217 results about "Medicine field" patented technology

The invention belongs to the field of natural language processing, and provides a pre-training large model physical examination text labeling method and system based on active learning. The method is realized through the following process: collecting and sorting structured and unstructured physical examination data, manually pre-labeling a small number of samples by an expert and standardizing a format; selecting a pre-training large model adaptive to the medical field task; designing a domain-specific cue word template to strengthen semantic understanding of the model; performing parameter optimization by adopting supervised fine tuning and low-rank adaptation technologies; an active learning closed loop is constructed, uncertain samples are selected through multiple rounds of iterative training to supplement labels, and the model is dynamically optimized by using a verification set; and the optimized model is applied to intelligently label the remaining data. According to the scheme, the key problems of low efficiency, poor rule method generalization ability, high machine learning model computing power demand and insufficient large model field adaptation of traditional manual labeling are solved, and the automatic extraction precision of medical entities such as pathological features and clinical indexes in the physical examination report can be effectively improved.

Improved novel 3D imaging and reconstruction methods for quantitative and accurate 3D imaging used in multiple industries, segments, and applications within each. Improvement includes methods and hardware configured to improve performance and lower radiation and improve accessibility. Using simplified system matrix and datasets of little scatter interference in tomographic image acquisition and reconstruction, in some cases, using time continuity and spatial continuity to generate parameter data for substances within VOI for a number of key applications in medical and non-medical fields.

The invention discloses a medical education-oriented knowledge graph construction, retrieval and application system, and the system comprises a data collection and integration module which is used for collecting and integrating various medical professional knowledge, and forming a medical knowledge material library; the intelligent algorithm module is used for constructing a knowledge graph according to the medical knowledge material library and then providing structured knowledge support for learning and reasoning of the knowledge graph by using a graph neural network model; the knowledge retrieval and content generation module is used for performing retrieval in the knowledge graph according to the input content and providing the retrieved knowledge to the large language model to obtain the corresponding content; and the knowledge application service module is used for providing medical education service according to learning and understanding of the graph neural network model on the knowledge graph and integration of the big language model on semantic information in the knowledge graph. The intelligent development of the medical field is better promoted, and more efficient and accurate support and service are provided for medical education, research and the like.

A case generation method, used for generating cases in professional fields such as the field of law, the field of medicine or the field of economy. In the method, on the basis of using existing cases as reference cases, similar new cases can be generated by means of using a large language model, and after the new cases are generated, the accuracy of the new cases can be evaluated from different dimensions by means of a large language model; and when the accuracy of the new cases satisfy requirements, the generated new cases are output. The present application uses knowledge repositories and semantic comprehension capabilities of large language models to instruct the large language models to generate new cases on the basis of existing cases, and further evaluate the generated new cases from different dimensions, thus solving the hallucination problem of large language models, and ensuring the accuracy of generated new cases. Moreover, the present solution uses large language models to automatically generate cases without requiring manual construction of cases by people, thereby effectively improving the case construction efficiency.

The invention relates to a professional knowledge graph construction method for the medical field, and the method comprises the following steps: obtaining a multi-modal medical document, carrying out the deep analysis through a Transform-based multi-modal model, and obtaining an analyzed multi-modal medical document; dynamically segmenting the analyzed multi-modal medical document by adopting a context-based adaptive text segmentation method to obtain independent text blocks; based on the independent text blocks, performing structured extraction, and performing verification by adopting a dynamic dual-verification mechanism to form knowledge sub-graphs; and based on the knowledge sub-graph, further constructing a standardized medical knowledge graph. Compared with the prior art, the method has the advantages of high precision, expandability and the like.

The invention relates to a contrast test recognition method and device based on a large language model and a storage medium, and is applied to the technical field of medical information, and the method comprises the steps: carrying out word segmentation processing on obtained medical literature data, and then combining the processed medical literature data with RCT-related cue words to obtain an instruction data set; setting a large language model framework and a corresponding loss function, performing iterative training on the model framework through the instruction data set, inputting to-be-classified medical literature data into a trained RCT recognition large language model, and outputting an RCT recognition result according to a format agreed by cue words; according to the scheme, the cue word is combined with the training data, the training data does not need to be labeled, and the problem that the generalization ability of an existing machine learning model in different medical fields and different research problem data sets is greatly different, and the machine learning model extremely depends on a large number of labeled data sets is solved.

The invention discloses a retrieval enhancement generation method and device based on a medical knowledge fine-tuning language model. The method comprises the steps of constructing a medical knowledge base, performing fine-tuning on the medical language model, inputting medical questions by a user, retrieving the knowledge base, screening knowledge fragments, generating answers and the like. And the medical knowledge base is constructed through semantic partitioning, so that the integrity and continuity of related knowledge are ensured. And a medical knowledge fine tuning model is used as a screener to further screen high-quality knowledge fragments most related to user questions, so that the professionality and reliability of generating answers are improved. The method is suitable for the medical field, and can provide more accurate and more professional medical consultation services for patients and doctors. The fine-adjusted medical model is innovatively used as a filter, knowledge fragments are evaluated from multiple dimensions, it is ensured that the knowledge fragments are highly related to questions, powerful support is provided for generating professional and accurate medical answers, and the precise medical consultation requirement of a user is better met.

The invention belongs to a data generation method, provides a multi-modal medical data generation method and a related device, and aims to solve the technical problems of multi-modal medical data resource limitation, modal missing and data scarcity of an existing medical data generation method. Obtaining a fine-tuning medical large model; obtaining a text instruction and a multi-modal data stream associated with the task, and obtaining a task type, an existing modal list, a target modal list and a task instruction after analysis of the text instruction according to the text instruction and the multi-modal data stream; according to the existing modalities in the existing modality list and the task instruction, obtaining a comprehensive shared feature representation; encoding and decoding the comprehensive shared feature representation to obtain a converted feature instruction, and generating a modal mark for a target modal in the target modal list; and updating a generation state through dynamic estimation based on the converted feature instruction.

The invention discloses high-performance modified calcium carbonate and application thereof in a breathable film. The modified calcium carbonate is prepared by combining a three-element composite modification system composed of stearic acid, titanate and a silane coupling agent with a disc-nest mill three-stage gradient grinding process and antibacterial-hydrophobic dual-functionalization treatment of silver-loaded hydroxyapatite and a fluorinated modifier. The indexes of the prepared modified calcium carbonate are as follows: the median particle size (D50) is 1.8-2.2 mu m, the particle size (D97) of 97% particles is less than 6.5 mu m, the particles with the particle size of 1-5 mu m account for more than 60%, and the particles with the particle size of more than 10 mu m are less than 100 ppm; the content of calcium carbonate exceeds 97%, and the content of harmful impurities such as Fe is less than 200ppm; the whiteness is higher than 95; the oil absorption value is less than 12.5%, and the water content is less than 0.18%. When the composite material is applied to the breathable film in the medical field, the mechanical property, the antibacterial property and the hydrophobic property of the breathable film can be remarkably improved, the special requirements of the medical field on the breathable film are effectively met, and the composite material has good application prospects and industrial value.

The invention provides a method for acquiring a three-dimensional model of an ankle skeleton of a human body by simulating load-bearing CT scanning. The method comprises the following steps: acquiring CT scanning data; uploading the CT scanning data to medical image processing and three-dimensional reconstruction software to obtain an initial scanning image; constructing a three-dimensional model according to the initial scanning image; and carrying out model verification on the three-dimensional model to obtain a skeleton three-dimensional model. According to the method, the high-resolution three-dimensional model of the ankle skeleton can be obtained, and reliable support is provided for medical research, clinical diagnosis and treatment of the ankle and research and development of medical instruments. Compared with a traditional method, the data obtained by simulating the load is more practical, the model quality is remarkably improved through the advanced technology and algorithm, and development of related research and application in the medical field is promoted.

The invention discloses a medical informatization data intelligent analysis system based on a large model, and belongs to the technical field of medical informatization and artificial intelligence, and the system comprises a data collection and standardization module, a medical knowledge graph construction module, a knowledge enhancement inference analysis module, a data quality evaluation module and a structured output module. The system collects multi-source heterogeneous medical data from an electronic medical record system, a laboratory information system, a medical image information system and a hospital information system, performs standardization processing, automatically constructs a medical knowledge graph, and performs intelligent analysis and reasoning on the medical data by using a knowledge retrieval enhanced medical field large language model. Meanwhile, the data quality is evaluated in four dimensions of integrity, accuracy, timeliness and relevance, and finally a structured analysis report is generated. The multi-source medical data can be effectively integrated, the accuracy and interpretability of medical data analysis are improved, and intelligent support is provided for clinical decision making.

The embodiment of the invention relates to a method and a device for generating a medical report based on evidence-based medicine. The method comprises the following steps: acquiring patient information and an original clinical problem; inputting the patient information, the original clinical question and the first cue word into a target model to generate a structured clinical question; the target model is a medical field large language model; retrieving a medical literature library according to the clinical problem to obtain a plurality of medical literatures; inputting the target medical literature and the second cue word into a target model, so that the target model performs bias risk assessment on the target literature, and a structured initial assessment result of the target literature is generated; inputting the clinical problem, each medical literature, the initial evaluation result of each medical literature and the third cue word into a target model, and enabling the target model to carry out thinking chain gradual reasoning based on a GRADE evaluation process in the third cue word to generate a medical report; the medical report includes medical suggestions for clinical issues, and recommendation intensities and evidence quality levels of the medical suggestions.

The invention relates to a method for processing medical images of human tissue of an area of a patient's body and in particular of the breast by means of a medical imaging device (1) comprising a microwave probe array consisting of K>1 probes spaced apart from one another, the array comprising P>1 different configurations defining transmitting probes and receiving probes for one or more position(s) around the area, in which the transmitting probes are configured to transmit microwave signals so as to illuminate an area of the body and the receiving probes are configured to receive microwave signals after scattering and reflection in the area, the probes being capable, in a complementary manner, of being configured to transmit and receive simultaneously.

The invention discloses a graph embedding-based medical field retrieval enhancement method, a question-answering system and equipment, and the method comprises the steps: collecting a question-answering pair data set in the medical field, and combining questions in the question-answering pair data set with questions queried by a user to establish a question set; classifying sentences in the question set through a large language model (LLM), and judging categories of departments corresponding to the sentences; for the problems in the same category, extracting medical entities in the problems through a UIE model, and constructing a problem map; on the basis of the obtained problem graph, graph embedding of all nodes in the sequence is obtained through random walk and a Word2Vec algorithm to serve as vector representation of the nodes, and the vector representation is stored in a vector database; searching N most similar problems from the vector database, and constructing a search prompt; after the retrieval prompt is acquired, the generator generates a final answer from the retrieval prompt. According to the method, the understanding and reasoning capabilities of the model on user questions are enhanced, and accurate information retrieval and knowledge enhancement generation in the medical field are better supported.

The invention discloses an obsessive-compulsive disorder diagnosis system based on brain multi-modal indexes, and belongs to the field of mental diseases. The problem of lack of a cross-modal feature fusion mechanism is solved. The system comprises an electroencephalogram signal acquisition unit used for acquiring an EEG signal of a testee under a preset stimulation normal form and executing preprocessing operation; the brain imaging data acquisition unit is used for synchronously acquiring brain structure imaging data and brain function imaging data of the testee; the multi-modal data fusion unit is used for extracting frequency band power spectrum density characteristics and event-related potential amplitude or incubation period characteristics from the EEG signals; performing standardization processing on the EEG features, the sMRI structural features and the fMRI functional features; integrating modal features by adopting a weighted average fusion algorithm; screening fused feature subsets through a recursive feature elimination method; and the diagnosis model unit is used for inputting the fusion feature vector into a trained SVM classification model and outputting an obsessive-compulsive disorder diagnosis result. Used in the medical field.

The invention discloses a medical question-answering system based on a large language model, belongs to the field of large language models in artificial intelligence in the field of computers, and particularly relates to the medical question-answering system based on the large language model. The objective of the invention is to solve the problems of low answering accuracy and poor medical problem solving ability of a general large language model in the medical field. The system comprises a large language base module used for selecting an open source large language model of a general field as a base model; the knowledge instance sampling module is used for sampling knowledge instances from the knowledge graph; the question-answer data generation module is used for generating question-answer data according to the knowledge instances by using a large language base model; the large language base model fine tuning module is used for performing fine tuning on the large language base model by using the generated question and answer data to obtain a fine-tuned large language base model; and the reply generation module is used for answering the to-be-processed medical knowledge question based on the fine-tuned large language base model.

The invention relates to the technical field of clinical data synthesis, provides a controllable condition clinical data synthesis method and device supporting logic relation perception, and aims to solve the problem of logic inconsistency in an existing synthesis method and flexibly generate data meeting user-defined conditions. The method comprises two key stages: a logical relationship perception stage: capturing inherent semantic information in original data, and learning a complex logical relationship between clinical data columns; and a conditional diffusion model generation stage: fitting data distribution characteristics by using a diffusion model, and integrating conditional semantic embedding to realize controllable clinical data synthesis. Through mutual cooperation of the two stages, a difficult electronic clinical data generation task is decomposed into two relatively simple problems, and the problems of logic inconsistency and lack of controllability are efficiently solved. According to the scheme, the quality and availability of the synthesized data are greatly improved, and a set of high-quality data synthesis scheme is provided for the medical field.

The invention discloses a post-radiotherapy patient nursing auxiliary decision-making system based on artificial intelligence, and relates to the field of medical rehabilitation nursing, and the system comprises a management and control module which serves as a core management end of each function module and carries out the editing and sending of a control instruction; the data archive library is used for storing all the collected user personal data and analysis data thereof; the data acquisition module is used for acquiring basic physique data, illness state related data and radiotherapy plans of the patient through a preset period; individual data of patients are analyzed through a prediction model, personalized nursing suggestions are generated based on medical history, health indexes and radiotherapy plans, personalized nursing schemes are provided for each patient according to curative effect analysis of similar patients, customization is carried out according to unique illness states, physiques and treatment plans of the patients, professional knowledge and data in the medical field are combined, and the patient health management system is established. Potential abnormal changes are output, and patients and medical staff are helped to make timely decisions.

The invention discloses an intelligent pulmonary tuberculosis detection method and system based on images and clinical data, and belongs to the field of medicines.The method comprises the steps that S1, high-resolution chest X-ray images and clinical data such as serum C-reactive protein concentration, erythrocyte sedimentation value, erythrocyte distribution width and body temperature are collected; s2, performing non-linear contrast enhancement on the image, and extracting lung gate texture, lung field transparency and cavity edge features; s3, fusing the image and the clinical features through a graph attention mechanism, and generating a high-dimensional fusion vector; s4, risk grade discrimination is carried out through a multi-scale residual mapping network, and five-grade labels are output; and S5, optimizing the model by utilizing the pathology definite diagnosis sample in combination with the cross entropy and the center loss. The method has the beneficial effects that accurate grading evaluation of the pulmonary tuberculosis risk is realized, and the accuracy of early screening and the clinical interpretability of the model are improved.

The invention belongs to the field of computational medicine, particularly relates to a method and a system for constructing full-parameter digital twinning of a patient and performing treatment simulation, and aims to solve the problems that an existing digital twinning model cannot fuse multi-scale data, lacks dynamic optimization capability and is disjointed with a clinical decision process. The method comprises the following steps: acquiring and integrating multi-source heterogeneous data of a patient; performing cross-scale fusion modeling based on the data, and constructing a personalized digital twinborn initial parameter set containing genetic background correction; driving a multi-physics field coupling engine to simulate an intervention effect, constructing a reverse optimization problem taking real-time monitoring data as a dynamic constraint, and solving an optimal intervention scheme parameter; and carrying out verification simulation on the optimization scheme and generating a treatment report containing quantitative evaluation and risk early warning. According to the invention, by constructing a full-parameter and mechanism model and introducing a dynamic closed-loop optimization verification process, the personalized precision, safety and clinical decision support value of treatment scheme simulation are significantly improved.

The invention provides a text data subject-object association relationship extraction method based on medical field features, which comprises the following steps: extracting feature information from a medical text to be extracted by using an encoder, and encoding context information in the medical text to obtain an encoding vector of the medical text; constructing a medical subject marker, and marking a starting position and an ending position of a subject entity in the medical text according to the coding vector; optimizing a medical subject marker by adopting a likelihood function, and obtaining a subject entity list in the medical text; constructing a medical relationship marker, modeling the medical relationship of each subject entity in the subject entity list, performing semantic enhancement through a star topology structure, identifying objects related to the subject entities, and extracting relationship features; and optimizing a medical relationship marker by adopting a likelihood function, and completing extraction of the subject-object association relationship of the text data based on the medical domain characteristics.

The present application relates to the technical field of medical three-dimensional reconstruction, and particularly relates to an endoscopic-image-based three-dimensional reconstruction method and apparatus for a pediatric adenoid situation, which method and apparatus can solve, to a certain extent, the problems whereby existing three-dimensional reconstruction methods in the medical field still lack research on three-dimensional reconstruction of adenoid regions, and reconstruction results in existing technology have low completeness and cannot meet clinical requirements. The method comprises: by means of local plane parameter initialization, establishing relationships between corresponding points in different images; by means of local plane parameter optimization, accurately updating local plane parameters of each pixel point in a reference image; on the basis of a filtering strategy using relative depth difference, implementing depth filtering; by means of a spatial grid surface fitting method, restoring missing depth information of some regions in a depth map after the depth filtering, so as to densify a reconstruction result; and by taking into consideration two metrics, i.e., relative depth difference and reprojection error, converting into a point cloud the depth map which has been subjected to surface fitting, so as to reconstruct a three-dimensional model of an adenoid region.

The invention discloses a preparation method and equipment of a craniocerebral physical model and a storage medium. The preparation method of the craniocerebral physical model comprises the steps that a mold is manufactured, and a liquid injection hole is formed in the mold; mixing agar powder with conductive salt and water to prepare an agar solution; and introducing the agar solution into the mold through the liquid injection hole, and cooling to form the brain three-dimensional physical model. According to the preparation method of the craniocerebral physical model, the obtained craniocerebral three-dimensional physical model is high in accuracy, accurate detection data for reference can be provided for the medical field, and the accuracy requirements of experiments and researches can be well met.

A spectral sensing device and associated methods for enhanced diagnostic capabilities across medical fields are disclosed. The device incorporates multispectral, hyperspectral, and photoplethysmography technologies to analyze biological features including tongue, oral cavity, saliva, teeth, and other tissues. The system transforms any standard RGB camera into a multispectral imaging device by training machine learning models to associate RGB values with spectral values inside and outside the visible spectrum using measurements from a single pixel detector spectroradiometer. A multimodal neural network with separate processing branches analyzes spectral images, non-spectral images, and tabular data to predict microbiome composition. The system generates health risk assessments by comparing predicted microbial abundances to thresholds associated with various medical conditions. Near-infrared sensing enables blood flow monitoring, subcutaneous imaging, and assessment of physiological parameters. Convolutional neural networks enable spectral reconstruction without requiring the physical device, while supporting continuous monitoring in various form factors.

The invention belongs to the technical field of artificial intelligence and medical information processing, and particularly relates to a medical text big data mining system based on natural language processing, which comprises a medical field pre-training module, a text structured extraction engine module, a knowledge graph guide reasoning module, a clinical path optimization module and a medical question and answer and literature mining platform module, according to the system, a self-adaptive hierarchical attention mechanism is adopted, and medical texts of any length are processed through dynamic fusion of local attention and global attention; constructing an entity dependency relationship graph and coding semantic association between entities by adopting a graph neural network; introducing a medical ontology knowledge graph to carry out conditional random field joint reasoning, and correcting unreasonable annotations; the optimal diagnosis and treatment mode is mined and recognized through the frequent mode, the entity recognition F1 value reaches 96.2%, the long-distance relation recognition accuracy reaches 91%, the structured data accuracy reaches 93.7%, the data preparation time is shortened by 85%, and the document review efficiency is improved by 320%.

The invention provides a systematized literature review method and system based on a large language model. The systematized literature review method based on the large language model comprises the following steps that an SLR scheme first draft is generated according to project requirements based on the large language model; confirming the first draft of the SLR scheme to obtain an SLR research scheme; performing literature retrieval and analysis based on the SLR research scheme to obtain a preliminary retrieval result; and modifying the SLR research scheme based on the preliminary retrieval result to obtain a literature review result. According to the technical scheme, the efficiency and reliability of the SLR are effectively improved, and important support is provided for the scientific research and medical field.

The invention relates to the crossing field of natural language processing and biomedicine, and discloses a diagnosis and treatment path mining method and system based on internet hospital dialogue data, and the method comprises the steps: obtaining medical dialogue data, and carrying out the preprocessing of the data; designing an instruction to guide the large language model to identify and label medical entities in the doctor-patient dialogue, and distributing a preset label for each medical entity; the medical entities are subdivided into four classes, namely, feature, examination, disease and treatment; analyzing a context relationship between entities through a large language model, and extracting sub-chains with logic relevance; strict examination and logic rule filtering are carried out on the sub-chain, so that the medical rationality and clinical significance of the sub-chain are ensured; and fusing the sub-chains to generate a standardized diagnosis and treatment path. According to the method, the diagnosis and treatment process in the medical dialogue is effectively mined, and the method not only conforms to the specification of the medical field, but also has relatively high operability and universality.

According to the PDF document structuring processing and conversion tool, contents (including texts, tables, images, structures and the like) in PDF documents are analyzed and converted into structured data (Markdown) capable of being used for downstream LLM tasks, and the PDF structuring processing and conversion tool is particularly suitable for PDFs of complex typesetting of academic literatures, reports and the like. Through a literature vectorization function, medical professional literatures can be precisely processed, core ideas, key data and logic relations in the literatures can be deeply understood, vectors capable of accurately reflecting the essence of the literatures can be generated, important information is prevented from being lost or misread, and information processing and application effects are improved. Meanwhile, the personalized Agent can perform adaptive optimization aiming at diversified tasks in the medical academic field, and can fit research directions, knowledge backgrounds and working habits of different users, for example, the personalized Agent provides support conforming to a rigorous logic structure and standard academic expression during academic paper writing; and when the academic slide is manufactured, concise and clear contents with highlighted key points can be presented, so that the working efficiency of medical workers and researchers is effectively improved, and the high-standard requirements of the medical field are met.

The invention discloses a multi-modal fusion fact verification method and system for reducing large model medical illusion. The method comprises the following steps: constructing a high-quality multi-modal medical data set; a fusion feature is obtained on the basis of a multi-mode Transform architecture; constructing a fact verification module, executing four verification steps, including semantic layer verification, logic layer verification, evidence layer verification and time sequence layer verification, on the basis of the fact verification module and the fusion features, endowing the preprocessed multi-modal medical data and each verification step with a dynamic confidence score, and determining whether the multi-modal medical data and the verification steps are matched or not on the basis of the confidence score and a preset threshold value. And medical illusion is corrected. According to the invention, cross validation and fact verification of multi-modal data are carried out, and a multi-level and all-around hallucination detection and correction system is constructed, so that the hallucination rate of a large model in the medical field is reduced fundamentally.

The invention discloses a short text matching method based on enhanced contrast learning and multi-task optimization, and belongs to the technical field of natural language processing. According to the method, a multi-source data set is constructed by fusing general field and medical field texts, a generative language model is adopted to generate a high-quality difficult case to form a training triple, and a character-level noise enhancement mechanism based on a medical similar character dictionary is introduced to simulate an OCR error; aLBERT is used as an encoder, supervised comparative learning and mask language modeling tasks are jointly optimized, multi-task cooperative training is achieved through dynamic gradient balance, and finally a short text matching model with high semantic discrimination ability and noise robustness is obtained. On a test set containing 50% OCR noise in the cardiovascular field, the accuracy rate of the method reaches 94.3% and is improved by 12.2% compared with that of a traditional BERT-base model.