CN107273681B - Intelligent sequencing system for diagnosis input - Google Patents
Intelligent sequencing system for diagnosis input Download PDFInfo
- Publication number
- CN107273681B CN107273681B CN201710436440.5A CN201710436440A CN107273681B CN 107273681 B CN107273681 B CN 107273681B CN 201710436440 A CN201710436440 A CN 201710436440A CN 107273681 B CN107273681 B CN 107273681B
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- input
- result
- module
- degree
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 129
- 238000012163 sequencing technique Methods 0.000 title claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims abstract description 43
- 238000000926 separation method Methods 0.000 claims description 7
- 208000007882 Gastritis Diseases 0.000 description 16
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 208000015181 infectious disease Diseases 0.000 description 2
- 230000002458 infectious effect Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 210000002784 stomach Anatomy 0.000 description 2
- 208000004232 Enteritis Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000002318 cardia Anatomy 0.000 description 1
- 208000023652 chronic gastritis Diseases 0.000 description 1
- 206010009887 colitis Diseases 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0237—Character input methods using prediction or retrieval techniques
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an intelligent sequencing system for diagnosis input, which comprises an initialization module, a parameter calculation module, an association degree calculation module and a result return module, wherein the initialization module is used for initialization setting and establishing a diagnosis dictionary in a diagnosis input module of an electronic medical record system; the parameter calculation module is used for calculating the number m of the phase differences, the occurrence position n and the word splitting degree o and recording the calculation results of the three parameters in a parameter record table; the correlation degree calculation module calculates the correlation degree x according to the parameter record table and records the correlation degree x value in a temporarily stored x value table in the controller; the result returning module returns the diagnosis result matching sorting result to the selection box pulled down by the input box and provides the user with the selection, so that the diagnosis result input by the user is enabled to be in accordance with the standard on one hand, and the input efficiency of the user is improved on the other hand.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to an intelligent sequencing system for diagnosis input.
Background
After the doctor makes a diagnosis according to the symptoms of the patient, the doctor needs to input a diagnosis result in an electronic medical record system. However, the diagnosis result needs to be specified to a certain degree, a dictionary of the diagnosis result exists in the electronic medical record system, the standardized expression of various disease diagnoses is provided, after a doctor inputs part of characters for diagnosis in a diagnosis input box, the content which needs to be input by the system searches for the diagnosis result which is possibly matched in the dictionary, and therefore the selection is returned to the user, and meanwhile, the input efficiency is greatly improved.
Disclosure of Invention
Aiming at the problems in the background technology, the invention aims to provide an intelligent sequencing system for diagnosis input, which is used for sequencing partial characters input in a diagnosis input box by a user and then returning the sequenced characters to the user for selection, so that on one hand, a diagnosis result input by the user is in accordance with a standard, and on the other hand, the input efficiency of the user is improved.
The technical scheme of the invention is realized as follows: the intelligent sequencing system for diagnosis input comprises an initialization module, a parameter calculation module, an association degree calculation module and a result return module, wherein the initialization module: the system is used for initializing setting, and establishing a diagnosis dictionary in a diagnosis entry module of an electronic medical record system, wherein the diagnosis dictionary is stored in a relational database mode and records the standard expression of tens of thousands of diagnosis results; a parameter calculation module: the device is used for calculating three parameters which are respectively the number m of difference words, the occurrence position n and the word splitting degree o, and recording the calculation results of the three parameters in a parameter record table which is temporarily stored in a controller of the electronic medical record system; a correlation degree calculation module: calculating the correlation degree χ according to the parameter record table by the following formula, wherein χ is exp (10-m) -0.1 xo-ln, and recording the correlation degree χ value in a χ value table temporarily stored in the controller; and a result returning module: and after the relevance degree chi value is calculated, arranging the chi values in a descending order, calling a diagnosis result from the diagnosis dictionary according to the diagnosis ID and the relation view, returning the diagnosis result matching and sequencing result to a selection box pulled down by the input box, and providing the selection for a user.
In the above technical solution, the diagnosis dictionary uses diagnosis ID as a main key, and each diagnosis result corresponds to a diagnosis name and ICD-9 code.
In the technical scheme, in the parameter calculation module, before parameter calculation, a user inputs partial characters of a target diagnosis in a diagnosis input frame, a system searches for a diagnosis result containing input characters according to the input characters, if the diagnosis result in a dictionary does not contain the input characters, the diagnosis result not containing the input characters is directly shielded, and after shielding, the system does not need to perform parameter calculation on each diagnosis result, but only performs parameter calculation on the diagnosis result containing the input characters, so that the efficiency is improved.
In the above technical solution, the number m of the phase differences refers to the number of characters that each diagnosis result is different from an input character, and the occurrence position n refers to the position where the first character of the input character appears in the diagnosis result; the degree of separation o refers to the difference in the number of characters between the first position and the last position where the input character appears in the diagnosis result minus the number of input characters.
The invention relates to an intelligent sequencing system for diagnosis input, which comprises an initialization module, a parameter calculation module, an association degree calculation module and a result return module, wherein the initialization module is used for initialization setting and establishing a diagnosis dictionary in a diagnosis input module of an electronic medical record system; the parameter calculation module is used for calculating the number m of the phase differences, the occurrence position n and the word splitting degree o and recording the calculation results of the three parameters in a parameter record table; the correlation degree calculation module calculates the correlation degree x according to the parameter record table and records the correlation degree x value in a temporarily stored x value table in the controller; the result returning module returns the diagnosis result matching sorting result to the selection box pulled down by the input box and provides the user with the selection, so that the diagnosis result input by the user is enabled to be in accordance with the standard on one hand, and the input efficiency of the user is improved on the other hand.
Drawings
FIG. 1 is a schematic partial flow diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention relates to an intelligent sequencing system for diagnosis input, which comprises an initialization module, a parameter calculation module, an association degree calculation module and a result return module. The following is a detailed description of the above modules in conjunction with fig. 1:
(1) an initialization module:
the initialization module is used for initializing setting, and a diagnosis dictionary is created in a diagnosis entry module of the electronic medical record system, is stored in a relational database mode, and records the standard expression of tens of thousands of diagnosis results. The diagnosis dictionary takes diagnosis ID as a main key, and each diagnosis result corresponds to a diagnosis name, an ICD-9 code and the like. The diagnostic dictionary representation is shown in the following table:
| diagnostic ID | Name of diagnosis | ICD-9 code |
| 00001 | Gastritis (gastritis) | |
| 00002 | Pyloritis of stomach | |
| 00003 | Inflammation of stomach fundus | |
| 00004 | Infectious gastritis | |
(2) A parameter calculation module:
the parameter calculation module is used for calculating parameters, before parameter calculation, a user inputs partial characters of a target diagnosis in the diagnosis input box, the system searches a diagnosis result containing input characters in the system according to the input characters, and if the diagnosis result in the dictionary does not contain the input characters, the diagnosis result which does not contain the input characters is directly shielded. After the shielding, the system does not need to carry out parameter calculation on each diagnosis result, but only carries out parameter calculation on the diagnosis result containing the input characters, thereby greatly improving the operation speed.
And after the preliminary screening is finished, performing parameter calculation on the screened diagnosis result, wherein the parameter calculation needs to calculate three parameters, namely the number of difference words, the appearance position and the word splitting degree.
a. Calculating the phase difference word number m: and in the screened diagnosis results, calculating the number of characters which are different from the input characters in each diagnosis result according to the characters input by the user.
b. Calculating the occurrence position n: the appearance position refers to a position where the first character of the input character appears in the diagnosis result, for example, the first character "intestine" of "enteritis" input by the user appears in the second position in "colitis".
c. And (3) calculating the word splitting degree o: the degree of separation means that the difference between the number of characters between the first position and the last position where the input character appears in the diagnosis result is subtracted by the number of input characters, for example, the difference between the number of characters is 4 when the input character "gastritis" appears in "gastritis cardia inflammation" is 1 at the first position, the last position is 4, the difference between the number of characters is 4-1+ 1-4, the number of input characters is 2, and the degree of separation is 2.
Recording the calculation results of the three parameters in a parameter record table, wherein the parameter record table is temporarily stored in a controller of the electronic medical record system, and the following table shows that:
| diagnostic ID | By a difference word number m | Occurrence position n | Degree of separation o |
(3) A correlation degree calculation module:
and the association degree calculation module is used for calculating the association degree, and calculating the association degree x according to a formula according to a parameter record table after parameter calculation is carried out on the screened diagnosis results. The formula is shown below:
χ＝exp(10-m)-0.1×o-ln n；
among the three parameters, the most significant for the matching of the diagnosis result is the number of the phase difference characters, because the fewer the phase difference characters between the diagnosis result and the input characters are, when the diagnosis result is placed above the selection box, the more concise the user feels when selecting the diagnosis result, and the better the user experience is; but also the influence on the browsing look and feel is reduced as the number of phase differences increases, so an exponential function is constructed to describe the role it plays in the degree of association.
The degree of word separation is followed, the greater the degree of word separation, the smaller the degree of association with the entered character, and the correlation relationship is positively correlated according to practical experience, so that a proportional function is given to describe the correlation.
And finally, the appearance position, and because the actual role of the appearance position in the description of the association degree is minimum, the user often needs to select a diagnosis result with the appearance position of the input character not at the front, so that a logarithmic function is given to the diagnosis result to describe the change of the association degree.
The correlation χ values are recorded in a χ value table temporarily stored in the controller, as shown in the following table:
| diagnostic ID | Value of χ |
(4) And a result returning module:
and the result returning module is used for returning the calculation result. And after the value of the relevance degree chi is calculated, arranging the chi values in a descending order, calling a diagnosis result from the diagnosis dictionary according to the diagnosis ID and the relation view, returning the diagnosis result matching and sequencing result to a selection box pulled down by an input box, and providing the selection for a user.
Therefore, on the basis that the user inputs characters in the diagnosis input box, the method compares the input characters with all the diagnosis results in the diagnosis dictionary, calculates three parameters of the number of difference characters, the appearance position and the word splitting degree, calculates the association degree x by using a standardized formula according to the three parameters, performs descending order arrangement on all the diagnosis results according to the x value, returns the diagnosis result matching result, and provides the diagnosis result matching result for the user to select.
The most important key point is that the diagnosis dictionary is pre-screened, and the correlation degree calculation formula for processing the three parameters is established by adopting different mathematical models through a large amount of practices, wherein the former greatly reduces the operation amount, and the latter establishes a scientific and effective sequencing formula.
The following is a further description taken in conjunction with a specific example:
a user inputs gastritis in a diagnosis input box, the system firstly carries out primary screening in a diagnosis dictionary according to the input character gastritis, removes diagnosis results not containing gastritis characters, and obtains the screened diagnosis results as shown in the following table:
| diagnostic ID | Name of diagnosis | ICD-9 code |
| 00001 | Gastritis (gastritis) | |
| 00002 | Pyloritis of stomach | |
| 00003 | Inflammation of stomach fundus | |
| 00004 | Infectious gastritis | |
| 00005 | Acute gastritis | |
| 00006 | Chronic gastritis | |
| 00007 | Gastric mucositis |
Through parameter operation, three parameters are respectively:
| diagnostic ID | m | n | o |
| 00001 | 0 | 1 | 0 |
| 00002 | 2 | 1 | 2 |
| 00003 | 1 | 1 | 1 |
| 00004 | 3 | 4 | 0 |
| 00005 | 2 | 3 | 0 |
| 00006 | 2 | 3 | 0 |
| 00007 | 2 | 1 | 2 |
The result of the calculation of the degree of association is:
| diagnostic ID | χ |
| 00001 | 22026.36579 |
| 00002 | 2982.857987 |
| 00003 | 8103.983928 |
| 00004 | 1095.146864 |
| 00005 | 2979.759375 |
| 00006 | 2979.759375 |
| 00007 | 2982.857987 |
Arranging the chi values in descending order:
therefore, after the sorting, the row which is the simplest and closest to the input characters is arranged above, and the row which is the farthest from the input characters is arranged below, so that the browsing and the selection of the user are greatly facilitated.
In conclusion, the intelligent sequencing system for diagnosis entry has the following beneficial effects:
1. if the result searched in the diagnosis dictionary according to the characters input by the user is not subjected to sequencing operation, and only the result is subjected to descending sequencing according to the ID of the diagnosis result, the diagnosis results which have a large number of words and a large difference and do not accord with the matching target are arranged on the top, while the diagnosis results which accord with the matching target are arranged on the bottom, and the user can find the diagnosis result to be searched only by pulling down the result one by one. The system obtains the association degree of each diagnosis result through the operation of three parameters, and after descending order arrangement, the word number difference is minimum and the arrangement which best accords with the matching target is arranged on the system, so that the selection interface is simple, and the working efficiency of the user is improved.
2. The traditional electronic medical record diagnosis input method is that a user inputs a diagnosis result by himself, and because the same disease category can be named by several names, the input result is easy to lack of uniformity and is not easy to file. In the system, each entry in the diagnosis dictionary is a diagnosis name normalized for various diseases, the character input by the user is searched for the diagnosis entry which best meets the requirement in the diagnosis dictionary, and the diagnosis result name has normalization. Meanwhile, each diagnosis result corresponds to an ICD-9 code, so that the filing of electronic medical records and the submission of the first page of medical records are greatly facilitated.
3. If the characters input by the user are not screened out, three-parameter calculation is performed on each diagnosis item in the diagnosis dictionary, the calculation amount is huge, many items do not contain input characters at all, and the calculation speed is greatly reduced. The system firstly screens out the characters input by the user in the diagnosis dictionary preliminarily, removes the items which do not contain the input characters, and then carries out parameter operation on the screened out diagnosis items for sequencing, thereby reducing a large amount of unnecessary operation and greatly improving the operation speed.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (1)
1. An intelligent sequencing system for diagnostic logging, characterized by: comprises an initialization module, a parameter calculation module, an association degree calculation module and a result return module, wherein,
an initialization module: the system is used for initializing setting, and establishing a diagnosis dictionary in a diagnosis entry module of an electronic medical record system, wherein the diagnosis dictionary is stored in a relational database mode and records the standard expression of tens of thousands of diagnosis results; the diagnosis dictionary takes diagnosis ID as a main key, and each diagnosis result corresponds to a diagnosis name and an ICD-9 code;
a parameter calculation module: the system is used for calculating three parameters which are respectively the number m of difference words, the appearance position n and the word splitting degree o, a user inputs partial characters of target diagnosis in a diagnosis input frame, the system searches for a diagnosis result containing input characters according to the input characters, and if the diagnosis result in the dictionary does not contain the input characters, the diagnosis result without the input characters is directly shielded; recording the calculation results of the three parameters in a parameter record table, and temporarily storing the parameter record table in a controller of the electronic medical record system; the difference word number m refers to the number of characters which are different between each diagnosis result and the input character, and the appearance position n refers to the position of the first character of the input character in the diagnosis result; the degree of separation o means the difference in the number of characters between the first position and the last position where the input character appears in the diagnosis result minus the number of input characters;
a correlation degree calculation module: the degree of association χ is calculated by the following formula based on the parameter record table,
x ═ exp (10-m) -0.1 xo-ln n, and the correlation degree x value is recorded in a temporarily stored x value table in the controller; and a result returning module: after the relevance degree chi value is calculated, the chi values are arranged according to a descending order and are viewed according to the relation according to the diagnosis ID
And calling a diagnosis result from the diagnosis dictionary, returning the diagnosis result matching and sequencing result to a selection box pulled down by the input box, and providing the selection for the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710436440.5A CN107273681B (en) | 2017-06-09 | 2017-06-09 | Intelligent sequencing system for diagnosis input |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710436440.5A CN107273681B (en) | 2017-06-09 | 2017-06-09 | Intelligent sequencing system for diagnosis input |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107273681A CN107273681A (en) | 2017-10-20 |
| CN107273681B true CN107273681B (en) | 2021-07-20 |
Family
ID=60067047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710436440.5A Active CN107273681B (en) | 2017-06-09 | 2017-06-09 | Intelligent sequencing system for diagnosis input |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107273681B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096187B (en) * | 2019-03-13 | 2022-01-28 | 中国平安人寿保险股份有限公司 | Information input method, device, equipment and computer readable storage medium |
| CN110660459B (en) * | 2019-08-30 | 2024-07-09 | 腾讯科技（深圳）有限公司 | Method, device, server and storage medium for medical records quality control |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025750A (en) * | 2006-09-08 | 2007-08-29 | 丁光耀 | Characteristic character string matching method based on dispersion, cross and in completeness |
| CN105468743A (en) * | 2015-11-25 | 2016-04-06 | 钟岑 | Intelligent diagnosis operation code retrieval method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10262081B2 (en) * | 2014-08-29 | 2019-04-16 | Alvin Roy Reed | Method and apparatus for improved database searching |
-
2017
- 2017-06-09 CN CN201710436440.5A patent/CN107273681B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025750A (en) * | 2006-09-08 | 2007-08-29 | 丁光耀 | Characteristic character string matching method based on dispersion, cross and in completeness |
| CN105468743A (en) * | 2015-11-25 | 2016-04-06 | 钟岑 | Intelligent diagnosis operation code retrieval method |
Non-Patent Citations (1)
| Title |
|---|
| "基于编辑距离和相似度改进的汉字字符串匹配";邵清;《电子科技》;20160930;第7-11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107273681A (en) | 2017-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9753986B2 (en) | Multi-dimensional feature merging for supporting evidence in a question and answering system | |
| CN107799160B (en) | Medication aid decision-making method and device, storage medium and electronic equipment | |
| RU2018119771A (en) | COMPARISON OF HOSPITALS FROM DECLINED HEALTH DATABASES WITHOUT OBVIOUS QUASI-IDENTIFIERS | |
| CN109215754A (en) | Medical record data processing method, device, computer equipment and storage medium | |
| CN108133752A (en) | A kind of optimization of medical symptom keyword extraction and recovery method and system based on TFIDF | |
| CN110427486B (en) | Body condition text classification method, device and equipment | |
| CN107273681B (en) | Intelligent sequencing system for diagnosis input | |
| CN112507138B (en) | Method and device for constructing special disease knowledge map, medium and electronic equipment | |
| CN108198603A (en) | A kind of nutrition dietary based on personal physical examination information recommends method | |
| CN109284761A (en) | A kind of image characteristic extracting method, device, equipment and readable storage medium storing program for executing | |
| Kahya | Classification enhancement of breast cancer histopathological image using penalized logistic regression | |
| CN107480435A (en) | A kind of automatic searching machine learning system and method applied to clinical data | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| CN113990424A (en) | Registration recommendation method and system based on electronic medical record | |
| CN113724814A (en) | Diagnosis method, diagnosis device, calculation equipment and storage medium | |
| CN109299467A (en) | Medicine text recognition method and device, sentence identification model training method and device | |
| CN110517747B (en) | Pathological data processing method and device and electronic equipment | |
| CN111599487A (en) | Traditional Chinese medicine compatibility assistant decision-making method based on correlation analysis | |
| CN113705477B (en) | Medical image recognition method, system, equipment and medium | |
| CN110889288A (en) | Chinese entity linking method and device, text processing method, text processing equipment and storage medium | |
| CN110473636B (en) | Intelligent medical advice recommendation method and system based on deep learning | |
| CN119252449A (en) | Diagnosis guidance methods, equipment, media and products based on large models | |
| Atiea et al. | Transformer-based neural network for electrocardiogram classification | |
| CN113722418A (en) | Clinical case standardization method, device, equipment and medium | |
| CN108877925A (en) | A kind of determination method and device of pneumonia cause of disease |
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 |