CN110867228A - Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient - Google Patents
Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient Download PDFInfo
- Publication number
- CN110867228A CN110867228A CN201911116794.7A CN201911116794A CN110867228A CN 110867228 A CN110867228 A CN 110867228A CN 201911116794 A CN201911116794 A CN 201911116794A CN 110867228 A CN110867228 A CN 110867228A
- Authority
- CN
- China
- Prior art keywords
- wound
- severity
- trauma
- scoring
- description
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to an intelligent information grasping and evaluating method and system for the wound severity of a wound inpatient. The method comprises the steps of extracting scoring related information used for scoring the severity of the wound from medical record information, comparing the extracted scoring related information with a wound severity scoring standard to form a wound severity score, analyzing the medical record to obtain the text content of the medical record, analyzing the wound severity scoring standard to obtain the name of a wound part and the name of a wound condition, searching and positioning through a keyword of the wound part and the keyword of the name of the wound condition to obtain a sentence describing the wound as a wound example of the medical record, calculating and obtaining k wound description samples most similar to the wound example by utilizing a word vector and a KNN algorithm, scoring the severity of the wound corresponding to most of the wound description samples into the wound severity score of the wound description example, and achieving automatic scoring. The system includes a processor for score calculation, and program memory and data memory.
Description
Technical Field
The invention relates to an intelligent information capturing and evaluating method for the wound severity of a wound inpatient, and also relates to an intelligent information capturing and evaluating system for the wound severity of the wound inpatient by adopting the method, belonging to the technical field of medical treatment and data processing.
Background
The medical record refers to the sum of characters, symbols, diagrams, images, slices and other data formed by medical staff in the process of medical activities, and comprises an outpatient (emergency) medical record and an inpatient medical record.
The wound scoring method is to adopt a standard method to evaluate the severity of the wound of a wound patient so as to facilitate comparability between different diagnoses, and since the first time a wound Score is proposed by De Haven in 1952, a scoring system is continuously developed and perfected, wherein AIS (Abbreviated Injury Scale, concise Injury rating Scale) -ISS (Injury severity Score) is the most internationally applied hospital assessment system at present.
However, the existing work of scoring the severity of the wound in the hospital in China is still deficient, doctors have no time to consider the scoring of the severity of the wound in busy work, so that the scoring of the severity of the wound is rarely recorded in hospital records, but related information serving as the basis of scoring is generally recorded in the hospital records. Therefore, if such related information could be utilized to automatically generate related scores without substantially increasing the workload on the physician, it would be helpful to solve the problem of lack of scores that is common today.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an intelligent information grasping and evaluating method and system for the wound severity of the trauma inpatient, so that the related information in the medical record is utilized to automatically generate a wound severity score.
The technical scheme of the invention is as follows: the intelligent information grasping and evaluating method for the wound severity of the hospitalized wound patient extracts scoring related information for scoring the wound severity from medical record information, and compares the extracted scoring related information with a wound severity scoring standard to form a wound severity score.
The medical record is analyzed to obtain the text content.
Analyzing the scoring standard of the severity of the wound to obtain the name of the wound part, the name of the wound condition and the name of the wound condition corresponding to the name of the wound part.
And searching in the text content of the medical record by taking the name of the wound part as the keyword of the wound part, and positioning or marking the position of each keyword of the wound part obtained by searching in the text content of the medical record.
And searching in the text content of the medical record by taking the wound condition name as a wound condition keyword, and positioning or marking the position of each wound part keyword obtained by searching in the text content of the medical record.
Intercepting any wound part keyword in the text content of the medical record, taking the sentence where the wound part keyword is located to the adjacent sentence (contained) where the corresponding wound condition keyword is located as a wound description example (score related information) of the medical record, comparing the wound description example with the wound description samples of the same wound part in a wound description sample library to obtain the same wound description sample or the most similar (most adjacent) k wound description samples, and scoring the wound severity of the wound description example by using the wound severity score corresponding to the same wound description sample or scoring the wound severity score corresponding to the most similar wound description samples in the k wound description samples, wherein k is a positive integer greater than 1.
When there are two groups of samples with the highest number among the k most similar wound description samples, and the samples correspond to two different scores, the wound severity score of the wound description example is given by a higher score value.
And according to the scoring standard, dividing any scoring area, and taking the maximum value of the wound severity scores of all wound description examples of the wound positions contained in the dividing area as the wound severity score of the scoring area.
The word content of the medical record can be segmented by using NLP (Natural Language Processing) technology.
Words may be represented as word vectors using word2vec (word to vector) techniques.
According to the practical situation, the word segmentation and word vector conversion can be carried out on the wound description sample of the text content in the same way.
A kNN (K-Nearest Neighbor, Neighbor algorithm or K Nearest Neighbor classification algorithm) technique may be adopted, where the number of samples is set to K, K is a positive integer greater than 1, and the distance between the wound description example and the wound description sample is used as a similar judgment criterion.
When a wound description sample identical to the wound description example appears, the distance calculation and the approximation judgment are stopped, and the wound severity score of the wound description sample identical to the wound description example is divided into the wound severity score of the wound description example.
In the case where there is no wound description sample identical to the wound description example, all the wound description samples of the same wound site in the wound description sample library are traversed, and the wound severity score of the wound description example is scored by the wound severity score corresponding to the majority of the k wound description samples most similar to the wound description example.
Comma, sentence and semicolon are used as sentence boundary points, and the text content between adjacent sentence boundary points is a sentence.
When intercepting the example of the wound description, it is preferable to ignore the sentence where the wound site keyword is located to the adjacent sentence where the corresponding wound condition keyword is located.
Preferably, a maximum sentence interval or a maximum sentence distance (a distance in terms of a calculation unit of a sentence) between a sentence where the wound site keyword is located and an adjacent sentence where the wound condition keyword is located is set, for example, a maximum interval of 1 or 2 sentences, and when a wound description example is extracted, if any wound site keyword does not have a wound condition keyword corresponding thereto within the maximum sentence interval or the maximum sentence distance, the wound site keyword is ignored.
And establishing a wound description sample library for the wound description sample by using the related description in the actual medical record, and manually determining the wound severity score corresponding to the wound description sample according to the corresponding wound severity score standard.
The scoring value may serve as a corresponding label for the wound description sample.
The system for intelligently grabbing and evaluating the wound severity of the trauma inpatient comprises a program memory, a data acquisition unit and a data processor, and is characterized in that the program memory stores a scoring program for realizing any one of the methods for grabbing and evaluating the wound severity of the trauma inpatient, the data processor calls and operates the scoring program, acquires medical record information through the data acquisition unit, extracts scoring related information for scoring the wound severity from the medical record information, and compares the extracted scoring related information with a wound severity scoring standard to form a wound severity score.
The data processor is provided with a communication module for wireless and/or wired communication, and is connected or not connected with a computer network.
The data processor is connected with a display device for displaying information.
The data processor is connected with a local data memory for storing non-program data.
The invention has the beneficial effects that: relevant information in the existing medical records is fully utilized, intellectualization of hospital trauma scoring is achieved, burden of doctors is basically not increased, and the problem that diagnosis conclusion comparison is difficult among different medical institutions in different periods due to lack of uniform scoring at present is effectively solved.
The invention is not only suitable for inpatients, but also suitable for outpatients and other similar occasions.
Detailed Description
The invention adopts the existing equipment to realize corresponding data processing, can be an independent computer and auxiliary equipment, can also be a computer system, can be provided with a central control computer, and can also adopt distributed or cloud computing and cloud storage.
The computer system comprises a program memory, a data acquisition unit and a data processor, wherein the program memory stores a scoring program for realizing the invention, the data processor calls and runs the scoring program, acquires medical record information through the data acquisition unit, extracts scoring related information for scoring the wound severity from the medical record information, and compares the extracted scoring related information with a wound severity scoring standard to form a wound severity score.
Generally, an existing computer information management system or computer-aided diagnosis and treatment system of a medical institution may be used.
Typically, the computer network of the facility or the internet is accessed, and the network typically obtains sample information, e.g., reads medical records from the facility's database, and/or crawls medical records from the network.
The acquisition and the use of the medical records are in compliance, desensitization treatment is carried out if necessary, and personal privacy information irrelevant to diagnosis and treatment is deleted.
The device configuration may be performed according to the prior art. For example:
the data processor may be provided with a communication module for wireless and/or wired communication, with or without access to a computer network.
The data processor may be connected to a display device and/or a printing apparatus for displaying and printing information, respectively.
The data processor may be connected to a local data store for storing non-program data.
Personal health (medical) profiles may be created and stored in a local data store and/or a remote storage facility in accordance with existing diagnostic systems.
The basic content of the intelligent information grasping and evaluating method for the wound severity of the trauma inpatient is as follows: and extracting scoring related information for scoring the severity of the wound from the medical record information, and comparing the extracted scoring related information with a scoring standard of the severity of the wound to form a score of the severity of the wound.
The information extraction and comparison may be performed in any suitable manner.
The digital medical record can be directly processed without being converted into characters, images and the like.
The medical record is analyzed to obtain the text content.
Any suitable prior art can be adopted to carry out corresponding analysis on the electronic medical record. For example, the text content may be recognized by using or converting the text content into a uniform format such as HTML or the like, based on a tag, a label, a control, or the like.
The text contents of a plurality of files in the medical record can be spliced into one file. May take the form of a plain text file or the like.
Analyzing the adopted wound severity scoring standard to obtain the name of the wound part, the name of the wound condition and the name of the wound condition corresponding to the name of the wound part.
Although the description of the wound site and wound condition is generally normative, the possibility that the same or similar terms exist should be considered, and thus, in determining the name of the wound site and the name of the wound condition, terms that are the same as or similar to those used in the wound severity scoring criteria that exist in practice are included. These tasks may advantageously be performed manually.
For convenience of description, in the following description, the name of the wound site or the name of the wound condition includes terms related to the wound severity scoring criteria and also includes terms which are identical or similar to those used in practice for the wound severity scoring criteria.
The method can establish the logical relationship among the trauma position, the trauma state (symptom) and the trauma severity scoring value through manual analysis according to a corresponding scoring table or other rules, establish a data table reflecting the logical relationship among related data (fields) and store the data table in a data memory of the system, and utilize a relational database technology to input, modify, query and the like the related data. Other fields, such as partitions, may be set according to actual needs.
The severity score of the wound corresponding to each wound condition of each part of the body can be determined according to the scoring table, and the score under each wound condition is determined, so that the scoring value is necessarily determined after obtaining the description of the wound condition consistent with the scoring table.
However, in practice, the description of the wound condition is not based on the description mode of the scoring table, the description of the same condition is different, and different doctors have different word habits and expression modes, so that the problems of how to obtain the related wound description from the medical record and how to correspond the different wound descriptions to the wound description of the scoring table need to be solved.
Firstly, the description of the wound in the medical record needs to be found, and according to the text recording mode of the medical record, the name of the wound part can be used as the key word of the wound part to search in the text content of the medical record, and the position of each key word of the wound part obtained by searching in the text content of the medical record can be positioned or marked.
And searching in the text content of the medical record by taking the wound condition name as a wound condition keyword, and positioning or marking the position of each wound part keyword obtained by searching in the text content of the medical record.
For any wound part keyword in the text contents of the medical record, intercepting all text contents from the sentence where the wound part keyword is located to the adjacent sentence where the corresponding wound condition keyword is located (including) as a wound description example of the medical record. Although this interception may involve textual information not related to the corresponding wound, it is believed that substantially all of the wound documentation is contained.
Comparing the wound description sample with wound description samples of the same wound site in the wound description sample library to obtain the same wound description sample or the k most similar (nearest) wound description samples, and scoring the wound severity of the wound description sample according to the wound severity score corresponding to the same wound description sample or scoring the wound severity of the wound description sample according to the plurality of wound description samples in the k most similar wound description samples.
k is a positive integer greater than 1.
And according to the scoring standard, dividing any scoring area, and taking the maximum value of the wound severity scores of all wound description examples of the wound positions contained in the dividing area as the wound severity score of the scoring area.
In the background of the prior art, artificial intelligence has not achieved the real understanding of the description of the wound, so that the "understanding" of the description of the wound needs to be achieved through learning existing cases (samples) in an empirical mode, and whether the descriptions are "similar" needs to be judged.
The textual content of the medical records may be segmented using NLP (Natural Language Processing) techniques, such as fdlp (fudannlp).
Words may be represented as word vectors using word2vec (word to vector) techniques, for example, using a Bag-of-words model.
According to actual needs, the trauma description sample of the text content can be subjected to word segmentation and word vector conversion in the same way, so that the two are comparable and related operations can be used.
A kNN (K-nearest neighbor, neighbor algorithm or K nearest neighbor classification algorithm) technique may be used to set the number of nearest neighbor samples K, K being a positive integer greater than 1, such as 3 or 5 or 7 or 11, and the distance (proximity) between the wound description sample and the wound description sample is taken as a close judgment criterion.
When a wound description sample identical to the wound description example appears, the distance calculation and the approximation judgment are stopped, and the wound severity score of the wound description sample identical to the wound description example is divided into the wound severity score of the wound description example.
In the case where there is no wound description sample identical to the wound description example, all the wound description samples of the same wound site in the wound description sample library are traversed, and the wound severity score of the wound description example is scored by the wound severity score corresponding to the majority of the k wound description samples most similar to the wound description example.
Comma, sentence and semicolon are used as sentence boundary points, and the text content between adjacent sentence boundary points is a sentence.
Punctuation marks such as colon, parenthesis, dash, etc. are generally not suitable as sentence boundary points.
When intercepting the example of the wound description, it is preferable to ignore the sentence where the wound site keyword is located to the adjacent sentence where the corresponding wound condition keyword is located.
When the wound description example is extracted, it is preferable to set a maximum term interval or a maximum term distance (a distance in terms of a calculation unit) between a term in which the wound site keyword is located and an adjacent term in which the corresponding wound condition keyword is located, for example, a maximum interval of 1 or 2 terms, and to ignore the wound site keyword when there is no corresponding wound condition keyword in the maximum term interval or the maximum term distance range.
And establishing a wound description sample library for the wound description sample by using the related description in the actual medical record, and manually determining a wound severity score corresponding to the wound description sample according to a corresponding wound severity score standard to serve as a corresponding label of the wound description sample.
To ensure the accuracy of the result, a large sample size should be selected, and these samples should be usually related to records in actual medical cases, but possible expressions can also be introduced as samples, so as to make the coverage of the samples more comprehensive and avoid the limitation of sample collection.
Since the medical record in practice is often silent on the score of the severity of the wound, and even if the score of the severity of the wound is recorded, the score is the score of the wound with the best score when a plurality of wounds exist according to the general scoring rule, and the score of the corresponding value of other wounds is not recorded. Therefore, existing medical records are often used only as samples of wound descriptions, and manual scoring of the wound severity is required for the wound descriptions used as samples.
In view of the above, when multiple wounds are described in the same medical record, the description of each wound should be separately extracted and assigned a score value manually, and used as an independent sample.
Similarly, even if only one wound is documented in a case, the description of the wound should be extracted separately and assigned manually with a score value, ignoring other information in the case for use as a separate sample.
The description used as a sample should include all the information involved in the scoring, e.g., wound site, wound condition, and score value, and for case records that do not contain all the information required, the information should be discarded or supplemented without changing the description of the wound condition.
Claims (10)
1. The intelligent information grasping and evaluating method for the wound severity of the hospitalized wound patient extracts scoring related information for scoring the wound severity from medical record information, and compares the extracted scoring related information with a wound severity scoring standard to form a wound severity score.
2. The method as claimed in claim 1, wherein the intelligent information capturing and evaluating method for the wound severity of the hospitalized trauma patient comprises analyzing the medical record, obtaining the text content thereof, analyzing the scoring standard for the wound severity, obtaining the name of the trauma part, the name of the trauma part and the name of the trauma part corresponding to the name of the trauma part, searching in the text content of the medical record by using the name of the trauma part as the keyword of the trauma part, locating or marking the position of each keyword of the trauma part obtained by searching in the text content of the medical record, intercepting any keyword of the trauma part in the text content of the medical record to the whole text content between the adjacent sentences in which the keyword of the trauma part is located and the corresponding to describe a wound of the medical record Comparing the wound description example with wound description samples of the same wound position in a wound description sample library to obtain the same wound description sample or the k most similar wound description samples, and scoring the wound severity of the wound description example according to the wound severity score corresponding to the same wound description sample or scoring the wound severity of the wound description example according to the wound severity scores corresponding to the plurality of wound description samples in the k most similar wound description samples.
3. The method for intelligently capturing and evaluating the wound severity of a trauma inpatient as claimed in claim 2, wherein NLP technology is used to segment words from the text of a medical record, word2vec technology is used to represent words as word vectors, kNN technology is used to set the number of samples to k, k is a positive integer greater than 1, the distance between a wound description example and a wound description sample is used as a similar judgment standard, when a wound description sample identical to the wound description example appears, the distance calculation and the similar judgment are stopped, the wound severity score of the wound description sample identical to the wound description example is used as the wound severity score of the wound description example, and in the absence of the wound description sample identical to the wound description example, all the wound description samples of the same wound part in the wound description sample library are traversed, and the wound severity scores corresponding to the majority of the k wound description samples most similar to the wound description example are used The severity score is the wound severity score of the wound description example.
4. The intelligent information capture and assessment method for the wound severity of the trauma inpatient as claimed in claim 3, wherein comma, period and semicolon are used as sentence boundary points, and the text content between adjacent sentence boundary points is a sentence.
5. The intelligent information capture and assessment method for wound severity of trauma inpatient as claimed in any one of claims 2-4, wherein when intercepting the instance of the trauma description, the sentence where the keyword of the trauma site is located is ignored to the adjacent sentence where the keyword of the trauma status is located.
6. The intelligent information capture and assessment method for wound severity of trauma inpatient as claimed in any one of claims 2 to 4, wherein the maximum sentence interval or maximum sentence distance between the sentence where the trauma site keyword is located and the adjacent sentence where the trauma condition keyword corresponding to the trauma site keyword is located is set, and when the trauma description example is intercepted, if any trauma site keyword has no trauma condition keyword corresponding to it within the maximum sentence interval or maximum sentence distance range, the trauma site keyword is ignored.
7. The intelligent information capture and assessment method for wound severity of trauma inpatient according to any one of claims 2-4, characterized in that a database of wound description samples is established for the wound description samples based on the relevant descriptions in the actual medical records, and the corresponding wound severity scores of the wound description samples are manually determined according to the corresponding wound severity scoring criteria.
8. The intelligent information grasping and evaluating system for the wound severity of the trauma inpatient comprises a program memory, a data collector and a data processor, and is characterized in that the program memory stores a scoring program for realizing the intelligent information grasping and evaluating method for the wound severity of the trauma inpatient according to any one of claims 1 to 7, the data processor invokes and runs the scoring program, obtains medical record information through the data collector, extracts scoring related information for scoring the wound severity from the medical record information, and compares the extracted scoring related information with a scoring standard for the wound severity to form a score for the wound severity.
9. The intelligent wound severity information capture and assessment system for trauma hospitalized patients according to claim 8, wherein said data processor is provided with a communication module for wireless and/or wired communication with or without access to a computer network.
10. The intelligent wound severity information capture and assessment system for trauma hospitalized patients according to claim 8 or 9, wherein said data processor is connected to a display device for displaying information, and said data processor is connected to a local data storage device for storing non-program data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911116794.7A CN110867228B (en) | 2019-11-15 | 2019-11-15 | Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911116794.7A CN110867228B (en) | 2019-11-15 | 2019-11-15 | Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110867228A true CN110867228A (en) | 2020-03-06 |
| CN110867228B CN110867228B (en) | 2023-01-17 |
Family
ID=69653780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911116794.7A Active CN110867228B (en) | 2019-11-15 | 2019-11-15 | Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110867228B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111710408A (en) * | 2020-04-16 | 2020-09-25 | 禹宝庆 | Intelligent decision making system and method for wound emergency treatment |
| CN112053771A (en) * | 2020-09-08 | 2020-12-08 | 南通市第一人民医院 | Wound patient material use management method and system |
| CN116776105A (en) * | 2023-08-22 | 2023-09-19 | 北京大学人民医院 | Method and device for constructing wound data safety management system and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100076780A1 (en) * | 2008-09-23 | 2010-03-25 | General Electric Company, A New York Corporation | Methods and apparatus to organize patient medical histories |
| CN105719217A (en) * | 2016-01-25 | 2016-06-29 | 山东海博科技信息系统有限公司 | Legal medical expert injury identification management method and system |
| US20160188832A1 (en) * | 2014-12-30 | 2016-06-30 | Cerner Innovation, Inc. | Physiologic Severity of Illness Score for Acute Care Patients |
| CN106326640A (en) * | 2016-08-12 | 2017-01-11 | 上海交通大学医学院附属瑞金医院卢湾分院 | Medical speech control system and control method thereof |
| CN106874643A (en) * | 2016-12-27 | 2017-06-20 | 中国科学院自动化研究所 | Build the method and system that knowledge base realizes assisting in diagnosis and treatment automatically based on term vector |
| CN107656952A (en) * | 2016-12-30 | 2018-02-02 | 青岛中科慧康科技有限公司 | The modeling method of parallel intelligent case recommended models |
| US20180075194A1 (en) * | 2016-09-12 | 2018-03-15 | International Business Machines Corporation | Medical Condition Independent Engine for Medical Treatment Recommendation System |
| CN107887036A (en) * | 2017-11-09 | 2018-04-06 | 北京纽伦智能科技有限公司 | Construction method, device and the clinical decision accessory system of clinical decision accessory system |
| US20180121618A1 (en) * | 2016-11-02 | 2018-05-03 | Cota Inc. | System and method for extracting oncological information of prognostic significance from natural language |
| CN109545373A (en) * | 2018-11-08 | 2019-03-29 | 新博卓畅技术（北京）有限公司 | A kind of automatic abstracting method of human body diseases symptom characteristic, system and equipment |
-
2019
- 2019-11-15 CN CN201911116794.7A patent/CN110867228B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100076780A1 (en) * | 2008-09-23 | 2010-03-25 | General Electric Company, A New York Corporation | Methods and apparatus to organize patient medical histories |
| US20160188832A1 (en) * | 2014-12-30 | 2016-06-30 | Cerner Innovation, Inc. | Physiologic Severity of Illness Score for Acute Care Patients |
| CN105719217A (en) * | 2016-01-25 | 2016-06-29 | 山东海博科技信息系统有限公司 | Legal medical expert injury identification management method and system |
| CN106326640A (en) * | 2016-08-12 | 2017-01-11 | 上海交通大学医学院附属瑞金医院卢湾分院 | Medical speech control system and control method thereof |
| US20180075194A1 (en) * | 2016-09-12 | 2018-03-15 | International Business Machines Corporation | Medical Condition Independent Engine for Medical Treatment Recommendation System |
| US20180121618A1 (en) * | 2016-11-02 | 2018-05-03 | Cota Inc. | System and method for extracting oncological information of prognostic significance from natural language |
| CN106874643A (en) * | 2016-12-27 | 2017-06-20 | 中国科学院自动化研究所 | Build the method and system that knowledge base realizes assisting in diagnosis and treatment automatically based on term vector |
| CN107656952A (en) * | 2016-12-30 | 2018-02-02 | 青岛中科慧康科技有限公司 | The modeling method of parallel intelligent case recommended models |
| CN107887036A (en) * | 2017-11-09 | 2018-04-06 | 北京纽伦智能科技有限公司 | Construction method, device and the clinical decision accessory system of clinical decision accessory system |
| CN109545373A (en) * | 2018-11-08 | 2019-03-29 | 新博卓畅技术（北京）有限公司 | A kind of automatic abstracting method of human body diseases symptom characteristic, system and equipment |
Non-Patent Citations (8)
| Title |
|---|
| I.SEFRIOUI 等: "Survival prediction of trauma patients:a study on US National Trauma Data Bank", 《EUROPEAN JOURNAL OF TRANUMA AND EMERGENCY SURGERY》 * |
| INSU SONG 等: "Anonymous Indexing of Health Conditions for a Similarity Measure", 《IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE》 * |
| 丁训杰: "《急诊抢救手册》", 30 September 1998, 金盾出版社 * |
| 张艺帆: "基于语义技术的临床决策知识库研究", 《中国博士学位论文全文数据库信息科技辑》 * |
| 李涛: "《数据挖掘的应用与实践 大数据时代的案例分析》", 31 October 2013, 厦门大学出版社 * |
| 聂洪鑫 等: "创伤评分在胸部损伤中的应用", 《解放军医学杂志》 * |
| 谭志明: "《健康医疗大数据与人工智能》", 31 March 2019, 华南理工大学出版社 * |
| 陈敏: "《认知计算导论》", 30 April 2017, 华中科技大学出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111710408A (en) * | 2020-04-16 | 2020-09-25 | 禹宝庆 | Intelligent decision making system and method for wound emergency treatment |
| CN112053771A (en) * | 2020-09-08 | 2020-12-08 | 南通市第一人民医院 | Wound patient material use management method and system |
| CN112053771B (en) * | 2020-09-08 | 2021-12-21 | 南通市第一人民医院 | Wound patient material use management method and system |
| CN116776105A (en) * | 2023-08-22 | 2023-09-19 | 北京大学人民医院 | Method and device for constructing wound data safety management system and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110867228B (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110867228B (en) | Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient | |
| CN110993064A (en) | Deep learning-oriented medical image labeling method and device | |
| Ng et al. | The role of artificial intelligence in enhancing clinical nursing care: A scoping review | |
| US20200294654A1 (en) | System and method for generating descriptions of abnormalities in medical images | |
| Sharghi et al. | Automatic operating room surgical activity recognition for robot-assisted surgery | |
| CN108899064A (en) | Electronic health record generation method, device, computer equipment and storage medium | |
| CN111489800A (en) | Analysis method and system for identifying and storing medical record and report list images | |
| US20190095590A1 (en) | Personalized Questionnaire for Health Risk Assessment | |
| CN112614565A (en) | Traditional Chinese medicine classic famous prescription intelligent recommendation method based on knowledge-graph technology | |
| CN110197715B (en) | Medical image browsing system for film reading teaching | |
| CN108140044A (en) | For determining the equipment, system and method with the relevant information of clinician | |
| Forestier et al. | Discovering discriminative and interpretable patterns for surgical motion analysis | |
| CN116860739A (en) | Severe medical big data processing system and method | |
| CN113611401A (en) | Perioperative blood management system and method | |
| CN112328806A (en) | Data processing method, system, computer equipment and storage medium | |
| CN113707323B (en) | Disease prediction method, device, equipment and medium based on machine learning | |
| Wu et al. | A preliminary study of sperm identification in microdissection testicular sperm extraction samples with deep convolutional neural networks | |
| CN111383726B (en) | Electronic medical record data processing method and device, electronic equipment and readable medium | |
| CN117251527A (en) | Medical evidence-based method, system, electronic equipment and storage medium | |
| CN116469505A (en) | Data processing method, device, computer equipment and readable storage medium | |
| CN116206767A (en) | Disease knowledge mining method, device, electronic equipment and storage medium | |
| CN112101034B (en) | Method and device for judging attribute of medical entity and related product | |
| CN113626413A (en) | Special disease database construction method and system | |
| CN115700826A (en) | Receipt processing method, receipt display method, receipt processing device, receipt display device, computer equipment and storage medium | |
| CN111241834A (en) | Medical care quality evaluation obtaining method, device, medium and terminal equipment |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Jin Zongxue Inventor after: Zhang Peng Inventor before: Jin Zongxue Inventor before: Wang Xiaolin Inventor before: Zhang Peng |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |