CN111199050B - System for automatically desensitizing medical records and application - Google Patents
System for automatically desensitizing medical records and application Download PDFInfo
- Publication number
- CN111199050B CN111199050B CN201811378972.9A CN201811378972A CN111199050B CN 111199050 B CN111199050 B CN 111199050B CN 201811378972 A CN201811378972 A CN 201811378972A CN 111199050 B CN111199050 B CN 111199050B
- Authority
- CN
- China
- Prior art keywords
- medical record
- module
- desensitized
- sample
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioethics (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a system for automatically desensitizing medical records and application thereof. The system comprises: the template generation module is used for classifying the sample medical records of different layout types, and respectively acquiring sensitive information areas corresponding to each type according to the types so as to generate medical record templates of different types corresponding to the sample medical records of different types; the training module is used for inputting the sample medical record list corresponding to each type of medical record template into the convolutional neural network for training so as to obtain a neural network model for classifying the medical record list. The desensitization module is used for matching the corresponding medical record template according to the type of the medical record list to be desensitized acquired by the neural network model acquired by the training module, and labeling and desensitizing the area of the medical record list to be desensitized according to the matched medical record template so as to acquire the medical record after the desensitization. By the method, the medical record can be efficiently and accurately desensitized.
Description
Technical Field
The application relates to the technical fields of pattern recognition, machine learning, convolutional neural networks and the like, in particular to a system for automatically desensitizing medical records and application thereof.
Background
In the process of processing medical records and collecting information, in order to avoid privacy disclosure of patients, sensitive private information needs to be processed in a fuzzy manner, such as patient names, addresses, contact ways and the like, so that other non-medical staff (such as data analysts) can learn to call information. With the increasing number of medical persons and the diversification of disease types, medical record desensitization by using manpower has shown great limitation in efficiency and reliability. Because medical records of different hospitals and departments are different in general layout, the structure standard for unifying out information is lacking. If the existing cursor recognition technology is directly used for recognizing the whole content of the medical record and then desensitizing the medical record, the same information can be repeatedly recognized continuously to cause unnecessary time consumption, and the recognition accuracy is poor due to rough recognition. Therefore, the prior art can not realize high-efficiency and accurate automatic desensitization of medical records.
Therefore, there is a need for a system for automatically desensitizing medical records that achieves efficient and accurate automatic desensitization of medical records.
Disclosure of Invention
In view of this, the present application provides a system for automatically desensitizing medical records to achieve efficient and accurate desensitization of medical records.
The application provides a system for automatically desensitizing medical records, which comprises:
the template generation module is used for classifying the sample medical records of different layout types, and respectively acquiring sensitive information areas corresponding to each type according to the types so as to generate medical record templates of different types corresponding to the sample medical records of different types;
the training module is used for inputting the sample medical record list corresponding to each type of medical record template into the convolutional neural network for training so as to obtain a neural network model for classifying the medical record list.
The desensitization module is used for matching the corresponding medical record template according to the type of the medical record list to be desensitized acquired by the neural network model acquired by the training module, and labeling and desensitizing the area of the medical record list to be desensitized according to the matched medical record template so as to acquire the medical record after the desensitization.
By the automatic desensitization system, the automatic desensitization of different types of medical records can be realized efficiently and accurately, so that privacy of patients is prevented from being revealed. Not only overcomes the defect of limitation of medical record desensitization on efficiency and reliability by using manpower in the prior art; by the functions of the modules, the defect that when the medical record is desensitized by utilizing a cursor identification technology in the prior art, the same information is repeatedly identified continuously to cause unnecessary time consumption due to the fact that the whole content of the medical record is required to be identified is overcome.
Preferably, the template generating module is specifically configured to:
the collecting sub-module is used for collecting sample medical record sheets of different layout types of different hospitals;
the labeling sub-module is used for labeling sensitive information areas in the sample medical record list;
the classification sub-module is used for dividing the sample medical record list into different types of sample medical record lists according to different layout structures and positions of sensitive information areas in the marked sample medical record list;
the recording sub-module is used for recording coordinate values of marked sensitive information areas of each type of sample medical record list;
a template generation sub-module for, for each type of sample medical record sheet: and taking the sensitive information area with the largest area as the final sensitive information area of each type of sample medical record according to the coordinate value of the marked sensitive information area of each type of sample medical record, and taking the sample medical record marked with the final sensitive information area as a medical record template of the type of sample medical record.
By the method, different types of medical record templates corresponding to different types of sample medical record sheets are generated. The template generation sub-module takes the sensitive information area with the largest area as the final sensitive information area of each type of medical record template. It is beneficial to ensure that sensitive information can be fully contained in the desensitized region when the medical record is desensitized.
Preferably, the template generating module further includes: and the image preprocessing sub-module is used for denoising and binarizing the sample medical record sheet marked by the marking sub-module.
By the above, the denoising process can remove noise points irrelevant to sensitive information, and the binarization process is beneficial to the fact that when the image is further processed, the aggregate property of the image is only related to the position of the point with the pixel value of 0 or 255, the multi-level value of the pixel is not involved, so that the processing is simple, and the processing and compression amount of data are small.
Preferably, the template generating module further includes:
and the sample expansion sub-module performs affine transformation on each type of sample medical record list recorded by the recording sub-module to obtain a specified number of sample medical record lists.
From this, it is advantageous to expand the number of sample medical records used for training.
Preferably, the training module is specifically configured to:
inputting each type of sample medical record list and the type of the sample medical record list into an input layer of a convolutional neural network;
the convolution layer of the convolution neural network extracts a feature map of the sample medical record list;
the pooling layer of the convolutional neural network compresses the feature map and is used for extracting main features;
the full connection layer of the convolutional neural network is used for carrying out full connection or global average processing on the features extracted by the pooling layer, and carrying out classification processing to obtain a neural network model for classifying medical records.
By the method, the neural network model for classifying medical records of different layout types and labeling the initial area to be desensitized is generated. And taking the sensitive information area with the largest area as the final sensitive information area of each type of medical record template. It is beneficial to ensure that sensitive information can be fully contained in the desensitized region when the medical record is desensitized.
Preferably, the convolution layer of the convolutional neural network extracts a mapping relation between the feature map of the medical record template and the sample medical record list as follows:
x m ＝f(Σx m i *k m ij +b m j )
wherein said x m An output vector representing the m-th layer; the x is m i An input vector representing an ith node of the mth layer; the k is m ij Representing filter parameters to be trained by an ith node of an mth layer; said b m j Representing a base to be trained of an ith borrowing point of an mth layer; the m represents the current layer number; the i represents the current node; the j represents the current layer.
The feature map of the medical record template is better extracted.
Preferably, the square cost function of the fully connected layer of the convolutional neural network when used for classification is:
E N ＝Σ N Σ c (t k n -y k n )2
wherein N represents the number of sample medical record sheets, E N Representing the type of the Nth sample order of the output; and c represents the number of the types of the medical record templates, and k represents the layout type of the sample medical record sheet and the dimension on the type of the medical record template output by the full connection layer of the convolutional neural network.
Thus, the optimal classification is facilitated to be obtained.
Preferably, the desensitizing module specifically includes:
the matching sub-module is used for matching the corresponding medical record template according to the type of the medical record list to be desensitized obtained by the neural network model obtained by the training module;
the labeling sub-module is used for labeling the initial area to be desensitized of the medical record with desensitization according to the medical record template;
the positioning sub-module is used for accurately positioning the initial area to be desensitized by utilizing an image processing technology;
and the desensitization sub-module is used for carrying out independent desensitization treatment on each precisely positioned area to be desensitized.
By the method, the initial area to be desensitized of the medical record with desensitization is obtained through the neural network model for extracting the characteristics of the medical records with different layout types, and the medical record with desensitization is further accurately positioned and desensitized. The method overcomes the defect that when the medical record is desensitized by utilizing a cursor identification technology in the prior art, the same information is repeatedly identified continuously to cause unnecessary time consumption due to the fact that the whole content of the medical record is required to be identified.
Preferably, the sensitive information includes at least, but is not limited to, one of: name, address, contact.
Thus, the sensitive information of the present application is not limited to the above information, but includes other information related to personal privacy.
Based on the system, the application also provides a method for automatically desensitizing medical records, which comprises the following steps:
A. acquiring an original medical record picture to be desensitized;
B. judging the picture quality of the original medical record picture to be desensitized, and reserving the original medical record picture with the resolution ratio higher than a specified threshold value;
C. denoising and binarizing the original medical record picture to obtain a binary image of the processed original medical record picture;
D. classifying the original medical record picture through the neural network model for classifying the medical record list according to the binary image of the original medical record picture so as to acquire the type of medical record to which the original medical record picture belongs;
E. matching corresponding medical record templates according to the types of the medical records, and accordingly obtaining an initial area to be desensitized of the original medical record;
F. accurately positioning the initial area to be desensitized by using an image processing technology to obtain an accurately positioned area to be desensitized;
G. and desensitizing the precisely positioned area to be desensitized.
By the method, the medical records of different types can be automatically desensitized efficiently and accurately, so that privacy leakage of patients is avoided when other non-medical staff call to learn the medical record information. Not only overcomes the defect of limitation of medical record desensitization on efficiency and reliability by using manpower in the prior art; meanwhile, the application classifies the original medical record and positions the original area to be desensitized, and further carries out accurate positioning and desensitization treatment on the original medical record, thereby overcoming the defect that unnecessary time consumption is caused by repeated identification of the same information due to the fact that the whole content of the medical record needs to be identified when the medical record is desensitized by utilizing a cursor identification technology in the prior art.
In summary, the system and the application for automatically desensitizing medical records provided by the application can realize the efficient and accurate automatic desensitization of medical records of different types, so that privacy leakage of patients is avoided when other non-medical staff call to learn the medical record information. Not only overcomes the defect of limitation of medical record desensitization on efficiency and reliability by using manpower in the prior art; and the defect that unnecessary time consumption is caused by the fact that the same information is repeatedly identified continuously because the whole content of the medical record needs to be identified when the medical record is desensitized by utilizing a cursor identification technology in the prior art is overcome.
Drawings
FIG. 1 is a schematic diagram of a system for automatically desensitizing medical records in accordance with the present application;
FIG. 2 is a schematic diagram of a template generation module and training module of a system for automatically desensitizing medical records provided by the present application;
FIG. 3 is a flow chart of a method for automatically desensitizing medical records provided by the present application;
FIG. 4 is a flow chart of a method for automatically desensitizing medical records provided by the present application;
Detailed Description
In order to make the objects, technical solutions and advantageous effects of the present application more apparent, the present application will be described in further detail with reference to the following examples. It should be understood that the detailed description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the application.
Example 1
As shown in fig. 1-2, the present application provides a system for automatically desensitizing medical records, comprising:
the template generating module 101 is configured to perform sensitive information region labeling on sample medical records with different layout types to generate medical record templates with different types corresponding to the sample medical records with different types. Wherein a in said fig. 2 shows a schematic diagram of a template generation module 101, in particular comprising in particular:
the collecting sub-module is used for collecting sample medical record sheets of different layout types of different hospitals;
the labeling sub-module is used for labeling sensitive information areas in the sample medical record list; wherein the sensitive information may be: name, address, contact, or other information related to personal privacy.
The classification sub-module is used for dividing the sample medical record list into different types of sample medical record lists according to different layout structures and positions of sensitive information areas in the marked sample medical record list;
the recording sub-module is used for recording coordinate values of marked sensitive information areas of each type of sample medical record list;
and the image preprocessing sub-module is used for denoising and binarizing the sample medical record sheet marked by the marking sub-module so as to obtain a binary image of the processed sample medical record sheet.
A template generation sub-module for, for each type of sample medical record sheet: and taking the sensitive information area with the largest area as the final sensitive information area of each type of sample medical record according to the coordinate value of the marked sensitive information area of each type of sample medical record, and taking the sample medical record marked with the final sensitive information area as a medical record template of the type of sample medical record. Here, the sensitive information area with the largest area is taken as the final sensitive information area of each type of medical record template. It is beneficial to ensure that sensitive information can be fully contained in the desensitized region when the medical record is desensitized.
And the sample expansion sub-module performs affine transformation on each type of sample medical record list recorded by the recording sub-module to obtain a specified number of sample medical record lists.
The training module 102 is configured to input each type of medical record template processed by the template processing module into a convolutional neural network for training to obtain a neural network model for extracting sensitive information of medical records with different layout types. Wherein B in said fig. 2 shows a schematic diagram of the training module 102, in particular for:
n1, inputting each type of sample medical record list and the type of the sample medical record list into an input layer of a convolutional neural network;
n2, extracting a characteristic diagram of the sample medical record sheet by a convolution layer of the convolution neural network; the convolution layer of the convolution neural network extracts a mapping relation between the characteristic diagram of the medical record template and the sample medical record list as follows:
x m ＝f(Σx m i *k m ij +b m j )
wherein said x m An output vector representing the m-th layer; the x is m i An input vector representing an ith node of the mth layer; the k is m ij Representing filter parameters to be trained by an ith node of an mth layer; said b m j Representing a base to be trained of an ith borrowing point of an mth layer; the m represents the current layer number; the i represents the current node; the j represents the current layer.
N3, compressing the feature map by a pooling layer of the convolutional neural network and extracting main features;
and N4, the full connection layer of the convolutional neural network is used for carrying out full connection or global average processing on the features extracted by the pooling layer, and carrying out classification processing to obtain a neural network model for classifying medical records.
The square cost function of the full-connection layer of the convolutional neural network when being used for classification is as follows: e (E) N ＝Σ N Σ c (t k n -y k n )2
Wherein N represents the number of sample medical record sheets, E N Representing the type of the Nth sample order of the output; and c represents the number of the types of the medical record templates, and k represents the layout type of the sample medical record sheet and the dimension on the type of the medical record template output by the full connection layer of the convolutional neural network.
The training module 102 adopts a supervised learning method, trains the initial parameters of each layer through a back propagation algorithm, and realizes the feature extraction of training samples.
The desensitization module 103 is configured to match the medical record template corresponding to the medical record list to be desensitized according to the type of the medical record list to be desensitized acquired by the neural network model acquired by the training module, and label the area to be desensitized and desensitize the medical record list to be desensitized according to the matched medical record template, so as to acquire the medical record after desensitization. The method specifically comprises the following steps:
the matching sub-module is used for matching the corresponding medical record template according to the type of the medical record list to be desensitized obtained by the neural network model obtained by the training module;
the labeling sub-module is used for labeling the initial area to be desensitized of the medical record with desensitization according to the medical record template;
the positioning sub-module is used for accurately positioning the initial area to be desensitized by utilizing an image processing technology;
and the desensitization sub-module is used for carrying out independent desensitization treatment on each precisely positioned area to be desensitized.
Example two
Based on the system for automatically desensitizing medical records in the first embodiment, the application also provides a method for automatically desensitizing medical records, as shown in fig. 3-4, which comprises the following steps:
s301, acquiring a medical record list to be desensitized;
s302, judging the picture quality of the medical record list to be desensitized, and reserving the medical record list to be desensitized with the resolution ratio higher than a specified threshold value;
s303, denoising and binarizing the medical record list to be desensitized;
s304, classifying the medical record list to be desensitized processed in S303 through the neural network model for classifying the medical record list, which is obtained by the training module 102 in the first embodiment, so as to obtain the type of the medical record list to which the medical record list belongs;
s305, matching a medical record template of a corresponding type according to the type of the medical record list, and accordingly acquiring an initial area to be desensitized of the original medical record;
s306, accurately positioning the initial area to be desensitized by using an image processing technology, and obtaining the accurately positioned area to be desensitized; further accurate positioning may be performed here using OCR recognition techniques.
S307, desensitizing the precisely positioned area to be desensitized. The region to be desensitized may be hidden or obscured using a mosaic overlay or other means to effect desensitization of sensitive private information to avoid privacy disclosure for the patient.
By the method, the medical records of different types can be automatically desensitized efficiently and accurately, so that privacy leakage of patients is avoided when other non-medical staff call to learn the medical record information. Not only overcomes the defect of limitation of medical record desensitization on efficiency and reliability by using manpower in the prior art; meanwhile, the application classifies the original medical record and positions the original area to be desensitized, and further carries out accurate positioning and desensitization treatment on the original medical record, thereby overcoming the defect that unnecessary time consumption is caused by repeated identification of the same information due to the fact that the whole content of the medical record needs to be identified when the medical record is desensitized by utilizing a cursor identification technology in the prior art.
In summary, the system and the application for automatically desensitizing medical records provided by the application can realize the automatic desensitization of medical records of different types efficiently and accurately so as to avoid privacy disclosure of patients. Not only overcomes the defect of limitation of medical record desensitization on efficiency and reliability by using manpower in the prior art; and the defect that unnecessary time consumption is caused by the fact that the same information is repeatedly identified continuously because the whole content of the medical record needs to be identified when the medical record is desensitized by utilizing a cursor identification technology in the prior art is overcome.
The above description is merely illustrative of the preferred embodiments of the present application and is not intended to limit the application, but any modifications, equivalents, improvements or the like falling within the spirit and principles of the present application are intended to be included within the scope of the present application.
Claims (6)
1. A system for automatically desensitizing medical records, comprising:
the template generation module is used for classifying the sample medical records of different layout types, and respectively acquiring sensitive information areas corresponding to each type according to the types so as to generate medical record templates of different types corresponding to the sample medical records of different types;
the training module is used for inputting sample medical records corresponding to each type of medical record template into the convolutional neural network for training to obtain a neural network model for classifying the medical records;
the desensitization module is used for matching the corresponding medical record template according to the type of the medical record list to be desensitized acquired by the neural network model acquired by the training module, and labeling and desensitizing the area of the medical record list to be desensitized according to the matched medical record template so as to acquire the medical record after the desensitization;
the template generation module comprises:
the collecting sub-module is used for collecting sample medical record sheets of different layout types of different hospitals;
the labeling sub-module is used for labeling sensitive information areas in the sample medical record list;
the classification sub-module is used for dividing the sample medical record list into different types of sample medical record lists according to different layout structures and positions of sensitive information areas in the marked sample medical record list;
the recording sub-module is used for recording coordinate values of marked sensitive information areas of each type of sample medical record list; and
a template generation sub-module for, for each type of sample medical record sheet: according to the coordinate values of marked sensitive information areas of each sample medical record sheet in each type of sample medical record sheet, taking the sensitive information area with the largest area capable of covering each marked sensitive information area of the sample medical record sheet of the current type as the final sensitive information area of each type of sample medical record sheet, and taking the sample medical record sheet marked with the final sensitive information area as a medical record template of the sample medical record sheet of the type;
the desensitization module includes:
the matching sub-module is used for matching the corresponding medical record template according to the type of the medical record list to be desensitized obtained by the neural network model obtained by the training module;
the labeling sub-module is used for labeling the initial region to be desensitized of the medical record to be desensitized according to the medical record template;
the positioning sub-module is used for accurately positioning the initial area to be desensitized by utilizing an image processing technology; and
and the desensitization sub-module is used for carrying out independent desensitization treatment on each precisely positioned area to be desensitized.
2. The system of claim 1, wherein the template generation module further comprises:
and the image preprocessing sub-module is used for denoising and binarizing the sample medical record sheet marked by the marking sub-module.
3. The system of claim 2, wherein the template generation module further comprises:
and the sample expansion sub-module performs affine transformation on each type of sample medical record list recorded by the recording sub-module to obtain a specified number of sample medical record lists.
4. The system of claim 3, wherein the training module comprises an input sub-module and a convolutional neural network:
the input sub-module is used for inputting each type of sample medical record list and the type thereof to an input layer of the convolutional neural network;
the convolution layer of the convolution neural network is used for extracting a feature map of the sample medical record sheet;
the pooling layer of the convolutional neural network is used for compressing the feature map and extracting main features;
the full connection layer of the convolutional neural network is used for carrying out full connection or global average processing on the features extracted by the pooling layer, and carrying out classification processing to obtain a neural network model for classifying medical records.
5. The system of claim 1, wherein the sensitive information includes at least one of, but not limited to: name, address, contact.
6. A method of automatically desensitizing medical records based on the system of any of claims 1-5, comprising:
A. acquiring a medical record list to be desensitized;
B. judging the picture quality of the medical record list to be desensitized, and reserving the medical record list to be desensitized with the resolution ratio higher than a specified threshold value;
C. denoising and binarizing the medical record list to be desensitized;
D. classifying the medical records to be desensitized after processing through the neural network model for classifying the medical records to obtain the type of the medical records to which the medical records belong;
E. matching medical record templates of corresponding types according to the types of the medical record sheets, and accordingly obtaining an initial to-be-desensitized area of the medical record sheets to be desensitized;
F. accurately positioning the initial area to be desensitized by using an image processing technology to obtain an accurately positioned area to be desensitized;
G. and desensitizing the precisely positioned area to be desensitized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811378972.9A CN111199050B (en) | 2018-11-19 | 2018-11-19 | System for automatically desensitizing medical records and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811378972.9A CN111199050B (en) | 2018-11-19 | 2018-11-19 | System for automatically desensitizing medical records and application |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111199050A CN111199050A (en) | 2020-05-26 |
| CN111199050B true CN111199050B (en) | 2023-10-17 |
Family
ID=70743973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811378972.9A Active CN111199050B (en) | 2018-11-19 | 2018-11-19 | System for automatically desensitizing medical records and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111199050B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361254A (en) * | 2021-06-03 | 2021-09-07 | 重庆南鹏人工智能科技研究院有限公司 | Automatic electronic medical record analysis method and device |
| CN116610659A (en) * | 2023-05-22 | 2023-08-18 | 南方医科大学南方医院 | Method for constructing database of liver cancer specific disease, database, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239666A (en) * | 2017-06-09 | 2017-10-10 | 孟群 | A kind of method and system that medical imaging data are carried out with desensitization process |
| CN108831559A (en) * | 2018-06-20 | 2018-11-16 | 清华大学 | A kind of Chinese electronic health record text analyzing method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170039222A1 (en) * | 2014-04-29 | 2017-02-09 | Farrow Norris Pty Ltd | Method and system for comparative data analysis |
| US10810317B2 (en) * | 2017-02-13 | 2020-10-20 | Protegrity Corporation | Sensitive data classification |
| CN109920501B (en) * | 2019-01-24 | 2021-04-20 | 西安交通大学 | Electronic medical record classification method and system based on convolutional neural network and active learning |
-
2018
- 2018-11-19 CN CN201811378972.9A patent/CN111199050B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239666A (en) * | 2017-06-09 | 2017-10-10 | 孟群 | A kind of method and system that medical imaging data are carried out with desensitization process |
| CN108831559A (en) * | 2018-06-20 | 2018-11-16 | 清华大学 | A kind of Chinese electronic health record text analyzing method and system |
Non-Patent Citations (2)
| Title |
|---|
| 程健一 ; 关毅 ; 何彬 ; .基于SVM和CRF双层分类器的英文电子病历去隐私化.智能计算机与应用.2016,第6卷(第06期),17-24页. * |
| 臧昊 ; 赵强 ; 卞水荣 ; .基于XML的电子病历隐私数据脱敏技术的研究与设计.信息技术与信息化.2017,(03),111-114页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111199050A (en) | 2020-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086756B (en) | Text detection analysis method, device and equipment based on deep neural network | |
| CN109858555B (en) | Image-based data processing method, device, equipment and readable storage medium | |
| CN110210413B (en) | Multidisciplinary test paper content detection and identification system and method based on deep learning | |
| CN111695392B (en) | Face recognition method and system based on cascade deep convolutional neural network | |
| WO2020224221A1 (en) | Tracking method and apparatus, electronic device, and storage medium | |
| CN112862024B (en) | Text recognition method and system | |
| CN108986137B (en) | Human body tracking method, device and equipment | |
| Chandran et al. | Missing child identification system using deep learning and multiclass SVM | |
| CN112861575A (en) | Pedestrian structuring method, device, equipment and storage medium | |
| CN111008576A (en) | Pedestrian detection and model training and updating method, device and readable storage medium thereof | |
| CN111401322A (en) | Station entering and exiting identification method and device, terminal and storage medium | |
| CN111199050B (en) | System for automatically desensitizing medical records and application | |
| CN113837151A (en) | Table image processing method and device, computer equipment and readable storage medium | |
| CN113205047A (en) | Drug name identification method and device, computer equipment and storage medium | |
| CN110895661A (en) | Behavior identification method, device and equipment | |
| CN110969173B (en) | Target classification method and device | |
| CN113076860B (en) | Bird detection system under field scene | |
| CN112396060B (en) | Identification card recognition method based on identification card segmentation model and related equipment thereof | |
| CN113255557A (en) | Video crowd emotion analysis method and system based on deep learning | |
| CN111062388B (en) | Advertisement character recognition method, system, medium and equipment based on deep learning | |
| CN112417974A (en) | Public health monitoring method | |
| CN115984968A (en) | Student time-space action recognition method and device, terminal equipment and medium | |
| CN115424293A (en) | Living body detection method, and training method and device of living body detection model | |
| CN115311664A (en) | Method, device, medium and equipment for identifying text type in image | |
| CN111209924B (en) | System for automatically extracting medical advice and application |
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 |