CN115662647A - Similar disease mining method and application - Google Patents
Similar disease mining method and application Download PDFInfo
- Publication number
- CN115662647A CN115662647A CN202211679383.0A CN202211679383A CN115662647A CN 115662647 A CN115662647 A CN 115662647A CN 202211679383 A CN202211679383 A CN 202211679383A CN 115662647 A CN115662647 A CN 115662647A
- Authority
- CN
- China
- Prior art keywords
- disease
- diseases
- similar
- mining
- vector representation
- 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
- 201000010099 disease Diseases 0.000 title claims abstract description 168
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 168
- 238000005065 mining Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000013598 vector Substances 0.000 claims abstract description 60
- 238000005295 random walk Methods 0.000 claims abstract description 12
- 239000003814 drug Substances 0.000 claims description 36
- 208000024891 symptom Diseases 0.000 claims description 24
- 229940079593 drug Drugs 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000001225 therapeutic effect Effects 0.000 claims description 4
- 230000003190 augmentative effect Effects 0.000 claims 1
- 206010034464 Periarthritis Diseases 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 206010028391 Musculoskeletal Pain Diseases 0.000 description 3
- 206010028836 Neck pain Diseases 0.000 description 3
- 208000007613 Shoulder Pain Diseases 0.000 description 3
- 239000008187 granular material Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 208000019693 Lung disease Diseases 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 208000030533 eye disease Diseases 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000017520 skin disease Diseases 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a method for mining similar diseases and application thereof, wherein the method comprises the following steps: step one, establishing a knowledge graph: the knowledge graph comprises a pharmacy knowledge graph and a disease knowledge graph; step two, acquiring vector representation of diseases based on the knowledge graph: in order to obtain vector representation of diseases, a plurality of node sequences are obtained in a random walk mode; taking diseases as initial nodes, obtaining next hop nodes according to the connection relation among the nodes, and so on; after acquiring a plurality of node sequences, generating vector representation of diseases by a Word2Vec model; thirdly, evaluating similarity based on vector representation of diseases: and calculating the cosine similarity of the two diseases according to the vector representation of the diseases, wherein the numerical value of the cosine similarity is the similarity between the two diseases.
Description
Technical Field
The invention relates to the technical field of intelligent medical treatment, in particular to a method for mining similar diseases and application.
Background
The method for mining similar diseases can be used as a part of a prescription checking system, is mainly used for mining the correlation among different diagnostic terms, and provides reference for a pharmacist to check an electronic prescription.
The current main methods in the prior art for assessing similarity between diseases are based on edit distance. For example, chinese patent publication No. CN105095665B discloses a method for structuring disease information, which analyzes a disease into information such as a diseased part, a disease degree, and a disease body according to a predetermined dimension, and compares the information of two diseases to evaluate the similarity of the diseases.
Because the description of the diseases is diversified, the similarity among the diseases is estimated based on the editing distance, so that the large deviation exists, and the high false positive rate is generated in the disease matching.
Disclosure of Invention
The invention aims to provide a method for mining similar diseases so as to solve the problem of how to improve the accuracy of similarity measurement among diseases.
The invention aims to solve the defects of the prior art and provides a method for similar disease excavation, which comprises the following steps:
step one, establishing a knowledge graph: the knowledge graph comprises a pharmacy knowledge graph and a disease knowledge graph;
step two, acquiring vector representation of diseases based on the knowledge graph: in order to obtain vector representation of diseases, a plurality of node sequences are obtained in a random walk mode; taking diseases as initial nodes, obtaining next hop nodes according to the connection relation among the nodes, and so on; after a plurality of node sequences are obtained, generating vector representation of diseases through a Word2Vec model;
thirdly, evaluating similarity based on vector representation of diseases: and calculating the cosine similarity of the two diseases according to the vector representation of the diseases, wherein the numerical value of the cosine similarity is the similarity between the two diseases.
Preferably, the pharmaco-knowledgeable map comprises major components of a drug, treatment sites, treatment disease information, ATC codes, and treatment ICD10 code information; the disease knowledge map comprises treatment of diseases, disease parts, common symptoms, ICD10 codes and treatment relations of medicines and diseases; the main components, treatment parts and treatment disease information of the medicine are obtained through the instruction book of the medicine; the information for treating the ICD10 code is supplemented by the ICD10 code for treating the disease; the ATC code is obtained by reasoning the main components of the medicine; treatment of diseases, disease parts, common symptoms and ICD10 codes are extracted through disease encyclopedia description; the therapeutic relationship of the drugs to the disease is obtained by a plurality of electronic prescriptions.
Preferably, the generation of the vector representation of the disease through the Word2Vec model is divided into two steps of node sequence generation and disease vector calculation.
Preferably, the generation of the node sequence specifically refers to the construction of the node sequence by random walk on the knowledge graph.
Preferably, the random walk on the knowledge graph specifically refers to a random walk according to a meta-path.
Preferably, the meta path refers to a path that is medically interpretable.
Preferably, the meta-pathway specifically includes 1) drug-disease; 2) Drug-symptom-disease; 3) Drug-major ingredient-disease; 4) Drug-site-disease; 5) drug-ICD 10 encodes a disease.
Preferably, the nodes sampled by different meta-paths can be spliced by the same node to generate a longer sequence, and more nodes of different drugs or diseases can be spliced into a sequence by the disease node or the drug node.
Preferably, in the calculation of the disease vector, the input of the disease vector is a plurality of node sequences generated based on the knowledge graph walk; the node sequence may include a plurality of disease nodes associated by drug nodes and symptom nodes, i.e., the associated disease nodes may be more likely to be treated by similar drugs or include the same similar symptoms, i.e., have similar medical manifestations; generating vector representation of each node in the knowledge graph by adopting a universal Word2Vec algorithm; the disease vectors generated in the mode can ensure that the cosine similarity of the vector representation of diseases which are closer in medical performance is larger.
Preferably, the vector representation of the disease of high dimensionality is reduced to a 2-dimensional vector using the t-SNE algorithm and plotted on a 2D coordinate system.
The invention also provides application of the similar disease mining method in mining the relation of symptoms in a multi-medicine multi-symptom prescription and/or expanding the relation of symptoms.
Advantageous effects
Compared with the prior art, the invention has the beneficial effects that:
the method for mining the similar diseases is a similarity measurement method based on a knowledge graph, and the core hypothesis is that the more the two diseases have the same symptoms, the more the two diseases are similar; from this it can further be assumed that two diseases are more similar if they have more of the same contiguous nodes on the knowledge-graph.
The method for similar disease mining adopts a general Word2Vec algorithm to generate vector representation of each node in the knowledge graph. The disease vectors generated in this way can ensure that the cosine similarity of the vector representation of diseases with closer medical performance is larger. Meanwhile, the invention adopts a t-SNE algorithm to reduce the dimension of the high-dimensional vector of the disease to a 2-dimensional vector and draws the vector on a 2D coordinate system, so that the distance between two diseases can be visually represented on a 2D plane diagram.
The similar disease mining method provided by the invention is mainly applied to two scenes:
1. the relation of the traditional Chinese medicine symptoms in the prescription of multi-medicine and multi-symptom is excavated. The keyword matching mode can not determine which disease is treated by each medicine in the prescription, and the diagnosis of the indication of the medicine treatment which is most similar to the diagnosis in the prescription can be evaluated based on the keyword matching mode, so that the accuracy of medicine relation mining is improved.
2. The relation of the drug-expanding disease. The invention can realize the clustering of diseases, if a certain medicine can treat most diseases in a certain category, other diseases in the category can be treated with high probability, and the relation of the medicine symptoms can be expanded.
Both of the above two scenarios are the improvement of the work of the pharmacist, and the final extraction result needs the rechecking of the pharmacist.
The similar disease mining method can generate vector representation of diseases based on a random walk algorithm of a knowledge graph, evaluates the similarity of the diseases through cosine similarity, and is obviously superior to the method based on an editing distance in effect.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a block diagram of a pharmaceutical knowledge map and a disease knowledge map.
FIG. 2 is a schematic diagram of a sample mining result of similar diseases.
FIG. 3 is a schematic diagram of a sample knowledge graph.
Detailed Description
The present invention is described in more detail below to facilitate an understanding of the invention.
The complete structure of the pharmaco-and disease profiles used in the present invention is shown in FIG. 1.
The method for similar disease mining comprises the following steps:
step one, constructing a knowledge graph shown in figure 1: the knowledge graph comprises a pharmacy knowledge graph and a disease knowledge graph;
step two, acquiring vector representation of diseases based on the knowledge graph: in order to obtain vector representation of diseases, the invention adopts a random walk mode to obtain a large number of node sequences; and taking the disease as an initial node, and obtaining a next hop node according to the connection relation between the nodes, and so on. After a large number of node sequences are obtained, the vector representation of the disease is generated through a Word2Vec model.
The Word2Vec algorithm is a set of correlation models used to generate Word vectors. These models are shallow, two-level neural networks trained to reconstruct linguistic word text. The network is represented by words and the input words in adjacent positions are guessed, and the order of the words is unimportant under the assumption of the bag-of-words model in word2 vec. After training is completed, the word2vec model can be used to map each word to a vector, which can be used to represent word-to-word relationships, and the vector is a hidden layer of the neural network.
Specifically, generating a vector representation of a disease by the Word2Vec model is mainly divided into two steps: generating a node sequence and calculating a disease vector.
1) The node sequence is mainly constructed by random walk on a knowledge graph; however, in order to introduce interpretability, the present invention introduces the concept of meta-paths, which are used by the present invention and include: 1) Drug-disease; 2) Drug-symptom-disease; 3) Drug-main ingredient-disease; 4) Drug-site-disease; 5) drug-ICD 10 encodes a disease. The introduction of the meta-path concept ensures that the randomly generated node sequences have medical rationality and are interpretable. The present invention is not limited to the above-described five meta routes, and any route that is medically interpretable may be used as the meta route.
The explanation of the present invention is further explained by using FIG. 1 as an example. The invention generates a node sequence on the knowledge graph shown in FIG. 3; yuanping granule-shoulder-left scapulohumeral periarthritis) can be sampled by the Yuanping route 4), and the route can be explained as that the Gentonping granule can treat the shoulder of the part, and the diseased part of the left scapulohumeral periarthritis is the shoulder; yuanping granule-shoulder and neck pain-left scapulohumeral periarthritis) can be sampled by the Yuanping route 2), the route can be interpreted as that the Genanping granule can treat shoulder and neck pain, and the typical symptom of the left scapulohumeral periarthritis is shoulder and neck pain.
Furthermore, the nodes sampled by the meta-path 2) and the meta-path 4) can be spliced through the same node "Gentongping granule" and "left scapulohumeral periarthritis" to generate a longer sequence, and more nodes of different medicines or diseases can be spliced into a sequence through disease nodes or medicine nodes.
2) The input of the disease vector is a large number of node sequences generated based on the knowledge-graph walk. As mentioned above, the sequences may include a plurality of disease nodes related by nodes such as drug node and symptom node, i.e. the related disease nodes are more likely to be treated by similar drugs or include the same similar symptoms, i.e. have similar medical manifestations.
The invention adopts a general Word2Vec algorithm to generate vector representation of each node in the knowledge graph. The disease vectors generated in this way can ensure that the cosine similarity of the vector representation of diseases with closer medical performance is larger.
And step three, evaluating the similarity based on the vector representation of the diseases. In order to evaluate the similarity of two diseases, the invention firstly obtains the vector representation of the diseases, and calculates the cosine similarity of the two diseases according to the vector representation, and the numerical value is the similarity between the diseases.
The vector representation of the disease is a high dimensional vector representation, and it is difficult to graphically represent the distance between two diseases in a 2D plane figure. Therefore, the invention adopts a t-SNE algorithm to reduce the dimension of the high-dimensional vector of the disease to a 2-dimensional vector and draw the vector on a 2D coordinate system. Fig. 2 shows a sample similarity mining result generated by the present invention, and it can be seen that the upper left corner is more eye diseases, the lower left corner is lung diseases, and the right side is more skin diseases. Therefore, the disease similarity mining algorithm provided by the invention has certain accuracy and interpretability.
t-SNE algorithm: t-SNE (t-distributed stored neighbor embedding) is a machine learning algorithm for dimension reduction and was proposed by Laurens van der Maaten and Geoffrey Hinton in 08. the t-SNE is a nonlinear dimensionality reduction algorithm, and is very suitable for carrying out visualization on high-dimensional data from 2-dimension or 3-dimension reduction. In practical applications, t-SNE is rarely used for dimensionality reduction, mainly for visualization.
Preferably, the pharmaco-knowledgeable map comprises the main components of a drug, treatment site, treatment disease information, ATC codes, and treatment ICD10 code information.
Preferably, the disease knowledge map includes treatment of disease, site of onset, common symptoms, ICD10 coding, and drug-to-disease therapeutic relationships.
Preferably, the main components, treatment parts and treatment disease information of the medicine can be obtained through the instruction book of the medicine; the information encoding ICD10 for treatment may be supplemented with ICD10 encoding for treatment of a disease; the ATC code can be obtained by reasoning the main components of the medicine; information such as treatment of diseases, disease parts, common symptoms, ICD10 codes and the like can be extracted through encyclopedic description of the diseases; the therapeutic relationship of drugs to diseases can be obtained through a large number of electronic prescriptions.
The foregoing describes preferred embodiments of the present invention, but is not intended to limit the invention thereto. Modifications and variations of the embodiments disclosed herein may be made by those skilled in the art without departing from the scope and spirit of the invention.
Claims (10)
1. A similar disease mining method is characterized by comprising the following steps:
step one, establishing a knowledge graph: the knowledge graph comprises a pharmacy knowledge graph and a disease knowledge graph;
step two, acquiring vector representation of diseases based on the knowledge graph: in order to obtain vector representation of diseases, a plurality of node sequences are obtained in a random walk mode; taking diseases as initial nodes, obtaining next hop nodes according to the connection relation among the nodes, and so on; after acquiring a plurality of node sequences, generating vector representation of diseases by a Word2Vec model;
thirdly, evaluating similarity based on vector representation of diseases: and calculating the cosine similarity of the two diseases according to the vector representation of the diseases, wherein the numerical value of the cosine similarity is the similarity between the two diseases.
2. The method of similar disease mining of claim 1, wherein the pharmacomatic knowledgebase profile comprises drug identity, treatment site, treatment disease information, ATC coding, and treatment ICD10 coding information; the disease knowledge map comprises treatment of diseases, disease parts, common symptoms, ICD10 codes and treatment relations of medicines and diseases; the main components, treatment parts and treatment disease information of the medicine are obtained through the instruction book of the medicine; the information for treating the ICD10 code is supplemented by the ICD10 code for treating the disease; the ATC code is obtained by reasoning the main components of the medicine; treatment of diseases, disease parts, common symptoms and ICD10 codes are extracted through disease encyclopedia description; the therapeutic relationship of the drug to the disease is obtained by a plurality of electronic prescriptions.
3. The method for mining similar diseases according to claim 1, wherein the generation of the vector representation of the diseases through the Word2Vec model is divided into two steps of node sequence generation and disease vector calculation.
4. The method for similar disease mining as claimed in claim 3, wherein the node sequence generation specifically means to construct node sequences by random walk on the knowledge graph.
5. The method for similar disease mining as in claim 4, wherein the random walk on the knowledge-graph is a random walk according to meta-path.
6. The method of similar disease mining as claimed in claim 5, wherein the meta path is a medically interpretable path.
7. The method of similar disease mining as claimed in claim 5, wherein the meta-path includes 1) drug-disease; 2) Drug-symptom-disease; 3) Drug-major ingredient-disease; 4) Drug-site-disease; 5) drug-ICD 10 encodes a disease.
8. The method of similar disease mining as claimed in claim 3, wherein in the disease vector calculation, the input of the disease vector is a plurality of node sequences generated based on the knowledge graph walk; the node sequence may include a plurality of disease nodes associated by drug nodes and symptom nodes, i.e., the associated disease nodes may be more likely to be treated by similar drugs or include the same similar symptoms, i.e., have similar medical manifestations; generating vector representation of each node in the knowledge graph by adopting a universal Word2Vec algorithm; the disease vectors generated in the mode can ensure that the cosine similarity of the vector representation of diseases which are closer in medical performance is larger.
9. The method for similar disease mining as in claim 1, wherein the vector representation of the disease with high dimensionality is reduced to a 2-dimensional vector using a t-SNE algorithm and plotted on a 2D coordinate system.
10. Use of the method of similar disease mining according to any of claims 1 to 9 in medical relationship mining and/or augmenting medical relationships in a multi-drug multi-symptom prescription.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211679383.0A CN115662647B (en) | 2022-12-27 | 2022-12-27 | Method for excavating similar diseases and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211679383.0A CN115662647B (en) | 2022-12-27 | 2022-12-27 | Method for excavating similar diseases and application |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115662647A true CN115662647A (en) | 2023-01-31 |
| CN115662647B CN115662647B (en) | 2024-03-12 |
Family
ID=85023271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211679383.0A Active CN115662647B (en) | 2022-12-27 | 2022-12-27 | Method for excavating similar diseases and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115662647B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350502A1 (en) * | 2015-05-28 | 2016-12-01 | Ajou University Industry-Academic Cooperation Foundation | Method for providing disease co-occurrence probability from disease network |
| CN109325131A (en) * | 2018-09-27 | 2019-02-12 | 大连理工大学 | A kind of drug identification method based on biomedical knowledge map reasoning |
| CN109616169A (en) * | 2018-12-24 | 2019-04-12 | 广州天鹏计算机科技有限公司 | Similar patients' method for digging, device, computer equipment and storage medium |
| CN110675954A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN112151184A (en) * | 2020-09-27 | 2020-12-29 | 东北林业大学 | System for calculating disease similarity based on network representation learning |
| CN112309565A (en) * | 2020-08-28 | 2021-02-02 | 北京京东世纪贸易有限公司 | Method, apparatus, electronic device, and medium for matching drug information and disorder information |
| CN112542243A (en) * | 2020-12-05 | 2021-03-23 | 大连东软教育科技集团有限公司 | ICU electronic medical record knowledge graph construction method, system and storage medium |
| CN113539409A (en) * | 2021-07-28 | 2021-10-22 | 平安科技（深圳）有限公司 | Treatment scheme recommendation method, device, equipment and storage medium |
| CN113628726A (en) * | 2021-08-10 | 2021-11-09 | 海南榕树家信息科技有限公司 | Traditional Chinese medicine dialectical treatment recommendation system and method based on graph neural network and electronic equipment |
| CN114510579A (en) * | 2022-02-08 | 2022-05-17 | 吾征智能技术(北京)有限公司 | Disease automatic question-answering system, equipment and medium based on medical knowledge map |
-
2022
- 2022-12-27 CN CN202211679383.0A patent/CN115662647B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350502A1 (en) * | 2015-05-28 | 2016-12-01 | Ajou University Industry-Academic Cooperation Foundation | Method for providing disease co-occurrence probability from disease network |
| CN109325131A (en) * | 2018-09-27 | 2019-02-12 | 大连理工大学 | A kind of drug identification method based on biomedical knowledge map reasoning |
| CN109616169A (en) * | 2018-12-24 | 2019-04-12 | 广州天鹏计算机科技有限公司 | Similar patients' method for digging, device, computer equipment and storage medium |
| CN110675954A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN112309565A (en) * | 2020-08-28 | 2021-02-02 | 北京京东世纪贸易有限公司 | Method, apparatus, electronic device, and medium for matching drug information and disorder information |
| CN112151184A (en) * | 2020-09-27 | 2020-12-29 | 东北林业大学 | System for calculating disease similarity based on network representation learning |
| CN112542243A (en) * | 2020-12-05 | 2021-03-23 | 大连东软教育科技集团有限公司 | ICU electronic medical record knowledge graph construction method, system and storage medium |
| CN113539409A (en) * | 2021-07-28 | 2021-10-22 | 平安科技（深圳）有限公司 | Treatment scheme recommendation method, device, equipment and storage medium |
| CN113628726A (en) * | 2021-08-10 | 2021-11-09 | 海南榕树家信息科技有限公司 | Traditional Chinese medicine dialectical treatment recommendation system and method based on graph neural network and electronic equipment |
| CN114510579A (en) * | 2022-02-08 | 2022-05-17 | 吾征智能技术(北京)有限公司 | Disease automatic question-answering system, equipment and medium based on medical knowledge map |
Non-Patent Citations (5)
| Title |
|---|
| 余黄樱子 等: "基于网络表示学习的疾病知识关联挖掘与预测方法研究", vol. 42, no. 12 * |
| 拉姆什·沙尔达 等著: "《商业分析 基于数据科学及人工智能技术的决策支持系统 原书第11版》", 上海：上海科学技术出版社, pages: 524 - 526 * |
| 李杰 等: "基于疾病本体的疾病相似性计算方法", no. 02, pages 150 - 155 * |
| 王亦凡 等: "基于异构图嵌入学习的相似病案推荐", vol. 29, no. 10 * |
| 王青青: "融合知识图谱与图嵌入的电子病历推荐方法研究", no. 12, pages 1 - 40 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115662647B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shorten et al. | Deep Learning applications for COVID-19 | |
| CN109599185A (en) | Disease data processing method, device, electronic equipment and computer-readable medium | |
| CN109658208A (en) | Recommended method, device, medium and the electronic equipment of drug | |
| KR102327062B1 (en) | Apparatus and method for predicting result of clinical trial | |
| CN107016438A (en) | A kind of system based on Chinese medical discrimination artificial neural network algorithm model | |
| CN114093527B (en) | Drug repositioning method and system based on spatial similarity constraint and nonnegative matrix factorization | |
| CN112765370B (en) | Entity alignment method and device of knowledge graph, computer equipment and storage medium | |
| CN113707303A (en) | Method, device, equipment and medium for solving medical problems based on knowledge graph | |
| CN111048167A (en) | Hierarchical case structuring method and system | |
| CN112951362A (en) | Medicine recommendation method, device, equipment and storage medium | |
| CN113658662B (en) | Dispensing method, device, equipment and storage medium based on big medication data | |
| Robles-Bykbaev et al. | SPELTA: An expert system to generate therapy plans for speech and language disorders | |
| CN112149411B (en) | Method for constructing body in clinical application field of antibiotics | |
| CN107391927A (en) | A kind of method and electronic equipment for predicting medicine and disease corresponding relation | |
| CN113657105A (en) | Medical entity extraction method, device, equipment and medium based on vocabulary enhancement | |
| CN117854748A (en) | Knowledge graph and generation-based large model inquiry method and system | |
| Barh | Artificial intelligence in precision health: From concept to applications | |
| CN115662647A (en) | Similar disease mining method and application | |
| CN109616165A (en) | Medical information methods of exhibiting and device | |
| CN117035087A (en) | Method, device, equipment and medium for generating a rational map for medical reasoning | |
| Bhuiyan et al. | Retinal image matching using hierarchical vascular features | |
| CN115565636A (en) | Drug recommendation model construction method, device, equipment and readable storage medium | |
| CN115579153A (en) | Inquiry evaluation method, inquiry evaluation device, electronic device, and readable storage medium | |
| Kejriwal | Artificial intelligence (AI) in medicine and modern healthcare systems | |
| Zhang et al. | Toward navigation ability for autonomous mobile robots with learning from demonstration paradigm: A view of hierarchical temporal memory |
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 |