27 results about "Medline database" patented technology

A database structure obtained by means of information retrieval, and a reasoning system, which structure and system specifically relate to a gut microbe knowledge graph system, comprising: a gut microbe knowledge graph consisting of a gut microbe knowledge base, a gut microbe and small-molecule drug therapy association knowledge base, and a clinical medicine database; and a multimodal uncertainty reasoning system, using the gut microbe knowledge graph. The gut microbe knowledge graph system predicts potential diseases, drugs, genes, etc., which are associated with gut microbes.

The invention relates to the field of medical information processing and traditional Chinese medicine curative effect evaluation, in particular to a diabetic nephropathy traditional Chinese medicine curative effect evaluation method based on patient report outcome. The method comprises the following steps: searching related symptoms and clinical characterization data of diabetic nephropathy through a medical database, extracting target entries, performing language standardization processing, constructing an initial candidate entry set, calculating the occurrence frequency of each symptom entry, and screening entries meeting a set threshold value to form an entry set; carrying out dimension division on the entry set according to feature attributes to form a preliminary dimension structure set; forming a screening result set through preset logic screening conditions; and carrying out weighted regression fusion on the comprehensive curative effect score and clinical detection data, and outputting a patient curative effect index. In an item weight determination process, dynamic balance between subjective experience and objective statistical information is realized through a mixed weighting model, and the defects of strong subjectivity of expert scoring and large result fluctuation in a traditional method are overcome.

Described herein is an apparatus and method for generating a medical database query. An apparatus may include at least a processor; and a memory communicatively connected to the at least processor, wherein the memory contains instructions configuring the at least processor to receive a first natural language database query; input the first natural language database query into a large language model (LLM); receive from the LLM a feature set; using a medical database query map, generate a first medical database query as a function of the feature set; and generate, using the LLM, an aggregated output by querying a medical database interfaced with the LLM using the first medical database query.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to medical questions using neural networks and other components. In one aspect, a method includes: obtaining question data representing a medical question; obtaining a plurality of document snippets from a medical database that stores medical documents; for each document snippet in the plurality of document snippets, determining a relevance score for the document snippet by using a ranking neural network based on the document snippet and the medical question; selecting, based at least in part on the relevance scores, a subset of the plurality of document snippets; generating a prompt that includes (i) the medical question and (ii) the subset of the plurality of document snippets; and generating an answer to the medical question based on processing the prompt using a generative neural network.

The invention relates to the technical field of large models, and discloses a medical large model answer enhancement method, system and device and a medium, and the method comprises the steps: carrying out the medical named entity recognition of an inquiry question and an obtained preliminary answer result through a medical large model; generating a structured verification question set, an extended verification question set and an anti-fact verification question set based on the obtained medical entity recognition result and the preliminary answer result; identifying a first similarity result between the preliminary answer result and verification answer results corresponding to the structured verification question set and the extended verification question set, and identifying a second similarity result between the preliminary answer result and anti-fact verification answer results corresponding to the anti-fact verification question set; identifying a third similarity result of the preliminary answer result and an evidence file obtained from an evidence-based medical database; and correcting the preliminary answer result according to the first similarity result, the second similarity result and the third similarity result to obtain a target answer. According to the method, the output credibility of the large medical model is enhanced.

The invention relates to the technical field of traditional Chinese medicine formula matching, in particular to a traditional Chinese medicine formula intelligent matching system which comprises a data acquisition module, a data processing module, a model training module and a prescription matching module. The data acquisition module is used for acquiring medicinal material and formula information from traditional Chinese medicine literatures, a medical database, experimental research results and clinical cases through a data interface and a crawler technology, and storing the medicinal material and formula information into a unified database; the data processing module is used for performing structured processing on the acquired unstructured text data by adopting an NLP technology and extracting names, indications, doses, pharmacological actions and incompatibility of the medicinal materials; the model training module is used for carrying out classification and correlation analysis on the prescription combination based on a machine learning algorithm and generating model parameters for prescription matching; according to the prescription matching module, a user can perform retrieval according to various screening conditions such as a purpose, a dosage form, an action mechanism and a region, and a system screens a prescription combination which most accords with the conditions from a database according to a matching algorithm and a training model.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to medical questions using neural networks and other components. In one aspect, a method includes: obtaining question data representing a medical question; obtaining a plurality of document snippets from a medical database that stores medical documents; for each document snippet in the plurality of document snippets, determining a relevance score for the document snippet by using a ranking neural network based on the document snippet and the medical question; selecting, based at least in part on the relevance scores, a subset of the plurality of document snippets; generating a prompt that includes (i) the medical question and (ii) the subset of the plurality of document snippets; and generating an answer to the medical question based on processing the prompt using a generative neural network.

The invention relates to a medical information extraction method and device, electronic equipment and a storage medium, and can obtain medical information valuable for constructing a medical database, so that the data quality of the medical database can be improved, and the medical information retrieval efficiency of a user can be improved. The method comprises the following steps: acquiring medical literatures; segmenting the medical literature to obtain segmented literature statements; based on knowledge rules in the medical field, the segmented literature statements are classified to obtain classification tags of the literature statements, and the classification tags of the literature statements are medical information or non-medical information; and performing information extraction on the literature statement marked with the medical information to obtain a medical entity and an entity relationship in the literature statement marked with the medical information, and storing the medical entity and the entity relationship in the literature statement marked with the medical information.

The invention discloses a septicopyemia early warning system based on multi-parameter fusion. Comprising the following steps: S1, data preparation and preprocessing; extracting clinical data from the intensive care medicine database; according to the method, two web version operation interfaces are respectively developed through R language core algorithm codes optimized by a shock risk model and a death risk model, and when the method is used by a clinician, 21 index data such as SOFA and systolic pressure are input aiming at shock risk prediction; for death risk prediction, 15 index data such as SOFA and GCS are input, the model automatically calculates the shock or death probability of a patient and an operation interface which is convenient for clinicians to operate and can predict the sepsis shock and death occurrence rate, and the risk prediction model can be applied to clinical treatment practice and has a wide application prospect. The risk prediction of shock and death of the sepsis patient is realized, clinical doctors are assisted in evaluating the condition of the patient, early intervention and treatment are carried out, and the overall control of the clinical doctors on the condition progress of the sepsis patient is improved.

The present disclosure provides concepts for searching a medical database comprising electrocardiogram (ECG) data. The method includes obtaining a database comprising a plurality of subject entries, each corresponding to a historic subject and comprising recorded metadata describing characteristics of the respective subject and a recorded vector embedding representing ECG data of the respective subject. A query vector embedding representing ECG data of a query subject is generated with an ECG encoder. The recorded metadata of the plurality of subject entries is compared with query metadata describing characteristics of the query subject, and the recorded vector embeddings are compared with the query vector embedding. One or more similar subject entries are identified based on a result of the comparison. Accordingly, the invention provides a searching means that is designed to take into account characteristics of subjects to identify subjects with similar cardiological conditions, thereby reducing a burden on a clinician whilst reducing a rate of misdiagnosis. For example, this may be particularly useful for triaging subjects.

The invention provides a clinical test target information extraction method and device, computer equipment and a computer readable storage medium. The method comprises the steps of obtaining a clinical test text; inputting the clinical test text into a trained target information extraction model, and outputting target field information in the clinical test text; wherein the trained target information extraction model is obtained by training preset label contents and a medical knowledge graph, and the preset label contents comprise indications, stages, pathologies, biomarkers, baseline features, treatment threads and scheme elements; and if the target field information is valid field information, summarizing the valid field information to construct a medical database. By adopting the method, the extraction efficiency of the clinical test target information can be effectively improved.

The invention discloses a colorectal cancer pathological image prognosis auxiliary prediction method and system, and belongs to the technical field of medical image processing. According to the method, the problem that an existing method is difficult to comprehensively understand the overall view of a tumor is solved, the pathological image, related clinical information and disease course data of a historical colorectal cancer patient are collected from a medical database, after the pathological image and the clinical data are preprocessed and labeled, features in the pathological image are automatically learned through a convolutional neural network model, and the overall view of the tumor is obtained. Introducing a clustering algorithm to obtain a convolutional neural network model with clustering prediction capability; the pathological image and clinical data of the current patient are imported into the convolutional neural network model for prediction to obtain a lesion area and a lesion result, and the lesion area and the lesion result are fed back to the medical care interaction terminal in real time for display to assist a doctor in judging the lesion result of the patient, so that the prediction accuracy of the convolutional neural network model is improved, and the prediction efficiency is improved. And more targeted and personalized diagnosis and treatment suggestions can be provided for clinicians.

A method and system for generating medical analysis reports are proposed. The method includes: receiving a piece of text data, extracting at least one piece of first sub-data using a parsing module according to a natural language processing technique, analyzing the first sub-data using at least one medical database and at least one rule engine to generate at least one first intermediate result, executing a large language model to generate a first medical analysis report according to the at least one first intermediate result, using the parsing module and feedback information to parse the first medical analysis report or the piece of text data into at least one piece of second sub-data, which is analyzed to generate at least one second intermediate result, and a second medical analysis report is generated according to the at least one second intermediate result.

The invention relates to a safe access method of a medical database, which comprises the following steps of: in a mutual access process of the medical database, calculating by a central server and each medical database to obtain a comprehensive similarity between a user access request and a similar user access request, and judging whether the current access request is suspicious according to the comprehensive similarity; therefore, suspicious access behaviors can be found in time, and the security of medical database access is improved.

The invention discloses a gene prediction system based on phenotype-gene relevance and a storage medium, and the system comprises a data integration module, a knowledge graph construction module, a neural network module and a rapid updating module. The data integration module is used for integrating a plurality of medical databases to obtain a multi-modal database; the data of the multi-modal database is in a gene-disease-phenotype association form; the knowledge graph construction module is used for constructing a knowledge graph according to the data of the multi-modal database; the neural network module is used for processing the preprocessed data according to a knowledge graph and a multi-modal database to obtain a pathogenic gene prediction result; and the rapid updating module is used for updating the multi-modal database, the knowledge graph and the neural network module. According to the application, a plurality of medical databases are integrated through the data integration module to obtain the multi-modal database, and the preprocessed data are processed through the neural network module to obtain the pathogenic gene prediction result. Through correlation of phenotypes and genes, the accuracy of gene prediction is improved.

This invention relates to a method and system for intelligent editing of medical forms. The method includes: performing version number verification in response to user-input natural language editing instructions; after successful verification, reading the corresponding original form abstract syntax tree from a medical database and inputting the natural language editing instructions and the summary information of the original form abstract syntax tree into a directed graph editing pipeline; outputting an operation instruction list or clarification request through an operation planning node, and performing multi-level verification on the operation instruction list through an operation verification node when outputting the operation instruction list; and feeding back the clarification question to the front end for visualization through a clarification return node when outputting the clarification request. After the multi-level verification is successful, executing the operation instruction list through an operation execution node to generate the target form abstract syntax tree; performing structural verification on the target form abstract syntax tree, and writing the target form abstract syntax tree into a data table after successful structural verification to obtain the target medical form.

The application relates to a data query method and device, which comprises the following steps: determining a target data cube based on a target database, a first query field in a historical query process and a conditional entropy correlation algorithm; determining a data cube meta-database based on the target data cube; the data cube meta-database comprises at least one tree branch tree node; storing the data of the parent nodes of different levels in each tree branch in the at least one tree branch into different storage nodes based on a consistent hash algorithm and the access amounts of different tree nodes; storing the data of the tree nodes with different access amounts into different virtual nodes; and searching the query result corresponding to a second query field from the corresponding storage node in response to a query request of the second query field from a user end. Therefore, simple and efficient data query of a medical database is realized.

This invention relates to the field of drug safety assessment technology, and particularly to a drug safety assessment method and system based on multi-source data fusion. The method includes: receiving the SMILES structural formulas and research information of candidate drugs; encoding the SMILES structural formulas of the candidate drugs and each combination drug to obtain molecular structure feature vectors; constructing a knowledge graph by fusing multiple public biomedical databases to obtain knowledge graph embedding vectors; performing cross-modal multi-source information fusion on the molecular structure feature vectors and knowledge graph embedding vectors to obtain a multi-source fusion representation vector; inputting the concatenated vector into a prediction model to predict and calibrate drug-drug interactions and adverse reactions, obtaining calibration confidence levels; and conducting a safety assessment of drug interactions based on indications and calibration confidence levels, generating a comprehensive safety assessment report. This invention provides a reliable reference for decision-making regarding the safety of combination drug use during the drug development stage.

An object of the system according to the embodiment is to unitarily analyze a plurality of symptoms of an individual and specify the possibility of a potential disease.SOLUTION: A system includes a symptom input part, a symptom analysis part, and a database collation part. The symptom input unit collects symptoms input by a user. The symptom analysis unit analyzes the symptoms collected by the symptom input unit. The database collation unit collates the symptom analyzed by the symptom analysis unit with the medical database.SELECTED DRAWING: Figure 1

The present disclosure provides concepts for searching a medical database comprising electrocardiogram (ECG) data. The method includes obtaining a database comprising a plurality of subject entries, each corresponding to a historic subject and comprising recorded metadata describing characteristics of the respective subject and a recorded vector embedding representing ECG data of the respective subject. A query vector embedding representing ECG data of a query subject is generated with an ECG encoder. The recorded metadata of the plurality of subject entries is compared with query metadata describing characteristics of the query subject, and the recorded vector embeddings are compared with the query vector embedding. One or more similar subject entries are identified based on a result of the comparison. Accordingly, the invention provides a searching means that is designed to take into account characteristics of subjects to identify subjects with similar cardiological conditions, thereby reducing a burden on a clinician whilst reducing a rate of misdiagnosis. For example, this may be particularly useful for triaging subjects.

A mobile device (110) and an emergency entity (120) in a mobile network (130) are adapted for emergency calls. The network is coupled to a medical database (140) including corresponding electronic health records (EHRs) regarding corresponding persons. The mobile device is arranged to obtain an encrypted medical identifier of a user of the device; and, after determining that the user may be a victim of an emergency, include the encrypted medical identifier in an emergency message during an emergency call. The emergency entity is arranged to retrieve the encrypted medical identifier from the emergency message and access the medical database based on the encrypted medical identifier to retrieve at least one electronic health record so as to enable forwarding of information from the electronic health record to a responder to the emergency.

According to the multi-platform medical data integration and diagnosis and treatment assistance method and system, data such as patient chatting records, behavior logs and past medical histories stored in all medical service platforms are received and subjected to normalization processing, multi-platform data matching is completed with identity information of patients as the core, and a patient identity mapping table is established to achieve full-platform data association; during diagnosis and treatment, corresponding full-platform patient data are retrieved from a patient identity mapping table through patient identity information, disease information is accurately extracted based on an SOAP medical framework, a medical record first draft is automatically generated in combination with a medical knowledge base, and preliminary diagnosis and treatment suggestions have scientific basis and clear confidence by taking an evidence-based medical database as a support; a closed loop from data integration to clinical application is realized, accurate and efficient diagnosis and treatment decision support is provided for medical staff, normalization and accuracy of diagnosis and treatment services are promoted, and misdiagnosis and missed diagnosis risks are reduced.

A computer-implemented method for deriving study types from a dataset is disclosed. The method includes: (i) tokenizing extracted text from a plurality of metadata of a dataset to identify a plurality of tokens; (ii) generating a first numerical representation of each token of the plurality of tokens; (iii) partitioning the plurality of metadata into a plurality of clusters according to a predetermined criterion; (iv) for each cluster of the plurality of clusters, identifying a subset of tokens of the plurality of tokens that are common to all metadata of that cluster; and (vi) for each identified subset of tokens corresponding to each cluster of the plurality of clusters: (a) generating a second numerical representation of each token of that subset of tokens; and (b) based on the second numerical representation of each token, generating a respective study type corresponding to each cluster of the plurality of clusters.

A brain-like auxiliary diagnosis and treatment method for rare diseases is realized based on a GPU or NPU server, a system review agent is used as a sensing front end of the method, is connected with an external medical database through a standard API interface, executes automatic retrieval and quality preliminary screening of literatures, and outputs an original literature set; the document processing agent is used for receiving an original document set of the system review agent, performing structured extraction on an unstructured PDF document by utilizing a deep analysis tool, and generating a structured knowledge base containing a core clinical field; and the NHSC brain-like agent adopts a brain-like architecture based on a dual processing theory, receives the structured knowledge base and the patient data of the document processing agent, and outputs a final dynamic diagnosis and treatment suggestion through fast and slow dual-channel cooperative processing. Algorithm evaluation of evidence quality is realized, an evidence screening mechanism is enhanced from the source, risks caused by illusion of a large language model are effectively reduced, and stability and reliability of an evidence synthesis result are guaranteed.

The present application relates to the technical field of drug safety evaluation, and particularly relates to a drug safety evaluation method and system based on multi-source data fusion, comprising the following steps: receiving SMILES structural formula and research information of a candidate drug, encoding the SMILES structural formula of the candidate drug and each combination drug to obtain a molecular structure feature vector; fusing multi-source public biomedical databases to construct a knowledge graph and obtain a knowledge graph embedding vector; performing cross-modal multi-source information fusion on the molecular structure feature vector and the knowledge graph embedding vector to obtain a multi-source fusion representation vector; inputting the multi-source fusion representation vector into a prediction model after splicing to perform drug-drug interaction and adverse reaction prediction and calibration, and obtaining a calibration confidence; based on the indications and the calibration confidence, performing safety evaluation on the drug interaction, and generating a comprehensive safety evaluation report. The technical scheme of the present application can provide reliable reference for joint drug safety decision-making in the drug research and development stage.

A radiology workstation (14) used to interpret a radiology examination (48) includes a display (20, 22), a user input device (24, 26, 28), and an electronic processor (12, 16). A radiology image of the radiology examination is displayed on the display. A radiology report is entered. An imaged anatomical region (54) is determined from the stored radiology examination. An examination basis medical condition is identified from the reason for examination (52). At least one additional medical condition is determined based on information on the patient retrieved from one or more medical databases (10, 44, 46) and is classified as reviewable or not reviewable based on the imaging modality (50) and the imaged anatomical region. An attention list (40) is created with items directed to the examination basis medical condition and to each reviewable additional medical condition. A representation (42) of the attention list is displayed on the display.

The present invention relates to the field of large model technology, and discloses a method, system, device, and medium for enhancing answers to medical large models. The method uses a medical large model to perform medical named entity recognition on medical questions and obtained preliminary answer results; based on the obtained medical entity recognition results and preliminary answer results, a structured verification question set, an extended verification question set, and a counterfactual verification question set are generated; a first similarity result between the preliminary answer result and the verification answer results corresponding to the structured verification question set and the extended verification question set is identified, and a second similarity result between the preliminary answer result and the counterfactual verification answer results corresponding to the counterfactual verification question set is identified; a third similarity result between the preliminary answer result and an evidence file obtained from an evidence-based medicine database is identified; and the preliminary answer result is corrected according to the first similarity result, the second similarity result, and the third similarity result to obtain a target answer. The method of the present application enhances the credibility of the output of the medical large model.