CN116913532A - Clinical path recommendation method - Google Patents
Clinical path recommendation method Download PDFInfo
- Publication number
- CN116913532A CN116913532A CN202311169605.9A CN202311169605A CN116913532A CN 116913532 A CN116913532 A CN 116913532A CN 202311169605 A CN202311169605 A CN 202311169605A CN 116913532 A CN116913532 A CN 116913532A
- Authority
- CN
- China
- Prior art keywords
- layer
- matrix
- coding
- clinical path
- label
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 239000011159 matrix material Substances 0.000 claims description 79
- 230000004927 fusion Effects 0.000 claims description 36
- 230000010354 integration Effects 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 230000009191 jumping Effects 0.000 claims description 8
- 230000037361 pathway Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000009472 formulation Methods 0.000 abstract description 2
- 239000000203 mixture Substances 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 description 6
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention provides a clinical path recommending method, which relates to the technical field of path recommending and comprises the following steps: acquiring a user visit ID, and acquiring corresponding electronic medical record data according to the user visit ID; determining label groups of the electronic medical record data according to the electronic medical record data corresponding to the user visit ID; and constructing a clinical path recommendation model, and inputting the label group of the electronic medical record data into the clinical path recommendation model to generate an optimal clinical path. The invention carries out label grouping according to the medical data of the user so as to determine the specific group of the user; meanwhile, the invention constructs a clinical path recommendation model, and inputs medical data of each group into the clinical path recommendation model, so that a localized clinical path with high accuracy and strong universality can be generated, and the clinical path is closer to the actual situation of a user, thereby providing a reference basis for clinical quality management, hospital clinical path formulation and management.
Description
Technical Field
The invention relates to the technical field of path recommendation, in particular to a clinical path recommendation method.
Background
Clinical pathway refers to a standardized workflow written in advance that optimizes the sequence and timing of critical treatment, examination, care activities of a disease or operation as much as possible by professionals of various disciplines based on the principles of evidence-based medicine. At present, in hospitals at home and abroad, analysis and summarization of diagnosis and treatment paths provided for users are mainly handled by doctors manually. The method can be applied to the condition of simple diagnosis scheme, but the disease diagnosis nodes are more, and the diagnosis scheme is complex, so that the existing diagnosis and treatment path analysis and summarization method has the defects of low utilization efficiency of sanitary resources and imperfect diagnosis paths.
Disclosure of Invention
The invention aims to provide a clinical path recommending method.
The embodiment of the invention is realized by the following technical scheme:
a clinical pathway recommendation method comprising the steps of:
acquiring a user visit ID, and acquiring corresponding electronic medical record data according to the user visit ID;
determining label groups of the electronic medical record data according to the electronic medical record data corresponding to the user visit ID;
and constructing a clinical path recommendation model, and inputting the label group of the electronic medical record data into the clinical path recommendation model to generate an optimal clinical path.
Further, determining a tag group of the electronic medical record data according to the electronic medical record data corresponding to the user visit ID, including the following steps:
extracting all medical data of the electronic medical record data corresponding to the user visit ID;
data cleaning is carried out on all medical data to obtain a standard medical data set;
calculating the label value of each standard medical data in the standard medical data set;
and determining label groups of the electronic medical record data according to the label values of the standard medical data.
Further, the tag value of standard medical dataαThe calculation formula of (2) is as follows:
in the method, in the process of the invention,l k represent the firstkThe weight of the individual standard medical data in all medical data sets,Krepresenting the number of standard medical data.
Further, the specific method for determining the label group of the electronic medical record data comprises the following steps: sequencing the label values of all standard medical data from large to small to obtain a label value sequence, and leading the label value sequence to be the frontStandard medical data corresponding to the individual tag values are used as a first tag group, and the tag value sequences except the first tag group are added with the front +.>Standard medical data corresponding to the tag values are used as a second tag group, standard medical data corresponding to the rest tag values in the tag value sequence except the first tag group and the second tag group are used as a third tag group, wherein,Mrepresenting the number of medical data.
Further, the clinical path recommendation model comprises a first convolution layer, a second convolution layer, a third convolution layer, a first coding layer, a second coding layer, a third coding layer, a fusion layer and a full connection layer;
the input end of the first convolution layer, the input end of the second convolution layer and the input end of the third convolution layer are all used as input ends of a clinical path recommendation model;
the first output end of the first convolution layer is connected with the input end of the first coding layer; the second output end of the first convolution layer is connected with the input end of the integration layer;
the first output end of the second convolution layer is connected with the input end of the second coding layer; the second output end of the second convolution layer is connected with the input end of the integration layer;
the first output end of the third convolution layer is connected with the input end of the third coding layer; the second output end of the third convolution layer is connected with the input end of the integration layer;
the output end of the first coding layer, the output end of the second coding layer, the output end of the third coding layer and the output end of the fusion layer are all connected with the input end of the full-connection layer;
the output end of the full connection layer is used as the output end of the clinical path recommendation model.
Further, the first convolution layer is used for inputting the first label group into the clinical path recommendation model, and carrying out convolution operation on the first label group to generate a first group matrix; the second convolution layer is used for inputting the second label group into the clinical path recommendation model, and carrying out convolution operation on the second label group to generate a second grouping matrix; the third convolution layer is used for inputting a third label group into the clinical path recommendation model, and carrying out convolution operation on the third label group to generate a third group matrix;
the first coding layer is used for coding the first grouping matrix to generate a first coding matrix; the second coding layer is used for coding the second grouping matrix to generate a second coding matrix; the third coding layer is used for coding the third grouping matrix to generate a third coding matrix;
the fusion layer is used for fusing the first grouping matrix, the second grouping matrix and the third grouping matrix to generate a fusion matrix;
the full connection layer is used for adding the first coding matrix, the second coding matrix, the third coding matrix and the fusion matrix to generate a fusion characteristic matrix, and generating an optimal clinical path according to the fusion characteristic matrix.
Further, jump connection is adopted between the first convolution layer and the fusion layer; the second convolution layer is connected with the fusion layer in a jumping way; and the third convolution layer and the fusion layer are connected in a jumping manner.
Further, fusion matricesZThe expression of (2) is:
in the method, in the process of the invention,Aa first coding matrix is represented and is used to represent,Ba second encoding matrix is represented and is used,Crepresenting a third encoding matrix.
Further, the loss function of the full connection layerLossThe expression of (2) is:
in the method, in the process of the invention,Nthe number of neurons representing the fully connected layer,θ n representing the first of the fully connected layersnThe pulse values of the individual neurons are set,θ n-1 representing the first of the fully connected layersnThe pulse value of 1 neuron is chosen,Aa first coding matrix is represented and is used to represent,Ba second encoding matrix is represented and is used,Ca third coding matrix is represented and is used to represent,Zrepresenting the fusion characteristics.
The technical scheme of the embodiment of the invention has at least the following advantages and beneficial effects: the clinical path recommending method comprises the steps of grouping labels according to medical data of users so as to determine specific groups of the users; meanwhile, the invention constructs a clinical path recommendation model, and inputs medical data of each group into the clinical path recommendation model, so that a localized clinical path with high accuracy and strong universality can be generated, and the clinical path is closer to the actual situation of a user, thereby providing a reference basis for clinical quality management, hospital clinical path formulation and management.
Drawings
FIG. 1 is a flowchart of a clinical path recommendation method according to an embodiment of the present invention;
fig. 2 is a block diagram of a clinical path recommendation model according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
As shown in fig. 1, the present invention provides a clinical path recommendation method, comprising the steps of:
and acquiring the user visit ID, and acquiring corresponding electronic medical record data according to the user visit ID.
Determining label groups of the electronic medical record data according to the electronic medical record data corresponding to the user visit ID; the method specifically comprises the following steps:
and extracting all medical data of the electronic medical record data corresponding to the user visit ID.
Data cleaning is carried out on all medical data to obtain a standard medical data set; wherein the tag value of the standard medical dataαThe calculation formula of (2) is as follows:
in the method, in the process of the invention,l k represent the firstkThe weight of the individual standard medical data in all medical data sets,Krepresenting the number of standard medical data.
A tag value is calculated for each standard medical data in the set of standard medical data.
Determining label groups of the electronic medical record data according to the label values of the standard medical data; the specific method for determining the label group of the electronic medical record data comprises the following steps: sequencing the label values of all standard medical data from large to small to obtain a label value sequence, and leading the label value sequence to be the frontStandard medical data corresponding to the individual tag values are used as a first tag group, and the tag value sequences except the first tag group are added with the front +.>Standard medical data corresponding to the tag values are used as a second tag group, standard medical data corresponding to the rest tag values in the tag value sequence except the first tag group and the second tag group are used as a third tag group, wherein,Mrepresenting the number of medical data. .
Generally, electronic medical record data of users contains various medical data, so that the medical data needs to be preprocessed, so that the data in a standard medical data set is free from redundancy. In addition, the labels are grouped according to the weights of the standard medical data in all medical data sets, so that the label grouping accuracy can be ensured.
And constructing a clinical path recommendation model, and inputting the label group of the electronic medical record data into the clinical path recommendation model to generate an optimal clinical path.
As shown in fig. 2, the clinical path recommendation model includes a first convolution layer, a second convolution layer, a third convolution layer, a first coding layer, a second coding layer, a third coding layer, a fusion layer, and a full connection layer;
the input end of the first convolution layer, the input end of the second convolution layer and the input end of the third convolution layer are all used as input ends of a clinical path recommendation model;
the first output end of the first convolution layer is connected with the input end of the first coding layer; the second output end of the first convolution layer is connected with the input end of the integration layer;
the first output end of the second convolution layer is connected with the input end of the second coding layer; the second output end of the second convolution layer is connected with the input end of the integration layer;
the first output end of the third convolution layer is connected with the input end of the third coding layer; the second output end of the third convolution layer is connected with the input end of the integration layer;
the output end of the first coding layer, the output end of the second coding layer, the output end of the third coding layer and the output end of the fusion layer are all connected with the input end of the full-connection layer;
the output end of the full connection layer is used as the output end of the clinical path recommendation model.
In the embodiment of the invention, a first convolution layer is used for inputting a first label group into a clinical path recommendation model, and carrying out convolution operation on the first label group to generate a first group matrix; the second convolution layer is used for inputting the second label group into the clinical path recommendation model, and carrying out convolution operation on the second label group to generate a second grouping matrix; the third convolution layer is used for inputting a third label group into the clinical path recommendation model, and carrying out convolution operation on the third label group to generate a third group matrix; the first convolution layer, the second convolution layer and the third convolution layer can respectively extract the characteristics of label grouping to obtain a corresponding grouping matrix; the characteristics of the tag packet include tag values contained in the tag packet. The tag grouping features can be enriched through the convolution of the first convolution layer, the second convolution layer and the third convolution layer, so that the subsequent module can conveniently carry out coding processing.
The first coding layer is used for coding the first grouping matrix to generate a first coding matrix; the second coding layer is used for coding the second grouping matrix to generate a second coding matrix; the third coding layer is used for coding the third grouping matrix to generate a third coding matrix; the first coding layer, the second coding layer and the third coding layer respectively code the grouping matrixes, so that each grouping matrix occupies less space, and the coding operation has an automatic error correction function, and therefore, the coding operation of the grouping matrixes can also perform error correction processing on elements of the grouping matrixes.
The fusion layer is used for fusing the first grouping matrix, the second grouping matrix and the third grouping matrix to generate a fusion matrix; the fusion layer performs addition processing on the elements of the three grouping matrixes, so that the elements of the three matrixes can be fully fused, and an optimal clinical path can be generated conveniently.
The full connection layer is used for adding the first coding matrix, the second coding matrix, the third coding matrix and the fusion matrix to generate a fusion characteristic matrix, and generating an optimal clinical path according to the fusion characteristic matrix.
In the embodiment of the invention, the first convolution layer and the fusion layer are connected in a jumping manner; the second convolution layer is connected with the fusion layer in a jumping way; and the third convolution layer and the fusion layer are connected in a jumping manner.
In an embodiment of the invention, the matrix is fusedZThe expression of (2) is:
in the method, in the process of the invention,Aa first coding matrix is represented and is used to represent,Ba second encoding matrix is represented and is used,Crepresenting a third encoding matrix.
In the embodiment of the invention, the loss of the full connection layerLoss functionLossThe expression of (2) is:
in the method, in the process of the invention,Nthe number of neurons representing the fully connected layer,θ n representing the first of the fully connected layersnThe pulse values of the individual neurons are set,θ n-1 representing the first of the fully connected layersnThe pulse value of 1 neuron is chosen,Aa first coding matrix is represented and is used to represent,Ba second encoding matrix is represented and is used,Ca third coding matrix is represented and is used to represent,Zrepresenting the fusion characteristics.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A clinical pathway recommendation method, comprising the steps of:
acquiring a user visit ID, and acquiring corresponding electronic medical record data according to the user visit ID;
determining label groups of the electronic medical record data according to the electronic medical record data corresponding to the user visit ID;
and constructing a clinical path recommendation model, and inputting the label group of the electronic medical record data into the clinical path recommendation model to generate an optimal clinical path.
2. The clinical path recommendation method according to claim 1, wherein: the method for determining the label grouping of the electronic medical record data according to the electronic medical record data corresponding to the user visit ID comprises the following steps:
extracting all medical data of the electronic medical record data corresponding to the user visit ID;
data cleaning is carried out on all medical data to obtain a standard medical data set;
calculating the label value of each standard medical data in the standard medical data set;
and determining label groups of the electronic medical record data according to the label values of the standard medical data.
3. The clinical path recommendation method according to claim 2, wherein: tag value of the standard medical dataαThe calculation formula of (2) is as follows:
in the method, in the process of the invention,l k represent the firstkThe weight of the individual standard medical data in all medical data sets,Krepresenting the number of standard medical data.
4. The clinical path recommendation method according to claim 2, wherein: the specific method for determining the label group of the electronic medical record data comprises the following steps: sequencing the label values of all standard medical data from large to small to obtain a label value sequence, and leading the label value sequence to be the frontStandard medical data corresponding to the individual tag values are used as a first tag group, and the tag value sequences except the first tag group are added with the front +.>Standard medical data corresponding to the tag values are used as a second tag group, standard medical data corresponding to the rest tag values in the tag value sequence except the first tag group and the second tag group are used as a third tag group, wherein,Mrepresenting the number of medical data.
5. The clinical path recommendation method according to claim 1, wherein: the clinical path recommendation model comprises a first convolution layer, a second convolution layer, a third convolution layer, a first coding layer, a second coding layer, a third coding layer, a fusion layer and a full connection layer;
the input end of the first convolution layer, the input end of the second convolution layer and the input end of the third convolution layer are all used as input ends of a clinical path recommendation model;
the first output end of the first convolution layer is connected with the input end of the first coding layer; the second output end of the first convolution layer is connected with the input end of the integration layer;
the first output end of the second convolution layer is connected with the input end of the second coding layer; the second output end of the second convolution layer is connected with the input end of the integration layer;
the first output end of the third convolution layer is connected with the input end of the third coding layer; the second output end of the third convolution layer is connected with the input end of the integration layer;
the output end of the first coding layer, the output end of the second coding layer, the output end of the third coding layer and the output end of the fusion layer are all connected with the input end of the full-connection layer;
and the output end of the full-connection layer is used as the output end of the clinical path recommendation model.
6. The clinical pathway recommendation method of claim 5, wherein: the first convolution layer is used for inputting a first label group into the clinical path recommendation model, and carrying out convolution operation on the first label group to generate a first group matrix; the second convolution layer is used for inputting a second label group into the clinical path recommendation model, and carrying out convolution operation on the second label group to generate a second grouping matrix; the third convolution layer is used for inputting a third label group into the clinical path recommendation model, and carrying out convolution operation on the third label group to generate a third group matrix;
the first coding layer is used for coding the first grouping matrix to generate a first coding matrix; the second coding layer is used for coding the second grouping matrix to generate a second coding matrix; the third coding layer is used for coding the third grouping matrix to generate a third coding matrix;
the fusion layer is used for fusing the first grouping matrix, the second grouping matrix and the third grouping matrix to generate a fusion matrix;
the full connection layer is used for adding the first coding matrix, the second coding matrix, the third coding matrix and the fusion matrix to generate a fusion characteristic matrix, and generating an optimal clinical path according to the fusion characteristic matrix.
7. The clinical pathway recommendation method of claim 5, wherein: the first convolution layer and the fusion layer are connected in a jumping manner; the second convolution layer is connected with the fusion layer in a jumping manner; and the third convolution layer and the fusion layer are connected in a jumping manner.
8. The clinical pathway recommendation method of claim 6, wherein: the fusion matrixZThe expression of (2) is:
in the method, in the process of the invention,Aa first coding matrix is represented and is used to represent,Ba second encoding matrix is represented and is used,Crepresenting a third encoding matrix.
9. The clinical pathway recommendation method of claim 5, wherein: loss function of the full connection layerLossThe expression of (2) is:
in the method, in the process of the invention,Nthe number of neurons representing the fully connected layer,θ n representing the first of the fully connected layersnThe pulse values of the individual neurons are set,θ n-1 representing the first of the fully connected layersnThe pulse value of 1 neuron is chosen,Aa first coding matrix is represented and is used to represent,Ba second encoding matrix is represented and is used,Ca third coding matrix is represented and is used to represent,Zrepresenting the fusion characteristics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311169605.9A CN116913532B (en) | 2023-09-12 | 2023-09-12 | Clinical path recommendation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311169605.9A CN116913532B (en) | 2023-09-12 | 2023-09-12 | Clinical path recommendation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116913532A true CN116913532A (en) | 2023-10-20 |
| CN116913532B CN116913532B (en) | 2023-12-08 |
Family
ID=88356926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311169605.9A Active CN116913532B (en) | 2023-09-12 | 2023-09-12 | Clinical path recommendation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116913532B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223741A (en) * | 2019-06-10 | 2019-09-10 | 四川互慧软件有限公司 | A kind of clinic path information system |
| JP2019185234A (en) * | 2018-04-05 | 2019-10-24 | 富士通株式会社 | Recommended treatment notification program, recommended treatment notification method and information processing apparatus |
| CN110739036A (en) * | 2019-10-09 | 2020-01-31 | 武汉志软科技有限公司 | clinical path analysis application data retrieval method |
| CN111581510A (en) * | 2020-05-07 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Shared content processing method and device, computer equipment and storage medium |
| CN112873211A (en) * | 2021-02-24 | 2021-06-01 | 清华大学 | Robot man-machine interaction method |
| US11222217B1 (en) * | 2020-08-14 | 2022-01-11 | Tsinghua University | Detection method using fusion network based on attention mechanism, and terminal device |
| CN114077844A (en) * | 2020-08-17 | 2022-02-22 | 北京金山数字娱乐科技有限公司 | Data processing method and device |
| CN114116825A (en) * | 2021-12-02 | 2022-03-01 | 浙江和仁科技股份有限公司 | Health portrait recommendation engine and method and medical data integrated display system and method |
| US20220188595A1 (en) * | 2020-12-16 | 2022-06-16 | Microsoft Technology Licensing, Llc | Dynamic matrix convolution with channel fusion |
| CN116562307A (en) * | 2022-02-07 | 2023-08-08 | 辉达公司 | Performing text translation using one or more neural networks |
| CN116665210A (en) * | 2023-07-28 | 2023-08-29 | 珠海横琴圣澳云智科技有限公司 | Cell classification method and device based on multichannel information fusion |
-
2023
- 2023-09-12 CN CN202311169605.9A patent/CN116913532B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019185234A (en) * | 2018-04-05 | 2019-10-24 | 富士通株式会社 | Recommended treatment notification program, recommended treatment notification method and information processing apparatus |
| CN110223741A (en) * | 2019-06-10 | 2019-09-10 | 四川互慧软件有限公司 | A kind of clinic path information system |
| CN110739036A (en) * | 2019-10-09 | 2020-01-31 | 武汉志软科技有限公司 | clinical path analysis application data retrieval method |
| CN111581510A (en) * | 2020-05-07 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Shared content processing method and device, computer equipment and storage medium |
| US11222217B1 (en) * | 2020-08-14 | 2022-01-11 | Tsinghua University | Detection method using fusion network based on attention mechanism, and terminal device |
| CN114077844A (en) * | 2020-08-17 | 2022-02-22 | 北京金山数字娱乐科技有限公司 | Data processing method and device |
| US20220188595A1 (en) * | 2020-12-16 | 2022-06-16 | Microsoft Technology Licensing, Llc | Dynamic matrix convolution with channel fusion |
| CN112873211A (en) * | 2021-02-24 | 2021-06-01 | 清华大学 | Robot man-machine interaction method |
| CN114116825A (en) * | 2021-12-02 | 2022-03-01 | 浙江和仁科技股份有限公司 | Health portrait recommendation engine and method and medical data integrated display system and method |
| CN116562307A (en) * | 2022-02-07 | 2023-08-08 | 辉达公司 | Performing text translation using one or more neural networks |
| CN116665210A (en) * | 2023-07-28 | 2023-08-29 | 珠海横琴圣澳云智科技有限公司 | Cell classification method and device based on multichannel information fusion |
Non-Patent Citations (3)
| Title |
|---|
| 刘文雅 等: "老年性白内障日间手术临床路径模式效果分析", 《中国医院管理》, vol. 37, no. 09, pages 42 - 44 * |
| 张飞飞 等: "图文跨模态检索研究进展", 《数据采集与处理》, vol. 38, no. 03, pages 479 - 505 * |
| 徐梦遥: "基于梯度下降的脉冲神经网络训练算法", 《现代计算机》, vol. 27, no. 35, pages 1 - 11 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116913532B (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220198150A1 (en) | Ontologically driven procedure coding | |
| CN113643821B (en) | Multi-center knowledge graph joint decision support method and system | |
| WO2022267678A1 (en) | Video consultation method and apparatus, device and storage medium | |
| US20200227175A1 (en) | Document improvement prioritization using automated generated codes | |
| CN105190634A (en) | Method of calculating a score of a medical suggestion as a support in medical decision making | |
| US20190108264A1 (en) | System prototype of intelligent regional mobile healthcare integrated data center based on metadata | |
| CN103440421A (en) | Medical data processing method and system | |
| CN115148370B (en) | Method and system for generating DIP disease seed catalogue | |
| CN111652135A (en) | Electrocardiogram data generation method and device and electronic equipment | |
| CN113053513A (en) | Wisdom medical system based on wisdom community | |
| CN105574355B (en) | The recording method of clinical research data and system | |
| CN110349653A (en) | Display methods, equipment and the storage medium of image analysing computer data | |
| CN117034142B (en) | Unbalanced medical data missing value filling method and system | |
| CN116913532B (en) | Clinical path recommendation method | |
| CN114420279A (en) | Medical resource recommendation method, device, equipment and storage medium | |
| Wang et al. | A high-fidelity model to predict length of stay in the neonatal intensive care unit | |
| CN113160914A (en) | Online inquiry method and device, electronic equipment and storage medium | |
| JP2012043430A (en) | Validity confirmation of sensor data expressed by characteristic function | |
| JP5691935B2 (en) | Retrieving sensor data stored as a binary decision diagram | |
| CN116168828A (en) | Disease prediction method and device based on knowledge graph and deep learning and computer equipment | |
| Mathew et al. | Distributed privacy preserving decision support system for predicting hospitalization risk in hospitals with insufficient data | |
| CN116543917A (en) | Information mining method for heterogeneous time sequence data | |
| CN111383123A (en) | Clinical medical expense statistical method and device, storage medium and electronic equipment | |
| CN113066531B (en) | Risk prediction method, risk prediction device, computer equipment and storage medium | |
| Permanasari et al. | A web-based decision support system of patient time prediction using iterative dichotomiser 3 algorithm |
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 |