CN112259183B - Method and device for extracting patient health time axis based on electronic medical record - Google Patents
Method and device for extracting patient health time axis based on electronic medical record Download PDFInfo
- Publication number
- CN112259183B CN112259183B CN202011252500.6A CN202011252500A CN112259183B CN 112259183 B CN112259183 B CN 112259183B CN 202011252500 A CN202011252500 A CN 202011252500A CN 112259183 B CN112259183 B CN 112259183B
- Authority
- CN
- China
- Prior art keywords
- medical record
- entity
- time axis
- target
- field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a method and a device for extracting a patient health time axis based on electronic medical records, wherein the scheme comprises the following steps: acquiring an electronic medical record of a target patient; preprocessing the electronic medical record; extracting a target field from the preprocessed electronic medical record; establishing a patient health time axis based on the target field, and marking the patient health time axis as a candidate health time axis; acquiring a history of the target patient; judging whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history medical record, and if so, replacing the entity name in the candidate patient health time axis by the entity name in the history medical record; and outputting the candidate patient health time axis after the entity name is replaced as a target health time axis, so that the patient health time axis is rapidly generated.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for extracting a patient health time axis based on electronic medical records.
Background
In the diagnosis and treatment process of a patient, medical staff needs to comprehensively know the health condition of the patient, and important diagnosis and treatment information is rapidly screened from the medical staff through clinical thinking and logical reasoning. In reality, however, patient information is incomplete, a large amount of data is not standardized, information emphasis is not outstanding, and even clinical judgment of medical staff is interfered. If the technology is available, the medical staff can be helped to comprehensively know the medical history and the whole diagnosis and treatment process of the patient, the important information of the patient can be visually checked on a long line, and clinical basis is provided for the medical process.
Therefore, there is an urgent need for a solution that can quickly generate a patient health timeline.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a method for extracting a patient health time axis based on an electronic medical record, so as to realize rapid generation of the patient health time axis.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
an extraction method of a patient health time axis based on electronic medical records comprises the following steps:
acquiring an electronic medical record of a target patient;
preprocessing the electronic medical record;
extracting a target field from the preprocessed electronic medical record;
normalizing the entity and the entity time in the target field;
establishing a patient health time axis based on the target field, and marking the patient health time axis as a candidate health time axis;
acquiring a history of the target patient;
judging whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history medical record, and if so, replacing the entity name in the candidate patient health time axis by the entity name in the history medical record;
and outputting the candidate patient health time axis after the entity name is replaced as a target health time axis.
Optionally, in the above method for extracting a patient health time axis based on an electronic medical record, preprocessing the electronic medical record includes:
carrying out structuring treatment on the electronic medical record to obtain an entity name;
and (5) carrying out data cleaning on the structured data.
Optionally, in the above method for extracting a patient health time axis based on electronic medical records, the target fields include, but are not limited to:
a combination of one or more of a symptom field, an examination field, a test field, a disease field, a surgery field, a radiation therapy field, and a chemotherapy field.
Optionally, in the above method for extracting a patient health time axis based on electronic medical records, obtaining the electronic medical record of the target patient includes:
acquiring an inpatient medical record document and an outpatient medical record document of a target patient;
the medical record document for hospitalization comprises: admission records, check reports, pathology reports, inspection reports, surgical records and orders; the outpatient medical record document comprises: outpatient medical records, outpatient orders, outpatient inspection reports, and outpatient inspection reports.
Optionally, in the above method for extracting a patient health time axis based on an electronic medical record, before determining whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history medical record, the method further includes:
judging whether a first target field and a second target field with the same entity time exist in the candidate health time axis, if so, judging whether the entities in the first target field and the second target field are the same, if so, removing the redundant first target field or the second target field, and if so, adding the entity and the entity related content of the first target field into the second target field.
An electronic medical record-based extraction device for a patient health timeline, comprising:
the data acquisition unit is used for acquiring an electronic medical record of the target patient;
the data processing unit is used for preprocessing the electronic medical record, extracting a target field from the preprocessed electronic medical record and carrying out standardization processing on an entity and entity time in the target field;
a candidate health time axis establishing unit, configured to establish a patient health time axis based on the target field, and record the patient health time axis as a candidate health time axis;
and the candidate health time axis optimizing unit is used for acquiring the historical medical record of the target patient, judging whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the historical medical record, if so, replacing the entity name in the candidate patient health time axis by the entity name in the historical medical record, and outputting the candidate patient health time axis after replacing the entity name as the target health time axis.
Optionally, in the above extraction device for a patient health time axis based on an electronic medical record, when the data processing unit performs preprocessing on the electronic medical record, the data processing unit is specifically configured to:
carrying out structuring treatment on the electronic medical record to obtain an entity name;
and (5) carrying out data cleaning on the structured data.
Optionally, in the above extraction device for a patient health time axis based on electronic medical records, the data processing unit extracts a target field from the preprocessed electronic medical records, and is specifically configured to:
extracting one or more of a symptom field, an examination field, a test field, a disease field, a surgery field, a radiotherapy field, and a chemotherapy field from the preprocessed electronic medical record.
Optionally, in the above extraction device for a patient health time axis based on electronic medical records, the data acquisition unit acquires an electronic duration of a target patient, and is specifically configured to:
acquiring an inpatient medical record document and an outpatient medical record document of a target patient from a medical record database;
the medical record document for hospitalization comprises: admission records, check reports, pathology reports, inspection reports, surgical records and orders; the outpatient medical record document comprises: outpatient medical records, outpatient orders, outpatient inspection reports, and outpatient inspection reports.
Optionally, in the above extraction device for a patient health time axis based on an electronic medical record, before determining whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history medical record, the method further includes:
judging whether a first target field and a second target field with the same entity time exist in the candidate health time axis, if so, judging whether the entities in the first target field and the second target field are the same, if so, removing the redundant first target field or the second target field, and if so, adding the entity and the entity related content of the first target field into the second target field.
Based on the technical scheme, the electronic medical record of the target patient is obtained through the scheme provided by the embodiment of the invention; preprocessing the electronic medical record; extracting a target field from the preprocessed electronic medical record; establishing a patient health time axis based on the target field, and marking the patient health time axis as a candidate health time axis; acquiring a history of the target patient; judging whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history medical record, and if so, replacing the entity name in the candidate patient health time axis by the entity name in the history medical record; and outputting the candidate patient health time axis after the entity name is replaced as a target health time axis, so that the patient health time axis is rapidly generated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for extracting a patient health time axis based on an electronic medical record according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for extracting a patient health timeline based on an electronic medical record according to another embodiment of the present application;
fig. 3 is a schematic structural diagram of an extraction device for a patient health time axis based on an electronic medical record according to an embodiment of the disclosure.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The application provides a method and a device for extracting a health time axis of a patient, wherein the health time axis can be rapidly extracted according to an electronic medical record.
Referring to fig. 1, an embodiment of the present application provides a method for extracting a patient health time axis based on an electronic medical record, including:
step S101: acquiring an electronic medical record of a target patient;
electronic Medical Records (EMR) are also known as computerized medical records systems or computer-based patient records. It is a digitized medical record stored, managed, transmitted and reproduced by electronic equipment (computer, health card, etc.) to replace handwriting paper medical record. Its contents include all information of the paper medical record. The electronic medical record system provides the ability for users to access complete and accurate data, alerts, prompts, and clinical decision support systems.
In this scheme, the electronic medical record of the patient refers to a medical record document stored in an electronic version, and the medical record document may include an inpatient medical record document and an outpatient medical record document, where the inpatient medical record document includes: admission records, check reports, pathology reports, inspection reports, surgical records and orders; the outpatient medical record document comprises: outpatient medical records, outpatient orders, outpatient inspection reports, and outpatient inspection reports.
The electronic duration of the target patient can be acquired by a local database of a hospital or by a cloud database, wherein the cloud database can be associated with a medical record database of any registered medical institution;
step S102: preprocessing the electronic medical record;
in this scheme, the preprocessing may refer to performing structural processing on the electronic medical record to obtain an entity name; and (5) carrying out data cleaning on the structured data.
The preprocessing action can be realized through a medical record model, and after the electronic record of the target patient is acquired, the electronic record can be preprocessed through the medical record model. The medical record using model is based on electronic medical record data, the electronic medical record data is stored according to a defined structure according to a structured data structure defined by an applicable scene, and the structure of the electronic medical record after the structure storage can be shown in a table 1.
TABLE 1
For example, the electronic medical record data of the target patient is: the patient is characterized in that the patient can feel squeeze-like pain behind the sternum after walking more than 2 years before being admitted, the patient can bear the pain, the patient can take a rest for about 10 minutes and can relieve the pain by self, palpitation, dyspnea, cold sweat, heavy sweat, dizziness, black , syncope, epigastric discomfort, nausea, vomiting and the like, the symptoms of the last complaint are intermittently started and are gradually aggravated in the period of 1 month, about 1-3 times a day, the duration is prolonged, the patient can take the pain for 20 minutes at most, the patient can diagnose unstable angina at An Zhen hospitals, the patient can take an LM (-) after coronary angiography examination, the long lesion at the far end in LAD (LAD) has the maximum of 70-80% of stenosis, the long lesion at the far end of LCX has the maximum of 80% of stenosis, the irregular branch after RCA (RCA) has the opening of 80% of stenosis, the stent is implanted at the far end of LCX, the postoperative regular coronary heart disease is treated in a second-stage prevention, the chest pain is not reoccurring, and the patient is stopped after 1 year. The pain is squeezed from the back of sternum after 7 months before the activity, the property, duration and relieving mode are the same, the chest pain is repeatedly caused during the activity for 1-3 times a day, and the duration is 5-20 minutes different, and the nitroglycerin can be relieved after the administration. For further diagnosis and treatment, the patient is admitted with unstable angina pectoris. Since the onset of the disease, the patients have good spirit, good sleep, good appetite, no abnormal urine, normal urine volume, no abnormal stool and no obvious change of body weight. ".
And adopting the medical record model to change the medical record data after the medical record data is structured into:
the structured medical record data can be displayed in a list form;
when the electronic medical record is preprocessed, the electronic medical record can be cleaned besides being subjected to structural processing; the cleaning refers to cleaning redundant data in the electronic medical record, and of course, the medical record model may also be used to perform normalization processing on entities and time nodes in the electronic medical record, where the normalization processing refers to: based on the entity synonym library of medical treatment and the medical record model, the medical record data after the structuring treatment is cleaned and standardized, and the following table 2 is the medical record data before and after cleaning and marking a patient:
the different entity names used for representing the same meaning in the structured medical record data are integrated into the same entity name, wherein the entity refers to a medical entity, and the medical entity: for things that are apparent in medicine and can be distinguished from each other, common medical entities include symptoms, diseases, examination, surgery, medicines, and the like.
For example, referring to Table 2, the previous column of cleaning, normalization is used to characterize the name representation of the medical entity before cleaning, normalization, the subsequent column of cleaning, normalization is used to characterize the name representation of the medical entity after cleaning, normalization,
TABLE 2
| Before cleaning and standardization | After cleaning and standardization |
| Hypertension of the type | Hypertension of the type |
| Hypertension disease | Hypertension of the type |
| Is hypertension? | Hypertension of the type |
| Coronary atherosclerotic heart disease | Coronary atherosclerotic heart disease |
| Coronary heart disease | Coronary atherosclerotic heart disease |
| Coronary atherosclerotic heart disease | Coronary atherosclerotic heart disease |
| Is coronary heart disease? | Coronary atherosclerotic heart disease |
In addition to the cleaning and standardization processing of the medical entity in the structured medical record data, the cleaning and standardization processing of the time node in the structured medical record data can be performed, when the processing is performed, the regular expression is used for standardization processing of the time node, different time expression modes are identified in a unified manner, as shown in the following table 2, the original time node in the table 2 is the expression form of the time node before standardization, and the time after standardization is the expression form of the time node after standardization processing.
TABLE 2
Step S103: extracting a target field from the preprocessed electronic medical record;
in this scenario, the target field may include seven major classes: the symptom field, the examination field, the disease field, the operation field, the radiotherapy field and the chemotherapy field can adopt a medical classification word stock to judge each field in the electronic medical record, and judge whether the fields belong to the symptom field, the examination field, the disease field, the operation field, the radiotherapy field or the chemotherapy field; when designing, one or more fields in the fields can be selected as target fields in the application according to requirements, and the health condition of a user can be represented through the target fields;
step S104: establishing a patient health time axis based on the target field, and marking the patient health time axis as a candidate health time axis;
after the target point is determined, extracting the medical entity in the target field and the entity time corresponding to the medical entity, and establishing a health time axis of the target patient, wherein the historical change condition of the physical health condition of the target patient can be displayed through the health time axis.
Step S105: acquiring a history of the target patient;
in this step, considering that the expression form of the medical entity after normalization may not be more intuitive than the expression form of the medical entity in the history, the medical entity in the history may be adopted for the medical entity after normalization in the candidate health timeline; the processing mode preferentially reserves objective medical records for treatment, not only reserves complete patient information, but also ensures the accuracy of the patient information, and provides effective basis for clinical judgment.
Based on the above objects, in this step, after the candidate health time axis is acquired, a history of the target patient is also required to be acquired;
step S106: judging whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history, and if so, executing step S107;
in this step, based on the entity in the candidate health time axis and the entity time corresponding to the entity, determining the entity with the same characterization object as the entity in the candidate health time axis and the entity time corresponding to the entity in the history, judging whether the description form of the entity in the candidate health time axis is the same as the description form of the entity in the history, if so, continuing to traverse other entities and entity times in the candidate health time axis, and if not, executing step S107; in this step, if the two entities represent the same object, it indicates that the two entities are corresponding, and in this scheme, whether the two entities represent the same object can be judged by a preset medical entity hyponym library, for example, about the entity name: coronary heart disease, coronary atherosclerosis heart disease, these three entity names are different, but all correspond to the same medical entity, namely: the method can be used for inquiring whether the entity corresponding to the entity in the candidate health time axis and the entity time exists in the history medical record or not through a near-meaning word library, and the entity name in the history medical record is used for replacing the corresponding entity name in the candidate health time axis due to more objectivity and description thereof.
Step S107: replacing entity names in the candidate patient health time axis with entity names in the history;
step S108: and outputting the candidate patient health time axis after the entity name is replaced as a target health time axis.
Further, in the technical solution disclosed in the embodiments of the present application, referring to fig. 2, in order to simplify the target health time axis, after the candidate health time axis is obtained, the following operations may be further performed:
step S201: judging whether a first target field and a second target field with the same entity time exist in the candidate health time axis, and if so, executing step S202;
the technical solution disclosed in this embodiment aims at removing redundant data in the candidate health time axis, and in this step, if some fields in the candidate health time axis have the same entity time, the fields are considered to have redundant data;
step S202: judging whether the entities in the first target field and the second target field are the same, if so, executing step S203, and if not, executing step S204;
if the entities in the first target field and the second target field are the same, it indicates that the two fields express the same event, and therefore, step S203 needs to be performed to remove one of the fields;
step S203: removing redundant first target fields or second target fields;
step S204: adding the entity of the first target field and the entity related content into the second target field;
if the entity time of the first target field is the same as the entity time of the second target field and the entity time of the second target field is different, redundant data exists in the entity time of the first target field and the entity time of the second target field, so that the two fields can be combined into one field, the combined fields share one entity time, the entity and the entity related content of the first target field can be added to the second target field, and the entity related content of the second target field can be added to the first target field.
The embodiment also discloses a device for extracting the patient health time axis based on the electronic medical record, and specific working contents of each unit are referred to in the embodiment of the method.
The device for extracting the patient health time axis based on the electronic medical record provided by the embodiment of the invention is described below, and the device for extracting the patient health time axis based on the electronic medical record described below and the method for extracting the patient health time axis based on the electronic medical record described above can be referred to correspondingly.
Referring to fig. 3, an extraction device for a patient health time axis based on an electronic medical record according to an embodiment of the present application includes:
a data acquisition unit 100, corresponding to step S101 in the above method, for acquiring an electronic medical record of the target patient;
a data processing unit 200, corresponding to steps S102 and S103 in the above method, for preprocessing the electronic medical record, and extracting a target field from the preprocessed electronic medical record;
a candidate health timeline creation unit 300, corresponding to step S104 in the above method, for creating a patient health timeline based on the target field, denoted as a candidate health timeline;
and a candidate health time axis optimizing unit 400, corresponding to steps S105-S108 in the above method, configured to obtain a history of the target patient, determine whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history, and if so, replace the entity name in the candidate patient health time axis with the entity name in the history, and output the candidate patient health time axis after replacing the entity name as the target health time axis.
Corresponding to the above method embodiment, when the data processing unit preprocesses the electronic medical record, the data processing unit is specifically configured to:
carrying out structuring treatment on the electronic medical record to obtain an entity name;
carrying out data cleaning on the structured data;
and normalizing the entity and the entity time in the target field.
Corresponding to the above method embodiment, the data processing unit extracts the target field from the preprocessed electronic medical record, specifically for:
extracting one or more of a symptom field, an examination field, a test field, a disease field, a surgery field, a radiotherapy field, and a chemotherapy field from the preprocessed electronic medical record.
Corresponding to the above method embodiment, the data acquisition unit acquires an electronic duration of the target patient, specifically for:
acquiring an inpatient medical record document and an outpatient medical record document of a target patient from a medical record database;
the medical record document for hospitalization comprises: admission records, check reports, pathology reports, inspection reports, surgical records and orders; the outpatient medical record document comprises: outpatient medical records, outpatient orders, outpatient inspection reports, and outpatient inspection reports.
Corresponding to the above method embodiment, before determining whether the historical medical record includes the entity corresponding to the entity and the entity time in the candidate health time axis, the method further includes:
judging whether a first target field and a second target field with the same entity time exist in the candidate health time axis, if so, judging whether the entities in the first target field and the second target field are the same, if so, removing the redundant first target field or the second target field, and if so, adding the entity and the entity related content of the first target field into the second target field.
For convenience of description, the above system is described as being functionally divided into various modules, respectively. Of course, the functions of each module may be implemented in the same piece or pieces of software and/or hardware when implementing the present invention.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The extraction method of the patient health time axis based on the electronic medical record is characterized by comprising the following steps of:
acquiring an electronic medical record of a target patient;
preprocessing the electronic medical record;
extracting a target field from the preprocessed electronic medical record;
establishing a patient health time axis based on the target field, and marking the patient health time axis as a candidate health time axis;
acquiring a history of the target patient;
judging whether an entity corresponding to the entity and the entity time in the candidate health time axis exists in the history medical record, and if so, replacing the entity name in the candidate health time axis by the entity name in the history medical record;
outputting the candidate health time axis after the entity name is replaced as a target health time axis;
before judging whether the entity corresponding to the entity and the entity time in the candidate health time axis exists in the history, the method further comprises:
judging whether a first target field and a second target field with the same entity time exist in the candidate health time axis, if so, judging whether the entities in the first target field and the second target field are the same, if so, removing the redundant first target field or the second target field, and if so, adding the entity and the entity related content of the first target field into the second target field.
2. The method for extracting a patient health timeline based on an electronic medical record according to claim 1, wherein preprocessing the electronic medical record comprises:
carrying out structuring treatment on the electronic medical record to obtain an entity name;
cleaning the nonstandard data in the electronic medical record;
and normalizing the entity and the entity time in the target field.
3. The method for extracting a patient health timeline based on electronic medical records according to claim 1, wherein the target fields include, but are not limited to:
a combination of one or more of a symptom field, an examination field, a test field, a disease field, a surgery field, a radiation therapy field, and a chemotherapy field.
4. The method for extracting a patient health timeline based on an electronic medical record according to claim 1, wherein obtaining the electronic medical record of the target patient comprises:
acquiring an inpatient medical record document and an outpatient medical record document of a target patient;
the medical record document for hospitalization comprises: admission records, check reports, pathology reports, inspection reports, surgical records and orders; the outpatient medical record document comprises: outpatient medical records, outpatient orders, outpatient inspection reports, and outpatient inspection reports.
5. An extraction device of patient's health time axis based on electronic medical record, characterized by comprising:
the data acquisition unit is used for acquiring an electronic medical record of the target patient;
the data processing unit is used for preprocessing the electronic medical record and extracting target fields from the preprocessed electronic medical record;
a candidate health time axis establishing unit, configured to establish a patient health time axis based on the target field, and record the patient health time axis as a candidate health time axis;
a candidate health time axis optimizing unit, configured to obtain a history medical record of the target patient, determine whether an entity corresponding to an entity and an entity time in the candidate health time axis exists in the history medical record, and if so, replace an entity name in the candidate health time axis with an entity name in the history medical record, and output a candidate health time axis after replacing the entity name as a target health time axis;
before judging whether the entity corresponding to the entity and the entity time in the candidate health time axis exists in the history, the method further comprises:
judging whether a first target field and a second target field with the same entity time exist in the candidate health time axis, if so, judging whether the entities in the first target field and the second target field are the same, if so, removing the redundant first target field or the second target field, and if so, adding the entity and the entity related content of the first target field into the second target field.
6. The electronic medical record-based patient health timeline extraction apparatus of claim 5, wherein when said electronic medical record is preprocessed by a data processing unit, said data processing unit is specifically configured to:
carrying out structuring treatment on the electronic medical record to obtain an entity name;
carrying out data cleaning on the structured data;
and normalizing the entity and the entity time in the target field.
7. The extraction device of the patient health time axis based on the electronic medical record according to claim 5, wherein the data processing unit is configured to extract a target field from the preprocessed electronic medical record, specifically:
extracting one or more of a symptom field, an examination field, a test field, a disease field, a surgery field, a radiotherapy field, and a chemotherapy field from the preprocessed electronic medical record.
8. The electronic medical record-based patient health timeline extraction device of claim 5, wherein the data acquisition unit acquires an electronic medical duration of a target patient, in particular for:
acquiring an inpatient medical record document and an outpatient medical record document of a target patient from a medical record database;
the medical record document for hospitalization comprises: admission records, check reports, pathology reports, inspection reports, surgical records and orders; the outpatient medical record document comprises: outpatient medical records, outpatient orders, outpatient inspection reports, and outpatient inspection reports.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011252500.6A CN112259183B (en) | 2020-11-11 | 2020-11-11 | Method and device for extracting patient health time axis based on electronic medical record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011252500.6A CN112259183B (en) | 2020-11-11 | 2020-11-11 | Method and device for extracting patient health time axis based on electronic medical record |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112259183A CN112259183A (en) | 2021-01-22 |
| CN112259183B true CN112259183B (en) | 2023-08-08 |
Family
ID=74265177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011252500.6A Active CN112259183B (en) | 2020-11-11 | 2020-11-11 | Method and device for extracting patient health time axis based on electronic medical record |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112259183B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116206774B (en) * | 2023-04-27 | 2023-07-14 | 深圳市浩然盈科通讯科技有限公司 | Method and system for automatically matching nursing treatment scheme by combining big data |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000048109A (en) * | 1999-06-04 | 2000-02-18 | Kameda Iryo Joho Kenkyusho:Kk | Medical care plan preparation supporting system and machine-readable medium having recorded program thereon |
| CN1288206A (en) * | 1999-09-10 | 2001-03-21 | 株式会社龟田医疗情报研究所 | Auxiliary system used for making medical schedule, and readable program storage device therefor |
| CN1604111A (en) * | 1997-03-13 | 2005-04-06 | 第一咨询公司 | Disease management system and method including correlation assessment |
| JP2014191511A (en) * | 2013-03-26 | 2014-10-06 | Fujitsu Fsas Inc | Document recording creation support device and document recording creation support program |
| CN105427217A (en) * | 2014-12-17 | 2016-03-23 | 伊斯雷尔·巴肯 | Interactive image electronic medical treatment research and management system |
| WO2016061589A1 (en) * | 2014-10-17 | 2016-04-21 | G-Tech Medical, Inc. | Systems and methods for processing electromyographic signals of the gastrointestinal tract |
| CN107887036A (en) * | 2017-11-09 | 2018-04-06 | 北京纽伦智能科技有限公司 | Construction method, device and the clinical decision accessory system of clinical decision accessory system |
| CN109493934A (en) * | 2018-11-09 | 2019-03-19 | 医渡云（北京）技术有限公司 | Data processing method, device and medium |
| CN110277149A (en) * | 2019-06-28 | 2019-09-24 | 北京百度网讯科技有限公司 | Processing method, device and the equipment of electronic health record |
| CN110444259A (en) * | 2019-06-06 | 2019-11-12 | 昆明理工大学 | Traditional Chinese medical electronic case history entity relationship extracting method based on entity relationship mark strategy |
| CN110634546A (en) * | 2019-08-14 | 2019-12-31 | 中国科学院苏州生物医学工程技术研究所 | Electronic medical record text standardization detection method |
| CN111292821A (en) * | 2020-01-21 | 2020-06-16 | 上海联影智能医疗科技有限公司 | Medical diagnosis and treatment system |
| CN111400529A (en) * | 2020-04-14 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Data processing method and device |
| CN111429989A (en) * | 2020-04-21 | 2020-07-17 | 北京嘉和海森健康科技有限公司 | Method and device for generating pre-diagnosis medical record |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160357914A1 (en) * | 2010-09-29 | 2016-12-08 | Humana Inc. | System and method for display and management of distributed electronic medical record data |
-
2020
- 2020-11-11 CN CN202011252500.6A patent/CN112259183B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1604111A (en) * | 1997-03-13 | 2005-04-06 | 第一咨询公司 | Disease management system and method including correlation assessment |
| JP2000048109A (en) * | 1999-06-04 | 2000-02-18 | Kameda Iryo Joho Kenkyusho:Kk | Medical care plan preparation supporting system and machine-readable medium having recorded program thereon |
| CN1288206A (en) * | 1999-09-10 | 2001-03-21 | 株式会社龟田医疗情报研究所 | Auxiliary system used for making medical schedule, and readable program storage device therefor |
| JP2014191511A (en) * | 2013-03-26 | 2014-10-06 | Fujitsu Fsas Inc | Document recording creation support device and document recording creation support program |
| WO2016061589A1 (en) * | 2014-10-17 | 2016-04-21 | G-Tech Medical, Inc. | Systems and methods for processing electromyographic signals of the gastrointestinal tract |
| CN105427217A (en) * | 2014-12-17 | 2016-03-23 | 伊斯雷尔·巴肯 | Interactive image electronic medical treatment research and management system |
| CN107887036A (en) * | 2017-11-09 | 2018-04-06 | 北京纽伦智能科技有限公司 | Construction method, device and the clinical decision accessory system of clinical decision accessory system |
| CN109493934A (en) * | 2018-11-09 | 2019-03-19 | 医渡云（北京）技术有限公司 | Data processing method, device and medium |
| CN110444259A (en) * | 2019-06-06 | 2019-11-12 | 昆明理工大学 | Traditional Chinese medical electronic case history entity relationship extracting method based on entity relationship mark strategy |
| CN110277149A (en) * | 2019-06-28 | 2019-09-24 | 北京百度网讯科技有限公司 | Processing method, device and the equipment of electronic health record |
| CN110634546A (en) * | 2019-08-14 | 2019-12-31 | 中国科学院苏州生物医学工程技术研究所 | Electronic medical record text standardization detection method |
| CN111292821A (en) * | 2020-01-21 | 2020-06-16 | 上海联影智能医疗科技有限公司 | Medical diagnosis and treatment system |
| CN111400529A (en) * | 2020-04-14 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Data processing method and device |
| CN111429989A (en) * | 2020-04-21 | 2020-07-17 | 北京嘉和海森健康科技有限公司 | Method and device for generating pre-diagnosis medical record |
Non-Patent Citations (1)
| Title |
|---|
| 基于命名实体识别的住院病历录入辅助系统的设计与实现;李山;《中国优秀硕士学位论文全文数据库 信息科技辑》;I138-83 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112259183A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7617078B2 (en) | Patient data mining | |
| JP6907831B2 (en) | Context-based patient similarity methods and equipment | |
| Solbiati et al. | Implantable loop recorder versus conventional diagnostic workup for unexplained recurrent syncope | |
| CN111429989B (en) | Method and device for generating pre-diagnosis medical record | |
| JP4866576B2 (en) | Medical support system | |
| Anderson et al. | Standardized cardiovascular data for clinical research, registries, and patient care: a report from the Data Standards Workgroup of the National Cardiovascular Research Infrastructure project | |
| CN112259183B (en) | Method and device for extracting patient health time axis based on electronic medical record | |
| CN114048343A (en) | Classification platform covering medical image information of patients in whole disease course | |
| CN112201350A (en) | Intelligent triage method and device and electronic equipment | |
| US9978165B2 (en) | Dynamic presentation of waveform tracings in a central monitor perspective | |
| Chiang et al. | Electronic clinical decision support tool for the evaluation of cardiovascular risk in general practice: a pilot study | |
| CN112992366A (en) | ICD (identity control document) code artificial intelligence audit quality control mode and system based on medical insurance disease payment system | |
| CN107066816B (en) | Medical treatment guidance method and device based on clinical data and server | |
| Ahsan et al. | Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges | |
| US20230377697A1 (en) | System and a way to automatically monitor clinical trials - virtual monitor (vm) and a way to record medical history | |
| Akmaz et al. | Developing process measures in value-based healthcare: the case of aortic valve disease | |
| CN105205334A (en) | Doctor-patient data processing method | |
| CN115295110A (en) | Postoperative complication prediction system and method | |
| JP5203481B2 (en) | Disease management system | |
| Georgieva-Tsaneva | Effective information methods for description and storage of data in health care | |
| KR20180108671A (en) | Method and system for identifying diagnostic and treatment options for medical conditions using electronic health records | |
| Chung | Understanding decision making through complexity in professional networks | |
| CN112992371B (en) | Disease risk monitoring system and method | |
| Mhlanga et al. | Factors Influencing the Choice of Healthcare Providing Facility among Households in South Africa | |
| F. John et al. | Definition of low‐value care in a low‐risk preoperative population: A scoping review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |