560 results about "Medical knowledge" patented technology

The present invention relates to a system and method of medical knowledge domain modeling and automated medical decision-making, such as for online, questionnaire-based medical triage. In the present invention, information such as conditions and characteristics related to a diagnosis or disposition level is modeled in a Bayesian Network. The Bayesian Network may comprise instantiable nodes, fault nodes, intermediary nodes, a utility node and a decision node. Using Bayesian inference, the conditional probability of any pair in the network may be determined in real-time. These conditional probabilities are modified upon the input of evidence, which is typically in the form of answers to a dynamic set of questions designed to identify a diagnosis or disposition level for the patient under evaluation.

The invention relates to the technology of a knowledge atlas, and aims to provide a Chinese medical knowledge atlas construction method based on deep learning. The Chinese medical knowledge atlas construction method comprises the following steps: obtaining relevant data of a medical field from a data source; using a word segmentation tool to carry out word segmentation on unstructured data, and using an RNN (Recurrent Neural Network) to finish a sequence labeling task to identify entities related to medical care, so as to realize the extraction of knowledge units; carrying out feature vector construction on the entity, and utilizing the RNN to carry out sequence labeling and finish the identification of a relationship among the knowledge units; carrying out entity alignment, and then utilizing the extracted entities and the relationship between the entities to construct the knowledge atlas. According to the Chinese medical knowledge atlas construction method, a recurrent neural network is artfully used for extracting the knowledge units and identifying the relationship among the knowledge units so as to favorably finish the processing of the unstructured data. According to the Chinese medical knowledge atlas construction method, features suitable for the medical care field are put forward to carry out a training task of a network. Compared with general features, the features put forward by the method can better represent a medical entity, and therefore, the relationship among the extracted knowledge units can be more accurate and comprehensive.

System for diagnosis, medical decision support, and healthcare information management that performs analysis of serial health data, adapts to the individual data, and represents dynamics of the most significant parameters (indicators), using at least two scales. The system uses the first-scale (low-resolution) analysis of a snapshot measurement of at least one indicator (primary element) such as heart rate or blood pressure and uses a second-scale (higher-resolution) analysis to determine serial changes in each of the said primary elements. The system optimizes information flow, usage of medical knowledge, and improves accuracy of analysis of serial changes, and adaptability to each individual's data. The information can be distributed in parallel to separate databases at different locations.

he invention discloses a medical information extraction system and method based on depth learning and distributed semantic features. The system is composed of a pretreatment module, a linguistic-model-based word vector training module, a massive medical knowledge base reinforced learning module, and a depth-artificial-neural-network-based medical term entity identification module. With a depth learning method, generation of the probability of a linguistic model is used as an optimization objective; and a primary word vector is trained by using medical text big data; on the basis of the massive medical knowledge base, a second depth artificial neural network is trained, and the massive knowledge base is combined to the feature leaning process of depth learning based on depth reinforced learning, so that distributed semantic features for the medical field are obtained; and then Chinese medical term entity identification is carried out by using the depth learning method based on the optimized statement-level maximum likelihood probability. Therefore, the word vector is generated by using lots of unmarked linguistic data, so that the tedious feature selection and optimization adjustment process during medical natural language process can be avoided.

A system and method for providing computerized, knowledge-based medical diagnostic advice. The medical advice is provided to the general public over a network, such as a telephone network with the use of a telephone or the Internet with the use of an Internet access device. Alternatively, the medical advice can be provided to a patient in a stand-alone mode by use of a computer. The invention utilizes a list-based processing method of generating and executing diagnostic scripts. For the purpose of diagnosing a health problem of a patient, medical knowledge is organized into a list of the diseases to be considered. Each disease on the disease list includes a list of symptoms that is checked in a patient. Each symptom on the symptom list is then further described as a response to a list of one or more questions asked of the patient about the symptom. This triply-nested list structure is converted by suitable data structure transformations into a script that is stored. When a patient requires diagnosis, the script is played back as a sequence of questions. The responses of the patient are analyzed and converted into symptoms. The symptoms are accumulated into diseases. Finally the diseases are selected and reported as a diagnosis.

The invention discloses a method and device for establishing a medical knowledge graph, and an auxiliary diagnosis method. The method for establishing the medical knowledge graph comprises the steps that a user dictionary is established according to a medical database; electronic medical record data is processed, and named entity recognition is conducted; correlation relations are established for each recognized entity; and the medical knowledge graph is established according to the correlation relations. The auxiliary diagnosis method based on the medical knowledge graph comprises the steps that a patient's chief complaint data and inspection data are acquired and processed, so that a symptom entity and a sign entity of the patient can be obtained; a disease entity correlated with the symptom entity and the sign entity is searched in the medical knowledge graph, and a posterior probability of each disease entity in a set composed of the corresponding symptom entity and the sign entity is computed respectively; and the disease entity with the maximum posterior probability and data corresponding to correlated nodes of the disease entity are output. According to the invention, intelligent auxiliary diagnosis is provided for clinical medical science, so that working burdens of medical workers are relieved; medical stress is relieved; and occurrence rate of medical accidents is reduced.

A palm APP based medical service system includes a query module, a user module, a medicine data module; through connection and information exchange among all the modules, a user can know information about hospitals, diseases and medicine data, and can record personal effective medical history data information; the palm APP based medical service system can effectively integrate all kinds of medical information resources, and integrate guidance, examination, payment, medical history information and medicine knowledge into a whole. The palm APP based medical service system can achieve collection of mobile terminal data through connection of all the databases, can save the time of seeing a doctor, embodies a quick service, and creates favorable conditions for hospital market development.

The invention discloses an intelligent medical aid decision making system on basis of a cloud computing technique and a medical knowledge base technique, and belongs to the technical field of medical information. The intelligent medical aid decision making system includes an inquiry knowledge base module and a doctor-patient communication inquiry module; the doctor-patient communication inquiry module includes a consultation launching unit, an intelligent inquiry unit, a manual inquiry unit, a diagnosis and treatment scheme generation unit and a medical history generation unit; and the inquiry knowledge base module is a purchased third party knowledge base service or a self-established knowledge base, and includes basic data of an expert knowledge base which are collected based on departments or disease entities, a personalization inquiry module corresponding to doctors, and an intelligent inquiry path associated with inquiry questions and patient answers. Through a cloud server, a neural network technique, and an intelligent mobile device, the intelligent medical aid decision making system can improve the efficiency and the accuracy of a whole diagnosis process, and effectively relieve the difficulty of getting medical service.

A big data health management system and method based on cloud computing is disclosed. The system comprises a data acquisition module, a big data analysis platform and an intelligent terminal. The dataacquisition module is used for collecting user health data and transmitting the user health data to the big data analysis platform. The big data analysis platform is used for receiving and storing the user health data, constructing a diagnosis and prediction model based on medical knowledge, and carrying out risk assessment and prediction on a common disease according to the user health data. Theintelligent terminal is used to display the health data, and risk assessment and prediction results to a user and to provide a personalized medical service. Comprehensive and personalized health management and a guarantee service are provided for the user, and the distribution efficiency of medical resources is improved.

The invention relates to a deep learning based intelligent skin disease auxiliary diagnosis system, which comprises a classifier training unit, a language model unit and an intelligent auxiliary diagnosis unit. The intelligent auxiliary diagnosis unit comprises an image acquisition module, a voice interrogation module, a voice recognition and keyword extraction module, a probability classificationmodel, a RNN condition analysis module and a fusion classifier. The classifier training unit comprises a state diagram training set under a dermatoscope, a state standard database under skin lesion and dermatoscope, a CNN network convolution module and a sampling and classifying module. The language model unit comprises a medical term standard library, a RNN questioning management module, a RNN chief complaint management module and a skin disease medical knowledge base. The auxiliary diagnosis system has advantages that by deep learning for classifying skin lesion images, probable results areinferred, then a pre-installed dermatoscope image and histodiagnosis tag database is retrieved for doctors' reference, and accordingly accuracy in skin disease diagnosis can be greatly improved.

A computer-based system and method is disclosed which constructs medical histories by direct interactions between the patient and system that acquires pertinent and relevant medical information covering the complete life of a given patient. The system and method insure that a complete life long medical history is acquired from every patient interacting with the health care system. Once acquired, the facts of the patient's life long and family medical history are analyzed automatically by databases to generate a set of the most reasonable diagnostic possibilities (the differential diagnosis) for each medical problem identified and for each risk factor for disease that is uncovered in the historical database. Further, the automatically analyzed database of historical medical information is used as the search tool for bringing to bear, on the diagnosis and treatment of each medical problem identified in each patient, the entirety of medical knowledge that relates to and can be useful for the correct and efficient diagnosis and treatment of each of every patient's medical problems. This collection of information is analyzed to generate a final diagnosis and treatment regimen.

The invention discloses an electronic medical record text structuring method. The method comprises the following steps that 1, a medical knowledge database is loaded; 2, an electronic medical record text is read; 3, word segmentation is carried out on short sentences through a forwards maximum match algorithm, and words in sentences, word properties and relative position relations are obtained; 4, whether the semantics in the sentences for disease information description is positive or negative is judged; 5, disease information elements are extracted; 6, the steps 2-5 are repeated till all interesting contents in the electronic medical record are obtained; 7, different expressions of the disease information elements are combined, the same disease information is combined according to a medical synonym bank, and redundant information is removed; 8, disease description information elements are stored in a structure / class mode, the structuring process is finished, disease relevant information can be effectively extracted from medical record description text, structural expression for disease information is formed, and therefore disease occurrence regularity, definite diagnosis ways, treatment effects and the like are deeply explored.

The invention discloses a patient portrait drawing method and device based on medical big data. A professional medical clinic knowledge base is established, a new calculation model and a new method are adopted on the basis to construct a patient label, and the problems that universal user portrait drawing is low in accuracy and is not suitable to apply in the medical field and the individual privacy of the patient is difficult in protection are solved. In the method and the device, the extraction and the calculation of a label system are established on the basis of a medical knowledge base so that the method and device exhibit strong speciality, and therefore, the accuracy of the patient portrait drawing system is improved to a great extent; secondly, the risk factor, the increasing-decreasing factor and the correlation factor of label characteristics are considered so that the method and device are more in line with the disease development law; thirdly, the patient participates in the confirmation and the management of portrait drawing so as to eliminate the calculation deviation of the label; and finally, a block chain technology is introduced to the aspect of the individual privacy of patient portrait drawing data, and a risk that sensitive medical data is leaked is technically lowered.

The invention provides a medical knowledge map construction method and device so that a technical problem that the clinical medical entities with the same types are not connected tightly can be solvedby constructing a medical knowledge map by using data driving and knowledge driving fully. The method comprises: word segmentation is carried out by using a natural language processing technology anda target entity is extracted from medical data; according to an Apriori algorithm, a frequent item set of a specified class of entity is determined to obtain a specified class of entity group; an intensity index of each node is calculated by using the target entity and the entity group as nodes in a knowledge map, so that a medical knowledge map is obtained; and the constructed medical knowledgemap is stored in a Neo4j graph database.

An intelligent care provider medical practice system which learns the care provider's preferences and historical diagnosis for predicting and treating patients based on provided information. The system makes use of one or more medical knowledge bases and utilizes artificial intelligence and reasoning to learn the provider's preferences and tendencies. The system also automatically generates the provider's notes, treatment plans, and other medical practice actions for treating, billing, and processing the patient after an exam or visit.

A system and method for providing computerized, knowledge-based medical diagnostic advice. The medical advice is provided to the general public over a network, such as a telephone network with the use of a telephone or the Internet with the use of an Internet access device. Alternatively, the medical advice can be provided to a patient in a stand-alone mode by use of a computer. The invention utilizes a list-based processing method of generating and executing diagnostic scripts. For the purpose of diagnosing a health problem of a patient, medical knowledge is organized into a list of the diseases to be considered. Each disease on the disease list includes a list of symptoms that is checked in a patient. Each symptom on the symptom list is then further described as a response to a list of one or more questions asked of the patient about the symptom. This triply-nested list structure is converted by suitable data structure transformations into a script that is stored. When a patient requires diagnosis, the script is played back as a sequence of questions. The responses of the patient are analyzed and converted into symptoms. The symptoms are accumulated into diseases. Finally the diseases are selected and reported as a diagnosis.

The invention discloses a medical interrogation dialogue system and a reinforcement learning method applied to the medical interrogation dialogue system, and relates to the technical field of medicalinformation. The system comprises a natural language understanding module used for classifying the intentions of users and filling slot values to form structured semantic frames; a dialogue managementmodule used for interacting with a user through a robot agent, inputting a dialogue state, performing action decision on the semantic frame through a decision network, and outputting final system action selection; a user simulator used for carrying out natural language interaction with the dialogue management module and outputting user action selection; a natural language generation module used for receiving system action selection and user action selection, enabling the user to check the selection through generating sentences similar to a human language by using a template-based method. According to the invention, the medical knowledge information between diseases and symptoms is introduced as a guide, and the inquiry historical experience is enriched through continuous interaction witha simulated patient. The reasonability of inquiry symptoms and the accuracy of disease diagnosis are improved, and the diagnosis result is higher in credibility.

The invention discloses a knowledge map construction method for medical images, belonging to the field of knowledge maps. The construction process includes a step of knowledge representation with a framework theory representation method, a step of knowledge acquisition, wherein the knowledge sources of entity, attribute and attribute value extraction is unstructured data, a step of knowledge fusion with the integration of acquired new knowledge and the elimination of ambiguity, a step of knowledge processing with the knowledge reasoning and quality assessment of the data which is subjected tothe knowledge fusion and the adding of qualified data to a knowledge map, and a step of knowledge update with the update of the knowledge map according to the update and development of medical image knowledge. According to the characteristics of the medical image knowledge, and the knowledge acquisition rate is greatly improved with the unstructured data such as textbooks and academic journals asa source of knowledge.

The invention discloses a method for establishing a medical image atlas based on image segmentation and the CNN. A CNN method is used to segment medical images finely, image segmentation identification is carried out on the collected medical images, medical knowledge unit segmentation is carried out on medical diagnosis knowledge, and knowledge units of different medical images are formed; an image relation of image segmentation is analyzed to connect the different image knowledge units and communicate with an additional medical illness knowledge unit, a knowledge base association relation isestablished on the basis of connection between medical image identification and medical diagnosis knowledge; characteristic matching is carried out on the knowledge units after image segmentation, entities with the same type of attribute serves as entity nodes in the knowledge atlas, a knowledge base entity is established by fusion, and entities are aligned; and a knowledge atlas is established byusing the entities and the associations therebetween. Suspected diagnosis prompt and treatment suggestion are provided, and AI diagnosis is made possible.

The invention provides a system and a method for presenting electronic medical records. The system comprises a standard management module, a template generator, an electronic medical record generating module, a logical inference engine and a display interface. The standard management module generates data element documents; the template generator generates electronic medical record templates, medical knowledge documents and search and inference rules according to the data element documents; the electronic medical record generating module loads the electronic medical record templates to generate electronic medical records; the logical inference engine obtains the electronic medical records according to patient information, calls the medical knowledge documents according to patients diseases and / or chief complaints, calls the search and inference rules according to the patient diseases and / or the chief complaints and specialized categories and / or service types of medical staff, and performs search and formalized inference on information in the electronic medical records by using the search and inference rules and the medical knowledge documents to obtain electronic medical record data subsets; and the display interface displays the electronic medical record data subsets. By means of the system and the method for presenting electronic medical records, the implicit inference and query can be performed on the electronic medical records, so that the interesting electronic medical record information can be presented on account of specific diseases and / or chief complaints and various specialized medical staff.

The invention discloses a medical knowledge base construction method based on a question-and-answer system, and relates to a medical knowledge base. The medical knowledge base construction technology based on the question-answering system mainly includes data processing, data analysis and an expert question-and-answer platform. Firstly, entity and correlation relations are extracted from clinical data by a hierarchical partitioning method at a data processing stage. Secondly, extracted results are analyzed by an association rule algorithm, entity correlation is mined, the mined entity correlation is matched with a medical dictionary, and correctly matched results are directly stored into the knowledge base. Finally, questions are automatically generated from entity correlation which cannot be confirmed by crowd-sourcing technology, the questions are submitted to an expert question-and-answer platform for answering the questions, and final results are selected from answers of experts by a majority voting algorithm and stored into the medical knowledge base.

A computer-implemented method of detecting an object in a three-dimensional medical image comprises determining the values of a plurality of features at each voxel in at least a portion of the medical image. Each feature characterises a respective property of the medical image at a particular voxel. The likelihood probability distribution of each feature is calculated based on the values of the features and prior medical knowledge. A probability map is generated by using Bayes' law to combine the likelihood probability distributions, and the probability map is analysed to detect an object.

The invention discloses a construction method and device for a medical knowledge map. The method comprises the following steps of obtaining all medical treatment key words in sample data and associations among the medical treatment key words; according to the sample data and the associations, calculating out association strength among the medical treatment key words; based on all the medical treatment key words and the association strength, constructing the medical knowledge map. By the adoption of the technical scheme, through the sample data, all the medical treatment key words obtained from the sample data and the associations among all the medical treatment key words, firstly, the association strength among all the medical treatment key words is calculated out, and then according to all the medical treatment key words and the association strength, the medical knowledge map is constructed. Not only can the associations among all the medical treatment key words be visually reflected, but also the strength of the associations among all the medical treatment key words can be determined, the rearrangement of medical knowledge in the sample data is facilitated, the experience is summarized, and the development of medicine is advanced.

A clinical decision support system enabling sharing of medical knowledge in a machine executable format, implementable as a network-based system in which individual executable knowledge modules (EKMs) define the data requirements for assessing a patient, the conclusions that can be drawn using that data, and instructions on how to generate those conclusions. Using standards-based messages transmitted over a network, client decision support applications provide patient data to the system and receive patient-specific assessments and recommendations. The system permits re-use of executable medical knowledge across diverse applications and care settings, easy authoring of knowledge modules, and use of the system framework to implement decision support applications having significant clinical utility.

The present invention discloses a method and a device for constructing a medical knowledge graph and an assistant diagnosis method. The assistant diagnosis method based on a medical knowledge graph comprises the steps of: acquiring complaint data and examination data of a patient and processing the data to obtain symptom entities and sign entities of the patient; searching, from the medical knowledge graph, disease entities associated with the symptom entities and the sign entities, calculating a posterior probability of each disease entity separately under a set of its corresponding symptom entities and sign entities; and outputting a disease entity with a maximum posterior probability as well as data corresponding to its associated nodes. The present invention provides an intelligent assistant diagnosis for clinical medicine to reduce the work burden of medical staff, relieve the medical pressure and reduce medical accidents.

A system generates medical knowledge base information by searching at least one repository of medical information to identify sentences including a received medical term. A data processor searches the identified sentences to identify sentences including a medical term different to the received term in response to a predetermined repository of medical terms and excludes sentences without a term different to the received term, to provide remaining multiple term sentences. The data processor groups different terms of individual sentences of the multiple term sentences to provide grouped terms, determines whether a medically valid relationship occurs between different terms of an individual group of terms of the grouped terms by using predetermined sentence structure and syntax rules and outputs data representing grouped terms having a medically valid relationship.

The invention relates to a disease risk predication method and system. The method comprises the following steps of: S1, receiving input gene sequencing result information; analyzing the input gene sequencing result information to obtain all mutant gene information; S2, looking up disease gene mutant information of corresponding gene sites from a precision medical knowledge base according to the gene sites corresponding to the mutant gene information, so as to obtain at least one piece of disease gene mutant information; S3, matching each piece of the disease gene mutant information with all the disease gene mutant information to obtain the similarity of each piece of the mutant gene information, and all the disease gene mutant information; and S4, obtaining a risk predication table aiming at the gene sequencing result information according to the similarity of each piece of the mutant gene information, and all the disease gene mutant information. By analyzing an association relation of susceptibility genes, mutation sites, mutation types and diseases, disease risk predication is carried out on healthy people and general disease risk grade predication is provided; disease risks in the future are reduced.

The invention discloses a disease diagnosis method and device. The method includes the steps of creating a disease model in advance, wherein the disease module is used for achieving disease diagnosisaccording to a learning result obtained by means of machine learning of existing electronic medical records and / or existing medical knowledge; on the basis of the information above, when disease diagnosis is carried out on a certain electronic medical record, obtaining a target electronic medical record to be diagnosed first, and then analyzing the medical record information in the target electronic medical record according to the disease model to generate a disease probability list, wherein the medical record information includes usable information used for achieving disease diagnosis, and the disease probability list comprises at least one suspected disease and the actual probability of the suspected disease. Since the disease model learns the existing electronic medical records and / or the medical knowledge, the disease knowledge coverage is more comprehensive; therefore, when the disease model is utilized to carry out disease diagnosis, the diagnosis result is more accurate.

A computer-implemented method of detecting an object in a three-dimensional medical image comprises determining the values of a plurality of features at each voxel in at least a portion of the medical image. Each feature characterises a respective property of the medical image at a particular voxel. The likelihood probability distribution of each feature is calculated based on the values of the features and prior medical knowledge. A probability map is generated by using Bayes' law to combine the likelihood probability distributions, and the probability map is analysed to detect an object.