CN111192689B - Patient identification method based on medical data - Google Patents
Patient identification method based on medical data Download PDFInfo
- Publication number
- CN111192689B CN111192689B CN201811361095.4A CN201811361095A CN111192689B CN 111192689 B CN111192689 B CN 111192689B CN 201811361095 A CN201811361095 A CN 201811361095A CN 111192689 B CN111192689 B CN 111192689B
- Authority
- CN
- China
- Prior art keywords
- same
- medical record
- record data
- patient
- medical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 206010033307 Overweight Diseases 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 4
- 239000008280 blood Substances 0.000 claims description 2
- 210000004369 blood Anatomy 0.000 claims description 2
- 238000012790 confirmation Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
Abstract
The application provides a patient identification method based on medical data, which comprises the following steps: A. performing point location extraction in each medical record data, and judging whether the extracted point locations are the same; B. classifying the medical record data with the same point positions; C. and (C) classifying the medical record data classified in the step (B) into medical record data of the same patient. By the technical scheme, whether the point positions are the same or not is directly judged, medical records with the same point positions are initially summarized into the same type, and therefore the same patient with different medical records is finally screened. Different from the similarity between calculation points in the prior art, the probability of erroneous classification exists, and the absolute point positions are the same to judge, so that the accuracy of patient identification can be improved, and the defects of the prior art are overcome to a certain extent.
Description
Technical Field
The application relates to the technical field of medical big data, in particular to a patient identification method based on medical data.
Background
During the processing of medical data, the patient is the basis of medical analysis. But most data processing scenarios are inaccurate for patient correlations between multiple patient data.
As shown in fig. 6, the conventional common practice is: and extracting point positions on the same data source data from different medical record data to judge the similarity, judging the same person when the similarity exceeds a threshold value, and judging two persons otherwise. The step of extracting the point positions on the same data source data in different medical record data comprises the steps of extracting information such as names, identification card numbers, mobile phone numbers, discharge dates, birthdays and the like in different medical record data.
However, the above method is very prone to identification errors and cannot split the data with the identified errors. Thus, the results of medical analysis performed on the basis of inaccurate data will also be inaccurate. And using these analysis results for medical treatment is a hidden danger.
Disclosure of Invention
The main object of the present application is to provide a patient identification method based on medical data, comprising the steps of:
A. performing point location extraction in each medical record data, and judging whether the extracted point locations are the same;
B. correlating the medical record data with the same point positions;
C. and (C) classifying the medical record data classified in the step (B) into medical record data of the same patient.
By the technical scheme, whether the point positions are the same or not is directly judged, medical records with the same point positions are initially summarized into the same type, and therefore the same patient with different medical records is finally screened. Different from the similarity between calculation points in the prior art, the probability of erroneous classification exists, and the absolute point positions are the same to judge, so that the accuracy of patient identification can be improved, and the defects of the prior art are overcome to a certain extent.
The step B comprises the following steps:
setting weights with different heights for each point;
and if at least one high-weight point position appears in different medical record data to be the same, associating the medical record data.
By judging with the absolute point positions the same, the accuracy of patient identification can be improved, and the defects of the prior art are eliminated to a certain extent.
The step B comprises the following steps:
setting weights with different heights for each point;
and if at least two low-weight point positions appear in different medical record data to be the same, associating the medical record data.
By the above, the accuracy of patient identification can be maintained by matching a plurality of low weight points for the case of lack of high weight points.
The step B comprises the following steps:
setting weights with different heights for each point;
if only one low-weight point position appears in different medical record data, manual screening prompt is carried out, and the medical record data are associated after confirmation.
By doing so, when a match of a single low weight point location occurs, false recognition is avoided by informing the manual screening.
The step C further comprises the following steps:
and (C) splitting the medical record data which cannot be associated in the step (B) into the medical record data in the step (A).
Therefore, when the medical records cannot be classified, the medical record data are split, and the purpose is to keep the accuracy of patient identification.
The point location includes at least one of: name, identification number, cell phone number, birthday, gender, blood type, hospital number, hospital, department, date of admission, date of discharge.
By the method, whether the medical record data are the same or not is judged through different information.
And D, identifying the identity of the patient according to the point location.
Drawings
FIG. 1 is a flow chart of the present application;
FIG. 2 is a schematic diagram of point location determination for different medical records;
FIG. 3 is a schematic diagram of initializing and categorizing medical records having the same points;
FIG. 4 is a corresponding schematic diagram of the associated medical records and patient;
FIG. 5-1 is a schematic diagram showing the simultaneous point location extraction in different medical records and determining if the point location is the same;
FIG. 5-2 is a schematic diagram of initializing and categorizing medical records having the same points;
5-3 are schematic diagrams of checking for initialization categorization;
5-4 are schematic views of the assignment of each medical record after examination to the subject patient;
fig. 6 is a flow chart of the prior art.
Detailed Description
The patient identification method based on medical data according to the present application will be described in detail with reference to fig. 1 to 5.
As shown in fig. 1, the method comprises the following steps:
s100: and synchronously extracting the point positions in different medical record data.
Compared with the prior art that batch point positions are extracted for medical record data, the method and the device adopt the mode that different medical record data are synchronously extracted.
As shown in connection with FIG. 2, the extracted points include, but are not limited to, name, identification number, phone number, birthday, etc. The extraction of the points is performed synchronously in four medical records (corresponding to the first through fourth histories in fig. 2). In addition, the point location may also include a hospital number, a hospital, a department, a date of admission, a date of discharge, and the like, which are not described in detail.
S200: it is determined whether the points extracted in step S100 are identical.
In contrast to the similarity-based judgment in the prior art, in this embodiment, patient identification is performed by using whether the points are the same or not as a basis.
Referring to fig. 2, the identification card numbers in the first medical record and the second medical record are the same as the mobile phone numbers; the names and the birthdays in the second medical record and the third medical record are the same; the name, the identification card number and the birthday in the third and fourth calendar are the same.
S300: and initializing and classifying the medical records with the same point positions.
And in combination with fig. 2 and 3, at least two identical points are arranged among four medical records in the drawing. The method can be used as a basis for initializing and classifying, and the first, second and third medical records are assumed to belong to the first patient, so that the four medical records are associated due to the fact that the fourth medical record and the third medical record have the same point. The association directs the first through fourth calendars to the same patient, i.e., the fourth calendar is also identified as the first patient at the time of initializing the classification.
Furthermore, through the initialization classification, a preliminary corresponding relationship can be established between each medical record and the patient. As shown in fig. 4, when two medical records have the same point location, the two medical records are considered to have an association, that is, the same patient is possible. In fig. 4, the same combination exists between the first to third medical records, which is summarized as the first patient, and the same point exists between the fourth to seventh medical records, which is summarized as the second patient.
S400: and checking the initialization classification, if the initialization classification passes the checking, entering a step S500, otherwise, splitting the initialization classification into an original state, and returning to the step S200.
Different weights are set for each point or combination of points, for example, the coincidence rate of combination information such as name, birthday and the like is higher, the coincidence rate is set to be lower, and for example, the coincidence rate of combination of hospitalization number, hospital and department is higher, and the coincidence rate is set to be lower. The combination of the identification card number and the mobile phone number has uniqueness, and is set as the highest weight. Of course, in the actual judgment process, combinations of the same points are various, and are not listed here.
When two medical records have the same combination with high weight, then the two medical records are considered to be the same patient. For example, in the first medical record and the second medical record in fig. 2, if the highest weight combination of the identification card number and the mobile phone number is the same, the two medical records are identified as the same patient. In the second medical record and the third medical record, although the name and the birthday are the same, the case that the two medical records do not belong to the same patient may occur even if the weights of the combination are the same because the weights of the combination are lower.
In addition, since the mobile phone number may be used by the patient b after the patient a is logged off, the weight of the mobile phone number may be set to be lower than the weight of the identification card number or to be a low weight having the same weight as the name and the date of birth. When the mobile phone numbers are the same and the identity card numbers are not available, at least two points including the mobile phone numbers are the same and can be listed as judgment conditions, so that a plurality of medical records can be accurately associated with a patient under the absolute authentication condition of lacking the identity card numbers. The number of specifically matched points is not limited herein.
Still in connection with the example described in fig. 4. When an eighth medical record exists, the eighth medical record and the third medical record have the same condition of the highest weight combination of the identity card number and the mobile phone number respectively. Meanwhile, the eighth medical record is the same as the fifth medical record in that the combination of name, birthday, hospitalization number, hospital and department has a low weight, and the first patient and the second patient may be the same patient.
Based on the situation, if the high weight is adopted for resolution, the relationship of the eighth medical record and the fifth medical record with the same low weight is ignored, namely the medical records belong to different patients A and B, and medical records corresponding to the patient A are first to third medical records and eighth medical records; if a low weight is used for resolution, the first patient and the second patient are considered to be the same patient.
In the case of FIG. 5, A to F are 6 different medical records. Wherein the number 1 indicates the same point location and the number 0 indicates different point locations. The dashed box between the medical record C and the medical record E indicates low weight matching, and the point positions of the rest medical records are the same and are high weight matching.
FIGS. 5-1 and 5-2 present an initialized categorization between medical records in tabular and block form, respectively.
Fig. 5-3 shows that medical records a-D are classified as patient a and medical records E-F are classified as patient b according to a high weight matching relationship.
Because there is also a low weight matching between medical record C and medical record E, and no other reference basis exists. In this case, a prompt is given to manually screen.
S500: the medical records that were successfully examined in step S400 are classified as the same patient.
Fig. 5-4 show the results of the manual screening, i.e., patient a and patient b are the same person. And the identity of the patient can be identified according to the point location.
The technical scheme of the application is different from the similarity between the calculation points in the prior art, and directly judges whether the points are the same or not. Medical records with the same points are initially grouped into the same class. The same patient with different medical records is finally screened by checking the initially generalized class.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
Claims (3)
1. A method of patient identification based on medical data, comprising the steps of:
A. performing point location extraction in each medical record data, and judging whether the extracted point locations are the same;
B. correlating the medical record data with the same point positions;
C. dividing the medical record data classified in the step B into medical record data of the same patient;
the step B comprises the following steps:
setting weights with different heights for each point;
if at least one high-weight point position appears in different medical record data to be the same, the medical record data are associated;
if at least two low-weight point positions appear in different medical record data to be the same, associating the medical record data;
if only one low-weight point position appears in different medical record data, carrying out manual screening prompt, and associating the medical record data after confirmation;
the step C further comprises the following steps:
and (C) splitting the medical record data which cannot be associated in the step (B) into the medical record data in the step (A).
2. The method of claim 1, wherein the point locations comprise at least one of: name, identification number, cell phone number, birthday, gender, blood type, hospital number, hospital, department, date of admission, date of discharge.
3. The method of claim 1, further comprising step D of identifying the identity of the patient from the point location.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811361095.4A CN111192689B (en) | 2018-11-15 | 2018-11-15 | Patient identification method based on medical data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811361095.4A CN111192689B (en) | 2018-11-15 | 2018-11-15 | Patient identification method based on medical data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111192689A CN111192689A (en) | 2020-05-22 |
| CN111192689B true CN111192689B (en) | 2023-11-24 |
Family
ID=70708890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811361095.4A Active CN111192689B (en) | 2018-11-15 | 2018-11-15 | Patient identification method based on medical data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192689B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007287027A (en) * | 2006-04-19 | 2007-11-01 | Fujifilm Corp | Medical planning support system |
| JP2009146345A (en) * | 2007-12-18 | 2009-07-02 | Mitsubishi Electric Information Systems Corp | Electronic medical chart system |
| CN101727535A (en) * | 2008-10-30 | 2010-06-09 | 北大方正集团有限公司 | Cross indexing method for patients crossing system and system thereof |
| JP2010167042A (en) * | 2009-01-21 | 2010-08-05 | Canon Inc | Medical diagnostic support apparatus and control method of the same and program |
| CN102576431A (en) * | 2009-10-06 | 2012-07-11 | 皇家飞利浦电子股份有限公司 | Autonomous linkage of patient information records stored at different entities |
| JP2015114721A (en) * | 2013-12-09 | 2015-06-22 | 株式会社東芝 | Medical information processing device |
| KR20150086089A (en) * | 2014-01-17 | 2015-07-27 | 주식회사 라이브존 | System and method of managing medical image using electronic medical record |
| JP2015230631A (en) * | 2014-06-06 | 2015-12-21 | 富士ゼロックス株式会社 | Information processing device and information processing program |
| CN105303499A (en) * | 2015-09-16 | 2016-02-03 | 西部天使（北京）健康科技有限公司 | Automatic medical record imputation method and system |
| JP2016099810A (en) * | 2014-11-21 | 2016-05-30 | 日本調剤株式会社 | Pharmacy information management system |
| CN106295182A (en) * | 2016-08-10 | 2017-01-04 | 依据数据（湖南）科技有限公司 | A kind of personal identification method based on patient biological information |
| CN106682439A (en) * | 2016-12-30 | 2017-05-17 | 广州慧扬信息系统科技有限公司 | Investigational follow-up based medical record screening method |
| CN106778021A (en) * | 2016-12-31 | 2017-05-31 | 深圳市前海康启源科技有限公司 | Medical diagnosis information management system and method |
| CN107038336A (en) * | 2017-03-21 | 2017-08-11 | 科大讯飞股份有限公司 | A kind of electronic health record automatic generation method and device |
| CN107193919A (en) * | 2017-05-15 | 2017-09-22 | 清华大学深圳研究生院 | The search method and system of a kind of electronic health record |
| CN108352196A (en) * | 2015-10-30 | 2018-07-31 | 皇家飞利浦有限公司 | There is no hospital's matching in the health care data library for going mark of apparent standard identifier |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040128163A1 (en) * | 2002-06-05 | 2004-07-01 | Goodman Philip Holden | Health care information management apparatus, system and method of use and doing business |
| US20050267782A1 (en) * | 2004-05-28 | 2005-12-01 | Gudrun Zahlmann | System for processing patient medical data for clinical trials and aggregate analysis |
| US20080212847A1 (en) * | 2007-01-08 | 2008-09-04 | Michael Davies | Method and system for identifying medical sample information source |
| US10340037B2 (en) * | 2014-09-23 | 2019-07-02 | Allscripts Software, Llc | Aggregating a patient's disparate medical data from multiple sources |
| US11106818B2 (en) * | 2015-12-11 | 2021-08-31 | Lifemed Id, Incorporated | Patient identification systems and methods |
-
2018
- 2018-11-15 CN CN201811361095.4A patent/CN111192689B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007287027A (en) * | 2006-04-19 | 2007-11-01 | Fujifilm Corp | Medical planning support system |
| JP2009146345A (en) * | 2007-12-18 | 2009-07-02 | Mitsubishi Electric Information Systems Corp | Electronic medical chart system |
| CN101727535A (en) * | 2008-10-30 | 2010-06-09 | 北大方正集团有限公司 | Cross indexing method for patients crossing system and system thereof |
| JP2010167042A (en) * | 2009-01-21 | 2010-08-05 | Canon Inc | Medical diagnostic support apparatus and control method of the same and program |
| CN102576431A (en) * | 2009-10-06 | 2012-07-11 | 皇家飞利浦电子股份有限公司 | Autonomous linkage of patient information records stored at different entities |
| JP2015114721A (en) * | 2013-12-09 | 2015-06-22 | 株式会社東芝 | Medical information processing device |
| KR20150086089A (en) * | 2014-01-17 | 2015-07-27 | 주식회사 라이브존 | System and method of managing medical image using electronic medical record |
| JP2015230631A (en) * | 2014-06-06 | 2015-12-21 | 富士ゼロックス株式会社 | Information processing device and information processing program |
| JP2016099810A (en) * | 2014-11-21 | 2016-05-30 | 日本調剤株式会社 | Pharmacy information management system |
| CN105303499A (en) * | 2015-09-16 | 2016-02-03 | 西部天使（北京）健康科技有限公司 | Automatic medical record imputation method and system |
| CN108352196A (en) * | 2015-10-30 | 2018-07-31 | 皇家飞利浦有限公司 | There is no hospital's matching in the health care data library for going mark of apparent standard identifier |
| CN106295182A (en) * | 2016-08-10 | 2017-01-04 | 依据数据（湖南）科技有限公司 | A kind of personal identification method based on patient biological information |
| CN106682439A (en) * | 2016-12-30 | 2017-05-17 | 广州慧扬信息系统科技有限公司 | Investigational follow-up based medical record screening method |
| CN106778021A (en) * | 2016-12-31 | 2017-05-31 | 深圳市前海康启源科技有限公司 | Medical diagnosis information management system and method |
| CN107038336A (en) * | 2017-03-21 | 2017-08-11 | 科大讯飞股份有限公司 | A kind of electronic health record automatic generation method and device |
| CN107193919A (en) * | 2017-05-15 | 2017-09-22 | 清华大学深圳研究生院 | The search method and system of a kind of electronic health record |
Non-Patent Citations (1)
| Title |
|---|
| 从医疗记录中提取结构化数据的双阅读/录入系统及其应用;罗立刚等;药物流行病学杂志;第26卷(第6期);第406-409页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111192689A (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272002B (en) | Bone age tablet classification method and device | |
| US20160283603A1 (en) | Methods and systems for testing performance of biometric authentication systems | |
| CN109637605B (en) | Electronic medical record structuring method and computer-readable storage medium | |
| US7949156B2 (en) | Biometric remediation of datasets | |
| CN111046879B (en) | Certificate image classification method, device, computer equipment and readable storage medium | |
| US20060120578A1 (en) | Minutiae matching | |
| JP2015032030A (en) | Document classification system, document classification method and document classification program | |
| CN107230154A (en) | The recognition methods of life insurance Claims Resolution case with clique's risk of fraud and device | |
| CN111210402A (en) | Face image quality scoring method and device, computer equipment and storage medium | |
| US20180196924A1 (en) | Computer-implemented method and system for diagnosis of biological conditions of a patient | |
| CN112989990A (en) | Medical bill identification method, device, equipment and storage medium | |
| CN111883253A (en) | Disease data analysis method and lung cancer risk prediction system based on medical knowledge base | |
| JP5812505B2 (en) | Demographic analysis method and system based on multimodal information | |
| CN112836041B (en) | Personnel relationship analysis method, device, equipment and storage medium | |
| CN111192689B (en) | Patient identification method based on medical data | |
| US11367311B2 (en) | Face recognition method and apparatus, server, and storage medium | |
| CN111816318A (en) | Heart disease data queue generation method and risk prediction system | |
| CN107423140B (en) | Return code identification method and device | |
| CN113807256A (en) | Bill data processing method and device, electronic equipment and storage medium | |
| JP5500930B2 (en) | Participation examination system, participation examination method, and program | |
| US7792573B2 (en) | Method for collecting and assigning patient data in a clinical trial | |
| CN110765232A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| US20240104178A1 (en) | Information processing apparatus, information processing method, matching system, program, and storage medium | |
| CN113257380B (en) | Method and device for difference checking and difference checking rule making | |
| CN112734035B (en) | Data processing method and device and readable 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 |