98 results about "Drug adverse reactions" patented technology

The present invention provides a set of oligonucleotide probe for detecting CYP450 enzyme gene hot mutant site and its uses, belonging to clinical molecular diagnosis field. The probe is designed at whole gene sequence of each subtype enzyme of CYP450 and has relative high sensitivity and specifity. The present invention also provides a gene chip for detecting cytochrome P450 enzyme series mutant sites and can detect gene typing of DNA specimen. The inventive probe can be used in P450 genetype diagnosi, clinical medicament and preventing drug adverse reaction.

The invention provides a sinomenine injection special for intravenous administration. The sinomenine injection is an injection which comprises 0.005-0.3wt% of sinomenine and an aqueous solvent for injection, or an injection which comprises sterile injection powder or lyophilized injection powder used for preparation just before injection to cause the sinomenine concentration to be 0.005-0.3wt% in the injection and the aqueous solvent for injection. The sinomenine injection of the invention is used for treating rheumatism, chronic pain and other chronic inflammatory diseases. Compared with other existing injection forms, the sinomenine injection special for intravenous injection has lower drug adverse reaction, and the clinical curative effect is obviously improved.

The invention provides a personalized adverse drug reaction prediction method, system and device and a medium, and belongs to the technical field of biomedicine. The invention provides a multi-task learning model (KEMULA) based on multi-kernel function learning so as to replace traditional learning methods of universal application and complete individuation. More specifically, the model calculatesand ranks the risks of ADR development of patients by learning a constrained personalized ADR ranking function by assuming a sharing function of the model. This function is referred to as a personalized ADR ranking function, which is a linear combination of several scoring functions that calculate the risk of developing related ADR of patients. In addition, the model is also combined with Laplacian regularization to ensure that variable information trained by personADRank functions of similar patients is close, so that the causal relationship (true positive) of the model to the association between a given patient and the corresponding ADR can be improved. Therefore, the method has good practical application value.

The invention provides a drug combination recommendation method based on a time attention mechanism and a graph convolutional network. According to the invention, reasonable drugs can be recommended for treatment of critical patients in a complex medical environment, and clinicians can be helped to treat patients. Diagnosis and treatment in electronic health records are coded in a unified coding format, time sequence information in diagnosis and treatment is stored, codes are converted into vectors, and the time attention mechanism composed of two layers of recurrent neural networks is used for capturing the time sequence information. The method aims at medicines of prescriptions issued by doctors in the electronic health records and medicines having adverse reactions with known medicines,graph network structure data are converted to describe the relation between different medicine combinations, and medical medication knowledge in a medicine graph network is learned by utilizing the graph convolutional network. Compared with the prior art, the simplified graph convolutional network reduces the calculation parameters of the neural network model and reduces the training and learningtime under the condition of maintaining the prediction accuracy unchanged.

The invention relates to a betahistine hydrochloride liposome and a preparation method of the betahistine hydrochloride liposome. The preparation method comprises the steps of: firstly dissolving lipide ingredients in methylene dichloride, and carrying out reduced-pressure evaporation in water bath until a film is formed; dissolving the film in diethyl ether, and then adding phosphate buffer containing betahistine into the solution; carrying out ultrasonic treatment on the mixed suspension liquid, placing the treated liquid on a rotary evaporator, and carrying out reduced-pressure vaporization until all the organic reagent is evaporated; and finally, obtaining the betahistine hydrochloride liposome. The betahistine hydrochloride is made into liposome, so that the medicine effect is obviously improved, the permeability of blood capillary can be improved, and the dosage of the medicine reaching blood vessels of the brain can be increased; the betahistine hydrochloride liposome is used for improving the treatment effect of Meniere syndrome, reduces the gastrointestinal irritation and the adverse drug reaction, and is beneficial to reducing the side effects such as stomach upset, nausea, dizziness and the like.

The invention provides a drug interaction and event prediction method and a model based on attention neural network. According to the method, more comprehensive feature vector representation is obtained by integrating heterogeneous drug feature networks on the basis of a deep attention neural network framework, and a graph representation learning method is combined, the difference of the influenceof drugs on other drugs in different characteristics and dimensions is analyzed, and the accuracy of drug interaction prediction and the robustness of the model are improved under the condition of adopting multiple data sources, so that the model has interpretability, the function of predicting a drug interaction event is realized, the understanding of a mechanism hidden behind adverse drug reactions is facilitated, meanwhile, reasonable combined medication can be guided, and medication safety is promoted.

The invention discloses a rapid identification method and system for adverse reactions of drugs based on big data. The rapid identification method for adverse reactions of drugs based on big data in the invention comprises the following steps: S11, acquiring adverse reaction data of a drug; S12, comparing the obtained adverse drug reaction data with a pre-stored drug name ontology knowledge base and an adverse reaction name ontology knowledge base to generate drug-adverse reaction distributed entity vectors; S13, according to the generated drug-adverse reaction distributed entity vectors, calculating a plurality of association degree values of the drug and an adverse reaction body; S14, solving a confidence interval of each association degree value according to the plurality of associationdegree values obtained by calculation, and comparing the confidence interval of each association degree value obtained by solving with a preset reference value to obtain a comparison result; and S15,judging whether the comparison result is greater than a preset threshold value or not, and if so, determining that the comparison result is an adverse drug reaction signal, or if not, conducting exclusion.

The invention discloses an ADR auxiliary decision-making system based on deep learning, and the system comprises a drug database module which is used for obtaining and storing drug information and related adverse drug reaction information; the CHPS drug evaluation module is used for exporting perfect adverse drug reaction data on the basis of a CHPS system; the deep learning module is used for learning adverse drug reaction data exported from the CHPS drug evaluation module; the auxiliary evaluation and risk early warning module is used for comparing the input certain medicine information by using the deep learning module; the medication decision-making module is used for carrying out medication decision-making judgment after passing through the auxiliary evaluation and risk early warning module and giving information about whether medication is carried out or not; the feedback module is used for feeding back the related physical sign data of the patient after medication and the dosage and frequency data of medication to the deep learning module; the system can make decision analysis and risk management on medication based on deep learning while improving and perfecting adverse drug reaction data.

The invention relates to an intelligent monitoring method, device and system for adverse drug reactions and computer equipment. The method comprises the following steps: acquiring patient diagnosis and treatment data of a terminal, wherein the patient diagnosis and treatment data comprises patient sign data and patient detection data; inputting the physical sign data of the patient and the detection data of the patient into an adverse drug reaction early-warning device; acquiring an output result of the adverse drug reaction early-warning device, wherein the output result is a drug result obtained by the drug adverse reaction early-warning device through analysis according to the patient sign data and the patient detection data; and sending the output result to the terminal for the terminal to display the output result. By adopting the scheme, the accuracy of intelligent monitoring of the adverse drug reactions can be improved, and the comprehensiveness of an intelligent monitoring system of the adverse drug reaction can be perfected.

The invention discloses applications of a traditional Chinese medicine composition in preparation of a drug used for inhibiting angiogenesis. The traditional Chinese medicine composition comprises traditional Chinese medicine ingredients such as radix astragali and ligustrum lucidum. The traditional Chinese medicine composition is capable of benefiting qi and nourishing yin, invigorating spleen and tonifying kidney, and removing stasis and relaxing vein; and the applications of the traditional Chinese medicine composition are right focused on pathomechanism. It is confirmed by experiments that the traditional Chinese medicine composition is capable of inhibiting angiogenesis effectively, and can be used for treating malignant tumor, rheumatoid arthritis, diabetic retinopathy and unstable arterial plaque in clinic. The traditional Chinese medicine composition is reasonable in compatibility of medicines, small in adverse drug reaction and taken by patients for a long term.

The invention provides an inter-drug adverse reaction early warning method, early warning device and early warning system, and the early warning method comprises the following steps: constructing a Chinese and Western drug interaction ontology, and storing the constructed Chinese and Western drug interaction ontology in an ontology knowledge base; the Chinese and western medicine interaction ontology comprises a semantic type, an instantiated entity and a semantic relationship; constructing an inference rule based on description logic; the inference rule is constructed based on a corresponding interaction result in the interaction of the Chinese and western medicine types and the medicine components; acquiring a drug name, and acquiring associated information of the drug from the constructed Chinese and western drug interaction ontology; and judging the reactions between the drugs by using the constructed inference rule according to the association information of the drugs, and performing early warning of the adverse reactions between the drugs according to the judgment result. According to the method, the early warning efficiency of the adverse reactions between the drugs can be greatly improved, and the recall ratio and the precision ratio of the adverse reactions between the drugs are improved.

The invention discloses an application of a traditional Chinese medicine composition in preparation of drugs for inhibiting rheumatoid arthritis angiogenesis. The traditional Chinese medicine composition comprises traditional Chinese medicines such as radix astragali, ligustrum lucidum and the like. The traditional Chinese medicine composition has the effects of tonifying qi and nourishing yin, invigorating spleen and tonifying kidney, dissipating binds and dredging collaterals, and focuses on the pathogenesis; experiments confirm that the traditional Chinese medicine composition of the invention can effectively inhibit angiogenesis, and can be clinically used for rheumatoid arthritis. The traditional Chinese medicine composition of the invention is reasonable in combination, has less adverse drug reaction, and is suitable for long-term use by patients.

The invention discloses a drug adverse reaction processing method and a drug storage medium device. The drug adverse reaction processing method comprises the following steps that patient information and monitoring drug information in a hospital information system are acquired; the obtained medicine is stored in an intelligent medicine box, the intelligent medicine box comprises camera equipment, astorage chamber and a processor, the camera equipment sends shot and scanned information to the processor, and patient information and monitored medicine information are sent to the processor throughthe Internet; the intelligent medical box contacts an emergency contact person through a network according to pre-input emergency contact person information, is connected to a hospital information system through communication, establishes a private inquiry channel between a patient and a main diagnosis doctor, calls disease information of the patient, opens for the main diagnosis doctor, emergency medical guidance is provided for online medical treatment of the main diagnosis doctor through camera equipment. According to the invention, adverse reactions of drugs of patients can be detected, and more importantly, a solution can be provided rapidly, which is more beneficial to the health and safety of the patients.

The invention discloses a method for detecting adverse drug reaction signal, and belongs to the technical field of computer software and medical informatization. According to the drug adverse reaction signal detection method, data related to adverse drug reactions in a national health information platform is obtained, the data is cleaned and normalized and then integrated into a clinical case data warehouse again, and adverse reaction risk signals are detected according to a preset mining algorithm and a signal detection model. The method for detecting the adverse drug reaction signals can timely, comprehensively and accurately monitor the safety of medical instruments on the market, processes the detected signals in time, reduces the risk of adverse drug reactions of patients, and has good popularization and application values.

The invention discloses a christina loosestrife herb polysaccharide with an immunity-strengthening effect and solves the problems that a drug for strengthening the human immunity is obvious in adverse reaction and inaccurate in effect in the prior art. The christina loosestrife herb polysaccharide is prepared through degreasing christina loosestrife herb, carrying out water extraction and alcohol precipitation, intercepting a component of which the molecular weight is greater than 10,000Dalton through dialysis and separating through macroporous weak-base anion-exchange resin. The preparation method comprises the following steps of degreasing, water extraction, alcohol precipitation, dialysis, macroporous weakly basic anion exchange resin column chromatography and drying. The christina loosestrife herb polysaccharide is applied to preparation of foods and health foods or drugs with the immunity-strengthening effect. The christina loosestrife herb polysaccharide is accurate in immunity-strengthening effect, small in adverse reaction, simple in preparation method, simple in operation and suitable for industrial production.

The invention relates to the technical field of text processing, in particular to a joint detection method for drug names and adverse drug reactions in web texts, and the method comprises the following steps: extracting local context information of the web texts to obtain local context representations of words in the web texts; extracting global context information of the web text to obtain global context representation of the web text; and based on the local context representation and the global context representation, utilizing a pre-trained classification model to identify an actual category of the web text, and obtaining a detection effect of the drug name and the adverse drug reaction in the web text according to the actual category. Therefore, the detection effect of the drug name and the adverse drug reaction in the web text is effectively improved.

The invention relates to an adverse drug reaction prediction system and method based on a knowledge graph, the system comprises a database module, a knowledge graph module and a prediction module, the database module is connected with the knowledge graph module, and the knowledge graph module is in interactive connection with the prediction module. The database module is used for constructing a database containing a plurality of drug names and corresponding adverse reaction data; the knowledge graph module is used for inquiring the adverse reaction of the to-be-detected medicine from the database and drawing a corresponding knowledge graph; judging whether adverse reaction conflicts exist among the plurality of to-be-detected medicines or not, and drawing a corresponding knowledge graph; the prediction module is used for predicting the potential adverse reaction of the to-be-detected medicine. Compared with the prior art, the method has the advantages that the known adverse reaction of the to-be-detected medicine can be quickly and accurately inquired, the potential adverse reaction of the medicine can be predicted, and meanwhile, the adverse reaction conflict among multiple medicines can be judged, so that the harm possibly generated by multi-medicine combination is avoided.

The present invention provides a composition for prevention and/or improvement of an adverse drug reaction, a symptom associated with an adverse drug reaction, and/or an adverse reaction associated with medical treatment. More specifically, the present invention provides a composition for prevention and/or improvement of an adverse drug reaction, a symptom associated with an adverse drug reaction, and/or an adverse reaction associated with medical treatment in a subject, comprising molecular hydrogen as an active ingredient.

A method of treating a patient with multiple drugs using adjusted phenotypes of CYP450 enzymes to assess the risk of adverse drug reactions occurring due to drug-enzyme interactions. CYP450 enzyme genotypes and phenotypes are measured in a patient. The phenotypes are scored numerically. The drugs intended for treatment are scored numerically for their ability to induce or inhibit the CYP450 enzymes. The drug scores are used to adjust the CYP450 phenotype scores relative to inducing or inhibiting the enzymes. An accurate adjusted phenotype score for a given CYP450 enzyme is converted to an accurate adjusted phenotype. Any of the intended drugs for treatment that are substrates for the given CYP450 enzyme can be evaluated for risk of an adverse drug reaction based on the adjusted phenotype. This method of rapid risk assessment provides an accurate basis for decisions regarding changes in dose, eliminating a drug, or replacing a drug.

The invention discloses a big data-oriented potential adverse drug reaction data mining system and method. The system comprises a plurality of acquisition terminals, an electronic medical record acquisition module, a specific drug data mining module, a cloud terminal adverse event data processing module, a cloud generation module, a main control computer, a human-computer interaction interface anda data switch, the method comprises the following steps: S1, networking electronic medical record systems of hospitals; S2, capturing a patient who takes the specific medicine in the electronic medical record system; S3, establishing a database of related drugs and adverse reactions after the drugs are used; S4, screening data; and S5, performing feature classification. According to the invention, adverse reactions of specific drugs are analyzed by integrating electronic medical records of various hospitals, the data source is wider, various populations exist, and the analysis of reactions ofdrugs relative to various populations is facilitated. Useless data can be eliminated in the analysis process, analysis is facilitated, the data analysis workload is reduced, and the sample accuracy is improved.

The invention discloses a drug adverse reaction data mining method based on a decision-making tree. The method comprises the steps of obtaining case information based on adverse reactions of the samemedicine, and establishing a case database; obtaining database fields related to the adverse reactions, and performing data generalization processing; and selecting clinical diagnosis as class label attributes, constructing the a decision-making tree, performing training data set classification research, and obtaining a model graph of the decision-making tree. According to the drug adverse reaction data mining method based on a decision-making tree provided by the invention, a decision-making tree method is applied to adverse drug reactions for data mining, and the correlation between the adverse reactions and the gender, age, allergy history, drug dosage form, dosage and the like of a patient is explored in mass data. The constructed decision-making tree improves the processing accuracy of data streams and reduces the possibility of system congestion.