34 results about "Drug Databases" patented technology

The invention relates to the technical field of medical information, in particular to a medical data conjoint analysis system based on medical knowledge graph driving. The system comprises a medical knowledge graph construction module, a medical data quality evaluation module, a medical feature engineering module and a medical knowledge driven analysis module, and heterogeneous knowledge graph modeling can be performed by integrating medical clinical guidelines, biomedical literatures, a drug database and historical medical data so as to generate a medical heterogeneous knowledge graph; obtaining new medical clinical test information and carrying out delayed contradictory learning update to generate a medical dynamic update knowledge graph; the method comprises the following steps: obtaining multi-modal medical data, carrying out quality verification evaluation and medical feature engineering analysis, carrying out knowledge path joint driving analysis at the same time, generating a decision support reasoning path corresponding to medical clinical knowledge, and outputting a corresponding medical knowledge path confidence coefficient. According to the method, fusion reasoning among cross-source data can be realized by constructing the multi-modal medical knowledge graph.

A system is provided.SOLUTION: A system comprising: means for receiving clinical test data and medical record information; means for obtaining drug information from a drug database; means for classifying data using a specific algorithm and extracting features; means for recommending optimal drugs based on the features; and means for generating and transmitting a recommended drug list.SELECTED DRAWING: Figure 1

The invention discloses preposed evaluation software for a parenteral nutrition prescription, relates to the field of parenteral nutrition support treatment, and relates to a whole process of parenteral nutrition. The software comprises a medicine database part, a patient information area, a parenteral nutrition prescription area, a substance and energy recommendation and judgment area, a stability judgment area and an infusion mode and time suggestion area. A doctor can be helped to make the most suitable parenteral nutrition prescription according to the information and the illness state of a patient, and the stability after mixing according to the prescription can be guaranteed. And the most suitable infusion mode and the minimum infusion time suggestion are given. Due to the fact that parenteral nutrition ingredients are complex, the requirements for stability and patient adaptability are high, the calculation workload is large, if calculation is conducted through a formula according to the requirement of a guide, time is long, and errors are prone to occurring, the software writes in the calculation formula recommended by the guide, the whole process of parenteral nutrition calculation is achieved, and energy intake standards, electrolyte intake standards and intake standards of all nutrient substances are included. And the stability is judged, a plurality of different calculation modes are provided, and more choices are provided.

An object of a system according to an embodiment is to provide side effect information of a drug described in a prescription quickly and in detail.SOLUTION: A system includes a prescription information inputting unit, a generation AI, an information acquiring unit, and an information providing unit. The prescription information input unit inputs prescription information. The generating AI analyzes the prescription information inputted by the prescription information inputting unit. The information acquisition unit acquires information from a plurality of medicine databases. The information providing unit provides detailed side effect information based on the information acquired by the information acquisition unit.SELECTED DRAWING: Figure 1

Disclosed are methods for assessing severity, determining future risk, matching with a drug treatment, and measuring response to treatment, for memory dysfunction, Alzheimer's disease, and cognitive decline. Also disclosed are new methods of use for drugs and natural compounds repurposed for use in improving memory, as well as for preventing and treating memory disorders, Alzheimer's disease and cognitive decline. All the above-mentioned methods are computer assisted methods analyzing the expression of panels of genes, clinical measures, and drug databases. A universal approach in everybody, as well as a personalized approaches by gender, and by diagnosis, are disclosed.

The invention, which relates to the technical field of medicine management, discloses an intelligent management method for the expiration date of a rescue medicine, comprising the following steps: obtaining priority data of rescue medicines at an early warning level and an emergency early warning level through a medicine database, and carrying out analysis and calculation in combination with the remaining expiration date and the expiration date weight index of the rescue medicines; obtaining a dynamic priority index of the rescue medicines, and sequencing the use priorities of the rescue medicines; according to the invention, by analyzing and calculating the remaining expiration date of the medicine and establishing the expiration date weight index model, the early warning level of the medicine is scientifically divided into three levels of safety, early warning and emergency early warning, so that the accuracy of medicine expiration date management is remarkably improved; and furthermore, through a dynamic priority index algorithm, in combination with multi-dimensional data such as the remaining validity period, the effectiveness weight index, the use frequency and the stock of the medicines, intelligent sorting of the use priorities of the rescue medicines is realized, and the priority use of the high-risk and high-value medicines is ensured.

The invention relates to the field of drug utilization value analysis, and particularly discloses a data stream-based drug utilization value analysis system, which comprises a data layer, an application layer and a user layer, according to the method, the multi-source drug data stream is constructed and stored in the multi-source drug database, and based on systematic management of drug information, drug use errors caused by drug name confusion, dosage errors and dosage form confusion can be reduced, the drug use safety is improved, and the method is beneficial to quickly and accurately retrieving and querying specific types of drug information; by integrating the elderly physiological features and the drug feature information, the drug utilization value analysis model is constructed, the elderly physiological features and the drug features are comprehensively considered, the utilization value of the drug on the elderly can be comprehensively evaluated, and the influence of the drug on the elderly patient can be predicted more accurately.

The application discloses application of an HTRA1 inhibitor in preparation of a drug for treating pancreatitis-cancer transformation, and belongs to the technical field of medicines.The HTRA1 inhibitor is screened through a drug database, the HTRA1 inhibitor is used to treat a pancreatic cancer cell line and a mouse pancreatitis-cancer transformation in-vivo model, it is proved that the HTRA1 inhibitor Carfilzomib can inhibit the malignant phenotype of Panc1 cells in vitro, and can inhibit the transformation of a KC mouse stimulated by cerulean into a pancreatic ductal adenocarcinoma in vivo, and the application provides a basis for using the HTRA1 inhibitor as the drug for treating pancreatitis-cancer transformation.

The invention discloses a drug interaction prediction method based on similarity network fusion, and relates to the technical field of biomedicine, and the method comprises the steps: integrating drug data sets in a plurality of well-known drug databases, and extracting drug feature data; calculating similarity according to features extracted from the drug data set, and constructing a similarity matrix; the entropy value of each similarity matrix and the pairwise distance between the similarity matrixes are calculated, and the similarity matrix with the maximum information amount is preferentially selected; combining the selected similarity matrixes by adopting a similarity network fusion technology to obtain a fused similarity matrix; constructing an interaction matrix according to the obtained fusion similarity matrix; and training a convolutional neural network (CNN) model by using the fusion similarity matrix and the interaction matrix of the drug, and realizing drug interaction prediction on test data by using the trained CNN model. By combining the similar network fusion technology and the convolutional neural network model, the accuracy and reliability of drug interaction prediction are remarkably improved.

The invention discloses a prescription drug interaction auditing method and system based on a knowledge graph, and relates to the technical field of medical information, and the method comprises the steps: constructing a drug ontology model, executing multi-source knowledge extraction from a drug specification, a clinical guide, a medical literature, a drug database and hospital historical prescription data, performing knowledge fusion to generate uniform medicine knowledge representation, constructing a medicine knowledge graph containing western medicine, traditional Chinese medicine and Chinese and western medicine combined action sub-graphs, performing prescription medicine identification, performing pairwise pairing analysis and multi-medicine combined cascade effect analysis on prescription medicines, and calculating a personalized medication risk value in combination with patient information. According to the method, the multi-drug combination cascade amplification effect and the Chinese and western medicine combination risk can be identified, and personalized drug use risk assessment is realized.

This invention proposes a drug recommendation method, system, and storage medium based on a large language model and user psychological inference. The method includes: acquiring the user's purchasing needs input during dialogue interaction; using a large language model to identify the completeness of multiple predetermined attributes of the drugs in the current dialogue; generating corresponding query conditions based on the complete values ​​of each predetermined attribute; retrieving a candidate drug set from a drug database; outputting user psychological need tags from a psychological need inference model using a step-by-step reasoning approach based on the user's historical behavior data, dialogue history, and environmental parameters; inputting the user's psychological need tags, the product characteristics and merchant characteristics of each candidate drug in the candidate drug set, and the user profile into the large language model for candidate drug set filtering, determining the top recommended drugs, and generating corresponding recommendation reasons. This invention can significantly improve the matching accuracy between recommendation results and user psychology, and improve the accuracy of drug search.

Disclosed are methods for assessing severity, determining future risk, matching with a drug treatment, and measuring response to treatment, for stress disorders. Also disclosed are new methods for use for drugs and natural compounds repurposed for use in reducing stress severity, as well as for preventing and treating stress disorders. All the above mentioned methods are computer assisted methods analyzing the expression of panels of genes, clinical measures, and drug databases. A universal approach in everybody, as well as a personalized approaches by gender, and by diagnosis, are disclosed.

The invention relates to an accurate medication time recommendation method and system based on a multi-organization rhythm map. The method comprises the following steps: constructing a drug database and a rhythm expression database; acquiring a drug identifier input by a user, performing retrieval in a database, performing rhythm feature analysis based on a retrieval result, and generating a drug-target rhythm analysis report; based on the drug information queried by the two-stage serial query architecture, querying all biological pathways and related genes in which the drug participates, carrying out standardized conversion on gene identifiers, carrying out rhythm feature analysis, and generating a drug-pathway rhythm analysis report; and taking the generated analysis report as input, carrying out semantic integration and reasoning through a locally deployed large language model, and automatically generating an optimal medication time suggestion. Compared with the prior art, the method has the advantages that batch rhythm characteristic analysis of drug target genes and related pathway genes is realized, the analysis efficiency and repeatability are greatly improved, and the decision intelligence level is improved.

The invention discloses a medicine use identification printing system for clinical medical treatment and an identification printer, and relates to the technical field of identification printing, the system comprises a remote input module used for establishing communication interaction with a handheld terminal, setting identification printing content and printing time based on remote control instruction input, and feeding back printing progress; the local input module is used for inputting based on a local control instruction and setting identification printing parameters as required; the networking configuration module is used for being in real-time butt joint with a hospital information system, acquiring clinical medical medication data and accessing a standardized medicine database updated in real time; and the printing control module is used for matching the format of the identification template, dynamically monitoring and adjusting the printing queue and outputting different types of identification labels based on the control instruction. According to the invention, through deep fusion of a modular hardware architecture and intelligent control logic, the operation efficiency, accuracy and compliance of clinical medical drug use identifier printing are significantly improved.

This invention provides a virtual reality-based drug retrieval training method, system, terminal, and medium, specifically relating to the fields of medical information technology and biomedical engineering technology. The solution includes: constructing several initial drug packaging models based on preset multimodal drug characteristics; constructing a drug database based on the initial drug packaging models and key feature information of several drugs, including target drugs and interfering drugs; rendering a virtual pharmacy environment using virtual reality equipment based on the drug database; and, in response to receiving a retrieval instruction for at least one target drug, performing human-computer interaction using the virtual reality equipment based on the retrieval instruction and the virtual pharmacy environment to obtain the retrieval result. This solution, by constructing a drug database with diverse packaging types and using virtual reality technology to create a realistic virtual pharmacy scene, enables medical personnel to perform immersive drug retrieval operations and training in a virtual environment, thereby improving the efficiency of drug retrieval for medical personnel.

The invention discloses a medicine filling dose automatic identification method and system, and relates to the technical field of production automation, a medicine main database and a main learning model are established, and the main learning model differentiates a corresponding derived learning model according to a medicine type; generating a lightweight learning model for each production batch of each type of medicine based on the derived learning model of each type of medicine, performing adaptive compensation adjustment on parameters of each level of the lightweight learning model based on difference information of the production batches, and fusing each level by outputting a corresponding dynamic fusion coefficient; and monitoring the operation process of each lightweight learning model based on a preset task trigger event, carrying out parameter retraining on the lightweight learning model by sharing the difference characteristic parameters, and carrying out canned dose real-time monitoring identification by using the retrained lightweight learning model. Automatic high-precision monitoring and intelligent optimization in the medicine production process are achieved, and the production efficiency and the product quality are improved.

The present invention relates to: a compound for inhibiting SOCS3 activity; a pharmaceutical composition for treating allergic diseases, comprising same as an active ingredient; and the like. More specifically, compounds capable of binding were derived from a drug database through AI-based SOCS3 binding site simulation, and it has been confirmed that these compounds actually inhibit SOCS3 and increase JAK2 kinase activity and the degree of STAT3 phosphorylation, and thus can be used for preventing or treating allergic diseases.

The invention provides an intelligent hospital medicine checking system based on image recognition. The intelligent hospital medicine checking system comprises a medicine image acquisition module, a medicine feature analysis module, a medicine information matching module and a checking strategy adjustment module, the medicine image acquisition module is used for extracting visible light and near infrared spectrum characteristics of medicine packages in the multi-angle visible light image sequence of the medicine to be checked; the drug feature analysis module performs multi-scale feature fusion on the surface image sequence to generate a composite feature vector; the medicine information matching module compares the composite feature vector with a standard feature template of a hospital medicine database layer by layer, and outputs a medicine identity verification result and a batch difference identifier; and the checking strategy adjustment module dynamically adjusts the image acquisition parameters and the feature comparison threshold according to the verification result, and triggers a secondary checking process for the medicines with the batch difference identifiers exceeding the preset fault tolerance range. According to the invention, the change of medicine checking from manual leading to intelligent automation is realized, and the workload of medical staff in the medicine checking link is reduced.

The invention relates to the technical field of drug knowledge maps, and provides a drug database knowledge map construction system, which comprises a data acquisition module, an analysis module, a map module, a risk assessment module and a verification module, key feature data information and map abnormal feature parameter information of target compound drugs of various compound structure types in a drug database are collected, drug key feature factors and map abnormal feature characterization values are analyzed, and whether system operation meets the standard or not is determined through a map module; and if not, starting a verification module based on the map structure risk tendency type, and adopting a corresponding processing mode based on the determined reason for not meeting the standard. By converting discrete drug data into a computable and explorable relation network, a structured knowledge graph is provided for drug research and development and clinical research, and system efficiency and accuracy are improved.

The application discloses an infusion pump control method and product, relates to the field of intelligent medical instruments, and combines a pre-stored knowledge base in a central controller to verify and calculate infusion parameters; and further generates a target infusion scheme, which includes the step of presetting a threshold value. The traditional parameter checking relying on the memory and experience of medical staff is converted into automatic completion by system software and logical verification based on an authoritative drug database. Through sensors (flow, pressure, etc.), the external environment is sensed in real time, compared with the expected model in the internal "target scheme", and the output (peristaltic pump driving instruction) is dynamically adjusted. This significantly improves the accuracy, stability and adaptability to individual differences / environmental changes of infusion, makes the infusion process from mechanization to intelligence, can be uniformly monitored and managed through remote control and monitoring of the infusion pump, and improves intelligent network processing capability.

The embodiment of the application provides a kind of drug database model construction method and device, electronic equipment and storage medium, belong to artificial intelligence technical field.The method comprises: obtaining drug knowledge text;The field extraction is carried out to drug knowledge text, and the drug attribute field of at least two drug attribute dimensions is obtained;Obtain database simulation model;Wherein, database simulation model includes at least two simulation coordinate axes, and simulation coordinate axis includes multiple simulation intervals;According to the simulation coordinate axis of drug attribute dimension, target coordinate axis is obtained, and according to the simulation interval of target coordinate axis of drug attribute field of drug attribute dimension, target interval is obtained, drug attribute field is stored to target interval, and target database model is obtained.The embodiment of the application can improve the reuse rate of drug knowledge, to realize more efficient, accurate knowledge transmission.

The invention discloses an asymmetric drug-drug interaction prediction method and system based on a graph network, and the method comprises the steps: obtaining drug data based on a comprehensive drug database, carrying out the data preprocessing, and constructing drug-DDI graph data and drug-drug graph data; introducing a graph attention network and a heterogeneous graph neural network, and constructing a heterogeneous graph neural network asymmetric DDI prediction model; and based on the heterogeneous graph neural network asymmetric DDI prediction model, performing drug interaction probability prediction on the drug-DDI graph data and the drug-drug graph data to obtain an asymmetric drug-drug interaction prediction result. The method can generate the interaction probability, achieves the precise prediction of the asymmetric DDI, and improves the accuracy and reliability of an asymmetric drug-drug interaction prediction result. The asymmetric drug-drug interaction prediction method and system based on the graph network can be widely applied to the technical field of drug interaction.

The invention provides a medicine order database table processing method and device, equipment and a medium. The method comprises the steps of obtaining a database table formed by various medicine order data in a target medicine database; sorting the order data according to the key values of the order data in the database table to obtain a target database table; performing apportionment processing on first target field data in each row of medicine data included in the order data to obtain a target order; and outputting a database table comprising the plurality of target orders. According to the scheme of the invention, the rationality of the allocation of the related data of the large-scale drug order data is realized, the interference of invalid data is avoided, and the calculation complexity is reduced.

The invention provides a medicine searching method and device and a computer readable storage medium. The medicine searching method comprises the steps of obtaining a query statement; semantic analysis is conducted on the query statement through the trained inference model to obtain multiple pieces of medicine dimension information, and different pieces of medicine dimension information represent different types of medicine information; according to the multiple pieces of medicine dimension information, a medicine database is inquired to obtain an inquiry result, and the inquiry result comprises basic information of the target medicine. The invention provides a scheme for improving drug search accuracy.

The invention discloses a self-adaptive parenteral nutrient solution preparation and calculation system and a self-adaptive parenteral nutrient solution preparation and calculation method. The system is constructed in spreadsheet software, the core of the system lies in a medicine database containing a selected parameter table and an optional parameter table, dynamic maintenance and updating of a medicine list and parameters are achieved through data links (such as a VLOOKUP function), and a core formula does not need to be modified. The system further comprises a logic judgment module which configures infusion modes (all-in-one / two-in-one) through option combinations (such as calcium grouping and definite grouping). The calculation module calculates the medicine dosage according to the nutritional requirements input by the user, the called medicine parameters and the infusion mode, and the unit output module synchronously outputs the results of multiple units. The problems that a traditional calculator is poor in universality and difficult to maintain are solved, long-term use after one-time configuration is achieved, and the efficiency and accuracy of clinical parenteral nutrition prescriptions are remarkably improved.

According to the present invention, a system: acquires a dataset composed of gene expression data of a sample belonging to either of two groups; generates a gene network representing interactions between a plurality of genes by referring to a pathway database; selects one gene from among the plurality of genes; extracts a path by following the gene network downstream with the selected gene as a starting point; calculates path scores by executing enrichment analysis by using, as inputs, a list of genes included in the path and the dataset; generates a ranked gene list by ranking the plurality of genes on the basis of the path scores of the plurality of genes; and calculates drug scores by executing the enrichment analysis by using, as inputs, a list of target genes of drugs stored in a drug database and the ranked gene list.

The invention belongs to the technical field of medical nutrition management, and particularly relates to a nutrition intake difference value analysis and quantitative matching system under a complex chronic common disease scene, which comprises a common disease nutrition demand knowledge base module, a common disease nutrition demand knowledge base module, a common disease nutrition demand knowledge base module, a common disease nutrition demand knowledge base module, a common disease nutrition demand knowledge base module and a common disease nutrition demand knowledge base module, setting a nutritional requirement priority; and the medicine-nutrition interaction adaptation module is used for generating a final nutrition constraint which overlaps the medicine influence by integrating a clinical chronic disease medicine database, automatically synchronizing a medicine use record of a patient, identifying a taboo nutrient corresponding to a medicine and recommending a collaborative nutrient, and performing risk early warning and replacement recommendation on a conflict scheme. The co-disease classification system is constructed according to the organ system and the disease severity, and the multi-dimensional nutrition constraint rule is matched for each type of co-diseases, so that the multi-dimensional nutrition constraint accurate adaptation in a complex co-disease scene is realized, and the limitation of nutrition management of a single disease is broken through.

Target genes are identified with high accuracy and the effectiveness of drugs is evaluated. [Solution] The system acquires a dataset consisting of gene expression data of samples belonging to one of two groups, references a pathway database to generate a gene network representing the interactions of multiple genes, selects one gene from the multiple genes, traces the gene network downstream starting from the selected gene to extract a path, calculates a path score by performing enrichment analysis using as input a list of genes included in the path and the dataset, ranks the multiple genes based on the path scores of the multiple genes to generate a ranked gene list, and calculates a drug score by performing enrichment analysis using as input a list of genes that are targets of drugs stored in a drug database and the ranked gene list.

This invention belongs to the field of molecular biology and drug screening technology, and provides a method for screening capsaicin targeting SOCS5-RBMX protein interactions and its application. The method involves analyzing the structure of the SOCS5-RBMX protein complex to determine the SOCS5-RBMX binding domain and key binding sites; verifying the inhibitory effect on protein binding through point mutations at these key sites; identifying the binding pocket; using drugs from the ZINC22 small molecule drug database and FDA-approved drugs as ligand molecules, and performing virtual screening with the binding pocket as the docking region to obtain compounds; screening the obtained compounds using AMDET to identify capsaicin as the drug inhibiting SOCS5-RBMX binding; and further screening and verification using capsaicin in in vivo and in vitro experiments. This invention, through the analysis of the SOCS5-RBMX protein complex structure to determine the binding domain and key sites, and then using this as a basis for virtual screening and experimental verification, can accurately screen for drugs inhibiting SOCS5-RBMX binding, improving the accuracy and efficiency of drug screening.

The invention belongs to the technical field of hemp essence medicine management systems, and particularly relates to a hemp essence medicine whole-process closed-loop management system and method, and the system comprises a two-dimensional code label, a manufacturer end, a transportation end, a hospital end, a central end, and a processing end. The two-dimensional code label can be pasted on the outer surface of a medicine storage bottle after a manufacturer produces a medicine, the manufacturer end can scan the two-dimensional code label, a corresponding medicine database is generated at the central end, and medicine delivery information can be input at the manufacturer end; the transportation end can scan the two-dimensional code label on the surface of the medicine, input transportation information and input the information into the medicine database generated in the central end; the hospital end can scan the two-dimensional code label on the surface of the medicine, input hospital entering information, use information and scrap information, and input the information into the medicine database generated in the central end; the processing end can process the used medicine bottles and the scrapped medicine bottles and then record the processing information into the medicine database generated in the central end.