49 results about "Disease taxonomy" patented technology

The invention relates to a data processing technology, and provides a big data-based medication scheme recommendation method and device, computer equipment and a storage medium. The method comprises the steps: obtaining and carrying out the structural processing of the case symptom information of a patient, and obtaining the target case symptom information; analyzing the target case symptom information to obtain a target entity, and determining the disease classification of the patient based on the target entity; traversing a preset mapping relationship between diseases and diagnosis and treatment according to the disease classification to obtain a target diagnosis and treatment scheme; obtaining drug information carried by the target diagnosis and treatment scheme to obtain an initialized medication scheme; based on a pre-trained drug rule network model, evaluating whether the initialized drug use scheme meets a preset drug use requirement or not; and when the evaluation result is that the initial medication scheme does not accord with the preset medication rule, adjusting the initial medication scheme to obtain a target medication scheme. According to the invention, the accuracy of medication scheme recommendation can be improved, and the construction of smart medical treatment and smart cities is promoted.

The invention relates to a multi-label stomach disease classification method and device based on a medical record text, and belongs to the technical field of medical text intelligent processing. The method comprises the steps that multiple sets of training data are acquired, and each set of training data comprises the medical record text and a disease label corresponding to the medical record text; training a preset network structure based on the multiple groups of training data to obtain a disease classification model; using the disease classification model for identifying disease classification in the input medical record text, wherein the network structure is a combination of a pre-training model and a seq2seq model; and converting a multi-label classification problem into a sequence generation problem by utilizing a network of a pre-training model and a self-attention mechanism, so that very good multi-label classification performance is obtained on limited training samples. Besides, manual participation is not needed in the classification process, human factors are reduced, meanwhile, accurate diagnosis reference can be provided for doctors, and the working pressure of medical staff is relieved.

A graph database for outbreak tracking and management is disclosed. In an example embodiment, an outbreak management system includes a memory device storing instructions that define a graph database for disease outbreak tracking. The instructions specify for a given host that a host node is created and an episode node is connected to the host node via a 'case' link. The episode node is associatedwith episode parameters that are related to a disease classification of the host. In addition, the instructions specify that an outbreak node is connected to the episode node via a 'part of' link to indicate that the host has become part of an outbreak of the disease. The outbreak node is connected to a definition node via a 'defined as' link. The definition node specifies disease parameters of the disease that is related to the outbreak node.

The invention discloses a medical information classification method and apparatus based on a classification model, computer equipment and a storage medium. The method comprises the steps of acquiringspecified medical information of a specified object; inputting the specified medical information into a first disease prediction architecture in a preset disease classification model to obtain a firstpredicted disease; inputting the first prediction disease into a selection connection layer, and acquiring a specified second disease prediction architecture selected by the selection connection layer; inputting the first predicted disease and the specified medical information into the specified second disease prediction architecture to obtain a second predicted disease; mapping the specified medical information, the first predicted disease and the second predicted disease into a disease classification vector; calculating the value of a distance between a standard classification vector and the disease classification vector; and if the distance value is smaller than a preset distance threshold, classifying the specified medical information into a specified category. Therefore, classification accuracy is improved.

The embodiment of the invention discloses a disease classification method and device, equipment and a storage medium. The method comprises the steps of obtaining a numerical vector of case informationof a to-be-classified target object; respectively inputting the numerical vectors of the case information into a trained first disease classification model and a trained second disease classificationmodel, and obtaining a first disease classification probability and a second disease classification probability that the case information belongs to each disease type, wherein the first disease classification model is obtained by training based on a plurality of non-standardized historical case history sample data and the second disease classification model is obtained by training based on a plurality of structured historical case sample data; and determining a target disease type of the case information of the target object based on the first disease classification probability and the seconddisease classification probability that the case information belongs to each disease type. Therefore, the effect of quickly and accurately determining the disease type of the patient according to themedical record information is achieved.

The invention discloses a training sample expansion method. The method comprises the following steps: determining samples of target disease types of which the quantity is less than a preset quantity threshold as target samples; performing vector conversion on the disease name corresponding to the target sample to obtain a name vector; according to a pre-trained first disease classification model,based on the precision of the first disease classification model and the gradient change of the discrimination network, training the generation network to obtain a trained generation model; inputtingthe name vector into a trained generation model to obtain a generated sample data set; and if a plurality of generation samples in the generation sample data set can be used for model training, determining the real sample data set and the generation sample data set as a first training sample data set of the auxiliary diagnosis model. The invention further provides a training sample expansion device, electronic equipment and a storage medium. The number of training samples can be increased, and the accuracy of the auxiliary diagnosis model is improved.

The invention provides an auxiliary diagnosis method based on electronic medical record texts, belongs to the field of medical care informatics, and adopts multiple text classification models to perform disease classification on multiple electronic medical record texts respectively. The electronic medical record texts comprise two types, namely a medical record text obtained by single inquiry activity and a medical record text obtained by multiple observations. The invention further provides an auxiliary diagnosis system based on electronic medical record texts. The system comprises a preprocessing unit group and a classification unit group. Through the mode that multiple models correspond to multiple texts, the data property difference of the texts as input data can be considered, so thatthe influence of the data property difference is smaller when the models are used for disease classification, the overall accuracy is higher, the upper limit of the accuracy is higher, and a better diagnosis and classification effect can be obtained more easily at a lower cost.

The invention discloses a cloud platform system for disease screening and whole-course prevention. The cloud platform system comprises a database, a screening item data analyzing and processing module, a remote collaborative screening module and a user terminal. The user terminal is used for creating files of a user, formulating a disease screening item scheme for the user and collecting disease data of each screening item; the database is used for storing case sample data information corresponding to each screening item; the screening item data analyzing and processing module is used for analyzing and processing the disease data of each screening item of the user and outputting a disease classification result of each screening item; the remote collaborative screening module is used for remote collaborative disease screening between cross-mechanism doctors and cross-region doctors. According to the platform system, a scientific disease screening item scheme is customized according to the actual situation of a user individual, and the comprehensiveness, accuracy and timeliness of disease screening are improved.

Embodiments of the invention provide a medical record classification code determination method and device. The method comprises the steps of obtaining a medical record; determining candidate disease names corresponding to the medical record and a similarity sequence corresponding to the candidate disease names by adopting a preset medical record processing model; determining a target disease namecorresponding to the medical record by adopting the candidate disease names and the similarity sequence corresponding to the candidate disease names; determining a target disease classification code corresponding to the medical record by adopting a preset disease classification code table and the target disease name, wherein the disease classification code table comprises a mapping relationship between disease names and disease classification codes. Through the medical record classification code determination method, the target disease name can be determined through the medical record processing model, and the processing efficiency is high. The target disease classification code of the medical record can be determined, so that the classification coding efficiency of the medical record is improved.

The invention relates to the technical field of digital medical treatment, and discloses a recommendation method and device for a disease maintenance and prevention scheme, equipment and a storage medium, and the method comprises the steps: obtaining target life and medical data obtained according to the body data, diet data, exercise data, medical record data and doctor treatment data of a target object; inputting the target life and medical data into a target disease classification prediction model for disease probability prediction to obtain a disease probability prediction result; finding out disease probabilities greater than the preset probability threshold from the disease probability prediction result to obtain a target disease probability set; obtaining a maintenance and prevention scheme library; and according to the target disease probability set and a maintenance and prevention scheme library, carrying out maintenance and prevention scheme recommendation to obtain a maintenance and prevention scheme recommendation result. The method achieves the accurate recommendation of the maintenance and disease prevention schemes, and provides the help of maintenance and disease prevention before illness.

The invention discloses a household intelligent inquiry system based on multifunctional household health care equipment, belongs to the technical field of medical treatment, solves the technical problems of long physical examination process, low inquiry efficiency and the like, and provides the household intelligent inquiry system based on the multifunctional household health care equipment. A method comprises the steps: obtaining patient information and main symptoms of inquiry; according to the patient information, searching key words extracted from the main symptoms of the patient, matching disease classification attribution according to the extracted key words, and establishing an associated question list of the disease classification attribution; feeding back the information of the established associated question list to an information obtaining surface, inputting the answers of corresponding supplementary questions in a matched mode to serve as auxiliary factors of symptom induction reasons, and collecting and determining the target symptom disease classification affiliation matching degree according to the question list; according to the matching degree of the disease classification of the target symptom, providing the treatment suggestion scheme for the target symptom, so the information inquired by the patient is more accurate, and the risk of misjudgment of the illness state of the patient by a doctor is effectively reduced.

The invention discloses a disease auxiliary diagnosis system and equipment based on oral acid, and a storage medium. The system comprises a sample obtaining module which obtains a case taking oral acid as a first complaint symptom from a case library, extracts case symptom information and a corresponding disease name, and constructs a vectorized case sample; a sample marking module which is used for marking the case samples according to the disease causes of the case samples; a model construction module which is used for constructing a disease classification model through an Adaboost algorithmand training the disease classification model through the case samples; and an auxiliary diagnosis module which is used for acquiring symptom information of a to-be-diagnosed case, carrying out vectorization representation, carrying out first case classification through the trained disease classification model, carrying out second case classification through a semantic similarity calculation mode, and taking a second classification result as an auxiliary diagnosis result. According to the method, the disease classification model is constructed through the Adaboost algorithm, and rapid diseaseauxiliary diagnosis with oral acid as the first chief complaint symptom is achieved.

The embodiment of the invention provides terminal equipment and device, a disease classification method and a readable storage medium, and is applied to the field of medical science and technology. The terminal equipment comprises a communication interface, a processor and a memory, wherein the processor is configured to: call a program instruction in the memory to receive a disease classificationrequest carrying identity information of a target user through the communication interface; acquire gene data of the target user from a memory based on the identity information, wherein the gene datacomprises a gene set and expression quantity data of each gene in the gene set; call the trained target disease classification model to perform data analysis on the expression quantity data of each gene in the gene set; determine the target disease type to which the target user belongs. The disease type to which the target user belongs can be accurately determined, and the method and the device relate to a block chain technology, for example, gene data of the target user can be written into a block chain to be used for scenes such as the target disease type to which the target user belongs.

The embodiment of the invention discloses a method and device for assisting a diagnosis technology, equipment and a storage medium, and the method comprises the following steps: obtaining all electronic medical record data related to a user based on a block chain technology, extracting characters of the electronic medical record data as text data, and storing the text data in a database; extracting a first data set in the electronic medical record data as structured data, wherein the first data set comprises examination vital sign data and examination index data of a preset number of hospitals; the text data is converted into text vector representation, the text vector representation comprises text information, the structured data is converted into structured vector representation, and the structured vector representation comprises structured information; the text information and the structured information are fused to obtain fusion vector representation, the fusion vector representation comprises fusion data, and the fusion data are used for assisting disease classification. According to the invention, the disease classification efficiency can be greatly improved.

A system adapted to receive a knowledge base, which may include drug data, human biological data, drug-drug interactions, protein-protein interactions, gene expression, protein and drug interaction data, genotypic information for cell lines, drug side effects, and disease classification labels. The system may generate a knowledge graph based on the knowledge base, and convert the knowledge graph into embeddings that include points in a k-dimensional metric space. The system may determine a medical effect weighting based on a drug combination query, and update the embeddings of the drug combination. The system may utilize a pooling method to update predicate embeddings. The system may determine polypharmacy scores for the embeddings, and rank the predicted links between a drug combination and side effects.