CN113223729A - Data processing method of medical data - Google Patents
Data processing method of medical data Download PDFInfo
- Publication number
- CN113223729A CN113223729A CN202110579970.1A CN202110579970A CN113223729A CN 113223729 A CN113223729 A CN 113223729A CN 202110579970 A CN202110579970 A CN 202110579970A CN 113223729 A CN113223729 A CN 113223729A
- Authority
- CN
- China
- Prior art keywords
- medical
- attribute
- target
- data
- value
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims description 15
- 201000010099 disease Diseases 0.000 description 16
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 16
- 208000024891 symptom Diseases 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 8
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioethics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a data processing method of medical data, which comprises the steps of selecting an actual medical text set associated with a first target medical ontology, and extracting a plurality of subsets from the actual medical text set G according to the grade of the first target medical ontologyAnd respectively taking each subset as a target subset and extracting attribute values meeting the conditions from the target subset as preset medical ontology attribute data, so that the accuracy of determining the preset medical ontology attribute data is improved.
Description
Technical Field
The invention relates to a computer technology, in particular to a data processing technology, and particularly relates to a data processing method of medical data.
Background
At present, a large amount of real medical text information, such as case information, operation information and the like, is recorded and stored in a hospital, the hospital has a large amount of medical data, and with the rapid growth of the medical data, medical related personnel need to know the existing medical data so as to enrich and perfect own medical knowledge, improve diagnosis and treatment level, or perform scientific research and teaching and the like.
For a medical ontology, for example, for a disease, different real medical texts record symptoms included in a plurality of diseases, and the symptoms included in the disease data in different real medical texts are different, so that whether a certain symptom is a symptom of the disease needs to be extracted, so that different symptoms are fused to obtain the symptom data of the disease. In the prior art, for example, in patent No. 201810645565.3, attribute data is obtained according to a target medical ontology and corresponding preset medical ontology attributes, and the preset medical ontology attribute data of the target medical ontology is determined according to attribute values in the attribute data and a related formula. However, in the technical solution described in this patent, the influence of the disease level on determining whether the attribute value is the preset medical ontology attribute data is not considered, so that symptoms existing only in severe cases cannot be accurately determined as the preset medical ontology attribute data, and the related probability calculation method in the prior art does not consider the influence caused by too small number of attribute values, for example, the total number of attribute values is too small and the value of the actual medical text associated with each attribute value is small, which may cause the calculated probability to be sufficiently large although the value is small, so that the attribute value that should not be determined as the preset medical ontology attribute data is determined as the preset medical ontology attribute data, and the calculation of the value in the prior art does not consider that the actual medical text may be associated with a plurality of target medical ontologies, so that the artifact that the value is sufficiently large. In view of the above problems in the prior art, no effective solution has been proposed.
Disclosure of Invention
In order to solve the technical problem, the invention provides a data processing method of medical data, which comprises the following steps: s1, selecting an actual medical text set G associated with the first target medical body from an actual medical text information base according to the first target medical body, wherein the set G comprises a plurality of actual medical texts; s2, extracting a plurality of subsets G from the actual medical text set G according to the grade of the first target medical ontology1,...,Gi,...,GnWhere 1 ≦ i ≦ n, n being the total number of levels of the first target medical ontology, subset G1To GnThe corresponding levels are sequentially increased; s3, according to the sub-set G1To GnRespectively taking each subset as a target subset and extracting attribute values meeting the conditions from the target subsets as preset medical ontology attribute data.
Preferably, in step S3, the extracting of the attribute values satisfying the condition from the target subset as the preset medical ontology attribute data includes the steps of: s31, extracting attribute data from each actual medical text in the target subset, wherein the attribute data comprise a plurality of attribute values and form an attribute value set Q; s32, removing attribute values belonging to a set P and a set Q from the set Q, wherein the set P is a preset medical ontology attribute data set; s33, sequentially taking each attribute value in the set Q as a candidate attribute value, calculating the numerical value of each actual medical text comprising the candidate attribute value, and accumulating the numerical values of all the actual medical texts comprising the candidate attribute value as the total number of the candidate attribute values; s34, determining the score of each attribute value in the set Q according to the calculated total numerical values; s35, determining the attribute value with the score larger than the target threshold value as preset medical ontology attribute data of the first target medical ontology, and storing the preset medical ontology attribute data in a preset medical ontology attribute data set P; wherein, the preset medical ontology attribute data set P is an empty set in the initial state.
Preferably, each actual medical text in the set G is taken as a target actual medical text, and the number NUM of target medical ontologies associated with the target actual medical text is obtainedjJ is more than or equal to 1 and less than or equal to m, and m is the total number of the actual medical texts in the set G.
Preferably, in step S33, each actual medical text k including the candidate attribute value has a numerical value ofWherein k is more than or equal to 1 and less than or equal to m.
Preferably, step S34 includes: if the total number u of attribute values in the set Q is greater than the predetermined total number, then the following steps are performed: calculating the probability of each attribute value in the set Q, whereinWherein PErIs a first probability, NE, of the r-th attribute value in the set QrFor the total value of the r-th attribute value in the set Q, NEvR is more than or equal to 1 and less than or equal to u, and v is more than or equal to 1 and less than or equal to u; based onCalculating the score of each attribute value in the set Q according to a combSUM method or a linear combination method by the calculated first probability of each attribute value in the set Q; if the total number u of attribute values in the set Q is less than the predetermined total number, then the following steps are performed: calculating a second probability for each attribute value in the set Q, whereinWherein the PFrProbability of the r-th attribute value in the set Q, NFrThe total value of the r attribute value in the set Q is NM, and the total number of the actual medical texts in the target subset is NM; calculating a score of each attribute value in the set Q according to a combSUM method or a linear combination method based on the calculated second probability of each attribute value in the set Q; .
Preferably, step S35 includes: if the total number u of attribute values in the set Q is greater than the predetermined total number, the target threshold is a first target threshold, which is a second target thresholdWherein MO istT is more than or equal to 1 and less than or equal to w; if the total number u of attribute values in the set Q is less than the predetermined total number, then the target threshold is a second target threshold that is a constant between 0.8 and 1.
According to the data processing method of medical data of the present invention, the grade of the disease is taken as the first consideration factor for determining the preset medical ontology attribute data, so that even if some attribute values appear only in the actual medical text of the disease under severe conditions, for example, the attribute values can be accurately determined as the preset medical ontology attribute data; the use of different probability calculation methods can overcome the influence caused by too small number of attribute values and small numerical value of the actual medical text associated with each attribute value, and avoid that the attribute values which are not determined as the preset medical ontology attribute data are determined as the preset medical ontology attribute data; in addition, the false image that the numerical value is large enough because the fact that the actual medical text is possibly associated with a plurality of target medical ontologies is not considered in the numerical value calculation in the prior art is overcome, and the accuracy of determining the attribute data of the preset medical ontology is improved. Other problems addressed by the present invention will be described in detail in the detailed description section.
Drawings
Fig. 1 shows a flow chart of a data processing method of medical data according to a preferred embodiment of the present invention.
Detailed Description
As shown in fig. 1, in order to solve the above technical problem, the present invention provides a data processing method of medical data, comprising the following steps:
step S1, selecting an actual medical text set G associated with the first target medical ontology from the actual medical text information base according to the first target medical ontology, wherein the set G comprises a plurality of actual medical texts. The actual medical text information base comprises actual medical texts from different hospitals, data specifications are already carried out when the actual medical texts are stored in the actual medical text information base, and expressions of related terms are unified, for example, the terms expressions in the different actual medical texts are unified according to medical ontology dictionary specifications. The present invention is mainly directed to the case where the target medical ontology is the target disease, and therefore all the actual medical texts in the set G in step S1 are associated with the first target medical ontology.
Step S2, extracting a plurality of subsets G from the actual medical text set G according to the grade of the first target medical ontology1,...,Gi,...,GnWhere 1 ≦ i ≦ n, n being the total number of levels of the first target medical ontology, subset G1To GnThe corresponding levels are successively higher. In this step, the set G is divided into a plurality of subsets G according to the level of the first target medical ontology1,...,Gi,...,GnFor example, if the disease a includes three grades of mild, moderate, and severe, the set G is divided into three subsets, and the total number of actual medical texts included in the three subsets is equal to the total number of actual medical texts in the set G. By dividing the set G according to the grade of the first target medical ontology, the subsequent step-by-step determination of actual medical texts with different grades is facilitatedThe preset medical ontology attribute data is determined so as to avoid the situation that the preset medical ontology attribute data is mistakenly excluded from the attribute values only in the medium disease or the severe disease under the condition of not dividing.
Step S3, according to the sub-set G1To GnRespectively taking each subset as a target subset and extracting attribute values meeting the conditions from the target subsets as preset medical ontology attribute data. Due to the subset G1To GnThe corresponding levels are successively higher, e.g. G1Mild disease, G2Is the middle disease, G3Since some symptoms occur only in the case of severe cases or moderate cases, the preset medical ontology attribute data is determined from, for example, a subset corresponding to mild cases.
In the present invention, in step S3, extracting an attribute value satisfying a condition from the target subset as preset medical ontology attribute data includes the steps of:
step S31, extracting attribute data from each actual medical text in the target subset, the attribute data comprising a plurality of attribute values and forming a set of attribute values Q. In the present invention, attribute data is specific to symptoms, that is, all data about symptoms are extracted from each actual medical text of the target subset, and the attribute data includes a plurality of attribute values, for example, symptom q1、q2、q3Etc., and from these symptoms constitute a set of attribute values Q.
And step S32, removing the attribute values belonging to a set P and belonging to a set Q from the set Q, wherein the set P is a preset medical ontology attribute data set. Wherein, the preset medical ontology attribute data set P is an empty set in the initial state. This step is to follow the subset G1After the preset medical ontology attribute data is extracted, the subset G is prevented from being subsequently processed2、G3The preset medical ontology attribute data extracted in isochronous mode is still extracted again as an attribute value, and the situation that other attribute values which should belong to the preset medical ontology attribute data are not extracted in error can be influenced occurs. It should be understood that in processing subset G1The medical ontology attribute data set P is preset to be an empty set.
And step S33, sequentially taking each attribute value in the set Q as a candidate attribute value, calculating the numerical value of each actual medical text comprising the candidate attribute value, and accumulating the numerical values of all the actual medical texts comprising the candidate attribute value as the total value of the candidate attribute value. In the invention, the numerical value of each actual medical text including the candidate attribute value is calculated firstly, and then the total value of the numerical values of all the actual medical texts including the candidate attribute value is accumulated to be used as the basis of the subsequent probability calculation and the like, so that when the actual medical texts also correspond to other target medical bodies different from the first target medical body, the actual total numerical value of the actual medical texts can be reduced, the influence generated by other target medical bodies is reduced, and the final extraction of the preset medical body attribute data is more accurate.
Step S34, determining the score of each attribute value in the set Q according to the calculated plurality of total numerical values. The score is calculated based on the probability of the attribute values, which is calculated based on the total number of attribute values.
Step S35, determining the attribute value with the score larger than the target threshold value as the preset medical ontology attribute data of the first target medical ontology, and saving the attribute value in the preset medical ontology attribute data set P. And determining whether the attribute value is the preset medical ontology attribute data of the first target medical ontology according to the comparison between the score of the attribute value calculated in the step 34 and the target threshold, wherein if the attribute value of which the score is greater than the target threshold is considered to meet the condition of the preset medical ontology attribute data of the first target medical ontology, the attribute value is determined as the preset medical ontology attribute data of the first target medical ontology, and the attribute value is stored in the preset medical ontology attribute data set P.
In the invention, the method also comprises the following steps of taking each actual medical text in the set G as a target actual medical text, and obtaining the target actual medical textNumber NUM of target medical ontologies associated with inter-medical textjJ is more than or equal to 1 and less than or equal to m, and m is the total number of the actual medical texts in the set G. The target medical ontology associated with the target actual medical text comprises a first target medical ontology and other target medical ontologies.
In the present invention, in step S33, each of the actual medical texts k including the candidate attribute values has a numerical value ofWhere 1 ≦ k ≦ m, that is, the more target medical ontologies associated with the same actual medical text that includes the candidate attribute value, the smaller the value of the candidate attribute value. Step S34 includes: if the total number u of attribute values in the set Q is greater than the predetermined total number, then the following steps are performed: calculating the probability of each attribute value in the set Q, whereinWherein PErIs a first probability, NE, of the r-th attribute value in the set QrFor the total value of the r-th attribute value in the set Q, NEvR is more than or equal to 1 and less than or equal to u, and v is more than or equal to 1 and less than or equal to u; and calculating the score of each attribute value in the set Q according to a combSUM method or a linear combination method based on the calculated first probability of each attribute value in the set Q. If the total number u of attribute values in the set Q is less than the predetermined total number, then the following steps are performed: calculating a second probability for each attribute value in the set Q, whereinWherein the PFrProbability of the r-th attribute value in the set Q, NFrThe total value of the r attribute value in the set Q is NM, and the total number of the actual medical texts in the target subset is NM; and calculating the score of each attribute value in the set Q according to a combSUM method or a linear combination method based on the calculated second probability of each attribute value in the set Q. The predetermined total number is, for example, 3, and each of the attribute values in the set Q is determined by comparing the total number u of attribute values in the set Q with the predetermined total numberThe probability algorithm of one attribute value can effectively avoid that the attribute value which is not determined as the preset medical ontology attribute data is determined as the preset medical ontology attribute data when the total number u of the attribute values in the set Q is too small and the proportion of the total number value of each attribute value to the total number of the actual medical texts in the set G is too small by using different probability algorithms, so that the preset medical ontology attribute data can be determined more accurately.
In the present invention, step S35 includes: if the total number u of attribute values in the set Q is greater than the predetermined total number, the target threshold is a first target threshold, which is a second target thresholdWherein MO istT is more than or equal to 1 and less than or equal to w; if the total number u of attribute values in the set Q is less than the predetermined total number, then the target threshold is a second target threshold that is a constant between 0.8 and 1. The method comprises the steps of comparing the total number u of attribute values in a set Q with a preset total number to determine different algorithms of a target threshold, and determining that preset medical ontology attribute data are very accurate by calculating different target thresholds, namely performing differential calculation on a first target threshold and a second target threshold, so that when the total number u of the attribute values in the set Q is larger than the preset total number, the target threshold is calculated according to the score ratio of the attribute values, and when the total number u of the attribute values in the set Q is smaller than the preset total number, the value of the second target threshold is obtained according to experience, and the attribute value with the score larger than the target threshold is determined to be the preset medical ontology attribute data of the first target medical ontology with higher accuracy through the statistical data of a large number of actual medical texts in advance.
As can be seen from the above detailed discussion of the embodiments of the present invention, in the data processing method of medical data according to the present invention, the grade of a disease is taken as a first consideration factor for determining the preset medical ontology attribute data, so that even if some attribute values appear only in the actual medical text of a disease under severe conditions, for example, they can be accurately determined as the preset medical ontology attribute data; the use of different probability calculation methods can overcome the influence caused by too small number of attribute values and small numerical value of the actual medical text associated with each attribute value, and avoid that the attribute values which are not determined as the preset medical ontology attribute data are determined as the preset medical ontology attribute data; in addition, the false image that the numerical value is large enough because the fact that the actual medical text is possibly associated with a plurality of target medical ontologies is not considered in the numerical value calculation in the prior art is overcome, and the accuracy of determining the attribute data of the preset medical ontology is improved. Other advantages and benefits of the present invention are set forth above and will not be described again.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (6)
1. A method of data processing of medical data, comprising the steps of:
s1, selecting an actual medical text set G associated with the first target medical body from an actual medical text information base according to the first target medical body, wherein the set G comprises a plurality of actual medical texts;
s2, extracting a plurality of subsets G from the actual medical text set G according to the grade of the first target medical ontology1,...,Gi,...,GnWhere 1 ≦ i ≦ n, n being the total number of levels of the first target medical ontology, subset G1To GnThe corresponding levels are sequentially increased;
s3, according to the sub-set G1To GnRespectively taking each subset as a target subset and extracting attribute values meeting the conditions from the target subsets as preset medical ontology attribute data.
2. The data processing method of medical data according to claim 1, wherein in step S3, extracting an attribute value satisfying a condition from the target subset as preset medical ontology attribute data includes the steps of:
s31, extracting attribute data from each actual medical text in the target subset, wherein the attribute data comprise a plurality of attribute values and form an attribute value set Q;
s32, removing attribute values belonging to a set P and a set Q from the set Q, wherein the set P is a preset medical ontology attribute data set;
s33, sequentially taking each attribute value in the set Q as a candidate attribute value, calculating the numerical value of each actual medical text comprising the candidate attribute value, and accumulating the numerical values of all the actual medical texts comprising the candidate attribute value as the total number of the candidate attribute values;
s34, determining the score of each attribute value in the set Q according to the calculated total numerical values;
s35, determining the attribute value with the score larger than the target threshold value as preset medical ontology attribute data of the first target medical ontology, and storing the preset medical ontology attribute data in a preset medical ontology attribute data set P;
wherein, the preset medical ontology attribute data set P is an empty set in the initial state.
3. The data processing method of medical data according to claim 2, further comprising obtaining a number NUM of target medical ontologies associated with the target actual medical texts by using each actual medical text in the set G as the target actual medical textjJ is more than or equal to 1 and less than or equal to m, and m is the total number of the actual medical texts in the set G.
5. The data processing method of medical data according to claim 2, wherein step S34 includes:
if the total number u of attribute values in the set Q is greater than the predetermined total number, then the following steps are performed: calculating the probability of each attribute value in the set Q, whereinWherein PErIs a first probability, NE, of the r-th attribute value in the set QrFor the total value of the r-th attribute value in the set Q, NEvR is more than or equal to 1 and less than or equal to u, and v is more than or equal to 1 and less than or equal to u; calculating a score of each attribute value in the set Q according to a combSUM method or a linear combination method based on the calculated first probability of each attribute value in the set Q;
if the total number u of attribute values in the set Q is less than the predetermined total number, then the following steps are performed: calculating a second probability for each attribute value in the set Q, whereinWherein the PFrProbability of the r-th attribute value in the set Q, NFrThe total value of the r attribute value in the set Q is NM, and the total number of the actual medical texts in the target subset is NM; calculating a score of each attribute value in the set Q according to a combSUM method or a linear combination method based on the calculated second probability of each attribute value in the set Q; .
6. The data processing method of medical data according to claim 5, wherein step S35 includes:
if the total number u of attribute values in the set Q is greater than the predetermined total number, the target threshold is a first target threshold, which is a second target thresholdWherein MO istT is more than or equal to 1 and less than or equal to w;
if the total number u of attribute values in the set Q is less than the predetermined total number, then the target threshold is a second target threshold that is a constant between 0.8 and 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110579970.1A CN113223729B (en) | 2021-05-26 | 2021-05-26 | Data processing method of medical data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110579970.1A CN113223729B (en) | 2021-05-26 | 2021-05-26 | Data processing method of medical data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113223729A true CN113223729A (en) | 2021-08-06 |
CN113223729B CN113223729B (en) | 2021-11-02 |
Family
ID=77098957
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110579970.1A Active CN113223729B (en) | 2021-05-26 | 2021-05-26 | Data processing method of medical data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113223729B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160239711A1 (en) * | 2013-10-18 | 2016-08-18 | Vision Semanatics Limited | Visual Data Mining |
CN107609980A (en) * | 2017-09-07 | 2018-01-19 | 平安医疗健康管理股份有限公司 | Medical data processing method, device, computer equipment and storage medium |
CN108831560A (en) * | 2018-06-21 | 2018-11-16 | 北京嘉和美康信息技术有限公司 | A kind of method and apparatus of determining medical data attribute data |
US20180342328A1 (en) * | 2015-10-28 | 2018-11-29 | Koninklijke Philips N.V. | Medical data pattern discovery |
CN109635121A (en) * | 2018-11-07 | 2019-04-16 | 平安科技(深圳)有限公司 | Medical knowledge map creation method and relevant apparatus |
CN109783651A (en) * | 2019-01-29 | 2019-05-21 | 北京百度网讯科技有限公司 | Extract method, apparatus, electronic equipment and the storage medium of entity relevant information |
CN109994215A (en) * | 2019-04-25 | 2019-07-09 | 清华大学 | Disease automatic coding system, method, equipment and storage medium |
CN111462069A (en) * | 2020-03-30 | 2020-07-28 | 北京金山云网络技术有限公司 | Target object detection model training method and device, electronic equipment and storage medium |
CN111950285A (en) * | 2020-07-31 | 2020-11-17 | 合肥工业大学 | Intelligent automatic construction system and method of medical knowledge map based on multi-modal data fusion |
CN112069394A (en) * | 2020-08-14 | 2020-12-11 | 上海风秩科技有限公司 | Text information mining method and device |
CN112699642A (en) * | 2020-12-31 | 2021-04-23 | 医渡云(北京)技术有限公司 | Index extraction method and device for complex medical texts, medium and electronic equipment |
-
2021
- 2021-05-26 CN CN202110579970.1A patent/CN113223729B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160239711A1 (en) * | 2013-10-18 | 2016-08-18 | Vision Semanatics Limited | Visual Data Mining |
US20180342328A1 (en) * | 2015-10-28 | 2018-11-29 | Koninklijke Philips N.V. | Medical data pattern discovery |
CN107609980A (en) * | 2017-09-07 | 2018-01-19 | 平安医疗健康管理股份有限公司 | Medical data processing method, device, computer equipment and storage medium |
CN108831560A (en) * | 2018-06-21 | 2018-11-16 | 北京嘉和美康信息技术有限公司 | A kind of method and apparatus of determining medical data attribute data |
CN109635121A (en) * | 2018-11-07 | 2019-04-16 | 平安科技(深圳)有限公司 | Medical knowledge map creation method and relevant apparatus |
CN109783651A (en) * | 2019-01-29 | 2019-05-21 | 北京百度网讯科技有限公司 | Extract method, apparatus, electronic equipment and the storage medium of entity relevant information |
CN109994215A (en) * | 2019-04-25 | 2019-07-09 | 清华大学 | Disease automatic coding system, method, equipment and storage medium |
CN111462069A (en) * | 2020-03-30 | 2020-07-28 | 北京金山云网络技术有限公司 | Target object detection model training method and device, electronic equipment and storage medium |
CN111950285A (en) * | 2020-07-31 | 2020-11-17 | 合肥工业大学 | Intelligent automatic construction system and method of medical knowledge map based on multi-modal data fusion |
CN112069394A (en) * | 2020-08-14 | 2020-12-11 | 上海风秩科技有限公司 | Text information mining method and device |
CN112699642A (en) * | 2020-12-31 | 2021-04-23 | 医渡云(北京)技术有限公司 | Index extraction method and device for complex medical texts, medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN113223729B (en) | 2021-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109460473B (en) | Electronic medical record multi-label classification method based on symptom extraction and feature representation | |
CN107578798B (en) | Method and system for processing electronic medical record | |
CN104050247B (en) | The method for realizing massive video quick-searching | |
CN113535974B (en) | Diagnostic recommendation method and related device, electronic equipment and storage medium | |
US20110078145A1 (en) | Automated Patient/Document Identification and Categorization For Medical Data | |
CN109036577A (en) | Diabetic complication analysis method and device | |
US11507746B2 (en) | Method and apparatus for generating context information | |
CN110097096B (en) | Text classification method based on TF-IDF matrix and capsule network | |
CN112420187A (en) | Medical disease analysis method based on migratory federal learning | |
CN112685324B (en) | Method and system for generating test scheme | |
US20200334410A1 (en) | Encoding textual information for text analysis | |
CN111046904B (en) | Image description method, image description device and computer storage medium | |
EP4053757A1 (en) | Degradation suppression program, degradation suppression method, and information processing device | |
CN116956190A (en) | Malicious information detection method and device, electronic equipment and storage medium | |
CN108536666A (en) | A kind of short text information extracting method and device | |
CN113223729B (en) | Data processing method of medical data | |
CN113420291A (en) | Intrusion detection feature selection method based on weight integration | |
Abu-Soud | A novel approach for dealing with missing values in machine learning datasets with discrete values | |
CN112818693A (en) | Automatic extraction method and system for electronic component model words | |
CN113609304B (en) | Entity matching method and device | |
KR102029181B1 (en) | A method and apparatus for selecting feature using neural network with weighted fuzzy membership function | |
CN115457023A (en) | Image thinning and segmenting method for retinal blood vessel contour and high-uncertainty area based on graph convolution | |
CN114864029A (en) | Hospital DRGs grouping judgment method and working system | |
CN111860441B (en) | Video target identification method based on unbiased depth migration learning | |
CN111402205B (en) | Mammary tumor data cleaning method based on multilayer perceptron |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A data processing method for medical data Granted publication date: 20211102 Pledgee: Guangdong Provincial Bank of Communications Co.,Ltd. Pledgor: GUANGZHOU TIANPENG COMPUTER TECHNOLOGY CO.,LTD. Registration number: Y2024980042203 |