario of a medical review report generation system, which may include a client and a server. The user may be a medical examiner in the medical field and needs to generate a medical examination report from the information in the safety report of the clinical study case.
The medical examiner first accepts a safety report of a clinical study case of a medical examination report transmitted from the second terminal to the first terminal and inputs a medical examination report template to the first terminal. The medical examination and evaluation template comprises a plurality of slot positions, and each slot position can contain an attribute tag needing to be filled with information. The client then sends a clinical study case security report to the server and requests a return medical review report. After receiving the clinical study case safety report, the server firstly extracts key information including main key information expressing adverse drug reaction events and secondary key information expressing causes of the adverse drug reaction events from the clinical study case safety report according to the attribute information included in the medical evaluation template slot.
After the key information is determined, the server can use the adverse drug reaction description in the key information as the main key information and the cause of the adverse drug reaction as the secondary key information. The server then determines whether the primary key information is related or unrelated to the secondary key information in the medical reports and medical review knowledge base. Wherein the medical examination knowledge base comprises the target drug, the adverse reaction of the target drug and the reason of the adverse reaction of the target drug. In the process of determining the relevance between the primary key information and the secondary key information by using the medical examination and evaluation knowledge base, the server can input the secondary key information and the adverse reaction reasons into the similarity calculation model to calculate the similarity between the secondary key information and the adverse reaction reasons. Then, the server sets the correlation analysis result of the secondary key information and the primary key information corresponding to the adverse reaction reasons of which the maximum value is greater than or equal to a preset threshold in the similarity to be related. And the server may set the association analysis result of the primary key information and the secondary key information having the maximum value smaller than the preset threshold value among the similarities to be irrelevant.
After the correlation analysis results of the primary key information and the secondary key information with different dimensions are obtained, the server can take the correlation analysis results and corresponding correlation degree data in preset correlation evaluation as correlation evaluation results between the target drug and the adverse drug reactions. Then, the server may fill the key information, the correlation analysis result of the primary key information and the secondary key information, and the correlation evaluation result into the corresponding event summary template, the correlation evaluation template, and the evaluation conclusion template according to the attribute tags corresponding to the key information to obtain the adverse drug reaction event summary report, the correlation evaluation report, and the evaluation conclusion report, thereby generating a medical evaluation report including the adverse drug reaction event summary report, the correlation evaluation report, and the evaluation conclusion report. Finally, the server will return a medical review report to the client. And the client displays the medical evaluation report to medical evaluation personnel through the display after receiving the medical evaluation report. Certainly, under the condition that the medical examination and evaluation report extraction system is installed in the client and the corresponding medical examination and evaluation knowledge base is downloaded, the medical examination and evaluation report can be directly generated in the client and presented to medical examination and evaluation personnel through the display. The medical examiner checks the automatically generated medical examination report and then sends the report to the sponsor of the target drug as the material for applying for drug marketing.
The above description is provided as an illustration of exemplary embodiments of the present invention and should not be construed as limiting the present invention, and any modifications, equivalents and the like which fall within the spirit and scope of the present invention should be construed as being included therein.
The embodiment of the specification provides a medical examination report generation system. The medical examination and evaluation report generation system can report a client and a server. The client may be an electronic device with network access capabilities. Specifically, for example, the client may be a desktop computer, a tablet computer, a notebook computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, a smart speaker, a microphone, and the like. Wherein, wearable equipment of intelligence includes but not limited to intelligent bracelet, intelligent wrist-watch, intelligent glasses, intelligent helmet, intelligent necklace etc.. Alternatively, the client may be software capable of running in the electronic device. The server may be an electronic device having a certain arithmetic processing capability. Which may have a network communication module, a processor, memory, etc. Of course, the server may also refer to software running in the electronic device. The server may also be a distributed server, which may be a system with multiple processors, memory, network communication modules, etc. operating in coordination. Alternatively, the server may also be a server cluster formed by several servers. Or, with the development of scientific technology, the server can also be a new technical means capable of realizing the corresponding functions of the specification implementation mode. For example, it may be a new form of "server" implemented based on quantum computing.
Please refer to fig. 3. The embodiment of the specification provides a medical examination report generation method which is applied to a first terminal and comprises the following steps.
Step S110: and receiving the medical report text aiming at the target medicine sent by the second terminal.
In some embodiments, to ensure the safety of the medical report text, the medical report text for the target drug is sent to the medical assessor by a medical worker who is conducting a clinical study of the target drug at a research facility. Therefore, the medical examiner needs to acquire the text of the medical report sent by the second terminal before writing the medical examination report.
The first terminal is terminal equipment used by a medical examiner. The first terminal can be a desktop computer, a tablet computer, a notebook computer, a smart phone, a digital assistant, a smart wearable device and the like, and is used for receiving and processing a medical report text for a target drug sent by the second terminal and generating a medical evaluation report. Wherein the medical examiner may be a project manager, a drug-alert specialist, a drug-alert medical specialist/manager/chief or the like in charge of the target drug.
The second terminal is a terminal device used by medical workers in clinical tests and can be used for sending a subject safety report including a diagnosis process, a treatment process and a treatment result participating in a target drug test to the first terminal. The second terminal can be a desktop computer, a tablet computer, a notebook computer, a smart phone, a digital assistant, a smart wearable device and the like.
Step S120: extracting key information in the medical report text; the key information comprises main key information for expressing the adverse drug reaction event and secondary key information for expressing the reason for causing the adverse drug reaction event; wherein the secondary key information corresponds to different evaluation dimensions.
The medical report text includes medical type data and non-medical type data, and is various and long in sentences. If all data in the medical report text are directly matched with the content required to be filled in the medical examination and evaluation template slot position, the calculation amount is large, and a large amount of time is consumed. Therefore, the key information in the medical report text can be determined, and then the key information is matched with the content required to be filled in the medical examination and evaluation template slot.
The medical report text is a safety report of a research case in the field of clinical trials. In particular, for example, in a pharmaceutical clinical study event, the study case safety report may include a patient's diagnostic procedure, a patient's therapeutic procedure, and a patient's therapeutic outcome. Of course, the study case safety report may also include the patient's past medical history, complications, and the like.
The key information comprises information required to be filled in the medical evaluation template. In the primary key information extraction process, if the information to be filled in the medical examination template includes diagnosis information of a patient, treatment process information of the patient, adverse reaction event description appearing in the patient and the like, corresponding information needs to be extracted in a medical report text to serve as key information, the key information which expresses the adverse drug reaction event in the key information serves as main key information, and the key information which expresses the cause of the adverse drug reaction event serves as secondary key information. Specifically, for example, the key information extracted from the medical report text includes: the malignant tumor of the breast, the malignant pleural effusion, the lung-stimulated malignant tumor, the pirocini, the nausea, the vomit and the diarrhea can be used as main key information, and the malignant tumor of the breast, the malignant pleural effusion and the lung-stimulated malignant tumor can be used as secondary key information.
The main key information is adverse drug reaction event description. Specifically, for example, in the medical report text, "the patient is admitted to a hospital and diagnosed with malignant breast tumor accompanied by malignant pleural effusion, and symptoms of vomiting and diarrhea appear after treatment with pirocini", so that the main key information in this sentence is "vomiting" and "diarrhea".
The secondary key information is the cause of adverse drug reactions. Specifically, for example, in the medical report text, "the patient is admitted to a hospital and diagnosed with malignant pleural effusion accompanied by malignant pleural effusion, and symptoms of vomiting and diarrhea are observed after treatment with pirocini", and the secondary key information in this sentence is "malignant pleural effusion" or "pirocini".
The evaluation dimension is used to determine whether there is a correlation between the drug and the adverse drug reaction event. Specifically, for example, in the dimension of the association between the combined medication and the adverse reaction, the main key information is "diarrhea", the secondary key information is "aspirin" and "penicillin", and the analysis shows that the "diarrhea" is associated with the aspirin and not associated with the "penicillin", so that the association between the combined medication and the adverse reaction is present in the dimension of the association between the combined medication and the adverse reaction.
The method for extracting the key information in the medical report text can be that the medical report text is firstly subjected to word segmentation processing to obtain word segmentation results and corresponding parts of speech of the medical report text. And extracting word segmentation results of the medical report text as key information according to the part of speech and contents required to be filled in the medical examination template, wherein each key information comprises an attribute label corresponding to the contents required to be filled in the medical report text. Of course, corresponding contents can also be extracted from the medical report text according to the sequence of the contents required to be filled in the medical evaluation template and filled in the slot position of the medical evaluation template.
Step S130: performing correlation analysis on the primary key information and the secondary key information based on the evaluation dimensions to obtain correlation analysis results between the primary key information and the secondary key information in different evaluation dimensions; wherein the correlation analysis result comprises the existence of correlation or the nonexistence of correlation.
In order to obtain the correlation analysis result between the target drug and the adverse drug reaction, the correlation between the adverse drug reaction event and the cause of the adverse drug reaction event needs to be analyzed. Accordingly, a correlation analysis between the primary key information and the secondary key information may be performed.
The obtained correlation analysis results between the primary key information and the secondary key information in different evaluation dimensions can be combined with the context of the primary key information and the secondary key information in the medical evaluation report to determine the correlation analysis results of the primary key information and the secondary key information in different evaluation dimensions. Of course, the association analysis result between the primary key information and the secondary key information, which have a corresponding relationship in the preset medical examination and evaluation knowledge base, may also be set as the existence association. Specifically, for example, in the medical report text, the target drug pirocini 480mg bid is regularly taken from 2021-03-16 on the day of the subject entering the group, and nausea, vomiting and diarrhea occur for a plurality of times during the target drug taking period, so that the patients can recover after symptomatic treatment. And the correlation analysis result between the last medication time and the adverse drug reaction shows that the correlation exists. As another example, in the medical report text, "post-hospitalization administration of omeprazole sodium for injection, compound amino acid (18AA) injection solution for symptomatic support treatment". Searching adverse reaction event reasons corresponding to adverse reaction event reports such as nausea, vomiting and diarrhea in a medical evaluation knowledge base, wherein the adverse reaction event reason is 'vomiting' in 'omeprazole sodium'; the "compound amino acid (18AA) injection" was not responsible for these three adverse events. Then, the correlation analysis result between the omeprazole sodium and the adverse reaction event is related, and the correlation analysis result between the compound amino acid (18AA) injection and the adverse reaction event is not related.
Step S140: and generating a correlation evaluation result between the target drug and the adverse drug reaction event based on the correlation analysis result and a preset correlation evaluation rule.
There is a need in medical evaluation reports to generate a correlation assessment between the target drug and the adverse drug reaction event. Therefore, in the case that the preset correlation evaluation rule is the same as the correlation analysis result in different dimensions, the corresponding correlation degree data in the correlation evaluation can be used as the correlation evaluation result between the target drug and the adverse drug reaction event.
Please refer to fig. 4. The relevance evaluation rule is to determine the degree of correlation between the target drug and the adverse drug reaction event. Specifically, for example, in the case where the last medication time is related to an adverse drug reaction event, the adverse reaction event is an adverse reaction event for which the target drug is known, the adverse reaction event does not occur after the study medication is stopped, and the adverse reaction event occurs after the study medication is taken again in the correlation evaluation rule, the correlation evaluation result between the target drug and the adverse drug reaction event is positively correlated.
The correlation evaluation result is used for evaluating the degree of correlation between the target drug and the adverse drug reaction event. Specifically, for example, in the correlation analysis result between the primary key information and the secondary key information of different dimensions, the last medication time is related to the adverse drug reaction event, the adverse reaction event is a known adverse reaction event of the target drug, the adverse reaction event does not occur after the study medication is stopped, and the adverse reaction event occurs after the study medication is taken again, so that the correlation evaluation result between the target drug and the adverse drug reaction event is positively related according to the correlation evaluation rule.
Step S150: and generating a medical evaluation report according to the correlation evaluation result.
There is a need in medical evaluation reports to determine the correlation between a drug of interest and an adverse drug reaction event. Therefore, the key information and the correlation evaluation template can be filled into the slots of the evaluation conclusion templates in the corresponding medical evaluation templates based on the corresponding attributes in the slots of the medical evaluation templates, so that the medical evaluation report comprising the evaluation conclusion report can be obtained.
In some embodiments, the step of extracting the key information in the medical report text may include: acquiring a preset medical examination and evaluation template; wherein the medical examination and evaluation template comprises a plurality of slot positions; wherein, the slot position comprises the attribute of the information to be filled; and extracting information corresponding to the attributes from the medical report text as key information.
The correct extraction of the key information in the medical report text can shorten the running time of a computer, thereby improving the efficiency, and can improve the accuracy of filling the key information into the corresponding medical evaluation template slot. Therefore, key information can be extracted from the medical report text by adopting a method of named entity identification and/or short text classification according to the attributes corresponding to the slots of the medical evaluation template.
The named entity is identified as searching the information of the attribute in the medical report text according to the attribute corresponding to the medical examination and evaluation template slot. Specifically, for example, the medical review template includes "age," sex, "ethnic group," and "subject" in the example. "then, the medical report text can be searched for information corresponding to the attributes" 54 "," women "and" Han nationality ", respectively, according to the three attributes" age "," gender "and" ethnicity ".
In some embodiments, the step of extracting the key information in the medical report text may include: performing word segmentation processing on the medical report text to obtain word segmentation results of the medical report text and part of speech of the word segmentation results; and extracting information required to be filled in by the medical evaluation template from the word segmentation result according to the part of speech to be used as key information.
In some cases, the medical report text can be subjected to word segmentation processing firstly, so that word segmentation results and parts of speech are obtained, then the word segmentation results are extracted according to the parts of speech and contents required to be filled in by the medical evaluation template, and the accuracy of extracting the key information can be improved to a certain extent.
The word segmentation processing method can be used for performing maximum matching on the medical report text in the medical dictionary to obtain a medical word segmentation result and a corresponding part of speech. Then, the content which is not matched in the medical dictionary in the medical report text can be input into a general word segmentation tool to obtain the word segmentation result and the corresponding part of speech of the non-medical word. For example, the content in the medical report text that is not matched in the medical dictionary may be input into the ending segmentation tool to obtain the segmentation result of the non-medical word and the corresponding part-of-speech information. Finally, the medical word segmentation result, the corresponding part-of-speech and non-medical word segmentation result and the corresponding part-of-speech can be used as the result of the medical report text after word segmentation processing.
The part of speech of the word segmentation result is a part of speech which is defined in a medical dictionary or a general word segmentation tool in advance. Specifically, for example, if "vomiting" corresponds to a part of speech in the medical dictionary as "symptom", the word "symptom" is used as the part of speech of the word "vomiting". For another example, if the part of speech of "breast malignancy" in the medical dictionary is "disease name", the "disease name" is defined as the part of speech of "breast malignancy". For another example, if the result of the non-medical word "2019-10-02" predicted by the segmentation tool is "date", the "date" is used as the part of speech of "2019-10-02".
The medical examination and evaluation template comprises slot position information used for filling in key information, and each slot position is provided with an attribute label needing to fill in the key information. Specifically, for example, the medical assessment template has the statement "subject adverse event [ SAE name ] from last dosing date [ last dosing date ] [ presence/absence ] reasonable temporal correlation". Wherein, ' [ ] is a slot position of the medical evaluation template, ' SAE name ', ' last medication date ', ' presence/absence ' and attribute information corresponding to the key information needs to be filled in each slot position.
In some embodiments, the step of extracting the key information in the medical report text may further include: adding attribute tags to the key information; the attribute labels correspond to attributes of information to be filled in the medical examination and evaluation template slot positions; correspondingly, the step of generating a medical evaluation report according to the correlation evaluation result may include: filling the key information and the correlation evaluation result into a correlation evaluation template according to the attribute tag to obtain an evaluation conclusion report; and generating a medical evaluation report according to the evaluation conclusion report.
In some cases, different pieces of key information in the medical report text correspond to the same part of speech, and when the key information is filled into the corresponding slots of the medical examination and evaluation template, the corresponding key information needs to be filled according to the attribute of each slot. Therefore, the key information with the attribute labels identical to the attribute labels defined in the medical examination and evaluation template slot can be filled into the medical examination and evaluation template slot for drinking by adding the corresponding attribute labels to the key information.
The method for adding the attribute tags to the key information can be filled according to the context in the medical report text. Specifically, for example, the medical report text includes a phrase "the subject suffers from nausea again at level 2 and vomiting at level 2 in 2021-05-29, and takes tropisetron hydrochloride tablet 5mg every day in 2021-05-29" so far, the key information of "taking tropisetron hydrochloride tablet orally" corresponds to an attribute label of "medication combination", and the attribute labels of "nausea" and "vomiting" correspond to two key information of "adverse drug reaction".
In some embodiments, after the step of extracting the key information in the medical report text for the target drug, the method may further include: acquiring clinical research process information of the medical report text; wherein the clinical study procedure information includes at least one of: diagnosis process information of the patient, treatment process information of the patient, and treatment effect analysis process information of the patient; filling key information corresponding to the clinical research process information into an event summary template to obtain an adverse drug reaction event summary report; correspondingly, the step of generating a medical evaluation report according to the correlation evaluation result may include: and generating a medical evaluation report according to the adverse drug reaction event summary report and the evaluation conclusion report.
In some cases, the medical review report template needs to be filled with information on the entire development process of the clinical trial of the drug as an adverse drug reaction event summary. Therefore, the adverse drug reaction event summary can be obtained by acquiring the clinical study process information of the medical report text to fill in the corresponding event summary template.
The clinical research process information for acquiring the medical report text is information such as diagnosis process information of the patient, treatment effect of the patient and the like acquired in the medical report text. Specifically, for example, the medical report text includes "subjects JIYA, women, 52 years old, han nationality, left breast cancer after surgery for more than 2 years, multiple metastasis for more than 1 year, admission diagnosis: malignant tumor targeted therapy, breast malignant tumor and malignant tumor secondary to lymph node, and the related content of the hospitalization diagnosis in the medical report text can be used as the diagnosis process of the patient.
In some embodiments, the method for generating a medical review report may further comprise: filling the primary key information, the secondary key information and the correlation analysis result between the primary key information and the secondary key information into a correlation analysis template to obtain a correlation analysis report; correspondingly, the step of generating a medical evaluation report according to the correlation evaluation result may include: and generating a medical evaluation report according to the adverse reaction event summary report, the correlation analysis report and the evaluation conclusion report.
In some cases, there is also a need to correlate adverse drug reactions with the cause of adverse drug reactions in medical evaluation reports. Therefore, the correlation between the target drug and the adverse drug reaction can be determined according to the result of the correlation evaluation and the evaluation conclusion template in the medical evaluation template.
The relevance analysis report comprises relevance analysis results of a plurality of dimensions. Specifically, for example, a correlation analysis report template with three dimensions, i.e., a correlation analysis of the last study medication time with an adverse reaction event, a correlation analysis of an adverse reaction event with an adverse reaction event known for the study medication, and a correlation analysis of an adverse reaction event after the patient stops using the study medication, is included in the correlation analysis template. After determining that there is a correlation between the adverse reaction event and the known adverse reaction event for the study medication and the adverse reaction event after the patient stops using the study medication, the correlation analysis report may be: reasonable time correlation exists between the medication time of the last study and adverse reaction events; the adverse event is a known adverse event; adverse events did not occur after patients stopped using study medication.
The method for generating the evaluation result report based on the correlation evaluation result and the evaluation conclusion template can be determined according to the correlation analysis results of different evaluation dimensions. Specifically, for example, if a ADR event is associated with the time of last dose, then the target drug is associated with the ADR event. For another example, in the case that the adverse drug reaction event is not an adverse drug reaction event known in the study medication, the adverse drug reaction event still exists after the study medication is stopped, and the adverse drug reaction event disappears after the study medication is reused, the adverse drug reaction event is related to the combined medication, and the target drug is unrelated to the adverse drug reaction event.
In some embodiments, the evaluation dimension includes at least one of: correlation analysis of the last study medication time and adverse reaction events; alternatively, analysis of the association of adverse events with known adverse events for study medication; alternatively, the patient stopped taking study medication and correlated analysis of adverse events; or, the patient stops using the study medication and then uses the study medication again to perform correlation analysis with adverse reaction events; alternatively, the patient uses other drugs during study medication with correlation analysis of adverse reaction events; or, correlating a drug with the same pharmacological toxicity as the target drug with an adverse reaction event; or, the patient's prior/combined medical history and association analysis of adverse events; alternatively, the patient is analyzed for a correlation between complications of the disease and adverse events.
When performing correlation analysis on the adverse drug reaction event and the cause of the adverse drug reaction event, analysis can be performed based on different evaluation dimensions. Thus, the relevance in a number of different evaluation dimensions can be used to determine whether a target drug is responsible for the adverse drug reaction event. Specifically, for example, by analyzing the correlation between the last medication time of a patient and the adverse reaction event in this dimension, the evaluation of the correlation between the target drug and the adverse drug reaction can be obtained.
In some embodiments, the dimension of the association analysis includes a plurality of dimensions, and the step of performing the association analysis on the primary key information and the secondary key information based on the evaluation dimension to obtain the result of the association analysis between the primary key information and the secondary key information in different evaluation dimensions may include: acquiring correlation analysis results of the primary key information and the secondary key information in different evaluation dimensions; taking the correlation analysis result and corresponding correlation degree data in a preset correlation evaluation rule as a correlation evaluation result of the target drug and the adverse drug reaction event; the relevance evaluation rule comprises relevance analysis results on different evaluation dimensions and corresponding relevance degree data.
The results of the correlation analysis between the target drug and the adverse drug reaction event need to be filled in the medical evaluation report template. Since different target drugs correspond to different correlation evaluation rules, the correlation evaluation rules need to be configured in advance before evaluating the correlation between the target drug and the adverse drug reaction event. Then, a correlation evaluation result between the target drug and the adverse drug reaction can be generated according to the correlation evaluation rule and the correlation analysis result of the primary key information and the secondary key information.
The analysis of the relevance of the primary key to the secondary key information in the different evaluation dimensions may include: the analysis of the correlation between the last study medication time and the adverse reaction event, the analysis of the correlation between the adverse reaction event and the adverse reaction event known for the study medication, the analysis of the correlation between the patient stopping using the study medication and the adverse reaction event, the analysis of the correlation between the patient using other drugs during using the study medication and the adverse reaction event, the analysis of the correlation between the drug with the same pharmacological toxicity as the target drug and the adverse reaction event, the analysis of the correlation between the patient's past/combined medical history and the adverse reaction event and the analysis of the correlation between the patient's complications of the disease and the adverse reaction event. Specifically, for example, the time of the last medication of the patient and the time of the adverse reaction event are 35 days, which is greater than the set date range by 30 days, so that there is no reasonable time correlation between the medication time of the last study and the adverse reaction event.
According to the method for generating the correlation evaluation result between the target drug and the adverse drug reaction event, under the condition that the correlation analysis result based on the primary key information and the secondary key information on different dimensions is the same as the correlation on different dimensions defined in the correlation evaluation rule, the corresponding correlation degree data in the correlation evaluation rule can be used as the correlation evaluation result between the target drug and the adverse drug reaction event. Of course, the correlation evaluation result of the primary key information and the secondary key information may also be determined by the cumulative sum of the correlations in the correlation analysis results of the primary key information and the secondary key information in different dimensions and a preset threshold range.
In some embodiments, the step of performing association analysis on the primary key information and the secondary key information based on the evaluation dimension to obtain association analysis results between the primary key information and the secondary key information in different evaluation dimensions may include: and determining the correlation analysis result of the primary key information and the secondary key information according to the context of the primary key information and the secondary key information in the medical report text.
In some cases, the result of the association analysis between the primary key information and the secondary key information may be obtained by analyzing the medical report text. Thus, it can be derived by analyzing the context of the primary and secondary key information in the medical report text. Specifically, for example, in the medical report text, there are included: "Subjects are on the day 2021-03-16 and begin to regularly take the object medicine piroxicam 480mg bid to date, nausea, emesis and diarrhea appear many times during taking the object medicine, and recovery is carried out after symptomatic treatment. The subjects had nausea grade 2 and vomiting grade 2 again in 2021-05-29, had oral tropisetron hydrochloride tablet 5mg daily in 2021-05-29 and oral omeprazole enteric capsule 20mg daily in 2021-06-01, and had no relief of symptoms. "indicates that the correlation analysis between the time to adverse drug reaction and the re-excitation is related.
In some embodiments, the step of performing association analysis on the primary key information and the secondary key information based on the evaluation dimension to obtain association analysis results between the primary key information and the secondary key information in different evaluation dimensions may further include: determining adverse drug reaction event descriptions corresponding to the main key information in a preset medical examination and evaluation knowledge base as the target adverse drug reaction event descriptions; wherein the medical examination and evaluation knowledge base comprises target drugs, adverse reaction events of the target drugs and reasons of the adverse reaction events of the target drugs; calculating the similarity between the cause of the adverse drug reaction event corresponding to the description of the target adverse drug reaction event in the medical examination and evaluation knowledge base and the secondary key information; and setting the association analysis result between the secondary key information and the primary key information as the existence of association relation under the condition that the maximum value in the similarity is greater than or equal to a preset threshold value. And setting the association analysis result between the secondary key information and the primary key information as no association relation when the maximum value in the similarity is smaller than a preset threshold value.
In some embodiments, the results of the association analysis between the primary key information and the secondary key information are not derived from the analysis of the medical report text. Therefore, correlation analysis by using the knowledge base of medical examination and evaluation is required. Of course, there may be a slight difference in description between the primary and secondary key information in the medical report text, but the meaning of the expression is the same. Therefore, the similarity between the secondary key information and the adverse reaction reasons in the medical examination and evaluation knowledge base can be larger than a preset threshold value, and the relevance between the primary key information and the secondary key information can be set to be relevant.
The medical evaluation knowledge base comprises target drugs, adverse drug reactions description and adverse drug reactions reasons. Specifically, for example, the target drug "pirocini" has a corresponding adverse reaction description; adverse reaction description there are also adverse reaction causes corresponding to it. Specifically, for example, in the medical report text, the target drug pirocini 480mg bid is regularly taken by the subjects on the day 2021-03-16 of group entry, nausea, vomiting and diarrhea occur repeatedly during the target drug taking, and the omeprazole sodium and compound amino acid (18AA) injection for symptom support treatment are given after the hospitalization period. Then, the method for determining the relevance between the major key information and the minor key information in the medical evaluation knowledge base may be to use "nausea", "vomiting" and "diarrhea" as the major key information, use "omeprazole sodium" and "compound amino acid (18AA) injection" as the minor key information, calculate that the maximum similarity between "omeprazole sodium" and the cause of the adverse reaction of the drug in the medical evaluation knowledge base is 100%, and is greater than the preset threshold value of 80%, and then use "omeprazole sodium" as the combined drug to be relevant to the relevance between the adverse reaction.
In some cases, the association between the primary key information and the secondary key information is irrelevant. Therefore, the correlation analysis result between the secondary key information and the primary key information with the maximum adverse reaction similarity value smaller than the preset threshold value in the medical evaluation knowledge base can be set to be irrelevant. Specifically, for example, in the medical report text, the target drug pirocini 480mg bid is regularly taken by the subjects on the day 2021-03-16 of group entry, nausea, vomiting and diarrhea occur repeatedly during the target drug taking, and the omeprazole sodium and compound amino acid (18AA) injection for symptom support treatment are given after the hospitalization period. Then, the method for determining the relevance between the major key information and the minor key information in the medical evaluation knowledge map may be to use nausea, vomiting and diarrhea as major key information, and use omeprazole sodium and compound amino acid (18AA) injection as minor key information, and calculate that the maximum similarity between the compound amino acid (18AA) injection and the adverse drug reaction causes in the medical evaluation knowledge base is 50% and is less than the preset threshold value of 80%, and then use the compound amino acid (18AA) injection as a combined drug and make the relevance between the combined drug and the adverse reaction irrelevant.
In some embodiments, the performing the association analysis on the primary key information and the secondary key information to obtain the association analysis result between the primary key information and the secondary key information may further include: and constructing a medical evaluation knowledge base comprising the target drug, the adverse reaction event of the target drug and the reason of the adverse reaction event of the target drug. Of course, the medical evaluation knowledge map can also be constructed according to the target drug, the adverse reaction event of the target drug and the reason of the adverse reaction event of the drug.
The deficiency that only facts are stated in a medical report text but the correlation between the adverse drug reaction event and the cause of the adverse drug reaction event is not analyzed can be made up by constructing a medical examination knowledge base. And because workers in the medical field are writing medical report texts, the correlation between the adverse drug reaction event and the described cause of the adverse drug reaction event cannot be completely determined due to the limited knowledge level of the workers. By constructing the medical evaluation knowledge base, the target drug, the adverse reaction event description of the target drug and the adverse reaction event reason of the target drug are brought into the medical evaluation knowledge base, so that the accuracy of the relevance evaluation between the primary key information and the secondary key information in the medical evaluation report is improved, and the relevance evaluation result of the target drug and the adverse reaction of the target drug can be further influenced.
In some embodiments, the performing the association analysis on the primary key information and the secondary key information to obtain the result of the association analysis between the primary key information and the secondary key information may further include: searching a medical literature base for relevant literature related to the adverse drug reaction event; determining the adverse drug reaction event and the cause corresponding to the adverse drug reaction event in the relevant literature; and storing the reason corresponding to the adverse drug reaction event into a medical examination knowledge base corresponding to the adverse drug reaction event as the reason of the adverse drug reaction event.
As clinical trials of drugs proceed, the number of adverse drug reaction event reports may increase, and the unknown adverse reaction events for many target drugs may become known adverse reaction events. Therefore, adverse reactions occurring in the target drug can be updated to the medical evaluation knowledge base by a literature search method, so that the accuracy of the relevance evaluation between the primary key information and the secondary key information in the medical evaluation report is further improved.
Please refer to fig. 5. In some embodiments, a medical review report generation apparatus may be provided, which may include: the system comprises a medical report text receiving module, a key information acquisition module, an association analysis module, a correlation evaluation module and a medical examination report generating module.
The key information acquisition module is used for extracting key information in the medical report text; the key information comprises main key information for expressing the adverse drug reaction event and secondary key information for expressing the reason for causing the adverse drug reaction event; wherein the secondary key information corresponds to different evaluation dimensions;
the association analysis module is used for performing association analysis on the primary key information and the secondary key information based on the evaluation dimensions to obtain association analysis results between the primary key information and the secondary key information in different evaluation dimensions; wherein the correlation analysis result comprises the existence of correlation or the nonexistence of correlation;
a correlation evaluation module for generating a correlation evaluation result between the target drug and the adverse drug reaction event based on the correlation analysis result and a preset correlation evaluation rule;
and the medical evaluation report generating module is used for generating a medical evaluation report according to the correlation evaluation result.
The specific functions and effects achieved by the medical examination report generation device can be contrasted and explained with reference to other embodiments in the present specification, and are not repeated herein. The various modules in the medical examination report generation device may be implemented in whole or in part by software, hardware, and combinations thereof. The modules may be embedded in hardware or independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor calls and executes operations corresponding to the modules.
Referring to fig. 6, in some embodiments, a computer device may be provided, which includes a memory and a processor, the memory storing a computer program, and the processor implementing the method steps in the embodiments when executing the computer program.
In some embodiments, a computer-readable storage medium may be provided, on which a computer program is stored, which, when being executed by a processor, carries out the method steps of the embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include processes of the embodiments of the methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The description is made in a progressive manner among the embodiments of the present specification. The different embodiments focus on the different parts described compared to the other embodiments. After reading this specification, one skilled in the art can appreciate that many embodiments and many features disclosed in the embodiments can be combined in many different ways, and for the sake of brevity, all possible combinations of features in the embodiments are not described. However, as long as there is no contradiction between combinations of these technical features, the scope of the present specification should be considered as being described.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, the embodiments are mainly intended to emphasize different portions from other embodiments, and the embodiments can be explained with reference to each other. Any combination of the embodiments in this specification based on general technical common knowledge by those skilled in the art is encompassed in the disclosure of the specification.
The above description is only an embodiment of the present disclosure, and is not intended to limit the scope of the claims of the present disclosure. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the claims of the present disclosure.
Claims (13)
1. A generation method of medical examination and comment is applied to a first terminal and is characterized by comprising the following steps:
receiving a medical report text aiming at the target medicine sent by the second terminal;
extracting key information in the medical report text; the key information comprises main key information for expressing the adverse drug reaction event and secondary key information for expressing the reason for causing the adverse drug reaction event; wherein the secondary key information corresponds to different evaluation dimensions;
performing correlation analysis on the primary key information and the secondary key information based on the evaluation dimensions to obtain correlation analysis results between the primary key information and the secondary key information in different evaluation dimensions; wherein the correlation analysis result comprises the existence of correlation or the nonexistence of correlation;
generating a correlation evaluation result between the target drug and the adverse drug reaction event based on the correlation analysis result and a preset correlation evaluation rule;
and generating a medical evaluation report according to the correlation evaluation result.
2. The method of claim 1, wherein the step of extracting key information from the medical report text comprises:
acquiring a preset medical examination and evaluation template; wherein the medical examination and evaluation template comprises a plurality of slot positions; wherein, the slot position comprises the attribute of the information to be filled;
and extracting information corresponding to the attributes from the medical report text as key information.
3. The method of claim 2, wherein the step of extracting key information from the medical report text further comprises: adding attribute labels to the key information; the attribute labels correspond to attributes of information to be filled in the medical examination and evaluation template slot positions;
correspondingly, the step of generating a medical evaluation report according to the correlation evaluation result comprises the following steps:
filling the key information and the correlation evaluation result into a correlation evaluation template according to the attribute tag to obtain an evaluation conclusion report;
and generating a medical evaluation report according to the evaluation conclusion report.
4. The method of claim 3, further comprising, after the step of extracting key information in the medical report text:
acquiring clinical research process information of the medical report text; wherein the clinical study procedure information includes at least one of: diagnosis process information of the patient, treatment process information of the patient, and treatment effect analysis process information of the patient;
filling key information corresponding to the clinical research process information into an event summary template to obtain an adverse drug reaction event summary report;
correspondingly, the step of generating a medical evaluation report according to the correlation evaluation result comprises the following steps:
and generating a medical evaluation report according to the adverse drug reaction event summary report and the evaluation conclusion report.
5. The method of claim 4, further comprising:
filling the primary key information, the secondary key information and the correlation analysis result between the primary key information and the secondary key information into a correlation analysis template to obtain a correlation analysis report;
correspondingly, the step of generating a medical evaluation report according to the correlation evaluation result comprises the following steps: and generating a medical evaluation report according to the adverse drug reaction event summary report, the correlation analysis report and the evaluation conclusion report.
6. The method of claim 1, wherein the evaluation dimension comprises at least one of:
correlation analysis of the last study medication time and adverse reaction events; or,
correlation analysis of adverse events with known adverse events for study medication; or,
correlation analysis with adverse events after patient discontinuation of study medication; or,
the patient stops using the study medication and then uses the study medication again to perform correlation analysis with adverse reaction events; or,
correlation analysis of adverse events with other drugs used by patients during study medication; or,
analyzing the association between the drug with the same pharmacological toxicity as the target drug and the adverse reaction event; or,
analyzing the association between the existing/combined medical history of the patient and adverse reaction events; or,
correlation analysis of complications and adverse events of patients suffering from diseases.
7. The method according to claim 6, wherein the step of performing association analysis on the primary key information and the secondary key information based on the evaluation dimension to obtain an association analysis result between the primary key information and the secondary key information in different evaluation dimensions comprises:
acquiring correlation analysis results of the primary key information and the secondary key information in different evaluation dimensions;
taking the correlation analysis result and corresponding correlation degree data in a preset correlation evaluation rule as a correlation evaluation result of the target drug and the adverse drug reaction event; the relevance evaluation rule comprises relevance analysis results on different evaluation dimensions and corresponding relevance degree data.
8. The method according to claim 1, wherein the step of performing association analysis on the primary key information and the secondary key information based on the evaluation dimension to obtain association analysis results between the primary key information and the secondary key information in different evaluation dimensions comprises:
and determining the correlation analysis result between the primary key information and the secondary key information according to the context of the primary key information and the secondary key information in the medical report text.
9. The method according to claim 8, wherein the step of performing association analysis on the primary key information and the secondary key information to obtain an association analysis result between the primary key information and the secondary key information further comprises:
determining adverse drug reaction event descriptions corresponding to the main key information in a preset medical examination and evaluation knowledge base as the target adverse drug reaction event descriptions; the medical examination and evaluation knowledge base comprises target drugs, adverse reaction events of the target drugs and reasons of the adverse reaction events of the target drugs;
calculating the similarity between the cause of the adverse drug reaction event corresponding to the description of the target adverse drug reaction event in the medical examination and evaluation knowledge base and the secondary key information;
setting the association analysis result between the secondary key information and the primary key information as the existence of an association relation under the condition that the maximum value in the similarity is greater than or equal to a preset threshold value;
and setting the association analysis result between the secondary key information and the primary key information as no association relation when the maximum value in the similarity is smaller than a preset threshold value.
10. The method according to claim 9, wherein before the step of determining the ADF event description corresponding to the primary key information in a preset medical review knowledge base as the target ADF event description, the method further comprises:
searching a medical literature repository for relevant literature to the adverse drug reaction event mentioned in the medical report text;
determining the adverse drug reaction event and the corresponding reason of the adverse drug reaction event in the relevant literature;
and storing the reason corresponding to the adverse drug reaction event into a medical evaluation knowledge base corresponding to the adverse drug reaction event to serve as the reason of the adverse drug reaction.
11. A medical examination and review generation device is applied to a first terminal and is characterized by comprising:
the medical report text receiving module is used for receiving a medical report text which is sent by the second terminal and aims at the target medicine;
the key information acquisition module is used for extracting key information in the medical report text; the key information comprises main key information for expressing the adverse drug reaction event and secondary key information for expressing the reason for causing the adverse drug reaction event; wherein the secondary key information corresponds to different evaluation dimensions;
the association analysis module is used for performing association analysis on the primary key information and the secondary key information based on the evaluation dimensions to obtain association analysis results between the primary key information and the secondary key information in different evaluation dimensions; wherein the correlation analysis result comprises the existence of correlation or the nonexistence of correlation;
a correlation evaluation module for generating a correlation evaluation result between the target drug and the adverse drug reaction event based on the correlation analysis result and a preset correlation evaluation rule;
and the medical evaluation report generating module is used for generating a medical evaluation report according to the correlation evaluation result.
12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of claims 1 to 10 when executing the computer program.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210253344.8A CN114639456A (en) | 2022-03-15 | 2022-03-15 | Medical evaluation generation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210253344.8A CN114639456A (en) | 2022-03-15 | 2022-03-15 | Medical evaluation generation method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114639456A true CN114639456A (en) | 2022-06-17 |
Family
ID=81947782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210253344.8A Pending CN114639456A (en) | 2022-03-15 | 2022-03-15 | Medical evaluation generation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114639456A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910277A (en) * | 2023-09-13 | 2023-10-20 | 之江实验室 | Knowledge graph construction method, resource searching method, computer equipment and medium |
-
2022
- 2022-03-15 CN CN202210253344.8A patent/CN114639456A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910277A (en) * | 2023-09-13 | 2023-10-20 | 之江实验室 | Knowledge graph construction method, resource searching method, computer equipment and medium |
| CN116910277B (en) * | 2023-09-13 | 2024-02-27 | 之江实验室 | Knowledge graph construction method, resource searching method, computer equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111863267B (en) | Data information acquisition method, data analysis method, device and storage medium | |
| CN100449531C (en) | Patient data mining | |
| US10878010B2 (en) | System and method for clinical trial candidate matching | |
| WO2020176476A1 (en) | Prognostic score based on health information | |
| CN114580007A (en) | Medical data desensitization methods and apparatus | |
| CN112017745B (en) | Decision information recommendation and drug information recommendation methods, devices, equipment and media | |
| CN112331298A (en) | Method and device for issuing prescription, electronic equipment and storage medium | |
| CN111199784A (en) | Medication guidance pushing method, device and equipment based on WeChat applet | |
| CN113488180B (en) | Clinical guideline knowledge modeling method and system | |
| CN109448811B (en) | Prescription auditing improvement method and device, electronic equipment and storage medium | |
| Faisal et al. | Dataset geography: Mapping language data to language users | |
| CN114639456A (en) | Medical evaluation generation method and device, computer equipment and storage medium | |
| CN114021563A (en) | Method, device, equipment and storage medium for extracting data in medical information | |
| CN109299214B (en) | Text information extraction method, text information extraction device, text information extraction medium and electronic equipment | |
| JP2022504508A (en) | Systems and methods for model-assisted event prediction | |
| CN113724830A (en) | Medicine taking risk detection method based on artificial intelligence and related equipment | |
| CN111383726A (en) | Electronic medical record data processing method and device, electronic equipment and readable medium | |
| CN112309579A (en) | Method and device for recommending treatment scheme, electronic equipment and storage medium | |
| Nair et al. | Automated clinical concept-value pair extraction from discharge summary of pituitary adenoma patients | |
| CN116913548A (en) | Adverse reaction data analysis method, device, electronic equipment and storage medium | |
| Park et al. | Criteria2Query 3.0: Leveraging generative large language models for clinical trial eligibility query generation | |
| CN112908488B (en) | Event recognition method and device, computer equipment and storage medium | |
| CN114783557A (en) | Method and device for processing tumor patient data, storage medium and processor | |
| CN112331356A (en) | Method and device for recommending treatment scheme, electronic equipment and storage medium | |
| CN114154502B (en) | Word segmentation method and device for medical text, computer equipment and storage medium |
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 |