CN114300083B - Medical record construction method and system - Google Patents
Medical record construction method and system Download PDFInfo
- Publication number
- CN114300083B CN114300083B CN202111356380.9A CN202111356380A CN114300083B CN 114300083 B CN114300083 B CN 114300083B CN 202111356380 A CN202111356380 A CN 202111356380A CN 114300083 B CN114300083 B CN 114300083B
- Authority
- CN
- China
- Prior art keywords
- medical
- medical record
- doctor
- similar
- records
- 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
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention provides a medical record construction method and system, and belongs to the field of intelligent medical treatment. The method comprises the following steps: acquiring doctor-patient conversation texts, and sorting the doctor-patient conversation texts into corresponding medical knowledge maps according to preset rules; performing relevancy retrieval in a pre-constructed medical record library according to the medical knowledge graph; screening out similar medical record sets with the relevance degrees larger than a preset threshold value, and screening out similar medical records with the highest relevance degrees in the similar medical record sets to serve as related similar medical records; pushing the related similar medical records to a doctor end, opening a modification function, and recovering the modified content of the doctor; and generating a new medical record based on the original content of the related similar medical record and the modified content of the doctor, and uploading the new medical record to the pre-constructed medical record library. The scheme of the invention reduces the time for a doctor to construct a medical record and ensures the efficiency of medical record construction on the premise of improving the accuracy of medical record construction.
Description
Technical Field
The invention relates to the field of intelligent medical treatment, in particular to a medical record construction method and a medical record construction system.
Background
In the existing medical record construction methods, there are two main methods. The first one is conventional doctor handwriting or input, which is a medical record arrangement based on the knowledge of personal habits of doctors through the inquiry process between doctors and patients, and the medical record arrangement method has the highest accuracy and is most close to the real situation of patients. Another method is to automatically generate the medical record, namely, the medical record of the patient is generated based on professional knowledge and a preset template according to the dialogue information between a doctor and the patient or the patient information acquired by an intelligent system. The method has fast processing efficiency, does not need doctors to manually process medical record arrangement, and has obvious significance for shortening medical treatment time and improving inquiry efficiency. However, the two methods have disadvantages of different degrees, and in the first method, because the arrangement process of the medical records needs the familiarity of doctors, the doctors inevitably spend a lot of time on the arrangement of the medical records, and although the method has a significant meaning for the storage of the files, the method further reduces the visit time of the doctors and affects the medical efficiency for the hospitals with deficient medical resources. Although the second method greatly improves the medical efficiency and frees the hands of doctors, the method has obvious disadvantages that the medical records generated according to the fixed template have poor flexibility, even if the patients with the same disease have different degrees of influence caused by different qualities, diseases can be distinguished, if the medical records are generated according to the fixed template, the differences of the patients cannot be effectively reflected, and the utilization value of the medical records is greatly reduced. Aiming at the defects of the existing medical record construction method, a new medical record construction method needs to be created.
Disclosure of Invention
The embodiment of the invention aims to provide a medical record construction method and a medical record construction system, which at least solve the problem that the existing medical record construction method cannot be compatible with efficiency and accuracy.
In order to achieve the above object, a first aspect of the present invention provides a medical record constructing method, including: acquiring doctor-patient conversation texts, and sorting the doctor-patient conversation texts into corresponding medical knowledge maps according to preset rules; performing relevancy retrieval in a pre-constructed medical record library according to the medical knowledge graph; screening out similar medical record sets with the association degrees larger than a preset threshold, and screening out similar medical records with the highest association degrees in the similar medical record sets as associated similar medical records; pushing the related similar medical records to a doctor end, opening a modification function, and recovering the modification content of the doctor; and generating a new medical record based on the original content of the associated similar medical record and the modified content of the doctor, and uploading the new medical record to the pre-constructed medical record library.
Optionally, the doctor-patient dialog text includes: acquiring text information of a doctor-patient voice inquiry process through a voice recognition algorithm; or text information of the voice inquiry process is acquired through the intelligent question-answering medical system; or inputting the text information of the question-answering process collected by the question-answering system.
Optionally, the collating the doctor-patient dialog text into a corresponding medical knowledge map according to a preset rule includes: carrying out semantic recognition on the doctor-patient conversation text according to a preset conversation structural model, and screening out feature words in the doctor-patient conversation text; and automatically dividing each characteristic word into corresponding medical knowledge map ranges according to the self attribute of each characteristic word.
Optionally, the attributes of the feature words include: self semantics, influence relationships and preset type labels.
Optionally, the medical knowledge-map scope includes: chief complaints, current medical history, past history, personal history, family history, and/or menstrual marriage and childbirth history.
Optionally, the screening out a similar medical record set with a relevancy greater than a preset threshold includes: taking each medical knowledge map range as a retrieval condition, and performing association degree retrieval in the pre-constructed medical record library to obtain an associated medical knowledge map range set corresponding to each medical knowledge map range; original medical records in each associated medical knowledge map range set are positioned, and the original medical records in each medical knowledge map range set are compared, and the original medical records are counted once when one same medical record exists; and counting the medical records with the technical times larger than the preset counting times to form a similar medical record set.
Optionally, the screening out the similar medical records with the highest relevance in the similar medical record set as the related similar medical records includes: setting weight for each medical knowledge map range in the medical knowledge maps according to preset rules; and performing overall association degree scoring according to the medical knowledge map range of the superposition of each similar medical record in the similar medical record sets and the medical knowledge map of the current patient, wherein the overall association degree scoring comprises the following steps: calculating the weight score of each overlapped medical knowledge map range, summing the weight scores of the overlapped medical knowledge map ranges in each similar medical record correspondingly, and taking the summed calculation result as the total association degree score; and comparing the overall association degree scores of all similar medical records, taking the similar medical record with the highest score as the similar medical record with the highest association degree, and taking the similar medical record as the associated similar medical record.
Optionally, the recommending the associated similar medical records to a doctor end and opening a modification function includes: pushing the related similar medical records to the equipment end of the doctor; identifying the medical knowledge map range of the associated similar medical record and the medical knowledge map of the current patient, and setting a selection opening button for the identified overlapping range; and for the medical knowledge map range which is not overlapped, directly opening a modification function and setting the modification function as a must-fill option.
A second aspect of the present invention provides a medical record constructing system, including: the acquisition unit is used for acquiring doctor-patient conversation texts; a processing unit to: the doctor-patient conversation texts are arranged into corresponding medical knowledge maps according to preset rules; performing relevancy retrieval in a pre-constructed medical record library according to the medical knowledge graph; screening out similar medical record sets with the relevance degrees larger than a preset threshold value, and screening out similar medical records with the highest relevance degrees in the similar medical record sets to serve as related similar medical records; the pushing unit is used for pushing the related similar medical records to a doctor end and opening a modification function; the acquisition unit is further configured to: recovering the modified content of the doctor; and the medical record sorting unit is used for generating a new medical record based on the original content of the associated similar medical record and the modified content of the doctor and uploading the new medical record to the pre-constructed medical record library.
In another aspect, the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the medical record constructing method described above.
Through the technical scheme, doctor-patient conversation information is collected and processed into conversation text information, then feature words are classified based on the text information to form a medical knowledge graph corresponding to a patient, retrieval is carried out in a pre-constructed medical record library based on the medical knowledge graph, related similar medical records are screened out, and then a doctor modifying function is provided on the basis of the related similar medical records. The time of a doctor for constructing the medical record is shortened, and the efficiency of medical record construction is ensured on the premise of improving the accuracy of medical record construction.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
FIG. 1 is a flowchart illustrating steps of a medical record constructing method according to an embodiment of the present invention;
fig. 2 is a system configuration diagram of a medical record constructing system according to an embodiment of the present invention.
Description of the reference numerals
10-an acquisition unit; 20-a processing unit; 30-pushing unit.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
Fig. 2 is a system configuration diagram of a medical record constructing system according to an embodiment of the present invention. As shown in fig. 2, an embodiment of the present invention provides a medical record constructing system, including: the acquisition unit is used for acquiring doctor-patient conversation texts; a processing unit to: arranging the doctor-patient conversation texts into corresponding medical knowledge maps according to preset rules; performing relevancy retrieval in a pre-constructed medical record library according to the medical knowledge graph; screening out similar medical record sets with the relevance degrees larger than a preset threshold value, and screening out similar medical records with the highest relevance degrees in the similar medical record sets to serve as related similar medical records; the pushing unit is used for pushing the related similar medical records to a doctor end and opening a modification function; the acquisition unit is further configured to: recovering the modified content of the doctor; and the medical record sorting unit is used for generating a new medical record based on the original content of the associated similar medical record and the modified content of the doctor and uploading the new medical record to the pre-constructed medical record library.
Fig. 1 is a flowchart of a method for constructing a medical record according to an embodiment of the present invention. As shown in fig. 1, an embodiment of the present invention provides a medical record constructing method, where the method includes:
step S10: and acquiring a doctor-patient conversation text, and sorting the doctor-patient conversation text into a corresponding medical knowledge map according to a preset rule.
Specifically, there are two main methods in the existing medical record construction method. The first one is conventional doctor handwriting or input, which is a medical record arrangement based on the knowledge of personal habits of doctors through the inquiry process between doctors and patients, and the medical record arrangement method has the highest accuracy and is most close to the real situation of patients. Another method is to automatically generate the medical record, namely, the medical record of the patient is generated based on professional knowledge and a preset template according to the dialogue information between a doctor and the patient or the patient information acquired by an intelligent system. The method has fast processing efficiency, does not need doctors to manually process medical record arrangement, and has obvious significance for shortening medical treatment time and improving inquiry efficiency. However, the two methods have disadvantages of different degrees, and in the first method, because the arrangement process of the medical records needs the familiarity of doctors, the doctors inevitably spend a lot of time on the arrangement of the medical records, which has significant meaning for the archive preservation, but for hospitals with scarce medical resources, the method further reduces the visit time of the doctors and affects the medical efficiency. Although the second method greatly improves the medical efficiency and frees the hands of doctors, the method has obvious disadvantages that the medical records generated according to the fixed template have poor flexibility, even if the patients with the same disease have different degrees of influence caused by different qualities, diseases can be distinguished, if the medical records are generated according to the fixed template, the differences of the patients cannot be effectively reflected, and the utilization value of the medical records is greatly reduced.
Therefore, in an ideal medical record construction method, the following conditions need to be satisfied: (1) The medical record sorting habits of doctors need to be known, and differential medical record sorting is carried out; (2) Differential medical record sorting is required to be carried out according to the actual condition of a patient, and unified template generation is refused; (3) The workload of doctors is reduced, and the condition that the doctors need to be in the right way in case history arrangement is avoided. The medical record management system is designed based on the centralized requirements, and the same doctors, departments and even hospitals have the medical record management habits of the doctors, departments and even hospitals. The medical record arrangement is carried out based on doctors, patients, hospitals or districts, wherein the medical record arrangement habit comprises differentiation. Then when the patient is received, according to the patient information of gathering, similar case history in the medical record storehouse can directly be drawed, wherein contained a large amount of the same information, only have some different places according to different patients, these places can be modified by the doctor, have embodied the differentiation of patient's condition simultaneously, have kept the specialization of case history, and the doctor only need carry out the data modification of the small part, its work load is for arranging from the beginning and reduce greatly, has also improved doctor's work efficiency.
To implement the above idea, the first step needs to acquire the dialogue information of the doctor and the patient, which includes the content that the medical records need to be collated. In conventional approaches, doctors perform self-judgment and arrangement according to dialogue information or perform content extraction according to a semantic recognition algorithm. Preferably, the present application also collects the voice dialogue information of the doctor and the patient directly or the text information collected by the inquiry system. The dialog information of the doctor and the patient is converted into text information by a speech recognition algorithm. The text information comprises the chief complaint information, the current medical history information, the past medical history information and the like of the patient, and the disease condition of the patient can be completely acquired by sorting the information. In order to classify the patient condition, the text information is divided according to types, each type corresponds to one medical knowledge map range, all medical knowledge map ranges are integrated, and a complete medical knowledge map for the patient is obtained. Preferably, the medical knowledge-map scope includes: chief complaints, current medical history, past history, personal history, family history, and/or menstrual marriage and childbirth history.
Firstly, carrying out doctor-patient dialogue text semantic recognition according to a preset dialogue structured model, and screening out feature words in the doctor-patient dialogue text semantic recognition. For example, doctor-patient dialog information is:
a doctor: where is uncomfortable?
The patients: the stomach begins to be dull and painful two days before, the stomach becomes more severe at last night, the stomach begins to prick, and the whole body does not have strength.
A doctor: has this been the case earlier?
The patients: the polyp operation on the stomach is performed two years ago, and the recurrence is not generated.
Through the medical conversation text information, the characteristic words are stomach, implicit pain, yesternight, aggravation, stabbing pain, whole body, no strength, stomach polyp operation and no recurrence. The characteristic words have strong characteristic orientations, and can be classified into different categories according to the respective meanings and simple screening algorithms. For example, implicit dull pain in the stomach, increased in the last night, stabbing pain, no strength of the whole body, and polyp operation in the stomach, no recurrence, which are determined by the associated weight, are the past information. According to the rule, feature words are extracted and classified from the complete doctor-patient communication text, and category labels are added to corresponding feature word attributes while classification is completed, so that word classification can be performed according to the labels subsequently. After all the value information is extracted, classifying according to the type label of each characteristic word to form each medical knowledge map range. All medical knowledge map ranges are integrated to form a complete medical knowledge map, and the current medical knowledge map is only used as a unit for forming a medical record and cannot be used as the medical record.
Step S20: and performing relevance retrieval in a pre-constructed medical record library according to the medical knowledge graph to obtain a relevant similar medical record.
Specifically, after the complete medical knowledge graph is obtained, similar medical records need to be screened based on the medical knowledge graph. The existing recommendation of similar medical records is to directly compare the similarity of two complete medical records and judge the similarity according to the matching degree. This method is not suitable for the present application because it presupposes a comparison of two complete medical records, i.e. a pre-generation of the medical record of the current patient is required to perform the similarity matching based on the current patient medical record. As is known above, the existing medical record generation method is mainly based on template generation, and cannot guarantee that the medical record is completely the same as the actual situation of the patient, so even if the degree of similarity matching is higher, it cannot be guaranteed that the acquired similar medical record is matched with the situation of the patient. The matching search is carried out based on the range of each medical treatment knowledge map, namely in a medical record library, all medical record contents are distinguished based on the range and then are matched one by one according to the range. That is, the chief complaint is matched with the chief complaint in the medical record library, and the past history is matched with the past history in the medical record library. And calculating the matching degree once each time one similarity matching is completed, and counting once when the matching degree is greater than a preset value. For example, if there are 50 medical records in the same medical records repository as the current patient complaint, 50 are counted and extracted, and then if there are 80 medical records matching the current medical history, 80 are calculated and extracted. And analogizing in turn, extracting the associated medical records in the range of all medical knowledge maps, for example, the number of the medical knowledge maps is 50, 80, 60, 70 and 100, integrating the medical records, counting 1 if a certain medical record is the same as the chief complaint of the current patient, counting 1 if the current medical history is the same, and adding 1 if the current medical history is the same, and analogizing in turn, obtaining the total count of the current similar medical records. Namely, the number of the repeated ranges of each preliminary screening medical record and the current patient is judged, and the more the repeated number is, the more the preliminary screening medical record and the current patient are approximately matched. Based on the above, count values of the medical records related in the above 50, 80, 60, 70 and 100 are respectively calculated, and then are respectively compared with preset count times, and similar medical records with times larger than a one-society technical time threshold value are reserved to form a similar medical record set. All medical records in the set of similar medical records have sufficient matching degree with the current patient, but further screening is needed to obtain the similar medical records closer to the current patient.
Preferably, after obtaining the similar medical record set, a medical record closer to the current patient needs to be found. For example, a similar medical record has many matching medical knowledge map ranges with a current patient, but the current patient has a gynecological disease, and the patient with the matched medical record is a male patient, even though the matching degree is high, the medical record is greatly different from the situation of the patient. This relates to matching ranges of weight values, i.e. patient-specific, disease-specific, the importance of which ranges are different. For example, gynecological diseases are highly weighted for gender, age diseases are highly weighted for age, and trauma patients are highly weighted for symptoms. Based on this, different departments can extract the corresponding needed weight, such as gynecology directly corresponding to sex weight and orthopedics directly corresponding to symptom weight. Based on the rule, the medical knowledge map range is subjected to weight setting based on the department hung by the patient or the specific marking condition, and then the association degree scoring is carried out based on the weight, wherein the higher the weight is, the larger the occupation ratio is. A weight score is calculated for each coincidence range and then the scores are added. For example, if there are 5 overlapping medical knowledge maps of a similar medical record and the current patient, the calculated association scores are 1.2, 3, 5, 2, and 7, respectively, and the final score is 18.2. And calculating the association score of each similar medical record in the similar medical record sets, then performing transverse comparison, and screening out the similar medical record with the highest score to obtain the final associated similar medical record.
Step S30: and pushing the related similar medical records to a doctor end, opening a modification function, and recovering the modification content of the doctor.
Specifically, after the associated similar medical records are found, the similar medical records have extremely high goodness of fit with the current patient, and the medical records of the current patient can be sorted only by modifying a small part of data. The similar medical records are pushed to the doctor end for the doctor to modify the small difference data. Preferably, because the data of the overlapping ranges are basically the same, the data are selectively modified, that is, if there is a small difference, but the doctor still feels that the modification is necessary, a selection modification button is provided, and the doctor triggers the modification. And for the range without superposition, the larger difference is shown, the modification function is opened, and the part of data is the data which needs to be modified, so that the situation that doctors play and guard to cause the part of data to be unmodified is avoided. And the doctor modifies the similar medical records according to the experience of the doctor and the content of the non-overlapped part of the binding push, so that the medical records become the medical records of the current patient.
Step S40: and generating a new medical record based on the original content of the associated similar medical record and the modified content of the doctor, and uploading the new medical record to the pre-constructed medical record library.
Specifically, after the system recovers the modified similar medical record, the modified content is written into the similar medical record, the previous data is replaced, then the medical record is used as the medical record of the current patient, the currently managed personal information is recorded, and the currently managed personal information is bound with the current patient. And then uploading the medical records to a medical record library, so that on one hand, the management of the medical records is improved, and on the other hand, the medical record library is continuously expanded so as to provide samples for subsequent similar medical record screening.
The embodiment of the invention also provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the medical record constructing method.
Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be implemented by a program, which is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps in 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.
While the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solution of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications are within the scope of the embodiments of the present invention. It should be noted that the various features described in the foregoing embodiments may be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not be described separately for the various possible combinations.
In addition, any combination of the various embodiments of the present invention is also possible, and the same should be considered as disclosed in the embodiments of the present invention as long as it does not depart from the spirit of the embodiments of the present invention.
Claims (7)
1. A medical record construction method is characterized by comprising the following steps:
acquiring a doctor-patient conversation text, performing semantic recognition on the doctor-patient conversation text according to a preset conversation structural model, and screening out feature words in the doctor-patient conversation text;
automatically dividing each characteristic word into corresponding medical knowledge map ranges according to the self attribute of each characteristic word;
performing relevancy retrieval in a pre-constructed medical record library according to the medical knowledge graph;
taking each medical knowledge map range as a retrieval condition, and performing association degree retrieval in the pre-constructed medical record library to obtain an associated medical knowledge map range set corresponding to each medical knowledge map range;
original medical records in each associated medical knowledge map range set are positioned, and the original medical records in each medical knowledge map range set are compared, and the original medical records are counted once when one same medical record exists;
counting medical records with the counting times larger than the preset counting times to form a similar medical record set;
screening out similar medical records with highest relevance in the similar medical record set as related similar medical records; the method comprises the following steps:
setting weight for each medical knowledge map range in the medical knowledge maps according to preset rules;
and performing overall association degree scoring according to the medical knowledge map range of the superposition of each similar medical record in the similar medical record sets and the medical knowledge map of the current patient, wherein the overall association degree scoring comprises the following steps:
calculating the weight score of each overlapped medical knowledge map range, summing the weight scores of the overlapped medical knowledge map ranges in each similar medical record correspondingly, and taking the summed calculation result as the total association degree score;
comparing the overall association degree scores of all similar medical records, taking the similar medical record with the highest score as the similar medical record with the highest association degree, and taking the similar medical record as the associated similar medical record;
pushing the related similar medical records to a doctor end, opening a modification function, and recovering the modified content of the doctor;
and generating a new medical record based on the original content of the related similar medical record and the modified content of the doctor, and uploading the new medical record to the pre-constructed medical record library.
2. The method of claim 1, wherein the doctor-patient dialog text comprises:
acquiring text information of a doctor-patient voice inquiry process through a voice recognition algorithm; or
Text information of a voice inquiry process is acquired through an intelligent question-answering medical system; or
And inputting the text information of the question answering process collected by the question answering system.
3. The method of claim 1, wherein the self-attribute of each feature word comprises:
self semantics, influence relationships and preset type labels.
4. The method of claim 1, wherein the medical knowledge-map scope comprises:
chief complaints, current medical history, past history, personal history, family history, and/or menstrual marriage and childbirth history.
5. The method of claim 1, wherein the pushing the related similar medical records to a doctor end and opening modification functions comprises:
pushing the related similar medical records to the equipment end of the doctor;
identifying the medical knowledge map range of the associated similar medical record and the medical knowledge map of the current patient, and setting a selection opening button for the identified overlapping range;
and for the medical knowledge map range which is not overlapped, directly opening a modification function and setting the modification function as a must-fill option.
6. A medical record construction system, the system comprising:
the acquisition unit is used for acquiring doctor-patient conversation texts;
a processing unit to:
carrying out semantic recognition on the doctor-patient conversation text according to a preset conversation structural model, and screening out feature words in the doctor-patient conversation text;
automatically dividing each characteristic word into corresponding medical knowledge map ranges according to the self attribute of each characteristic word;
performing relevancy retrieval in a pre-constructed medical record library according to the medical knowledge graph;
performing association degree retrieval on the medical knowledge graph in the pre-constructed medical record library by taking each medical knowledge graph range as a retrieval condition to obtain an associated medical knowledge graph range set corresponding to each medical knowledge graph range;
original medical records in each associated medical knowledge map range set are positioned, and the original medical records in each medical knowledge map range set are compared, and the original medical records are counted once when one same medical record exists;
counting the medical records with the counting times larger than the preset counting times to form a similar medical record set;
screening out similar medical records with highest relevance in the similar medical record set as related similar medical records; the method comprises the following steps:
setting weight for each medical knowledge graph range in the medical knowledge graphs according to preset rules;
and performing overall association degree scoring according to the medical knowledge map range of the superposition of each similar medical record in the similar medical record sets and the medical knowledge map of the current patient, wherein the overall association degree scoring comprises the following steps:
calculating the weight score of each overlapped medical knowledge map range, summing the weight scores of the overlapped medical knowledge map ranges in each similar medical record correspondingly, and taking the summed calculation result as the total association degree score;
comparing the overall association degree scores of all similar medical records, taking the similar medical record with the highest score as the similar medical record with the highest association degree, and taking the similar medical record as the associated similar medical record;
the pushing unit is used for pushing the related similar medical records to a doctor end and opening a modification function;
the acquisition unit is further configured to: recovering the modified content of the doctor;
and the medical record sorting unit is used for generating a new medical record based on the original content of the associated similar medical record and the modified content of the doctor and uploading the new medical record to the pre-constructed medical record library.
7. A computer-readable storage medium having instructions stored thereon, which when executed on a computer, cause the computer to perform the medical record construction method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111356380.9A CN114300083B (en) | 2021-11-16 | 2021-11-16 | Medical record construction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111356380.9A CN114300083B (en) | 2021-11-16 | 2021-11-16 | Medical record construction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114300083A CN114300083A (en) | 2022-04-08 |
| CN114300083B true CN114300083B (en) | 2022-10-18 |
Family
ID=80964542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111356380.9A Active CN114300083B (en) | 2021-11-16 | 2021-11-16 | Medical record construction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114300083B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108831559A (en) * | 2018-06-20 | 2018-11-16 | 清华大学 | A kind of Chinese electronic health record text analyzing method and system |
| CN112635011A (en) * | 2020-12-31 | 2021-04-09 | 北大医疗信息技术有限公司 | Disease diagnosis method, disease diagnosis system, and readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949759A (en) * | 2019-05-16 | 2020-11-17 | 北大医疗信息技术有限公司 | Method and system for retrieving medical record text similarity and computer equipment |
| CN111414393B (en) * | 2020-03-26 | 2021-02-23 | 湖南科创信息技术股份有限公司 | Semantic similar case retrieval method and equipment based on medical knowledge graph |
| US11755661B2 (en) * | 2020-03-31 | 2023-09-12 | Roche Molecular Systems, Inc. | Text entry assistance and conversion to structured medical data |
| CN111489821B (en) * | 2020-03-31 | 2021-02-02 | 宜昌市中心人民医院(三峡大学第一临床医学院、三峡大学附属中心人民医院) | Diagnostic group management system |
| CN112700831A (en) * | 2021-01-06 | 2021-04-23 | 北京左医科技有限公司 | Doctor auxiliary diagnosis method and system based on patient medical record information |
| CN112650860A (en) * | 2021-01-15 | 2021-04-13 | 科技谷（厦门）信息技术有限公司 | Intelligent electronic medical record retrieval system based on knowledge graph |
-
2021
- 2021-11-16 CN CN202111356380.9A patent/CN114300083B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108831559A (en) * | 2018-06-20 | 2018-11-16 | 清华大学 | A kind of Chinese electronic health record text analyzing method and system |
| CN112635011A (en) * | 2020-12-31 | 2021-04-09 | 北大医疗信息技术有限公司 | Disease diagnosis method, disease diagnosis system, and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114300083A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111414393B (en) | Semantic similar case retrieval method and equipment based on medical knowledge graph | |
| CN107731269B (en) | Disease coding method and system based on original diagnosis data and medical record file data | |
| CN107705839B (en) | Disease automatic coding method and system | |
| US6823331B1 (en) | Concept identification system and method for use in reducing and/or representing text content of an electronic document | |
| CN112183026B (en) | ICD (interface control document) encoding method and device, electronic device and storage medium | |
| CN110931128B (en) | Method, system and device for automatically identifying unsupervised symptoms of unstructured medical texts | |
| KR102298330B1 (en) | System for generating medical consultation summary and electronic medical record based on speech recognition and natural language processing algorithm | |
| CN113345577B (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| CN112241457A (en) | Event detection method for event of affair knowledge graph fused with extension features | |
| WO2022160454A1 (en) | Medical literature retrieval method and apparatus, electronic device, and storage medium | |
| CN116910172B (en) | Follow-up table generation method and system based on artificial intelligence | |
| CN114358001A (en) | Method for standardizing diagnosis result, and related device, equipment and storage medium thereof | |
| CN109087688B (en) | Patient information acquisition method, apparatus, computer device and storage medium | |
| WO2021120587A1 (en) | Method and apparatus for retina classification based on oct, computer device, and storage medium | |
| CN114330335A (en) | Keyword extraction method, device, equipment and storage medium | |
| CN116775897A (en) | Knowledge graph construction and query method and device, electronic equipment and storage medium | |
| CN111785383A (en) | Data processing method and related equipment | |
| CN110752027A (en) | Electronic medical record data pushing method and device, computer equipment and storage medium | |
| CN114678130A (en) | Standard rule based evaluation method, terminal equipment and storage medium | |
| CN114300083B (en) | Medical record construction method and system | |
| CN116108000B (en) | Medical data management query method | |
| CN116719840A (en) | Medical information pushing method based on post-medical-record structured processing | |
| CN110010231A (en) | A kind of data processing system and computer readable storage medium | |
| CN115841861A (en) | Similar medical record recommendation method and system | |
| CN115917528A (en) | Question inquiry device, method, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |