CN105608325B - Novel clinical case data collecting system and acquisition method - Google Patents
Novel clinical case data collecting system and acquisition method Download PDFInfo
- Publication number
- CN105608325B CN105608325B CN201511026452.8A CN201511026452A CN105608325B CN 105608325 B CN105608325 B CN 105608325B CN 201511026452 A CN201511026452 A CN 201511026452A CN 105608325 B CN105608325 B CN 105608325B
- Authority
- CN
- China
- Prior art keywords
- case report
- report table
- electronic case
- transient
- module
- 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 21
- 238000012795 verification Methods 0.000 claims abstract description 27
- 238000012937 correction Methods 0.000 claims abstract description 11
- 230000001052 transient effect Effects 0.000 claims description 112
- 238000012545 processing Methods 0.000 claims description 17
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000012015 optical character recognition Methods 0.000 description 34
- 230000000399 orthopedic effect Effects 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 6
- 239000003814 drug Substances 0.000 description 6
- 229940079593 drug Drugs 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention relates to a kind of novel clinical case data collecting system and acquisition method, the correction verification module of the identification device further comprises electronic medical records account comparison unit, the electronic medical records account comparison unit receives the first electronic medical records account that first OCR module and second OCR module are sent, second electronic medical records account, the electronic medical records account sent to first OCR module and second OCR module is compared verification, can be while raising papery case report form be converted to the work efficiency of electronic medical records account, effectively reduce the output of wrong electronic medical records account, improve the accuracy and speed of novel clinical case data collecting system.And first OCR module and second OCR module are respectively identified the papery case report form according to algorithms of different, by increasing capacitance it is possible to increase the accuracy that the electronic medical records account comparison unit is compared the first electronic medical records account and the second electronic medical records account.
Description
The application is a divisional application with application number 201310300966.2;
the application date of the original application is as follows: 7 month 17 in 2013;
the invention name of the original application is: a clinical case data acquisition system and an acquisition method.
Technical Field
The invention relates to a data acquisition system for converting a paper case report form into an electronic case report form, in particular to a novel clinical case data acquisition system, belonging to the technical field of electronic case report forms.
Background
In clinical studies or drug clinical trials, patient case reports are often collected, and the case reports used for statistical analysis in clinical studies or drug clinical trials must be electronic. At present, in most clinical research data centers, the content of a paper case report table is input into a computer by a manual input mode to form an electronic case report table, and the statistical analysis is carried out on the clinical data. In order to ensure the accuracy of data, the data needs to be entered twice or even three times, and the entered data is compared to correct data errors introduced in the manual entry process. Due to the fact that a large amount of manual intervention exists in the data management intermediate process, the work efficiency is limited, the possibility of data errors is increased in a multiple mode, and more manpower has to be added to eliminate the errors.
Chinese patent CN102968572A discloses an orthopedic case information acquisition system and an acquisition method thereof, wherein the orthopedic case information acquisition system comprises a paper case scanning acquisition module, an electronic case automatic conversion module, an orthopedic image acquisition module and a case information sharing platform; wherein, the paper case scanning acquisition module includes: the scanning module comprises a high-speed scanner, the scanning module converts paper case information of a patient into image information, and the image processing and character recognition module is document scanning software and converts the scanned image information into an electronic case text; the electronic automatic case conversion module comprises: an HL7 resource module, an HL7 comparison module, an HL7 conversion module, an HL7 application interface module and an HL7 information sending and receiving module; the orthopedics image acquisition module include: the device comprises an acquisition module, a storage module and a data transmission interface. The case information sharing platform comprises: the system comprises a paper case information interface, an electronic case information interface, an orthopedic image information data interface, a data processing module, a data storage module and a data sharing module. The orthopedic case information acquisition method comprises the following steps: (1) collecting paper orthopedic case information through a paper case scanning and collecting module; (2) collecting electronic medical information of orthopedics department through an electronic medical automatic conversion module; (3) collecting orthopedic image information through an orthopedic image collecting module; (4) transmitting the information collected in the steps to a case information sharing platform through the Internet; (5) the data sharing platform collects and arranges case information and provides the case information for doctors and patients to inquire. Although the technical scheme can convert the paper case into the electronic case, the converted electronic case is not verified, and once the converted electronic case has information errors caused by conversion, the errors cannot be verified. If wrong information exists in electronic cases inquired by doctors, patients and researchers during treatment or research, misdiagnosis of patients during treatment and inaccurate test data of clinical researches or drug clinical trials can be caused.
Disclosure of Invention
The technical problem to be solved by the invention is that in the prior art, in the process of converting a paper case report form into an electronic case report form, information errors exist in the electronic case report form due to the fact that the converted electronic case report form is not verified, and therefore, the novel clinical case data acquisition system and the novel clinical case data acquisition method for verifying the identified electronic case report form are provided.
In order to solve the technical problems, the invention is realized by the following technical scheme:
a novel clinical case data acquisition system comprises a scanning device and an identification device, wherein,
the scanning device is used for generating a case report table image by scanning a paper case report table and sending the case report table image to the identification device;
the identification device receives the case report table image sent by the scanning device and carries out image and character identification processing on the case report table image to obtain an electronic case report table; the recognition device further comprises a first OCR module, a second OCR module, and a verification module, wherein,
the first OCR module is used for carrying out image and character recognition processing on the image of the case report table to obtain a first electronic case report table and transmitting the first electronic case report table to the verification module;
the second OCR module is provided with a recognition algorithm different from that of the first OCR module, carries out image and character recognition processing on the case report table image recognized by the first OCR module to obtain a second electronic case report table, and transmits the second electronic case report table to the verification module;
the checking module is used for checking the electronic case report table and further comprises an electronic case report table comparison unit and a first checking unit,
the electronic case report table comparison unit receives a first electronic case report table and a second electronic case report table which are sent by the first OCR module and the second OCR module, compares and verifies the electronic case report tables sent by the first OCR module and the second OCR module, and outputs the first electronic case report table or the second electronic case report table as a first transient electronic case report table if the first electronic case report table is consistent with the second electronic case report table after the comparison and verification; otherwise, the inconsistent contents in the first electronic case report table and the second electronic case report table are marked and then output to the first checking unit;
the first checking unit receives the first electronic case report table and the second electronic case report table which are output after the electronic case report table comparison unit marks the electronic case report table, performs manual checking and correction on inconsistent contents marked in the first electronic case report table and the second electronic case report table, and outputs the first electronic case report table or the second electronic case report table after the manual checking and correction as a first transient electronic case report table.
The check module further comprises a syntax checking unit and a second checking unit,
the grammar checking unit receives the first transient electronic case report table, performs grammar checking on sentences in the first transient electronic case report table, and outputs the first transient electronic case report table as a second transient electronic case report table if a grammar checking result is correct; otherwise, the place in the electronic case report table which is incorrect in grammar check is output to the second checking unit after grammar error marking;
the second checking unit receives the first transient electronic case report table which is sent by the grammar checking unit and marked by the grammar error, carries out manual checking on the first transient electronic case report table, and outputs the first transient electronic case report table after the manual checking as a second transient electronic case report table.
The verification module further comprises a random interception verification unit and a third verification unit, wherein,
the random interception check unit further comprises a random interception module and a database,
the random interception module is used for receiving the second transient electronic case report table, carrying out random interception on the sentences in the second transient electronic case report table to obtain random phrases, inquiring the random phrases in the database, and outputting the second transient electronic case report table as a final electronic case report table if the random phrases are all or part of key words and key sentences; otherwise, the random phrases intercepted from the electronic case report table are output after being marked;
the database is used for receiving key words and key sentences and storing the received key words and key sentences;
and the third checking unit is used for receiving the marked second transient electronic case report table sent by the random interception module, performing manual checking on the second transient electronic case report table, and outputting the second transient electronic case report table subjected to manual checking as a final electronic case report table.
The database further comprises a storage module, an input module, and an adaptation module, wherein,
the storage module is used for receiving key words and key sentences and storing the received key words and key sentences;
the input module is used for outputting predetermined key words and key sentences to the storage module;
the self-adapting module is used for recording the times of accessing the database by the same random phrase, and if the times exceed the preset n times, the random phrase is used as a key word and a key sentence and is sent to the storage module for storage.
A clinical case data acquisition method comprises the following steps,
s0: scanning a paper case report form to generate a case report form image, and sending the case report form image;
s1: receiving a case report table image, performing image and character recognition processing on the case report table image to obtain a first electronic case report table, and outputting the first electronic case report table;
s2: receiving the case report table image identified in the step S1, performing image and character recognition processing on the case report table image by using a recognition algorithm different from that in the step S1 to obtain a second electronic case report table, and outputting the second electronic case report table;
s3: receiving the first electronic case report table and the second electronic case report table, and comparing and checking the first electronic case report table and the second electronic case report table; if the contents of the first electronic case report table and the second electronic case report table are consistent, outputting the first electronic case report table or the second electronic case report table as a first transient electronic case report table; otherwise, marking inconsistent contents in the first electronic case report table and the second electronic case report table and outputting the marked contents;
and S4, receiving the marked first electronic case report table and the marked second electronic case report table, performing manual checking and correction on the inconsistent marked contents in the first electronic case report table and the second electronic case report table, and outputting the manually checked and corrected first electronic case report table or the manually checked and corrected second electronic case report table as a first transient electronic case report table.
The method also comprises the following grammar checking steps:
s51: receiving the first transient electronic case report table, performing syntax check on sentences in the first transient electronic case report table, and outputting the transient case report table as a second transient electronic case report table if the syntax check result is correct; otherwise, marking grammar errors in the incorrect positions subjected to grammar check in the first transient electronic case report table and outputting the grammar errors;
and S52, receiving the first transient electronic case report table output after the grammar error marks, carrying out manual checking on the content of the grammar error marks on the first transient electronic case report table, and outputting the first transient electronic case report table after the manual checking as a second transient electronic case report table.
A phrase check step is also included after the syntax checking step:
s61: receiving the second transient electronic case report table, randomly intercepting sentences in the second transient electronic case report table to obtain random phrases, inquiring the random phrases in a preset database, and outputting the second transient electronic case report table as a final electronic case report table if the random phrases are all or part of key words or key sentences stored in the database; otherwise, carrying out phrase check error marking on the random phrases intercepted from the second transient electronic case report table and then outputting the random phrases;
and S62, receiving the second transient electronic case report table output after the phrase checking error mark, manually checking the random phrase of the phrase checking error mark in the second transient electronic case report table, and outputting the second transient electronic case report table after manual checking as a final electronic case report table.
The database in step S61 is generated according to the following steps:
s5' 1: storing predetermined key words and key sentences in a database;
s5' 2: and recording the times of accessing the database by the random phrase, and if the times exceed the preset n times, storing the random phrase into the database as a key word or a key sentence.
Compared with the prior art, the technical scheme of the invention has the following advantages:
(1) the novel clinical case data acquisition system comprises a checking module, wherein the checking module further comprises an electronic case report table comparison unit, the electronic case report table comparison unit receives a first electronic case report table and a second electronic case report table which are sent by a first OCR module and a second OCR module, compares and checks the electronic case report tables sent by the first OCR module and the second OCR module, outputs the first electronic case report table or the second electronic case report table as a first transient electronic case report table if the first electronic case report table and the second electronic case report table are accurate after comparison and check, otherwise marks inconsistent contents in the first electronic case report table and the second electronic case report table and manually checks the first electronic case report table and the second electronic case report table after manual check, The second electronic case report form is output in the form of a final electronic case report form. The invention can greatly improve the working efficiency of converting the paper case report form into the electronic case report form, effectively reduce the output of the wrong electronic case report form and improve the identification accuracy and the identification speed of the novel clinical case data acquisition system. And the first OCR module and the second OCR module respectively identify the paper case report form according to different algorithms, so that a case report form image can obtain the first electronic case report form and the second electronic case report form under different algorithms, and the accuracy of the comparison of the first electronic case report form and the second electronic case report form by the electronic case report form comparison unit can be improved.
(2) According to the novel clinical case data acquisition system, the check module further comprises a grammar checking unit, grammar checking can be carried out on sentences in the first transient electronic case report table, and the identification precision of the system is further improved. The verification module further comprises a random interception verification unit which can randomly intercept the sentences in the second transient electronic case report table to obtain random phrases, query the random phrases in the database, and output the second transient electronic case report table as a final electronic case report table if the random phrases are all or part of the key terms and key sentences; otherwise, marking the intercepted random phrases in the electronic case report table, carrying out manual check on the random phrases, and outputting the final-state electronic case report table after the manual check. The method can be used for verifying the accuracy of the sentences in the second transient electronic case report table, and effectively improves the identification accuracy of the system.
(3) According to the novel clinical case data acquisition system, the database further comprises a storage module, an input module and a self-adaptive module, key words and key sentences can be input according to manual input and self-adaptation of the system, the data volume of the database is increased, and accurate identification and verification of different key words and key sentences in different projects can be enhanced in the case report table identification process of the system.
Drawings
In order that the present invention may be more readily and clearly understood, reference is now made to the following detailed description of the invention taken in conjunction with the accompanying drawings, in which,
FIG. 1 is a block diagram of a novel clinical case data collection system in accordance with one embodiment of the present invention;
fig. 2 is a flow chart of a method of clinical case data acquisition in accordance with one embodiment of the present invention.
Detailed Description
Example 1
The structure of the novel clinical case data acquisition system of the invention, as shown in fig. 1, comprises a scanning device and an identification device. Wherein,
the scanning device is used for generating a case report table image by scanning a paper case report table and sending the case report table image to the identification device. The scanning device can be an electronic device such as a scanner, a camera and the like, and when a high-speed scanner or a high-speed camera is adopted, the overall acquisition speed of the system can be improved.
The identification device receives the case report table image sent by the scanning device and carries out image and character identification processing on the case report table image to obtain an electronic case report table; the recognition device further comprises a first OCR module, a second OCR module and a verification module. Wherein,
the first OCR module adopts a first OCR algorithm to perform image and character recognition processing on the image of the case report table to obtain a first electronic case report table, and transmits the first electronic case report table to the verification module. The case report table is an original data in-law file in clinical research or drug clinical trials, has a certain format and items, and all or part of the items need to be manually filled in a paper case report table by a human subject. The invention carries out OCR (Optical Character Recognition) on the case report table image filled by a tested person to obtain the electronic case report table, and finishes the conversion of the electronic data of the paper data item. The OCR module can analyze the morphological characteristics of characters according to an algorithm, judge the standard codes of the characters and store the standard codes into a computer text file according to a general format, and the existing OCR technology can process characters with poor printing quality or common handwritten characters.
And the second OCR module adopts a second OCR algorithm to perform image and character recognition processing on the case report table image recognized by the first OCR module to obtain a second electronic case report table, and transmits the second electronic case report table to the verification module. The first and second OCR algorithms are different. The first OCR module and the second OCR module respectively identify the same case report table image according to different algorithms, so that the case report table image can obtain the first electronic case report table and the second electronic case report table under different algorithms, and the accuracy of the comparison of the first electronic case report table and the second electronic case report table by the electronic case report table comparison unit can be improved.
The checking module is used for checking the electronic case report table and further comprises an electronic case report table comparison unit and a first checking unit.
The electronic case report table comparison unit receives a first electronic case report table and a second electronic case report table which are sent by the first OCR module and the second OCR module, compares and verifies the electronic case report tables sent by the first OCR module and the second OCR module, and outputs the first electronic case report table or the second electronic case report table as a first transient electronic case report table if the first electronic case report table is consistent with the second electronic case report table after the comparison and verification; otherwise, the inconsistent contents in the first electronic case report table and the second electronic case report table are marked and then output to the first checking unit.
The first checking unit receives the first electronic case report table and the second electronic case report table which are output after the electronic case report table comparison unit marks the electronic case report table, performs manual checking and correction on inconsistent contents marked in the first electronic case report table and the second electronic case report table, and outputs the first electronic case report table or the second electronic case report table after the manual checking and correction as a first transient electronic case report table. The transient report table can be used as the final output data of the invention, and can also be used as the input data of other modules for further data correction. The final state report table is an electronic case report table of a final output system.
The novel clinical case data acquisition system can greatly improve the working efficiency of converting a paper case report form into an electronic case report form, effectively reduce the output of wrong electronic case report forms and improve the identification accuracy and the identification speed of the novel clinical case data acquisition system.
As another embodiment of the present invention, on the basis of the above embodiment, the check module further includes a syntax checking unit and a second checking unit. The grammar checking unit receives the first transient electronic case report table output by the electronic case report table comparison unit, performs grammar checking on sentences in the first transient electronic case report table, and outputs the first transient electronic case report table as a second transient electronic case report table if a grammar checking result is correct; otherwise, the part of the electronic case report table which is incorrect in grammar check is output to the second checking unit after grammar error marking. The grammar checking unit can check the grammar of the sentences in the first transient electronic case report table, and further increases the recognition precision of the system.
The second checking unit receives the first transient electronic case report table which is sent by the grammar checking unit and marked by the grammar error, carries out manual checking on the first transient electronic case report table, and outputs the first transient electronic case report table after the manual checking as a second transient electronic case report table.
As another embodiment of the present invention, on the basis of any one of the above embodiments, the verification module further includes a random interception verification unit and a third verification unit. Wherein, the random interception check unit further comprises a random interception module and a database.
The random interception module is used for receiving the second transient electronic case report table, carrying out random interception on the sentences in the second transient electronic case report table to obtain random phrases, carrying out search query on the keywords searched by the random phrases in the database, considering that the random interception and verification are correct if the random phrases are all or part of the key terms and key sentences stored in the database, and outputting the second transient electronic case report table as a final electronic case report table; otherwise, the random phrases intercepted in the electronic case report table are marked and then output.
The database is used for receiving key words and key sentences and storing the received key words and key sentences, wherein the key words and key sentences are words and sentences in professional tool books such as traditional Chinese medicine dictionaries, modern Chinese dictionaries and the like.
And the third checking unit is used for receiving the marked second transient electronic case report table sent by the random interception module, performing manual checking on the second transient electronic case report table, and outputting the second transient electronic case report table subjected to manual checking as a final electronic case report table.
The invention can verify the accuracy of words and sentences in the second transient electronic case report table, thereby effectively increasing the identification accuracy of the system.
As a specific implementation of the above-mentioned embodiment of the present invention, which includes the database for storing the key words and key sentences, the database further includes a storage module, an input module, and an adaptation module. Wherein,
the storage module is used for receiving the key words and the key sentences and storing the received key words and key sentences.
The input module is used for outputting predetermined key words and key sentences to the storage module, and words and sentences in the tool books of the traditional Chinese medicine dictionary, the modern Chinese dictionary and the like are input to the input module through the input module.
The self-adapting module is used for recording the times of accessing the database by the same random phrase, and if the times exceed the preset n times, the random phrase is used as a key word and a key sentence and is sent to the storage module for storage. The database data volume can be increased according to manual input and adaptive input of key words and key sentences of the system, and the system can be enhanced to accurately identify and verify different key words and key sentences in different projects in the identification process of the case report table. Because the quantity of the medical terms is large and the medical terms are continuously created along with the development of science and technology, all the medical terms cannot be completely stored in the database, and after the self-adaptive module is adopted, the key terms and key sentences in the database can be automatically supplemented in time in a systematic way according to the identified key terms and key sentences, so that the self-adaptive module has the advantage of high real-time updating applicability.
As another specific embodiment of the present invention, the syntax detection module may be further disposed behind the random interception check unit, and is configured to receive the transient electronic case report table sent by the random check module, and perform syntax detection on the transient electronic case report table.
Example 2
As a clinical case data collecting method according to the present invention, as shown in fig. 2, it includes the steps of,
s0: scanning a paper case report form to generate a case report form image, and sending the case report form image;
s1: receiving a case report table image, performing image and character recognition processing on the case report table image to obtain a first electronic case report table, and outputting the first electronic case report table;
s2: receiving the case report table image identified in the step S1, performing image and character recognition processing on the case report table image by using a recognition algorithm different from that in the step S1 to obtain a second electronic case report table, and outputting the second electronic case report table;
s3: receiving the first electronic case report table and the second electronic case report table, and comparing and checking the first electronic case report table and the second electronic case report table; if the contents of the first electronic case report table and the second electronic case report table are consistent, outputting the first electronic case report table or the second electronic case report table as a first transient electronic case report table; otherwise, marking inconsistent contents in the first electronic case report table and the second electronic case report table and outputting the marked contents;
and S4, receiving the marked first electronic case report table and the marked second electronic case report table, manually checking and correcting the inconsistent marked contents in the first electronic case report table and the second electronic case report table, and outputting the manually checked and corrected first electronic case report table or the manually checked and corrected second electronic case report table as a final case report table.
The data acquisition method can greatly improve the working efficiency of converting the paper case report form into the electronic case report form, effectively reduce the output of wrong electronic case report forms and improve the identification accuracy and the identification speed of a novel clinical case data acquisition system. The step S1 and the step S2 are respectively performed by recognizing the paper case report form according to different algorithms, so that the first electronic case report form and the second electronic case report form can be obtained from case report form images under different algorithms, and the accuracy of comparing the first electronic case report form and the second electronic case report form by the electronic case report form comparing unit can be increased.
As another embodiment of the present invention, a syntax checking step is further included after the step S4.
S51: receiving the first transient electronic case report table, performing syntax check on sentences in the first transient electronic case report table, and outputting the transient case report table as a second transient electronic case report table if the syntax check result is correct; otherwise, marking grammar errors in the incorrect positions subjected to grammar check in the first transient electronic case report table and outputting the grammar errors;
and S52, receiving the first transient electronic case report table output after the grammar error marks, carrying out manual checking on the content of the grammar error marks on the first transient electronic case report table, and outputting the first transient electronic case report table after the manual checking as a second transient electronic case report table. The syntax checking step can perform syntax checking on the sentences in the first electronic case report table or the second electronic case report table, and further increases the recognition accuracy of the system.
As another embodiment of the present invention, a phrase checking step is further included after the syntax checking step.
S61: receiving the second transient electronic case report table, randomly intercepting sentences in the second transient electronic case report table to obtain random phrases, inquiring the random phrases in a preset database, and outputting the second transient electronic case report table as a final electronic case report table if the random phrases are all or part of key words or key sentences stored in the database; otherwise, carrying out phrase check error marking on the random phrases intercepted from the second transient electronic case report table and then outputting the random phrases;
and S62, receiving the second transient electronic case report table output after the phrase checking error mark, manually checking the random phrase of the phrase checking error mark in the second transient electronic case report table, and outputting the second transient electronic case report table after manual checking as a final electronic case report table.
The embodiment can verify the accuracy of the sentences in the second transient electronic case report table, and effectively increases the identification accuracy of the system.
In a specific implementation of the embodiment in which the key words and key sentences are sent to the storage module to store the above step including phrase checking, the database in step S61 is generated as follows.
S5' 1: pre-storing the key words and the key sentences in a database;
s5' 2: and recording the times of accessing the database by the random phrase, and if the times exceed the preset n times, storing the random phrase into the database as a key word or a key sentence. The step can automatically supplement the key words and the key sentences in the database in time according to the identified key words and key sentences, and has the advantage of high real-time updating applicability.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (2)
1. A novel clinical case data acquisition system is characterized by comprising a scanning device and an identification device, wherein,
the scanning device is used for generating a case report table image by scanning a paper case report table and sending the case report table image to the identification device;
the identification device receives the case report table image sent by the scanning device and carries out image and character identification processing on the case report table image to obtain an electronic case report table; the recognition device further comprises a first OCR module, a second OCR module, and a verification module, wherein,
the first OCR module is used for carrying out image and character recognition processing on the image of the case report table to obtain a first electronic case report table and transmitting the first electronic case report table to the verification module;
the second OCR module is provided with a recognition algorithm different from that of the first OCR module, carries out image and character recognition processing on the case report table image recognized by the first OCR module to obtain a second electronic case report table, and transmits the second electronic case report table to the verification module;
the checking module is used for checking the electronic case report table and further comprises an electronic case report table comparison unit and a first checking unit,
the electronic case report table comparison unit receives a first electronic case report table and a second electronic case report table which are sent by the first OCR module and the second OCR module, compares and verifies the electronic case report tables sent by the first OCR module and the second OCR module, and outputs the first electronic case report table or the second electronic case report table as a first transient electronic case report table if the first electronic case report table is consistent with the second electronic case report table after the comparison and verification; otherwise, the inconsistent contents in the first electronic case report table and the second electronic case report table are marked and then output to the first checking unit;
the first checking unit is used for receiving the first electronic case report table and the second electronic case report table which are output after the electronic case report table comparison unit marks the electronic case report table, carrying out manual checking and correction on inconsistent contents marked in the first electronic case report table and the second electronic case report table, and outputting the first electronic case report table or the second electronic case report table after the manual checking and correction as a first transient electronic case report table;
the check module further comprises a syntax checking unit and a second checking unit,
the grammar checking unit receives the first transient electronic case report table, performs grammar checking on sentences in the first transient electronic case report table, and outputs the first transient electronic case report table as a second transient electronic case report table if a grammar checking result is correct; otherwise, the place in the electronic case report table which is incorrect in grammar check is output to the second checking unit after grammar error marking;
the second checking unit is used for receiving the first transient electronic case report table which is sent by the grammar checking unit and marked by grammar errors, carrying out manual checking on the first transient electronic case report table, and outputting the first transient electronic case report table after manual checking as a second transient electronic case report table;
the verification module further comprises a random interception verification unit and a third verification unit, wherein,
the random interception check unit further comprises a random interception module and a database,
the random interception module is used for receiving the second transient electronic case report table, carrying out random interception on the sentences in the second transient electronic case report table to obtain random phrases, inquiring the random phrases in the database, and outputting the second transient electronic case report table as a final electronic case report table if the random phrases are all or part of key words and key sentences; otherwise, the random phrases intercepted from the electronic case report table are output after being marked;
the database is used for receiving key words and key sentences and storing the received key words and key sentences;
the third checking unit is used for receiving the marked second transient electronic case report table sent by the random interception module, performing manual checking on the second transient electronic case report table, and outputting the second transient electronic case report table subjected to manual checking as a final electronic case report table;
the database further comprises a storage module, an input module, and an adaptation module, wherein,
the storage module is used for receiving key words and key sentences and storing the received key words and key sentences;
the input module is used for outputting predetermined key words and key sentences to the storage module;
the self-adapting module is used for recording the times of accessing the database by the same random phrase, and if the times exceed the preset n times, the random phrase is used as a key word and a key sentence and is sent to the storage module for storage.
2. A clinical case data acquisition method is characterized by comprising the following steps,
s0: scanning a paper case report form to generate a case report form image, and sending the case report form image;
s1: receiving a case report table image, performing image and character recognition processing on the case report table image to obtain a first electronic case report table, and outputting the first electronic case report table;
s2: receiving the case report table image identified in the step S1, performing image and character recognition processing on the case report table image by using a recognition algorithm different from that in the step S1 to obtain a second electronic case report table, and outputting the second electronic case report table;
s3: receiving the first electronic case report table and the second electronic case report table, and comparing and checking the first electronic case report table and the second electronic case report table; if the contents of the first electronic case report table and the second electronic case report table are consistent, outputting the first electronic case report table or the second electronic case report table as a first transient electronic case report table; otherwise, marking inconsistent contents in the first electronic case report table and the second electronic case report table and outputting the marked contents;
s4, receiving the first electronic case report table and the second electronic case report table which are output after marking, carrying out manual check and correction on the inconsistent contents marked in the first electronic case report table and the second electronic case report table, and outputting the first electronic case report table or the second electronic case report table which is subjected to manual check and correction as a first transient electronic case report table;
the method also comprises the following grammar checking steps:
s51: receiving the first transient electronic case report table, performing syntax check on sentences in the first transient electronic case report table, and outputting the transient case report table as a second transient electronic case report table if the syntax check result is correct; otherwise, marking grammar errors in the incorrect positions subjected to grammar check in the first transient electronic case report table and outputting the grammar errors;
s52, receiving the first transient electronic case report table output after the grammar error marks, carrying out manual check on the content of the grammar error marks on the first transient electronic case report table, and outputting the first transient electronic case report table after the manual check as a second transient electronic case report table;
a phrase check step is also included after the syntax checking step:
s61: receiving the second transient electronic case report table, randomly intercepting sentences in the second transient electronic case report table to obtain random phrases, inquiring the random phrases in a preset database, and outputting the second transient electronic case report table as a final electronic case report table if the random phrases are all or part of key words or key sentences stored in the database; otherwise, carrying out phrase check error marking on the random phrases intercepted from the second transient electronic case report table and then outputting the random phrases;
s62, receiving the second transient electronic case report table output after the phrase checking error mark, carrying out manual checking on the random phrase of the short-language checking error mark in the second transient electronic case report table, and outputting the second transient electronic case report table after the manual checking as a final electronic case report table;
the database in step S61 is generated according to the following steps:
s5' 1: storing predetermined key words and key sentences in a database;
s5' 2: recording the times of accessing the database by the same random phrase, and if the times exceed the preset n times, storing the random phrase into the database as a key word or a key sentence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511026452.8A CN105608325B (en) | 2013-07-17 | 2013-07-17 | Novel clinical case data collecting system and acquisition method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511026452.8A CN105608325B (en) | 2013-07-17 | 2013-07-17 | Novel clinical case data collecting system and acquisition method |
CN201310300966.2A CN103425975B (en) | 2013-07-17 | 2013-07-17 | A kind of clinical case data collecting system and acquisition method |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310300966.2A Division CN103425975B (en) | 2013-07-17 | 2013-07-17 | A kind of clinical case data collecting system and acquisition method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105608325A CN105608325A (en) | 2016-05-25 |
CN105608325B true CN105608325B (en) | 2018-05-15 |
Family
ID=49650686
Family Applications (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201511021528.8A Expired - Fee Related CN105550524B (en) | 2013-07-17 | 2013-07-17 | A kind of clinical case data collecting system and acquisition method |
CN201310300966.2A Expired - Fee Related CN103425975B (en) | 2013-07-17 | 2013-07-17 | A kind of clinical case data collecting system and acquisition method |
CN201511026452.8A Active CN105608325B (en) | 2013-07-17 | 2013-07-17 | Novel clinical case data collecting system and acquisition method |
CN201511021525.4A Expired - Fee Related CN105468929B (en) | 2013-07-17 | 2013-07-17 | Clinical case data collecting system and acquisition method |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201511021528.8A Expired - Fee Related CN105550524B (en) | 2013-07-17 | 2013-07-17 | A kind of clinical case data collecting system and acquisition method |
CN201310300966.2A Expired - Fee Related CN103425975B (en) | 2013-07-17 | 2013-07-17 | A kind of clinical case data collecting system and acquisition method |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201511021525.4A Expired - Fee Related CN105468929B (en) | 2013-07-17 | 2013-07-17 | Clinical case data collecting system and acquisition method |
Country Status (1)
Country | Link |
---|---|
CN (4) | CN105550524B (en) |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105786934B (en) * | 2014-12-26 | 2020-06-12 | 北大医疗信息技术有限公司 | Medical record document defect processing method and system |
CN104915668B (en) * | 2015-05-29 | 2019-02-26 | 深圳市红源资产管理有限公司 | Text information recognition methods and device in medical image |
CN107145734B (en) * | 2017-05-04 | 2020-08-28 | 深圳市联新移动医疗科技有限公司 | Automatic medical data acquisition and entry method and system |
CN107609077A (en) * | 2017-09-04 | 2018-01-19 | 中国核工业第五建设有限公司 | Wlding approaches to IM |
CN107833600A (en) * | 2017-10-25 | 2018-03-23 | 医渡云(北京)技术有限公司 | Medical data typing check method and device, storage medium, electronic equipment |
CN107767929B (en) * | 2017-11-13 | 2024-04-05 | 医渡云(北京)技术有限公司 | Case report form filling method and device, electronic equipment and storage medium |
CN107767924A (en) * | 2017-11-13 | 2018-03-06 | 医渡云(北京)技术有限公司 | Initial data checking method, device, electronic equipment and storage medium |
CN108597565B (en) * | 2018-04-11 | 2021-07-02 | 浙江大学 | Clinical queue data collaborative verification method based on OCR and named entity extraction technology |
CN109102844B (en) * | 2018-08-24 | 2022-02-15 | 北京锐客科技有限公司 | Automatic calibration method for clinical test source data |
CN109616166B (en) * | 2018-11-09 | 2021-02-26 | 金色熊猫有限公司 | Medical data registration management method and device, electronic device and storage medium |
CN109583358A (en) * | 2018-11-26 | 2019-04-05 | 广东智源信息技术有限公司 | A kind of Medical Surveillance fast accurate enforcement approach |
CN109919253A (en) * | 2019-03-27 | 2019-06-21 | 北京爱数智慧科技有限公司 | Character identifying method, device, equipment and computer-readable medium |
CN109979547A (en) * | 2019-04-08 | 2019-07-05 | 皮敏 | A kind of novel clinical case data collection system and acquisition method |
CN112116968A (en) * | 2019-06-21 | 2020-12-22 | 上海交通大学医学院附属瑞金医院 | Medical examination report recognition method, device, equipment and storage medium |
CN110675924B (en) * | 2019-08-19 | 2023-03-10 | 医渡云(北京)技术有限公司 | Method and device for automatically generating case report table, readable medium and electronic equipment |
CN110490185A (en) * | 2019-08-23 | 2019-11-22 | 北京工业大学 | One kind identifying improved method based on repeatedly comparison correction OCR card information |
CN112308070B (en) * | 2020-10-30 | 2024-04-26 | 深圳前海微众银行股份有限公司 | Identification method and device for certificate information, equipment and computer readable storage medium |
CN113052557A (en) * | 2021-03-30 | 2021-06-29 | 贵州数智联云工程科技有限公司 | Three-dimensional model generation and analysis system and method for approval |
CN113724825A (en) * | 2021-09-06 | 2021-11-30 | 浙江海心智惠科技有限公司 | Medical record OCR-based patient and education video diagnosis and treatment scheme selecting and matching system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000132635A (en) * | 1998-10-29 | 2000-05-12 | Hitachi Ltd | Recognizing data confirming method |
JP2002157545A (en) * | 2000-11-22 | 2002-05-31 | Nippon Express Co Ltd | Method for reading and transferring document |
KR20100133663A (en) * | 2009-06-12 | 2010-12-22 | 김혁만 | Apparatus and method for generating electronic case report form, system and method for servicing clinical trial by using it |
CN201996534U (en) * | 2011-03-18 | 2011-10-05 | 车飞沦 | Clinical medical intelligent diagnosis and treatment system |
CN102999698A (en) * | 2012-11-21 | 2013-03-27 | 无锡市妇幼保健院 | System and method for managing potential critical diseases |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1116342A (en) * | 1994-07-08 | 1996-02-07 | 唐武 | Chinese automatic proofreading method and system thereof |
FR2851357B1 (en) * | 2003-02-19 | 2005-04-22 | Solystic | METHOD FOR THE OPTICAL RECOGNITION OF POSTAL SENDS USING MULTIPLE IMAGES |
CN100556062C (en) * | 2007-01-10 | 2009-10-28 | 刘强 | Based on the method for multiple OCR scheme combination verification with accurate extraction numeral |
JP2009146340A (en) * | 2007-12-18 | 2009-07-02 | Konica Minolta Medical & Graphic Inc | Medical image system, examination order generation device and program |
US8954339B2 (en) * | 2007-12-21 | 2015-02-10 | Koninklijke Philips N.V. | Detection of errors in the inference engine of a clinical decision support system |
CN101236579A (en) * | 2008-02-20 | 2008-08-06 | 杭州创业软件股份有限公司 | Dynamic structured electronic patient history |
CN101615225A (en) * | 2009-05-25 | 2009-12-30 | 刘晓峰 | Portable individual electronic medical record and read-write device matched with same |
CN101710369A (en) * | 2009-12-18 | 2010-05-19 | 北京华大智宝电子***有限公司 | Electronic medical record system for assisting in diagnosis and treatment and running method thereof |
CN101887519B (en) * | 2010-08-16 | 2012-04-18 | 同方知网(北京)技术有限公司 | Character recognition and modification method |
CN101984448A (en) * | 2010-12-24 | 2011-03-09 | 中山大学孙逸仙纪念医院 | Electronic medical record database system |
-
2013
- 2013-07-17 CN CN201511021528.8A patent/CN105550524B/en not_active Expired - Fee Related
- 2013-07-17 CN CN201310300966.2A patent/CN103425975B/en not_active Expired - Fee Related
- 2013-07-17 CN CN201511026452.8A patent/CN105608325B/en active Active
- 2013-07-17 CN CN201511021525.4A patent/CN105468929B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000132635A (en) * | 1998-10-29 | 2000-05-12 | Hitachi Ltd | Recognizing data confirming method |
JP2002157545A (en) * | 2000-11-22 | 2002-05-31 | Nippon Express Co Ltd | Method for reading and transferring document |
KR20100133663A (en) * | 2009-06-12 | 2010-12-22 | 김혁만 | Apparatus and method for generating electronic case report form, system and method for servicing clinical trial by using it |
CN201996534U (en) * | 2011-03-18 | 2011-10-05 | 车飞沦 | Clinical medical intelligent diagnosis and treatment system |
CN102999698A (en) * | 2012-11-21 | 2013-03-27 | 无锡市妇幼保健院 | System and method for managing potential critical diseases |
Also Published As
Publication number | Publication date |
---|---|
CN105550524B (en) | 2018-02-13 |
CN105608325A (en) | 2016-05-25 |
CN103425975A (en) | 2013-12-04 |
CN105550524A (en) | 2016-05-04 |
CN105468929B (en) | 2018-01-02 |
CN105468929A (en) | 2016-04-06 |
CN103425975B (en) | 2016-05-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105608325B (en) | Novel clinical case data collecting system and acquisition method | |
CN105844088B (en) | Universal clinical test Electronic environm entalsensor and acquisition methods | |
JP6706315B2 (en) | Computer-implemented method, system, and computer program for identifying errors in medical data | |
EP3879475A1 (en) | Method of classifying medical documents | |
US10503830B2 (en) | Natural language processing with adaptable rules based on user inputs | |
US20120022850A1 (en) | Statistical machine translation processing | |
KR20100031800A (en) | Method and apparatus for detecting errors of machine translation using parallel corpus | |
US9754083B2 (en) | Automatic creation of clinical study reports | |
US20040139384A1 (en) | Removal of extraneous text from electronic documents | |
US20030200079A1 (en) | Cross-language information retrieval apparatus and method | |
CN110750540A (en) | Method for constructing medical service knowledge base, method and system for obtaining medical service semantic model and medium | |
CN108597565A (en) | It is a kind of that method of calibration is cooperateed with the clinical queuing data of name entity extraction technology based on OCR | |
CN112380848B (en) | Text generation method, device, equipment and storage medium | |
CN103425976B (en) | A kind of case report table identification system and recognition methods | |
KR101966627B1 (en) | Medical documents translation system for mobile | |
CN113642562A (en) | Data interpretation method, device and equipment based on image recognition and storage medium | |
CN116469505A (en) | Data processing method, device, computer equipment and readable storage medium | |
WO2016059505A1 (en) | A system and a method for recognition of aerospace parts in unstructured text | |
TWI712979B (en) | System and method for processing insurance claims using long short-term memory model of deep learning | |
JP2018181370A (en) | Medicine name output device, medicine name output method and medicine name output program | |
KR102338949B1 (en) | System for Supporting Translation of Technical Sentences | |
Balasooriya | Improving and Measuring OCR Accuracy for Sinhala with Tesseract OCR Engine | |
CN113936787A (en) | Method and tool for realizing hospital diagnosis service data splitting and correcting | |
KR20230020155A (en) | Prescription ocr recognition method and prescription ocr recognition system | |
CN114416980A (en) | Asset duplicate checking method, system and equipment based on intelligent classification and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |