[go: up one dir, main page]

CN112164460A - An intelligent disease auxiliary diagnosis system based on medical knowledge graph - Google Patents

An intelligent disease auxiliary diagnosis system based on medical knowledge graph Download PDF

Info

Publication number
CN112164460A
CN112164460A CN202011120001.1A CN202011120001A CN112164460A CN 112164460 A CN112164460 A CN 112164460A CN 202011120001 A CN202011120001 A CN 202011120001A CN 112164460 A CN112164460 A CN 112164460A
Authority
CN
China
Prior art keywords
patient
layer
auxiliary diagnosis
medical knowledge
diagnosis
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
Application number
CN202011120001.1A
Other languages
Chinese (zh)
Other versions
CN112164460B (en
Inventor
陈思恩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tech Valley Xiamen Information Technology Co ltd
Jimei University
Original Assignee
Tech Valley Xiamen Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tech Valley Xiamen Information Technology Co ltd filed Critical Tech Valley Xiamen Information Technology Co ltd
Priority to CN202011120001.1A priority Critical patent/CN112164460B/en
Publication of CN112164460A publication Critical patent/CN112164460A/en
Application granted granted Critical
Publication of CN112164460B publication Critical patent/CN112164460B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • 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
    • G06N3/045—Combinations of networks
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • 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

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Epidemiology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Primary Health Care (AREA)
  • Biophysics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Medicinal Chemistry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Chemical & Material Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses an intelligent disease auxiliary diagnosis system based on a medical knowledge graph, which comprises a patient data layer, an entity extraction layer, an auxiliary diagnosis layer and a recommended treatment layer, wherein the patient data layer is used for collecting and storing patient data to form an electronic patient record, the entity extraction layer is used for carrying out entity identification and relation extraction according to patient chief complaints, the auxiliary diagnosis layer is used for carrying out auxiliary diagnosis analysis according to the result of the entity extraction layer to output a suspected disease diagnosis list and a corresponding recommended examination list, and the recommended treatment layer is used for carrying out analysis according to basic information of a patient, the result of an examination report and the diagnosis result of a doctor to output a final treatment scheme. The invention realizes intelligent auxiliary diagnosis of common diseases, provides auxiliary diagnosis with higher reliability for doctors, and helps to improve the diagnosis efficiency and accuracy of the doctors and accurate medication.

Description

Intelligent disease auxiliary diagnosis system based on medical knowledge map
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent disease auxiliary diagnosis system based on a medical knowledge graph.
Background
With the continuous improvement of medical systems in China, medical resources including medical equipment and medical staff are gradually increased, but the situations of shortage of medical resources and low operating efficiency of hospitals still exist, such as: the basic level of diagnosis and treatment is low, and the rate of missed diagnosis is as high as 40%; the time of the clinician cannot be effectively utilized, and more than 20-50% of the time is used for entering a text report; data islands exist in hospital systems and among large medical databases, information is difficult to integrate, and a great amount of medical information is wasted.
Disclosure of Invention
In order to solve the problems, the invention provides an intelligent disease auxiliary diagnosis system based on a medical knowledge graph, and a system thereof.
The invention adopts the following technical scheme:
an intelligent disease auxiliary diagnosis system based on a medical knowledge graph comprises a patient data layer, an entity extraction layer, an auxiliary diagnosis layer and a recommended treatment layer, wherein the patient data layer is used for collecting and storing patient data to form an electronic patient record, the entity extraction layer is used for carrying out entity identification and relation extraction according to patient chief complaints, the auxiliary diagnosis layer is used for carrying out auxiliary diagnosis analysis according to the result of the entity extraction layer to output a suspected disease diagnosis list and a corresponding recommended examination list, and the recommended treatment layer is used for carrying out analysis according to basic information of patients, the result of an examination report and the diagnosis result of a doctor to output a final treatment scheme.
Further, the patient electronic medical record comprises basic information of a patient, patient chief complaints, examination reports, diagnosis results and medication records, wherein the basic information of the patient comprises sex, height and weight.
Further, the entity extraction layer is composed of a data input module and a neural network module, the data input module adopts manual input or voice input to the patient to master complaints so as to generate texts, the neural network module is composed of a Bi-LSTM network and a CRF network, and output results of the entity extraction layer are composed of disease types, disease symptoms and causes.
Further, the process of entity identification and relationship extraction is specifically as follows:
a1, embedding words in the text generated by the patient complaint to generate word vectors;
a2, carrying out named entity recognition, word segmentation and part of speech tagging on the word vector by utilizing a Bi-LSTM network and CRF network combined model, and outputting a corresponding entity recognition result, wherein the entity recognition result is a part of speech subject and a non-part of speech word, and the part of speech subject is a disease symptom;
and A3, performing label embedding and relation extraction on the entity recognition result, and outputting a relation extraction result of the non-nominal words, namely the incentive.
Further, the auxiliary diagnosis layer comprises an input end, a deep learning model and an output end, wherein the input end is used for extracting the result of the entity extraction layer, the deep learning model is used for carrying out auxiliary diagnosis analysis on the data of the input end, and the output end is used for outputting a suspected disease diagnosis list and a corresponding recommended examination list.
Further, the construction process of the deep learning model specifically includes the following steps:
b1, constructing a basic network by using the relationship between diseases and symptoms in the medical knowledge map;
b2, incremental learning is carried out by using the prior medical knowledge;
b3, constructing a Bayesian probability model by utilizing a public database, wherein the public database comprises CDC, PubMed and Stanford;
and B4, fusing the basic network and the Bayesian probability model through a linear model fusion technology.
Further, the recommended treatment layer comprises a treatment scheme generation module, a personalized recommendation module and a fusion output module, wherein the treatment scheme generation module is used for generating a preliminary treatment scheme according to the result of the examination report and the diagnosis result of the doctor, the personalized recommendation module is used for searching treatment modes of similar patient groups according to the basic information of the patient and the diagnosis result of the doctor to generate personalized recommendations, and the fusion output module is used for integrating the treatment scheme and the personalized recommendations by utilizing a linear model fusion technology to obtain a final treatment scheme.
Further, the final treatment regimen includes possible complications, prognosis, medication recommendations and precautions.
Further, the generation process of the preliminary treatment plan specifically comprises:
c1, representing the clinical guideline as a decision tree and translating into executable rules;
c2, applying rules to the result of the examination report and the doctor diagnosis result by adopting an inference engine to generate a preliminary quality scheme.
Further, the personalized recommendation generating process specifically includes:
d1, performing association rule analysis on the clinical guideline, the medical knowledge picture and the clinical data to generate a common treatment mode;
d2, finding out clinically similar patient populations according to the basic information of the patients and the diagnosis results of the doctors, and generating personalized recommendations according to the treatment modes of the similar patient populations and the common treatment modes.
After adopting the technical scheme, compared with the background technology, the invention has the following advantages:
the medical data of each large medical database is integrated by using the medical knowledge map, the problem of the existing isolated island of the medical data is solved, and the utilization rate of the medical data is improved; the intelligent auxiliary diagnosis of common diseases is realized, possible complications, prognosis, medication recommendation, cautionary matters and the like are output, auxiliary diagnosis with higher reliability is provided for doctors, and the diagnosis efficiency, accuracy and accurate medication of the doctors are improved; based on the deep learning technology, the key information of the patient chief complaints is automatically identified and extracted, the electronic medical record of the patient is established, the burden of the medical record input by a doctor is reduced, and the unified and standard management of medical data is facilitated; in addition, the treatment of doctors can be standardized, and the satisfaction degree of patients is improved.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
An intelligent disease auxiliary diagnosis system based on a medical knowledge graph comprises a patient data layer, an entity extraction layer, an auxiliary diagnosis layer and a recommended treatment layer, wherein the patient data layer is used for collecting and storing patient data to form an electronic patient record, the entity extraction layer is used for carrying out entity identification and relation extraction according to patient chief complaints, the auxiliary diagnosis layer is used for carrying out auxiliary diagnosis analysis according to the result of the entity extraction layer to output a suspected disease diagnosis list and a corresponding recommended examination list, and the recommended treatment layer is used for carrying out analysis according to basic information of patients, the result of an examination report and the diagnosis result of a doctor to output a final treatment scheme.
The patient electronic medical record comprises basic information of a patient, patient complaints, examination reports, diagnosis results and medication records, wherein the basic information of the patient comprises sex, height and weight.
The entity extraction layer comprises a data input module and a neural network module, the data input module adopts manual input or voice input to the patient to complain so as to generate a text, the neural network module comprises a Bi-LSTM network and a CRF network, and the output result of the entity extraction layer comprises disease types, disease symptoms and causes.
The process of entity identification and relationship extraction is specifically as follows:
a1, embedding words in the text generated by the patient complaint to generate word vectors;
a2, carrying out named entity recognition, word segmentation and part of speech tagging on the word vector by utilizing a Bi-LSTM network and CRF network combined model, and outputting a corresponding entity recognition result, wherein the entity recognition result is a part of speech subject and a non-part of speech word, and the part of speech subject is a disease symptom;
and A3, performing label embedding and relation extraction on the entity recognition result, and outputting a relation extraction result of the non-nominal words, namely the incentive.
The auxiliary diagnosis layer comprises an input end, a deep learning model and an output end, wherein the input end is used for extracting the result of the entity extraction layer, the deep learning model is used for carrying out auxiliary diagnosis and analysis on the data of the input end, and the output end is used for outputting a suspected disease diagnosis list and a corresponding recommended examination list.
The construction process of the deep learning model is as follows:
b1, constructing a basic network by using the relationship between diseases and symptoms in the medical knowledge map;
b2, incremental learning is carried out by using the prior medical knowledge;
b3, constructing a Bayesian probability model by utilizing a public database, wherein the public database comprises CDC, PubMed and Stanford;
and B4, fusing the basic network and the Bayesian probability model through a linear model fusion technology.
The recommended treatment layer comprises a treatment scheme generation module, a personalized recommendation module and a fusion output module, wherein the treatment scheme generation module is used for generating a preliminary treatment scheme according to the result of the examination report and the diagnosis result of the doctor, the personalized recommendation module is used for searching the treatment modes of similar patient groups according to the basic information of the patient and the diagnosis result of the doctor to generate personalized recommendations, and the fusion output module is used for integrating the treatment scheme and the personalized recommendations by utilizing a linear model fusion technology to obtain a final treatment scheme.
The final treatment regimen includes possible complications, prognosis, medication recommendations and precautions.
The generation process of the primary treatment scheme specifically comprises the following steps:
c1, representing the clinical guideline as a decision tree and translating into executable rules;
c2, applying rules to the result of the examination report and the doctor diagnosis result by adopting an inference engine to generate a preliminary quality scheme.
The personalized recommendation generating process specifically comprises the following steps:
d1, performing association rule analysis on the clinical guideline, the medical knowledge picture and the clinical data to generate a common treatment mode;
d2, finding out clinically similar patient populations according to the basic information of the patients and the diagnosis results of the doctors, and generating personalized recommendations according to the treatment modes of the similar patient populations and the common treatment modes.
In this embodiment, for example, the patient mainly complains about "most recent polyuria and obesity", the entity extraction layer identifies "polyuria and obesity", and the list of suspected disease diagnoses is obtained through the auxiliary diagnosis layer analysis, such as: "type 1, 2 diabetes mellitus; 2. obesity; 3. diabetic retinopathy "and corresponding recommended exams list" 1, blood glucose test; 2. the urine is conventional; 3. visual acuity test "; then, the doctor gives out a final diagnosis result according to the examination result, and recommends a treatment layer to analyze according to the basic information of the patient, the result of the examination report and the diagnosis result of the doctor and output a final treatment scheme.
The probabilistic model of the embodiment covers more than 500 diseases, and the diagnosis schemes of more than 30 diseases are common in the whole family, and the diagnosis accuracy is 95%.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1.一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：包括患者数据层、实体抽取层、辅助诊断层和推荐治疗层，所述患者数据层用于采集和保存患者数据以形成患者电子病历，所述实体抽取层用于根据患者主诉进行实体识别和关系抽取，所述辅助诊断层用于根据所述实体抽取层的结果进行辅助诊断分析以输出疑似疾病诊断列表和相应的推荐检查列表，所述推荐治疗层用于根据患者基本信息、检查报告的结果和医生诊断结果进行分析输出最终的治疗方案。1. an intelligent disease auxiliary diagnosis system based on medical knowledge graph, it is characterized in that: comprise patient data layer, entity extraction layer, auxiliary diagnosis layer and recommended treatment layer, described patient data layer is used for collecting and saving patient data to form The patient electronic medical record, the entity extraction layer is used to perform entity recognition and relationship extraction according to the patient's main complaint, and the auxiliary diagnosis layer is used to perform auxiliary diagnosis analysis according to the results of the entity extraction layer to output a list of suspected disease diagnoses and corresponding recommendations The examination list, the recommended treatment layer is used for analyzing and outputting a final treatment plan according to the basic information of the patient, the results of the examination report and the diagnosis results of the doctor. 2.如权利要求1所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述患者电子病历包含患者基本信息、患者主诉、检查报告、诊断结果和用药记录，所述患者基本信息包括性别、身高和体重。2. a kind of intelligent disease auxiliary diagnosis system based on medical knowledge graph as claimed in claim 1, is characterized in that: described patient electronic medical record comprises patient basic information, patient chief complaint, inspection report, diagnosis result and medication record, described Basic patient information includes gender, height and weight. 3.如权利要求1所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述实体抽取层由数据输入模块、神经网络模块组成，所述数据输入模块采用人工手动输入或语音输入患者主诉从而生成文本，所述神经网络模块由Bi-LSTM网络和CRF网络组成，所述实体抽取层的输出结果由疾病种类、疾病症状和诱因组成。3. A kind of intelligent disease auxiliary diagnosis system based on medical knowledge graph as claimed in claim 1, it is characterized in that: described entity extraction layer is made up of data input module, neural network module, described data input module adopts manual manual input Or voice input patient complaints to generate text, the neural network module is composed of Bi-LSTM network and CRF network, and the output result of the entity extraction layer is composed of disease types, disease symptoms and incentives. 4.如权利要求3所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述实体识别和关系抽取的过程具体如下：4. a kind of intelligent disease auxiliary diagnosis system based on medical knowledge graph as claimed in claim 3, is characterized in that: the process of described entity identification and relation extraction is as follows: A1、对所述患者主诉生成的文本进行词嵌入，生成词向量；A1. Perform word embedding on the text generated by the patient's chief complaint to generate a word vector; A2、利用Bi-LSTM网络和CRF网络联合模型对所述词向量进行命名实体识别、分词和词性标注，输出对应的实体识别结果，所述实体识别结果为名词性主语和非名词性词语，所述名词性主语即疾病症状；A2. Use the Bi-LSTM network and the CRF network joint model to perform named entity recognition, word segmentation and part-of-speech tagging on the word vector, and output the corresponding entity recognition result. The entity recognition result is a nominal subject and a non-nominal word, so The noun subject is the disease symptom; A3、对所述实体识别结果进行标签嵌入、关系抽取，输出非名词性词语的关系抽取结果即诱因。A3. Perform label embedding and relation extraction on the entity recognition result, and output the relation extraction result of non-noun words, that is, the inducement. 5.如权利要求1所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述辅助诊断层包括输入端、深度学习模型和输出端，所述输入端用于提取所述实体抽取层的结果，所述深度学习模型用于对所述输入端的数据进行辅助诊断分析，所述输出端用于输出疑似疾病诊断列表和相应的推荐检查列表。5. The intelligent disease auxiliary diagnosis system based on medical knowledge graph according to claim 1, wherein the auxiliary diagnosis layer comprises an input end, a deep learning model and an output end, and the input end is used for extracting all The result of the entity extraction layer is obtained, the deep learning model is used to perform auxiliary diagnosis analysis on the data of the input end, and the output end is used to output a suspected disease diagnosis list and a corresponding recommended check list. 6.如权利要求5所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述深度学习模型的构建过程具体如下：6. a kind of intelligent disease auxiliary diagnosis system based on medical knowledge graph as claimed in claim 5, is characterized in that: the construction process of described deep learning model is as follows: B1、利用医疗知识图谱中的疾病和症状的关系构建基础网络；B1. Use the relationship between diseases and symptoms in the medical knowledge graph to build a basic network; B2、利用先验医学知识进行增量学习；B2. Use prior medical knowledge for incremental learning; B3、利用公共数据库构建贝叶斯概率模型，所述公共数据库包括CDC、PubMed和Stanford；B3. Build a Bayesian probability model using public databases, including CDC, PubMed and Stanford; B4、通过线性模型融合技术将所述基础网络和所述贝叶斯概率模型融合。B4. Integrate the basic network and the Bayesian probability model through a linear model fusion technology. 7.如权利要求1所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述推荐治疗层包括治疗方案生成模块、个性化推荐模块和融合输出模块，所述治疗方案生成模块用于根据所述检查报告的结果和所述医生的诊断结果生成初步治疗方案，所述个性化推荐模块用于根据所述患者基本信息和所述医生诊断结果查找相似患者人群的治疗模式生成个性化推荐，所述融合输出模块用于利用线性模型融合技术将所述治疗方案和所述个性化推荐整合得到最终的治疗方案。7. The intelligent disease auxiliary diagnosis system based on medical knowledge graph according to claim 1, wherein the recommended treatment layer comprises a treatment plan generation module, a personalized recommendation module and a fusion output module, and the treatment plan The generation module is used to generate a preliminary treatment plan according to the results of the inspection report and the diagnosis results of the doctor, and the personalized recommendation module is used to find the treatment mode of the similar patient population according to the basic information of the patient and the diagnosis result of the doctor A personalized recommendation is generated, and the fusion output module is used for integrating the treatment plan and the personalized recommendation using a linear model fusion technology to obtain a final treatment plan. 8.如权利要求7所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述最终的治疗方案包括可能的并发症、预后、用药推荐和注意事项。8 . The intelligent disease auxiliary diagnosis system based on a medical knowledge graph according to claim 7 , wherein the final treatment plan includes possible complications, prognosis, medication recommendations and precautions. 9 . 9.如权利要求7所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述初步治疗方案生成过程具体为：9. A kind of intelligent disease auxiliary diagnosis system based on medical knowledge graph as claimed in claim 7, is characterized in that: described preliminary treatment plan generation process is specifically: C1、将临床指南表示为决策树，进而翻译成可执行的规则；C1. Represent clinical guidelines as decision trees, which are then translated into executable rules; C2、采用推理引擎将规则应用到患所述检查报告的结果和所述医生诊断结果，生成初步质量方案。C2. Use an inference engine to apply the rules to the results of the examination report and the doctor's diagnosis results to generate a preliminary quality plan. 10.如权利要求7所述的一种基于医疗知识图谱的智能疾病辅助诊断系统，其特征在于：所述个性化推荐生成过程具体为：10. A kind of intelligent disease auxiliary diagnosis system based on medical knowledge graph as claimed in claim 7, it is characterized in that: described personalized recommendation generation process is specifically: D1、对临床指南、医疗知识图片和临床数据进行关联规则分析，生成常见的治疗模式；D1. Perform association rule analysis on clinical guidelines, medical knowledge pictures and clinical data to generate common treatment patterns; D2、根据所述患者的基本信息和所述医生诊断结果查找到临床上相似的患者人群，结合相似患者人群的治疗模式和所述常见治疗模式生成个性化推荐。D2. Find a clinically similar patient population according to the basic information of the patient and the doctor's diagnosis result, and generate a personalized recommendation in combination with the treatment mode of the similar patient population and the common treatment mode.
CN202011120001.1A 2020-10-19 2020-10-19 An intelligent disease auxiliary diagnosis system based on medical knowledge graph Active CN112164460B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011120001.1A CN112164460B (en) 2020-10-19 2020-10-19 An intelligent disease auxiliary diagnosis system based on medical knowledge graph

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011120001.1A CN112164460B (en) 2020-10-19 2020-10-19 An intelligent disease auxiliary diagnosis system based on medical knowledge graph

Publications (2)

Publication Number Publication Date
CN112164460A true CN112164460A (en) 2021-01-01
CN112164460B CN112164460B (en) 2023-06-30

Family

ID=73867480

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011120001.1A Active CN112164460B (en) 2020-10-19 2020-10-19 An intelligent disease auxiliary diagnosis system based on medical knowledge graph

Country Status (1)

Country Link
CN (1) CN112164460B (en)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113241172A (en) * 2021-03-25 2021-08-10 边缘智能研究院南京有限公司 ICU discrimination system for postoperative infection of neurosurgical patient
CN113380400A (en) * 2021-07-07 2021-09-10 中国科学院空间应用工程与技术中心 Intelligent traditional Chinese medicine diagnosis and treatment auxiliary system based on knowledge map and deep learning
CN113407841A (en) * 2021-06-25 2021-09-17 陈亮 Method and system for automatically recommending AI (artificial intelligence) scheme based on performance analysis of structured report
CN113539480A (en) * 2021-07-20 2021-10-22 武汉情智感知科技有限公司 Novel mental health intervention interactive system
CN113724858A (en) * 2021-08-31 2021-11-30 平安国际智慧城市科技股份有限公司 Artificial intelligence-based disease examination item recommendation device, method and apparatus
CN113871003A (en) * 2021-12-01 2021-12-31 浙江大学 Disease auxiliary differential diagnosis system based on causal medical knowledge graph
CN115062165A (en) * 2022-08-18 2022-09-16 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Medical image diagnosis method and device based on film reading knowledge graph
CN115083599A (en) * 2022-07-12 2022-09-20 南京云创大数据科技股份有限公司 A method for initial diagnosis and treatment of pathological conditions based on knowledge graph
TWI780608B (en) * 2021-02-26 2022-10-11 華碩電腦股份有限公司 Drug recommendation system and method thereof
CN115312186A (en) * 2022-08-09 2022-11-08 北京至真互联网技术有限公司 Auxiliary screening system for diabetic retinopathy
CN115312183A (en) * 2022-08-01 2022-11-08 安图实验仪器(郑州)有限公司 Intelligent interpretation method and system for medical inspection report
CN116682553A (en) * 2023-08-02 2023-09-01 浙江大学 Diagnosis recommendation system integrating knowledge and patient representation
CN117012374A (en) * 2023-10-07 2023-11-07 之江实验室 Medical follow-up system and method integrating event map and deep reinforcement learning
CN117690549A (en) * 2024-02-01 2024-03-12 中国中医科学院中医临床基础医学研究所 A TCM personalized intelligent prescription recommendation system based on similar patient matching
CN117690604A (en) * 2023-12-08 2024-03-12 浙江大学 Diabetes health ventilating and teaching and medication recommending system based on large language model
CN118173283A (en) * 2024-05-14 2024-06-11 四川互慧软件有限公司 Emergency emergency condition analysis method, device, equipment and medium
CN119296767A (en) * 2024-12-10 2025-01-10 中国科学院自动化研究所 Auxiliary diagnosis method and device based on generative model implemented by computer program

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106778042A (en) * 2017-01-26 2017-05-31 中电科软件信息服务有限公司 Cardio-cerebral vascular disease patient similarity analysis method and system
CN107145744A (en) * 2017-05-08 2017-09-08 合肥工业大学 Construction method, device and auxiliary diagnosis method of medical knowledge map
US20180137250A1 (en) * 2016-11-15 2018-05-17 Hefei University Of Technology Mobile health intelligent medical guide system and method thereof
CN109346169A (en) * 2018-10-17 2019-02-15 长沙瀚云信息科技有限公司 A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium
CN109801705A (en) * 2018-12-12 2019-05-24 平安科技（深圳）有限公司 Treat recommended method, system, device and storage medium
CN111785368A (en) * 2020-06-30 2020-10-16 平安科技（深圳）有限公司 Triage method, device, equipment and storage medium based on medical knowledge map

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180137250A1 (en) * 2016-11-15 2018-05-17 Hefei University Of Technology Mobile health intelligent medical guide system and method thereof
CN106778042A (en) * 2017-01-26 2017-05-31 中电科软件信息服务有限公司 Cardio-cerebral vascular disease patient similarity analysis method and system
CN107145744A (en) * 2017-05-08 2017-09-08 合肥工业大学 Construction method, device and auxiliary diagnosis method of medical knowledge map
CN109346169A (en) * 2018-10-17 2019-02-15 长沙瀚云信息科技有限公司 A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium
CN109801705A (en) * 2018-12-12 2019-05-24 平安科技（深圳）有限公司 Treat recommended method, system, device and storage medium
CN111785368A (en) * 2020-06-30 2020-10-16 平安科技（深圳）有限公司 Triage method, device, equipment and storage medium based on medical knowledge map

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI780608B (en) * 2021-02-26 2022-10-11 華碩電腦股份有限公司 Drug recommendation system and method thereof
CN113241172A (en) * 2021-03-25 2021-08-10 边缘智能研究院南京有限公司 ICU discrimination system for postoperative infection of neurosurgical patient
CN113407841A (en) * 2021-06-25 2021-09-17 陈亮 Method and system for automatically recommending AI (artificial intelligence) scheme based on performance analysis of structured report
CN113380400A (en) * 2021-07-07 2021-09-10 中国科学院空间应用工程与技术中心 Intelligent traditional Chinese medicine diagnosis and treatment auxiliary system based on knowledge map and deep learning
CN113539480A (en) * 2021-07-20 2021-10-22 武汉情智感知科技有限公司 Novel mental health intervention interactive system
CN113724858A (en) * 2021-08-31 2021-11-30 平安国际智慧城市科技股份有限公司 Artificial intelligence-based disease examination item recommendation device, method and apparatus
CN113871003A (en) * 2021-12-01 2021-12-31 浙江大学 Disease auxiliary differential diagnosis system based on causal medical knowledge graph
CN113871003B (en) * 2021-12-01 2022-04-08 浙江大学 Disease auxiliary differential diagnosis system based on causal medical knowledge graph
CN115083599A (en) * 2022-07-12 2022-09-20 南京云创大数据科技股份有限公司 A method for initial diagnosis and treatment of pathological conditions based on knowledge graph
CN115312183A (en) * 2022-08-01 2022-11-08 安图实验仪器(郑州)有限公司 Intelligent interpretation method and system for medical inspection report
CN115312186B (en) * 2022-08-09 2023-06-09 北京至真互联网技术有限公司 Auxiliary screening system for diabetic retinopathy
CN115312186A (en) * 2022-08-09 2022-11-08 北京至真互联网技术有限公司 Auxiliary screening system for diabetic retinopathy
CN115062165A (en) * 2022-08-18 2022-09-16 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Medical image diagnosis method and device based on film reading knowledge graph
CN116682553A (en) * 2023-08-02 2023-09-01 浙江大学 Diagnosis recommendation system integrating knowledge and patient representation
CN116682553B (en) * 2023-08-02 2023-11-03 浙江大学 Diagnosis recommendation system integrating knowledge and patient representation
CN117012374A (en) * 2023-10-07 2023-11-07 之江实验室 Medical follow-up system and method integrating event map and deep reinforcement learning
CN117012374B (en) * 2023-10-07 2024-01-26 之江实验室 A medical follow-up system and method that integrates event graphs and deep reinforcement learning
CN117690604A (en) * 2023-12-08 2024-03-12 浙江大学 Diabetes health ventilating and teaching and medication recommending system based on large language model
CN117690549A (en) * 2024-02-01 2024-03-12 中国中医科学院中医临床基础医学研究所 A TCM personalized intelligent prescription recommendation system based on similar patient matching
CN117690549B (en) * 2024-02-01 2024-05-17 中国中医科学院中医临床基础医学研究所 An intelligent prescription recommendation system for TCM based on similar patient matching
CN118173283A (en) * 2024-05-14 2024-06-11 四川互慧软件有限公司 Emergency emergency condition analysis method, device, equipment and medium
CN118173283B (en) * 2024-05-14 2024-07-26 四川互慧软件有限公司 Emergency emergency condition analysis method, device, equipment and medium
CN119296767A (en) * 2024-12-10 2025-01-10 中国科学院自动化研究所 Auxiliary diagnosis method and device based on generative model implemented by computer program
CN119296767B (en) * 2024-12-10 2025-02-18 中国科学院自动化研究所 Method and device for generating model-based auxiliary diagnosis implemented by computer program

Also Published As

Publication number Publication date
CN112164460B (en) 2023-06-30

Similar Documents

Publication Publication Date Title
CN112164460B (en) An intelligent disease auxiliary diagnosis system based on medical knowledge graph
Pezoulas et al. Medical data quality assessment: On the development of an automated framework for medical data curation
US11742092B2 (en) Health information transformation system
CN111540468B (en) A method and system for ICD automatic coding with visualization of diagnosis causes
US8949108B2 (en) Document processing, template generation and concept library generation method and apparatus
US11875884B2 (en) Expression of clinical logic with positive and negative explainability
CA2465706A1 (en) Patient data mining
CA2502983A1 (en) Categorization of information using natural language processing and predefined templates
CN112541066B (en) Text-based structured medical report detection method and related equipment
CN114664463A (en) General practitioner diagnoses auxiliary system
CN116737945B (en) Mapping method for EMR knowledge map of patient
CN113779179A (en) ICD intelligent coding method based on deep learning and knowledge graph
CN115312186B (en) Auxiliary screening system for diabetic retinopathy
del Mar Roldán-García et al. Towards an ontology-driven clinical experience sharing ecosystem: Demonstration with liver cases
US20240266070A1 (en) Application-Specific Processing of a Disease-Specific Semantic Model Instance
US11238988B2 (en) Large scale identification and analysis of population health risks
Ryan et al. Introduction of enhancement technologies into the intensive care service, Royal Prince Alfred Hospital, Sydney
Röhr et al. Revisiting Clinical Outcome Prediction for MIMIC-IV
CN111370081A (en) Artificial intelligence data collection method in time coding mode
US20230335299A1 (en) Translation of medical evidence into computational evidence and applications thereof
Alkan et al. Electronic Health Records: Towards Digital Twins in Healthcare
Zhang Semantic Data Integration of Health Information
CN119047557A (en) Method for constructing knowledge graph by combining and extracting relation triples based on health examination report
Chung Concept-value pair extraction from semi-structured clinical reports: a case study using echocardiogram reports
Kim Exploring data reusability: standardized representation of domain contents and feasibility testing

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20230529

Address after: No.185, Yinjiang Road, Jimei, Xiamen, Fujian Province, 361000

Applicant after: JIMEI University

Applicant after: TECH VALLEY (XIAMEN) INFORMATION TECHNOLOGY CO.,LTD.

Address before: 361000 room 404, building a, 88 anling 2nd Road, Huli District, Xiamen City, Fujian Province

Applicant before: TECH VALLEY (XIAMEN) INFORMATION TECHNOLOGY CO.,LTD.

GR01 Patent grant
GR01 Patent grant