CN114049929A - Medical examination report interpretation method and device and electronic equipment - Google Patents
Medical examination report interpretation method and device and electronic equipment Download PDFInfo
- Publication number
- CN114049929A CN114049929A CN202111318924.2A CN202111318924A CN114049929A CN 114049929 A CN114049929 A CN 114049929A CN 202111318924 A CN202111318924 A CN 202111318924A CN 114049929 A CN114049929 A CN 114049929A
- Authority
- CN
- China
- Prior art keywords
- examination report
- medical
- medical examination
- matching
- structured
- 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
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 61
- 238000003058 natural language processing Methods 0.000 claims abstract description 29
- 230000002159 abnormal effect Effects 0.000 claims description 58
- 238000007689 inspection Methods 0.000 claims description 37
- 238000012216 screening Methods 0.000 claims description 12
- 230000036541 health Effects 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 abstract description 10
- 210000001685 thyroid gland Anatomy 0.000 description 25
- 210000001165 lymph node Anatomy 0.000 description 8
- 210000003739 neck Anatomy 0.000 description 8
- 210000002307 prostate Anatomy 0.000 description 8
- 238000013139 quantization Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000001575 pathological effect Effects 0.000 description 5
- 230000017531 blood circulation Effects 0.000 description 4
- 238000012015 optical character recognition Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008961 swelling Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 208000024891 symptom Diseases 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 210000004907 gland Anatomy 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000035935 pregnancy Effects 0.000 description 2
- 230000008719 thickening Effects 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 210000004061 pubic symphysis Anatomy 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000002604 ultrasonography Methods 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
-
- 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
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a medical examination report reading method, a medical examination report reading device and electronic equipment, which are used for acquiring an unstructured medical examination report; based on a preset medical case model, a natural language processing mode is adopted to carry out structuralized processing on an unstructured medical examination report; matching the structured data in the medical examination report after structured processing with standard data in a medical knowledge database acquired in advance to obtain a matching result; and generating an interpretation file corresponding to the unstructured medical examination report based on the matching result. According to the method, a medical case model and a natural language processing technology are utilized to perform structured processing on an unstructured medical examination report, the unstructured medical examination report is matched with standard data in a medical knowledge database, an interpretation file is generated according to an obtained matching result, and the automatic interpretation requirement of a patient on the unstructured text-form examination report can be met.
Description
Technical Field
The invention relates to the technical field of medicine, in particular to a medical examination report interpretation method and device and electronic equipment.
Background
In the diagnosis and treatment process, the internal condition of the body of a patient can be checked in a medical image checking mode, and for most patients, due to the lack of professional medical knowledge, when a medical image checking report form is taken, what the content described by the report form means is often unclear; although there are many knowledge that can be searched and referred to on the internet, because each patient's individual condition is different, it is often not suitable for all people, even some misleading information can have negative effects; in the related art, the examination report can be interpreted by an OCR (Optical Character Recognition) Recognition technology, but this method can only interpret a structured laboratory examination report sheet, and for an unstructured text-form medical image examination report, a pathological examination report, and the like, automatic interpretation cannot be realized, so that the automatic interpretation requirement of a patient for an unstructured text-form examination report cannot be met.
Disclosure of Invention
The invention aims to provide a medical examination report interpretation method, a medical examination report interpretation device and electronic equipment, which are used for meeting the automatic interpretation requirement of a patient on an unstructured text form examination report.
The invention provides a medical examination report interpretation method, which comprises the following steps: obtaining an unstructured medical examination report; based on a preset medical case model, a natural language processing mode is adopted to carry out structuralized processing on an unstructured medical examination report; matching the structured data in the medical examination report after structured processing with standard data in a medical knowledge database acquired in advance to obtain a matching result; and generating an interpretation file corresponding to the unstructured medical examination report based on the matching result.
Further, the step of performing structured processing on the medical examination report by adopting a natural language processing mode based on a preset medical case model comprises the following steps: and storing unstructured data in the unstructured medical examination report according to a predefined structure of the medical case model by adopting a natural language processing mode to obtain the structured medical examination report.
Further, the step of matching the structured data in the medical examination report after the structured processing with the standard data in the medical knowledge database acquired in advance to obtain a matching result includes: screening out index characteristic values in a digital form from the structured data of the medical examination report after structured processing; matching the structured fields related to the index characteristic values in the digital form in the medical examination report after structured processing with a plurality of fields in a medical knowledge database acquired in advance to obtain standard fields with matching relations; standardizing the index name associated with the index characteristic value in the digital form to obtain a standardized index name; and determining a matching result based on the index characteristic value in the form of number, the standard field with matching relation and the standardized index name.
Further, the step of determining the matching result based on the index feature value in numerical form, the standard field having the matching relationship, and the standardized index name includes: acquiring a standard characteristic value from a medical knowledge database based on a standard field with a matching relationship and a standardized index name; comparing the index characteristic value in the digital form with the standard characteristic value to determine an abnormal index characteristic value; and determining a matching result based on the abnormal index characteristic value.
Further, the step of determining the matching result based on the abnormal index feature value includes: determining a first check result corresponding to the abnormal index characteristic value based on the abnormal index characteristic value; screening out specified characteristic values containing specified characters from other index characteristic values except the index characteristic values in a digital form from the structured data of the medical examination report after the structured processing; acquiring a designated index name and an inspection part name corresponding to the designated characteristic value; based on the designated characteristic value, spelling the designated index name and the name of the checked part according to a preset spelling rule to obtain a spelling result; determining a second check result corresponding to the specified characteristic value based on the spelling result; based on the first and second inspection results, a matching result is determined.
Further, the step of determining a matching result based on the first and second checking results comprises: acquiring specified information in an unstructured medical examination report; wherein the designation information includes at least one of: gender information, age information; based on the specification information, the first inspection result, and the second inspection result, a matching result is determined.
Further, the step of determining a matching result based on the specification information, the first check result and the second check result includes: screening out abnormal inspection results which accord with the specified information from the first inspection results and the second inspection results; acquiring interpretation information matched with the abnormal inspection result; wherein the interpretation information includes at least one of: medical explanation and health guidance suggestion corresponding to the abnormal examination result; based on the anomaly check result and the interpretation information, a matching result is determined.
The invention provides a medical examination report interpretation device, which comprises: an acquisition module for acquiring an unstructured medical examination report; the processing module is used for carrying out structural processing on the unstructured medical examination report by adopting a natural language processing mode based on a preset medical case model; the matching module is used for matching the structured data in the medical examination report after the structured processing with the standard data in the medical knowledge database acquired in advance to obtain a matching result; and the generating module is used for generating an interpretation file corresponding to the unstructured medical examination report based on the matching result.
The invention provides an electronic device which comprises a processor and a memory, wherein the memory stores machine executable instructions capable of being executed by the processor, and the processor executes the machine executable instructions to realize the medical examination report interpretation method.
The present invention provides a machine-readable storage medium having stored thereon machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the medical examination report interpretation method of any of the above.
The medical examination report interpretation method, the medical examination report interpretation device and the electronic equipment provided by the invention are used for acquiring an unstructured medical examination report; based on a preset medical case model, a natural language processing mode is adopted to carry out structuralized processing on an unstructured medical examination report; matching the structured data in the medical examination report after structured processing with standard data in a medical knowledge database acquired in advance to obtain a matching result; and generating an interpretation file corresponding to the unstructured medical examination report based on the matching result. According to the method, a medical case model and a natural language processing technology are utilized to perform structured processing on an unstructured medical examination report, the unstructured medical examination report is matched with standard data in a medical knowledge database, an interpretation file is generated according to an obtained matching result, and the automatic interpretation requirement of a patient on the unstructured text-form examination report can be met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a medical examination report interpretation method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another medical examination report interpretation method provided by an embodiment of the invention;
FIG. 3 is a flow chart of another medical examination report interpretation method provided by an embodiment of the invention;
FIG. 4 is a flow chart of another medical examination report interpretation method provided by an embodiment of the invention;
FIG. 5 is a schematic structural diagram of a medical examination report interpretation apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
Medical imaging examination is the main method for examining the internal condition of the body of a patient in the diagnosis and treatment process, and has clinical significance of diagnostic gold standard even for some diseases. In the related technology, the data of a structured laboratory examination report sheet can be identified and classified based on an OCR technology, and the abnormal index information is judged and extracted by capturing key word indexes and generating a laboratory examination report sheet reading report by combining a knowledge base; the steps of this approach generally include: performing OCR recognition on the test report sheet in the picture format; capturing abnormal index information and generating an electronic inspection report; automatically generating recommendation information by combining an expert knowledge base; and generating an interpretation file of the laboratory examination report sheet according to the recommendation information. But the biggest problems with this approach are: the method can only interpret the structured laboratory examination report, and does not achieve the effect of automatic interpretation for unstructured text-form medical image examination reports, pathological examination reports and the like.
Based on the above, the embodiments of the present invention provide a medical examination report interpretation method, apparatus and electronic device, which may be applied to applications that require interpretation of unstructured medical examination reports.
In order to facilitate understanding of the embodiment, a medical examination report interpretation method disclosed by the embodiment of the invention is first described in detail; as shown in fig. 1, the method comprises the steps of:
step S102, an unstructured medical examination report is acquired.
The unstructured medical examination includes medical image examination reports, pathological examination reports and the like, and report contents in the unstructured medical examination reports are generally unstructured text data; medical examination reports are written according to different individual patients according to medical record writing specifications, and the writing styles are diversified; for example, taking a medical image examination report as an example, based on the basic principle of writing the medical image examination report, the lesion description of the examination report in the medical record usually needs to include the examined region and the property characteristics of the examined region, wherein the property characteristics may include lesion distribution, number, size, thickness, and the like. In practical implementations, when an unstructured medical examination report needs to be automatically interpreted, the unstructured medical examination report usually needs to be acquired first.
And step S104, based on a preset medical case model, carrying out structural processing on the unstructured medical examination report by adopting a natural language processing mode.
The medical case model can be understood as a structured data structure defined according to an applicable scene based on electronic medical record data; the natural language processing is an important direction in the fields of computer science and artificial intelligence, and is used for researching various theories and methods for realizing effective communication between people and computers by using natural language, wherein the natural language processing is a science integrating linguistics, computer science and mathematics, namely, a computing mechanism is used for solving the value of the language used by people in daily life. In practical implementation, in order to effectively interpret the unstructured medical examination report, the unstructured medical examination report may be structured by using a natural language processing technique and a medical case model, so as to obtain a structured examined region and property characteristics such as size and thickness.
And step S106, matching the structured data in the medical examination report after the structured processing with the standard data in the medical knowledge database acquired in advance to obtain a matching result.
The medical knowledge database is relatively standardized knowledge formed by integrating design and associating knowledge points on the basis of inquiring medicine; in practical implementation, after unstructured medical examination reports are subjected to structured processing, structured medical examination reports can be obtained, report contents in the structured medical examination reports are structured data, and the structured data can be matched with standard data in a medical knowledge database, that is, abnormal comparison is performed under uniform conditions, so that matching results can be obtained.
And step S108, generating an interpretation file corresponding to the unstructured medical examination report based on the matching result.
The medical examination report interpretation method acquires an unstructured medical examination report; based on a preset medical case model, a natural language processing mode is adopted to carry out structuralized processing on an unstructured medical examination report; matching the structured data in the medical examination report after structured processing with standard data in a medical knowledge database acquired in advance to obtain a matching result; and generating an interpretation file corresponding to the unstructured medical examination report based on the matching result. According to the method, a medical case model and a natural language processing technology are utilized to perform structured processing on an unstructured medical examination report, the unstructured medical examination report is matched with standard data in a medical knowledge database, an interpretation file is generated according to an obtained matching result, and the automatic interpretation requirement of a patient on the unstructured text-form examination report can be met.
The embodiment of the invention also provides another medical examination report interpretation method, which is realized on the basis of the method of the embodiment; the method mainly describes a specific process of performing structured processing on a medical examination report by adopting a natural language processing mode based on a preset medical case model, and as shown in fig. 2, the method comprises the following steps:
step S202, an unstructured medical examination report is acquired.
And step S204, storing unstructured data in the unstructured medical examination report according to a structure defined in advance by the medical case model by adopting a natural language processing mode to obtain the structured medical examination report.
In practical implementation, the unstructured data in the unstructured medical examination report, that is, the electronic medical record data, may be stored according to a predefined structure of the medical case model by using a natural language processing technology to obtain a structured medical examination report, for example, see a table structure shown in table 1, where the table structure includes types of models, attributes, and data types, the table 1 takes a cervical ultrasound examination as an example, and the corresponding attributes may include side names, part names, whether nodules exist, whether there are multiple nodules, and the like, and may be filled in with reference to the table structure to obtain a structured medical examination report.
TABLE 1
For example, the content of a medical record examination report is: "the thyroid left lobe is 3.5cm thick, the thyroid left lobe can see a hypoecho, the echo size is about 0.9 x 0.6cm, the boundary is not clear, the morphology is not regular, the interior can see a punctate strong echo, CDI, a small amount of blood flow signals can be seen, the thyroid right lobe is 3.5cm thick, the isthmus is 0.3cm thick, the right lobe near isthmus can see no echo, the echo size is about 0.4 x 0.2cm, the boundary is clear, CDI, the thyroid parenchyma echo is even, the intrathyroid blood flow is normally distributed, the lymph nodes are obviously swollen at the double necks", when the structuralization processing is carried out, the processing result after the structuralization can be obtained, as follows:
and step S206, matching the structured data in the medical examination report after the structured processing with the standard data in the medical knowledge database acquired in advance to obtain a matching result.
And step S208, generating an interpretation file corresponding to the unstructured medical examination report based on the matching result.
The medical examination report interpretation method acquires an unstructured medical examination report. And storing unstructured data in the unstructured medical examination report according to a predefined structure of the medical case model by adopting a natural language processing mode to obtain the structured medical examination report. And matching the structured data in the medical examination report after structured processing with the standard data in the medical knowledge database acquired in advance to obtain a matching result. And generating an interpretation file corresponding to the unstructured medical examination report based on the matching result. According to the method, a medical case model and a natural language processing technology are utilized to perform structured processing on an unstructured medical examination report, the unstructured medical examination report is matched with standard data in a medical knowledge database, an interpretation file is generated according to an obtained matching result, and the automatic interpretation requirement of a patient on the unstructured text-form examination report can be met.
The embodiment of the invention also provides another medical examination report interpretation method, which is realized on the basis of the method of the embodiment; the method mainly describes a specific process of matching structured data in a medical examination report after structured processing with standard data in a medical knowledge database acquired in advance to obtain a matching result, as shown in fig. 3, the method comprises the following steps:
step S302, an unstructured medical examination report is acquired.
And step S304, based on a preset medical case model, carrying out structural processing on the unstructured medical examination report by adopting a natural language processing mode.
Step S306, screening out index characteristic values in a digital form from the structured data of the medical examination report after the structured processing.
The index feature value may be understood as a property feature value in a medical examination report; in the structured data of the medical examination report after the structured processing, there may exist index characteristic values in a digital form, i.e. the condition of direct comparison, and the characteristic features of the examination report after the structured processing can be compared with the normal range of the knowledge data by establishing the matching relationship between the structured field of the medical record and the knowledge field, for example, the characteristic features of the examination report after the structured processing are as follows: thickness of thyroid lobe, characteristic feature value: 3.5mm, etc.; there may also be a case where the index feature value is not in a numeric form, that is, it cannot be directly compared, that is, it cannot be compared with the normal range of the knowledge data, for example, the structured inspection report feature is: whether the part and lymph node are swollen or not, and the characteristic values: the neck part and the lymph node swelling are determined, the property characteristic value which cannot be directly compared is subjected to standard treatment by a synonym library of filtering medical entities, and then is compared, so that whether the property characteristic belongs to a normal or abnormal condition is determined.
The index characteristic value in a digital form can be directly compared with standard data in a medical knowledge database, so that the index characteristic value in a digital form can be screened from the structured data of the medical examination report after structured processing.
Step S308, matching the structured fields related to the index characteristic values in the digital form in the medical examination report after the structured processing with a plurality of fields in a medical knowledge database acquired in advance to obtain standard fields with matching relations.
In practical implementation, diverse medical record data needs to be matched with relatively standard knowledge fields, so that abnormal comparison can be performed under a uniform condition. The following medical record data and knowledge data samples:
medical record-examination report:
the thickness of the left thyroid leaf is 3.5cm, the left thyroid leaf can see a hypoecho, the echo size is about 0.9 multiplied by 0.6cm, the boundary is not clear, the morphology is not regular, the interior can see a punctate strong echo, CDI, a small amount of blood flow signals can be seen, the thickness of the right thyroid leaf is 3.5cm, the thickness of the isthmus is 0.3cm, the near isthmus of the right thyroid leaf can see no echo, the echo size is about 0.4 multiplied by 0.2cm, the boundary is clear, CDI, the thyroid parenchyma echo is uniform, the blood flow distribution in the thyroid is normal, and the lymph nodes are obviously swollen in the double necks.
Knowledge data:
"supine position, neck supine:
the normal thyroid lateral lobe has an anteroposterior diameter of 1-2cm, a left lateral diameter of 2-2.5cm, an upper lateral diameter of 3.5-5cm, an isthmus anterior-posterior diameter of 0.2-0.4cm, and is a small, densely distributed and uniform medium echo, and peripheral muscle tissue is low echo. Reduced, increased or echogenic irregularities may occur in abnormal situations.
For the case where the direct comparison is possible, for example, the structured medical record data is:
the knowledge data in the medical knowledge database are:
comparing the field values of the structured medical record data and the knowledge data, establishing a matching relation between the medical record field and the knowledge field based on the fields with the same content by adopting a keyword matching mode and the like, as shown in the following table 2:
TABLE 2
In step S310, the index name associated with the index feature value in the numeric form is normalized to obtain a normalized index name.
The index name may be understood as a name of a property feature in the medical examination report, for example, continuing with the example in the above step, the index name in the structured medical record data is thyroid lobe; in practical implementation, the property feature value may be normalized based on a thesaurus of medical entities, for example, a pre-normalization index name and a post-normalization index name as shown in table 3.
TABLE 3
| Before standardization | After standardization |
| Thyroid gland leaf | Thyroid gland lateral lobe |
| Thyroid gland leaf | Thyroid gland lateral lobe |
| Thickness of | Front and back diameter |
| Is thick and thick | Front and back diameter |
In step S312, a matching result is determined based on the index feature value in the numeric form, the standard field having the matching relationship, and the standardized index name.
The step S312 can be specifically obtained by the following steps one to three:
step one, acquiring a standard characteristic value from a medical knowledge database based on a standard field with a matching relation and a standardized index name.
And step two, comparing the index characteristic value in the digital form with the standard characteristic value to determine the abnormal index characteristic value.
And step three, determining a matching result based on the abnormal index characteristic value.
The standard characteristic value can be a specific numerical value or a numerical range; the abnormal index feature value may be understood as a numerical index feature value that does not conform to the standard feature value, for example, if the anteroposterior diameter of the "thyroid side lobe" in the medical record is "3.5" and the standard range indicated by the standard feature value in the knowledge database is "1-2", it is determined by comparison that the anteroposterior diameter of the "thyroid side lobe" in the medical record exceeds the upper limit of the standard range indicated by the standard feature value and belongs to the abnormal index feature value, and based on the abnormal index feature value, it can be found that the anteroposterior diameter property feature of the thyroid side lobe belongs to the abnormal range.
The third step can be specifically realized by the following steps A to E:
and step A, determining a first check result corresponding to the abnormal index characteristic value based on the abnormal index characteristic value.
Taking the case that the anterior-posterior diameter of the thyroid lateral lobe exceeds the upper limit of the standard range indicated by the standard characteristic value in the medical record, the symptom that the anterior-posterior diameter of the thyroid lateral lobe exceeds the upper limit of the normal item of the thyroid lateral lobe and the anterior-posterior diameter can be matched as thyroid thickening according to the knowledge graph, and the thyroid thickening is the first inspection result.
And B, screening out specified characteristic values containing specified characters from other index characteristic values except the index characteristic values in a digital form from the structured data of the medical examination report after the structured processing.
The designated characters can be set according to actual requirements, for example, the designated characters can include "yes" and the like; in practical implementation, other index characteristic values except for the index characteristic value in a digital form cannot be directly compared with standard data in the medical knowledge database, and at this time, other characteristic values in the structured medical examination report may be matched with the standard data in the medical knowledge database by a certain rule, and specifically, a specified characteristic value containing a specified character may be screened from other characteristic values, for example, data with a value of "yes" in the quantization _ boromean may be taken.
And step C, acquiring the designated index name and the inspection part name corresponding to the designated characteristic value.
D, spelling the name of the designated index and the name of the checked part according to a preset spelling rule based on the designated characteristic value to obtain a spelling result; based on the spelling result, a second check result corresponding to the specified feature value is determined.
The specified index name can also be understood as a project name in the medical examination report after the structured processing; in practical implementation, because the establishment based on the medical case model is established on the premise of medical knowledge specification and is consistent with the establishment standard of data in the medical knowledge database, the property characteristics of the inspection report can be matched with the knowledge data through a certain rule, and the following is a specific matching rule:
the data that the value of the quantization _ bold is 'yes' is taken, the value of the quantization _ project and the value of the quantization _ text corresponding to the 'part name' are spelled according to the rule of 'part name' + 'project name' (whether the project name is removed), and the spelled content is matched with the symptoms of the knowledge base to obtain the abnormal condition.
The structured inspection report data is as follows:
if the value of the quantization _ bolean is "yes", the quantization _ text corresponding to the name of the location where the quantization _ project "lymph node is swollen" is "neck", spelling is performed according to the rule of "neck" + "lymph node swelling", and the symptom "neck lymph node swelling" is matched, the abnormal condition obtained by the examination report is "neck lymph node swelling", which is the second examination result.
And E, determining a matching result based on the first checking result and the second checking result.
The step E may specifically include the following steps a and b:
step a, acquiring specified information in an unstructured medical examination report; wherein the designation information includes at least one of: gender information, age information.
For one examination item, different medical image expressions may exist in different populations, ages, body positions, pregnancies and other situations, and the judgment criteria corresponding to whether the knowledge data is abnormal also have differences, so when judging whether the examination report is abnormal, the knowledge data in the medical history information needs to be comprehensively compared with the information of the populations, the ages, the pregnancies and the like in the medical knowledge database to judge whether the examination report has abnormal indexes.
And b, determining a matching result based on the specified information, the first checking result and the second checking result.
The step b may specifically include:
and (1) screening out an abnormal inspection result which meets the specified information from the first inspection result and the second inspection result.
Step (2), acquiring interpretation information matched with the abnormal inspection result; wherein the interpretation information includes at least one of: and medical explanation and health guidance suggestion corresponding to the abnormal examination result.
And (3) determining a matching result based on the abnormal checking result and the interpretation information.
The knowledge data samples were examined as in table 4:
TABLE 4
First, basic information of a patient of a current medical record is acquired, such as: "sex: male, age: 73 years old "; then, according to the standard of age classification, the ages are classified according to the crowds, as shown in table 5, and finally, the knowledge data is matched and whether the patient belongs to the abnormal index or not is judged by combining the patient information.
TABLE 5
| People group | Age (age) |
| Newborn baby | Within 28 days |
| Babies | Within 28 days to within 1 year of age |
| Children's toy | 0-6 years old |
| Children's cycle | 7-17 years old |
| Young people | 18-40 years old |
| Middle-aged | 41-65 years old |
| Old age | After age 66 |
For example, a medical record data review report is: "transrectal scanning: the transverse diameter of prostate gland is 4.3cm, and the upper and lower oblique diameters are 4.0 cm. The internal gland is 3.2x2.4 cm. The moderate-severe enlargement of the internal gland, clear outline of the prostate, uneven echo and no obvious tumor.
The knowledge data is: "1, size: the radial line of the prostate increases with age. The average superior-inferior diameter, transverse diameter and anterior-posterior diameter of prostate are 3.0cm, 3.1cm and 2.3cm for young people, and 5.0cm, 4.8cm and 4.3cm for old people. 2. Prostate enlargement is a common abnormal sign, showing that the prostate is still visible at a transverse diameter > 5cm or at a level of 2cm above the pubic symphysis ".
Referring to the aforementioned quantifiable field matching rule, the transverse diameter of prostate is compared with 4.3cm, and this report indicates that the prostate belongs to an abnormal index if the patient is a young or middle-aged patient, and belongs to a normal index if the patient is an elderly patient.
And step S314, generating an interpretation file corresponding to the unstructured medical examination report based on the matching result.
And (4) retaining the knowledge entity judged as the abnormal index, reading the medical explanation and the health guidance suggestion in the knowledge base, and generating an inspection report interpretation file.
The medical examination report interpretation method can automatically interpret unstructured medical image examination reports and medical pathological examination reports, perform structured processing on text data in the examination reports by using a natural language processing technology, and match the text data with standard data in a medical knowledge database.
To further understand the above embodiments, another medical examination report interpretation method flowchart is provided as shown in fig. 4, which first acquires examination report case data, structures the location and property features in the examination report, comparing the standard data of the medical knowledge base to judge abnormal conditions, and for the conditions which can be directly compared, can carry out standardization processing on the property characteristic values, establish the matching relation between medical record fields and knowledge fields, obtain abnormal conditions through matching, for the condition that can not be directly compared, the abnormal condition can be obtained by matching the characteristic features with the knowledge data by using the rules, and after all the abnormal conditions in the medical record data of the inspection report are obtained, the abnormal indexes of the examination report can be read by combining the medical record information of the patient, the medical explanation and the health guidance significance of the abnormal indexes are called, and finally, an examination report reading file is generated.
For patients lacking medical knowledge reserves, when medical image examination report forms and pathological examination report forms are taken, the current abnormal indexes, medical explanations and health guidance suggestions of the patients are expected to be known in a mode of automatically reading the reports, and the requirement can be solved by adopting the mode.
Due to the fact that writing of medical image examination reports and medical pathology examination reports in electronic medical records is differentiated and not standardized, unstructured examination reports are subjected to structuring and standardization processing and then matched with standard knowledge data in a medical knowledge base, and the reading requirement of the unstructured examination reports is further solved. In addition, the mode can be combined with the medical record information of the patient, the knowledge data is matched, and the abnormal index of the examination report is judged, so that the interpretation of the examination report has the personalized characteristic.
The medical examination report interpretation method is to compare the examination report with the fields and data in the medical knowledge base according to individual different conditions of each patient, read the medical interpretation and health guidance suggestion corresponding to the abnormal field, and interpret the examination report. The medical examination report reading system can help a patient to read the abnormity of an examination report according to the self condition, give a specific health guidance suggestion, help the patient to quickly and directly know the self health condition and reduce the medical waiting time.
An embodiment of the present invention provides a medical examination report interpretation apparatus, as shown in fig. 5, the apparatus includes: an acquisition module 50 for acquiring unstructured medical examination reports; the processing module 51 is configured to perform structured processing on the unstructured medical examination report by adopting a natural language processing mode based on a preset medical case model; the matching module 52 is configured to match the structured data in the medical examination report after the structured processing with the standard data in the medical knowledge database acquired in advance, so as to obtain a matching result; and the generating module 53 is configured to generate an interpretation file corresponding to the unstructured medical examination report based on the matching result.
The medical examination report interpretation device acquires an unstructured medical examination report; based on a preset medical case model, a natural language processing mode is adopted to carry out structuralized processing on an unstructured medical examination report; matching the structured data in the medical examination report after structured processing with standard data in a medical knowledge database acquired in advance to obtain a matching result; and generating an interpretation file corresponding to the unstructured medical examination report based on the matching result. The device carries out structuralization processing on the unstructured medical examination report by utilizing a medical case model and a natural language processing technology, matches the unstructured medical examination report with standard data in a medical knowledge database, generates an interpretation file according to an obtained matching result, and can meet the automatic interpretation requirement of a patient on the unstructured text form examination report.
Further, the processing module is further configured to: and storing unstructured data in the unstructured medical examination report according to a predefined structure of the medical case model by adopting a natural language processing mode to obtain the structured medical examination report.
Further, the matching module is further configured to: screening out index characteristic values in a digital form from the structured data of the medical examination report after structured processing; matching the structured fields related to the index characteristic values in the digital form in the medical examination report after structured processing with a plurality of fields in a medical knowledge database acquired in advance to obtain standard fields with matching relations; standardizing the index name associated with the index characteristic value in the digital form to obtain a standardized index name; and determining a matching result based on the index characteristic value in the form of number, the standard field with matching relation and the standardized index name.
Further, the matching module is further configured to: acquiring a standard characteristic value from a medical knowledge database based on a standard field with a matching relationship and a standardized index name; comparing the index characteristic value in the digital form with the standard characteristic value to determine an abnormal index characteristic value; and determining a matching result based on the abnormal index characteristic value.
Further, the matching module is further configured to: determining a first check result corresponding to the abnormal index characteristic value based on the abnormal index characteristic value; screening out specified characteristic values containing specified characters from other index characteristic values except the index characteristic values in a digital form from the structured data of the medical examination report after the structured processing; acquiring a designated index name and an inspection part name corresponding to the designated characteristic value; based on the designated characteristic value, spelling the designated index name and the name of the checked part according to a preset spelling rule to obtain a spelling result; determining a second check result corresponding to the specified characteristic value based on the spelling result; based on the first and second inspection results, a matching result is determined.
Further, the matching module is further configured to: acquiring specified information in an unstructured medical examination report; wherein the designation information includes at least one of: gender information, age information; based on the specification information, the first inspection result, and the second inspection result, a matching result is determined.
Further, the matching module is further configured to: screening out abnormal inspection results which accord with the specified information from the first inspection results and the second inspection results; acquiring interpretation information matched with the abnormal inspection result; wherein the interpretation information includes at least one of: medical explanation and health guidance suggestion corresponding to the abnormal examination result; based on the anomaly check result and the interpretation information, a matching result is determined.
The medical examination report interpretation device provided by the embodiment of the invention has the same implementation principle and technical effect as the medical examination report interpretation method embodiment, and for the sake of brief description, the corresponding content in the medical examination report interpretation method embodiment can be referred to where the embodiment of the medical examination report interpretation device is not mentioned.
An embodiment of the present invention further provides an electronic device, as shown in fig. 6, the electronic device includes a processor 130 and a memory 131, the memory 131 stores machine executable instructions capable of being executed by the processor 130, and the processor 130 executes the machine executable instructions to implement the medical examination report interpretation method.
Further, the electronic device shown in fig. 6 further includes a bus 132 and a communication interface 133, and the processor 130, the communication interface 133, and the memory 131 are connected through the bus 132.
The Memory 131 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 133 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used. The bus 132 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 6, but that does not indicate only one bus or one type of bus.
The processor 130 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 130. The Processor 130 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 131, and the processor 130 reads the information in the memory 131 and completes the steps of the method of the foregoing embodiment in combination with the hardware thereof.
The embodiment of the present invention further provides a machine-readable storage medium, where the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to implement the medical examination report interpretation method, and specific implementation may refer to method embodiments, and is not described herein again.
The medical examination report interpretation method, the medical examination report interpretation device and the computer program product of the electronic device provided by the embodiment of the invention comprise a computer readable storage medium storing program codes, wherein instructions included in the program codes can be used for executing the method described in the previous method embodiment, and specific implementation can refer to the method embodiment, and is not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A medical examination report interpretation method, characterized in that the method comprises:
obtaining an unstructured medical examination report;
based on a preset medical case model, carrying out structured processing on the unstructured medical examination report by adopting a natural language processing mode;
matching the structured data in the medical examination report after structured processing with standard data in a medical knowledge database acquired in advance to obtain a matching result;
and generating an interpretation file corresponding to the unstructured medical examination report based on the matching result.
2. The method of claim 1, wherein the step of structuring the medical examination report using natural language processing based on a predetermined medical case model comprises:
and storing unstructured data in the unstructured medical examination report according to a structure which is defined in advance by the medical case model by adopting a natural language processing mode to obtain the structured medical examination report.
3. The method according to claim 1, wherein the step of matching the structured data in the structured medical examination report with the standard data in the pre-acquired medical knowledge database to obtain the matching result comprises:
screening out index characteristic values in a digital form from the structured data of the medical examination report after structured processing;
matching the structured fields related to the index characteristic values in the digital form in the medical examination report after structured processing with a plurality of fields in a medical knowledge database acquired in advance to obtain standard fields with matching relations;
standardizing the index name associated with the index characteristic value in the digital form to obtain a standardized index name;
determining the matching result based on the index feature value in numerical form, the standard field having a matching relationship, and the normalized index name.
4. The method according to claim 3, wherein the step of determining the matching result based on the index feature value in the numerical form, the standard field having a matching relationship, and the normalized index name comprises:
acquiring a standard characteristic value from the medical knowledge database based on the standard field having a matching relationship and the standardized index name;
comparing the index characteristic value in the digital form with the standard characteristic value to determine an abnormal index characteristic value;
and determining the matching result based on the abnormal index characteristic value.
5. The method of claim 4, wherein the step of determining the matching result based on the anomaly index feature value comprises:
determining a first check result corresponding to the abnormal index characteristic value based on the abnormal index characteristic value;
screening out specified characteristic values containing specified characters from other index characteristic values except the index characteristic values in the digital form from the structured data of the medical examination report after the structured processing;
acquiring a designated index name and an inspection part name corresponding to the designated characteristic value;
based on the designated characteristic value, spelling the designated index name and the name of the checked part according to a preset spelling rule to obtain a spelling result; determining a second check result corresponding to the specified characteristic value based on the spelling result;
determining the matching result based on the first and second inspection results.
6. The method of claim 5, wherein the step of determining the matching result based on the first and second inspection results comprises:
obtaining specified information in the unstructured medical examination report; wherein the designation information includes at least one of: gender information, age information;
determining a matching result based on the designation information, the first inspection result, and the second inspection result.
7. The method according to claim 6, wherein the step of determining a matching result based on the specification information, the first check result, and the second check result comprises:
screening out abnormal inspection results which accord with the specified information from the first inspection results and the second inspection results;
acquiring interpretation information matched with the abnormal inspection result; wherein the interpretation information includes at least one of: medical explanation and health guidance suggestion corresponding to the abnormal examination result;
determining the matching result based on the anomaly checking result and the interpretation information.
8. A medical examination report interpretation apparatus, characterized in that the apparatus comprises:
an acquisition module for acquiring an unstructured medical examination report;
the processing module is used for carrying out structural processing on the unstructured medical examination report by adopting a natural language processing mode based on a preset medical case model;
the matching module is used for matching the structured data in the medical examination report after the structured processing with the standard data in the medical knowledge database acquired in advance to obtain a matching result;
and the generating module is used for generating an interpretation file corresponding to the unstructured medical examination report based on the matching result.
9. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor, the processor executing the machine executable instructions to implement the medical examination report interpretation method of any one of claims 1-7.
10. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to implement the medical examination report interpretation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111318924.2A CN114049929A (en) | 2021-11-09 | 2021-11-09 | Medical examination report interpretation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111318924.2A CN114049929A (en) | 2021-11-09 | 2021-11-09 | Medical examination report interpretation method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114049929A true CN114049929A (en) | 2022-02-15 |
Family
ID=80207807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111318924.2A Pending CN114049929A (en) | 2021-11-09 | 2021-11-09 | Medical examination report interpretation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114049929A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459287A (en) * | 2018-05-08 | 2019-11-15 | 西门子医疗有限公司 | Structured report data from medicine text report |
| CN112562807A (en) * | 2020-12-11 | 2021-03-26 | 北京百度网讯科技有限公司 | Medical data analysis method, apparatus, device, storage medium, and program product |
| CN112927776A (en) * | 2021-02-03 | 2021-06-08 | 昆山慧医优策医疗科技有限公司 | Artificial intelligence automatic interpretation system for medical inspection report |
-
2021
- 2021-11-09 CN CN202111318924.2A patent/CN114049929A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459287A (en) * | 2018-05-08 | 2019-11-15 | 西门子医疗有限公司 | Structured report data from medicine text report |
| CN112562807A (en) * | 2020-12-11 | 2021-03-26 | 北京百度网讯科技有限公司 | Medical data analysis method, apparatus, device, storage medium, and program product |
| CN112927776A (en) * | 2021-02-03 | 2021-06-08 | 昆山慧医优策医疗科技有限公司 | Artificial intelligence automatic interpretation system for medical inspection report |
Non-Patent Citations (1)
| Title |
|---|
| 吴欢等: "乳腺癌病理文本的结构化信息提取", 《解放军医学院学报》, vol. 41, no. 7, 31 July 2020 (2020-07-31), pages 746 - 751 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110069779B (en) | Symptom entity identification method of medical text and related device | |
| US11031121B2 (en) | System and method for indicating the quality of information to support decision making | |
| CN109166608A (en) | Electronic health record information extracting method, device and equipment | |
| CN112541066B (en) | Text-structured-based medical and technical report detection method and related equipment | |
| JP2014505950A (en) | Imaging protocol updates and / or recommenders | |
| CN111429989B (en) | Method and device for generating pre-diagnosis medical record | |
| CN114912887B (en) | Clinical data input method and device based on electronic medical record | |
| Lau et al. | Psychometric evaluation of 5-and 4-item versions of the LATCH breastfeeding assessment tool during the initial postpartum period among a multiethnic population | |
| CN114580007A (en) | Medical data desensitization methods and apparatus | |
| CN112883157A (en) | Method and device for standardizing multi-source heterogeneous medical data | |
| CN111292814A (en) | Medical data standardization method and device | |
| US11449680B2 (en) | Method for testing medical data | |
| CN111177309A (en) | Medical record data processing method and device | |
| CN112349367B (en) | Method, device, electronic equipment and storage medium for generating simulated medical record | |
| CN113111660A (en) | Data processing method, device, equipment and storage medium | |
| Pirkle et al. | Validity and reliability of criterion based clinical audit to assess obstetrical quality of care in West Africa | |
| CN114155949A (en) | Examination and verification method, device and equipment for first page of medical record | |
| CN108831560B (en) | Method and device for determining medical data attribute data | |
| CN114049929A (en) | Medical examination report interpretation method and device and electronic equipment | |
| KR102461647B1 (en) | An artificial intelligence system that provides medical type information on an EEG test report and its implementation method | |
| CN115101193A (en) | Symptom recommendation method and device and computer-readable storage medium | |
| CN115458138A (en) | DIP pre-grouping recommendation method, device, equipment and storage medium | |
| WO2022141929A1 (en) | Health self-test system, server, and health testing system | |
| CN115631823A (en) | Similar case recommendation method and system | |
| CN114520035A (en) | Volunteer screening method and device, electronic 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 |