43 results about "Disease description" patented technology

The invention provides a miRNA-disease association prediction method based on a graph neural network, and relates to the technical field of graph neural networks. The method comprises the following steps: acquiring miRNA sequence, a disease description text, miRNA family information, a disease father-son relationship and miRNA-disease association relationship data, and constructing a heterograph after performing data alignment; based on the miRNA sequence and the disease description text, using a pre-training language model to obtain miRNA representation and disease representation as node features, and updating the heterogeneous graph; and constructing a heterograph MDA association prediction model, and inputting the updated heterograph and the to-be-predicted miRNA-disease pair to obtain an association prediction score of the to-be-predicted miRNA-disease pair. According to the method, the biological entity can be fully expressed in entity expression; according to the method, information of different types of nodes can be effectively aggregated on model construction, multi-depth message passing is executed on different types of edges, integration of heterogeneous information of the nodes and the edges is achieved, and improvement of miRNA-disease association prediction performance is facilitated.

Systems and methods for computer modeling in medicine. A sort of period table of medical models is described for personalized diagnostics, prognostics and therapeutics, including at least 80 major categories of medical models. Generative artificial intelligence and geometric deep learning techniques, and algorithms including 2D and 3D graph machine learning and GenAI algorithms, are described, tailored and applied to diagnostic disease description, prognostic prediction and therapeutic development and management, including generation of novel synthetic drugs. The AI and machine learning techniques and algorithms are applied to understand each individual's genetic, RNA and protein anomalies that represent the source of many unique patient diseases. AI-enabled software agents assist physicians and researchers in building patient medical models. Several personalized medicine applications of individualized medical modeling include cardiovascular disease, cancer, neurological disorders, immune system disorders and genetic diseases.

The invention provides a bridge disease named entity standardization processing method and device based on a large language model and a storage medium. The method comprises the steps that a bridge disease structured knowledge base is established; potential bridge disease names, corresponding disease positions and disease description information are extracted from the target bridge regular inspection report; traversing the standard disease name set for the potential bridge disease names to obtain a first standardized processing result; calculating the character string similarity between the potential bridge disease name and each standard disease name in a standard disease name set; extracting potential bridge disease names of which the character string similarity is greater than a set threshold value and corresponding standard disease names; aiming at the potential bridge disease names in the to-be-normalized relation group, constructing prompt words of a normalized task; and inputting a cue word into the large language model to obtain a second normalized processing result. By adopting the processing method provided by the invention, the bridge disease named entity can be quickly normalized without a special training model.

The invention provides a dynamic medication dosage optimization method fused with reinforcement learning. The method comprises the following steps: acquiring a first physiological index parameter of a target patient; obtaining a first diagnosis report of the target patient, wherein the first diagnosis report comprises basic information of the target patient and first disease information of the target patient; the first disease information comprises a first disease type and first disease description information; determining a first reinforcement learning algorithm corresponding to the first disease type; determining a first control parameter of the first reinforcement learning algorithm according to the first physiological index parameter and the basic information; and performing operation on the first disease description information through the first reinforcement learning algorithm and the first control parameter to obtain a first medication dosage parameter. Based on the application, the drug effect can be consistent with the physical condition of a patient, and poor drug effect and excessive side effects caused by too strong drug effect are avoided.

The invention relates to an RAG medical question answering method and system based on question rewriting and generation reverification, and the method comprises the steps: collecting a large amount of standard medical data, carrying out the partitioning processing and vectorization processing, building a chief complaint rewriting data set, and training a rewriting model; the oral complaint of a patient is rewritten into a standard professional disease description conforming to the habits of a doctor through a trained rewriting model, then K similar first quotation sets are retrieved through a retriever, and the K similar first quotation sets and a complaint text of the patient are input into a generator to be analyzed to generate a first disease diagnosis result. And inputting the first disease diagnosis result into the RAG system for secondary verification to generate a second quotation set with similar semantics, calculating a similarity matching score between the second quotation set and the patient complaint, and determining whether to output the diagnosis result according to the similarity matching score. Through a chief complaint rewriting mechanism, the retrieval accuracy is improved, and through a secondary verification mechanism, the misdiagnosis rate is remarkably reduced.

A consultation method and apparatus, and an electronic device and a computer-readable storage medium. The method comprises: acquiring target disease description information which is input by a user; and feeding back to the user a target diagnosis result about the target disease description information, wherein the determination of the target diagnosis result is related to the target disease description information and assistance diagnosis information, and the assistance diagnosis information comprises target profile information of a target consultation object that is indicated by the target disease description information. By means of the method, a high-quality consultation service can be provided for users.

The invention relates to the technical field of confidential transmission, in particular to a privacy data encryption protection method for an intelligent hospital informatization platform, which comprises the following steps: acquiring electronic medical record data of a plurality of patients, screening from a plurality of dimensions based on the disease description degree of medical information of each dimension to obtain a target disease description dimension, determining the general repetition degree of each segmented word in the medical information of the target disease description dimension of the patient, and obtaining the symptom particularity of the target disease description dimension of each patient in combination with the correlation of the medical information of the target disease description dimensions of different patients in the same department; fusing the symptom description degree and the symptom particularity of the target symptom description dimension of each patient to obtain the privacy confidentiality degree of the electronic medical record data of each patient, and using the accurate privacy confidentiality degree to determine encryption modes of different security levels. The method is helpful for improving the reliability of privacy data confidential transmission of the smart hospital informatization platform.

The invention discloses a urology department traditional Chinese medicine inquiry result prediction method and system applying a large language model, and belongs to the technical field of large language models. The method comprises the following steps: preprocessing disease description data, and obtaining self-correlation parameters among the disease description data; constructing a prediction model according to the large language model; the core keyword data used for describing the focus is output, so that the specific cause of disease in the inquiry is predicted, and the accuracy is improved; the method comprises the following steps: recording feedback data related to core keyword data in real time; inputting the feedback data into the self-correction model, and outputting an adjustment value; and according to the adjustment value, parameters in the large language model are adjusted in real time, and through continuous use and adjustment based on feedback data, continuous refinement of the prediction model in the specific knowledge field of the urology department field is further realized, so that prediction of specific causes in inquiry is further realized, and the accuracy is improved.

The invention provides an industrial injury intelligent auxiliary identification method and system based on a large language model, and establishes an efficient industrial injury automatic identification method and system based on deep semantic analysis and clause matching capability of the large language model, precise classification and judgment of multiple illness condition combinations are achieved, the injury condition description text content input by a user can be analyzed, core information is accurately extracted from the injury condition description text content, classification is automatically carried out according to the complexity of illness conditions, then corresponding industrial injury rules and terms are automatically matched, corresponding industrial injury levels are automatically judged, and manual intervention is not depended on. Moreover, through the multi-level semantic understanding capability of the large language model, multi-illness description can be effectively processed, and accurate identification suggestions can also be output for complex description of multiple illness. Compared with an existing method based on rule or symptom matching, the method and system can remarkably improve the efficiency and accuracy of industrial injury identification.

The invention discloses a medical data storage method based on semantic recognition, and belongs to the technical field of data processing, and the method comprises the steps: receiving medical data, carrying out the parallel processing of an unstructured medical text in the medical data through a large language model, and generating a structured semantic triple and a semantic vector representing the overall semantics; constructing a semantic graph index and a vector index to form a mixed index structure; the method comprises the following steps: receiving a natural language query, analyzing the query into a structured query condition and a query vector, forming an executable multi-modal query instruction, executing atlas query and a vector similarity search process in parallel, and mapping the structured query condition to a semantic atlas execution path for matching. In the implementation process of the technical scheme, natural language processing and a large language model are introduced, entity recognition, relation extraction and semantic role labeling are conducted on medical unstructured texts, and structured conversion of key information such as illness state description, diagnosis conclusions and treatment schemes is achieved.

The invention provides a data processing method, medical equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a target gestational week stage of a target fetus, and determining a plurality of disease categories corresponding to the target gestational week stage in a disease category database based on the target gestational week stage; acquiring disease characterization information of the target fetus, wherein the disease characterization information comprises one or more of a target section image and a disease description text of the target fetus; and for each disease category corresponding to the target gestational week stage, based on the disease characterization information of the target fetus, calculating the disease probability that the target fetus suffers from the disease of the disease category. And based on each disease probability, determining a final disease category in a plurality of disease categories corresponding to the target gestational week stage, and outputting a standard disease name corresponding to the final disease category. According to the invention, the realization difficulty of subsequent medical data statistics can be reduced.

The invention relates to the technical field of artificial intelligence, can be applied to the field of digital medical treatment, and discloses an artificial intelligence-based accompanying diagnosis method, device and equipment and a storage medium, the artificial intelligence-based accompanying diagnosis method comprises the steps of obtaining health data of a patient, the health data comprising a disease description text, physiological health data and historical doctor seeing data; according to the disease description text and the physiological health data, performing diagnosis and treatment item prediction processing on the patient through a pre-trained diagnosis and treatment item prediction model to obtain a required diagnosis and treatment item of the patient; acquiring a doctor-seeing preference time period of the patient; performing medical resource matching processing on the patient according to the historical doctor-seeing data, the required diagnosis and treatment items and the doctor-seeing preference time period to obtain required medical resources of the patient; and generating an accompanying diagnosis process for the patient according to the required medical resources. According to the invention, flexible high-quality accompanying diagnosis service meeting personalized treatment requirements can be provided for the patient, so that the treatment experience of the patient is improved.

System and methods for computer modeling in medicine. A sort of period table of medical models is described for personalized diagnostics, prognostics and therapeutics, including at least 80 major categories of medical models. Generative artificial intelligence and geometric deep learning techniques, and algorithms including 2D and 3D graph machine learning and GenAI algorithms, are described, tailored and applied to diagnostic disease description, prognostic prediction and therapeutic development and management, including generation of novel synthetic drugs. The AI and machine learning techniques and algorithms are applied to understand each individual's genetic, RNA and protein anomalies that represent the source of many unique patient diseases. AI-enabled software agents assist physicians and researchers in building patient medical models. Several personalized medicine applications of individualized medical modeling include cardiovascular

The invention relates to the technical field of insurance and intelligent data processing, and discloses an internet health insurance underwriting method and device based on disease characteristics, and the method comprises the following steps: S1, obtaining to-be-underwritten historical insurance data and current insurance application data; s2, constructing a health insurance special word vector library based on the historical insurance data; s3, inputting the feature vector into a pre-trained hierarchical disease recognition model, and obtaining an output disease severity score; s4, generating an underwriting risk prompt according to the disease severity score, and sending the underwriting risk prompt to an underwriting operation terminal; and S5, collecting an artificial underwriting decision result for the underwriting risk prompt, and taking the artificial underwriting decision result as a new training sample to carry out incremental updating on the hierarchical disease recognition model. According to the method, the non-standard disease description analysis precision is improved by fusing the claim co-occurrence word vector and the vertical domain attention mechanism.

The present invention provides a data processing method, medical equipment, storage medium and computer program product. The above method includes: obtaining a target gestational age stage of a target fetus, and based on the target gestational age stage, determining multiple disease categories corresponding to the target gestational age stage in a disease database. Obtaining disease characterization information of the target fetus, the disease characterization information includes one or more of a target cross-sectional image of the target fetus and a disease description text. For each disease category corresponding to the target gestational age stage, the probability of the target fetus suffering from a disease of the disease category is calculated based on the disease characterization information of the target fetus. Based on each disease probability, a final disease category is determined from the multiple disease categories corresponding to the target gestational age stage, and the corresponding standard disease name is output. The present invention is conducive to reducing the difficulty of implementing subsequent medical data statistics.

The application provides a disease probability prediction method and device and electronic equipment, at least one target keyword associated with a target disease and disease description information of a target patient are obtained, for each target keyword, the target keyword is marked according to whether the target keyword exists in the disease description information, and a first marking result is obtained, and the disease description information and the first marking result corresponding to each target keyword are input into a pre-trained BRF model to output the probability that the target patient has the target disease, in this way, at least one target keyword associated with the target disease is determined in advance, after each target keyword is marked based on the disease description information of the target patient, the first marking result corresponding to each target keyword and the disease description information are jointly used as the input of the BRF model, which can improve the comprehensiveness and accuracy of evaluating whether the target patient has the target disease.

This invention discloses a method and system for predicting the results of traditional Chinese medicine (TCM) consultations in urology using a large language model, belonging to the technical field of large language modeling. This invention preprocesses disease description data and obtains self-correlation parameters between the disease description data; then, based on the large language model, it constructs a prediction model; outputting core keyword data describing lesions enables the prediction of specific causes in consultations, improving accuracy; by recording feedback data related to the core keyword data in real time; inputting the feedback data into a self-correcting model and outputting adjustment values; and adjusting the parameters within the large language model in real time based on the adjustment values, through continuous use and adjustment based on feedback data, the prediction model for a specific knowledge domain in urology is further refined, thereby further improving the accuracy of predicting specific causes in consultations.

The application discloses an intelligent inquiry method and system based on a knowledge graph, equipment and a storage medium, and belongs to the technical field of intelligent medical treatment. The method can be applied to an intelligent inquiry scene and comprises the following steps: acquiring a disease description text; performing structural processing on the disease description text, performing semantic retrieval on the structural description data, and performing graph matching processing; fusing and enhancing the retrieved knowledge set and the graph matching data, and performing inquiry based on the fused and enhanced data. In the application, the knowledge graph is utilized, candidate knowledge sets are extracted from the structural description data and the knowledge graph, and the candidate knowledge sets and the knowledge graph are fused and enhanced to ensure that reasoning is based on real medical knowledge, the illusion rate of generated content is reduced, and the reasoning accuracy of existing medical intelligent reasoning is improved.

The application discloses a doctor-patient joint decision-making method based on LLM-Agent multidisciplinary dynamic cooperation and relates to the technical field of doctor-patient joint decision-making. The method comprises the following steps: acquiring a disease description, extracting symptoms and signs by an LLM, assigning a department according to the symptoms and signs by the LLM, acquiring a multidisciplinary team composed of doctor agents of the corresponding department, independently analyzing the disease description by each doctor agent, generating a scheme, then integrating the schemes, and determining whether to adopt the scheme as a treatment scheme by a voting review mechanism. Patient preferences are extracted from the disease description based on a predefined preference format and a pre-constructed lightweight LLM. Then, a patient model is constructed based on the patient preferences and the disease description. Potential conflicts between the treatment scheme and the patient preferences are identified by an LLM. The patient agent quantitatively evaluates whether the treatment scheme is satisfactory according to the potential conflicts. If not, the next iteration is entered, otherwise the negotiation is stopped. The treatment scheme when the negotiation is stopped is output.

The invention relates to the field of machine learning and the field of digital medical treatment, and provides a classification method based on multi-label prediction, which performs symptom text comparison on clauses corresponding to medical text data of a user, and extracts symptom texts in the clauses. Then, through a multi-label prediction model, on the basis of the relation and difference between physique symptoms and disease symptoms, performing physique symptom and disease symptom prediction on each symptom text to obtain a probability value that each symptom text is a physique symptom and a probability value that each symptom text is a disease symptom, and finally, in combination with a physique classification model and a disease classification model, obtaining a disease symptom probability value that each symptom text is a disease symptom probability value. And respectively classifying the physique and the disease of the user. Therefore, the constitution description and the disease description in the medical text data are accurately identified and classified, the low symptom classification accuracy caused by dividing the symptom text into single symptom categories is avoided, the accuracy of constitution classification and disease classification is improved, and the accuracy of a symptom text classification result is improved.

The application provides an auxiliary triage method and device based on illness description information, equipment and a medium. The method comprises the following steps: determining a reference set from a plurality of preset sets based on a target age, and constructing a target set based on a plurality of habitual description words associated with a target part in the reference set; inputting the target set and the illness description information into an NLP model to obtain a target description word determined by the NLP model from the target set based on the illness description information; determining target symptom information based on preset symptom information associated with the target description word, and determining a triage result based on the target symptom information. The target part and the target age can be used as information indexes, the target set can be dynamically constructed based on the habitual description words conforming to the part of the patient and the description habit, the risk of misrecognition of the NLP model can be reduced by excluding irrelevant classification basis, the habitual description words are used as the triage basis, the triage accuracy is improved in the case of being unfamiliar with professional terms, and the patient experience is improved.

The invention discloses a doctor-patient joint decision-making method based on LLM-Agent multidisciplinary dynamic cooperation, and relates to the technical field of doctor-patient joint decision-making. The method comprises the following steps: acquiring disease description, and extracting symptoms and signs from LLM; and according to the symptoms and the signs, performing department distribution by the LLM, and obtaining a multidisciplinary team composed of the doctor agents of the corresponding departments. Each doctor agent independently analyzes the disease description and generates a scheme, then integrates the schemes, and determines whether to adopt the scheme as a treatment scheme or not by a voting review mechanism. Patient preferences are extracted from the condition description based on a predefined preference format and a pre-constructed lightweight LLM. And then constructing a patient model by the patient preference and the condition description. Potential conflicts between treatment regimens and patient preferences are identified by LLM. And the patient intelligent agent quantitatively evaluates whether the treatment scheme is satisfied according to the potential conflict. And if not, entering the next iteration, otherwise, stopping negotiation. And outputting the treatment scheme when the negotiation is stopped.

The present application provides a kind of based on multi-view fusion graph convolution network parasitic disease drug association prediction method, to solve the problems such as data sparse, noise interference and incomplete feature information in drug development. The method is through "multi-view heterogeneous network construction-self-supervised learning-multilayer propagation and association prediction" process, accurately identify parasitic disease-drug association. First, collect data and construct benchmark dataset;Then, extract drug SMILES feature and disease MeSH descriptor, fuse drug similarity network, disease similarity network and drug-disease two-part network. Next, adopt self-supervised learning strategy to obtain node embedding representation, introduce neighbor information aggregation layer to enhance sparse relationship expression, and finally output association prediction score by weighted fusion multi-view features through attention mechanism. Compared with existing methods, the present application shows higher accuracy and stability in parasitic disease drug prediction task, and provides support for drug screening and new drug development.

The present application discloses a large-model hospital infection determination method and system based on an intelligent agent, which relates to the field of risk assessment technology, including: obtaining target physiological characteristics of a target patient; the target physiological characteristics include at least one of the target patient's course of disease description, examination results and test results; searching a hospital infection knowledge graph according to the target physiological characteristics to obtain a corresponding target sub-graph; wherein the hospital infection knowledge graph is constructed according to a hospital infection diagnosis standard document; generating a relationship vector set according to the target sub-graph to obtain a target relationship vector set; inputting the target physiological characteristics and the target relationship vector set into a pre-trained hospital infection prediction model to obtain a target infection outcome, thereby reducing the difficulty of data set screening of the hospital infection prediction model and improving the prediction accuracy of hospital infection prediction.

This invention discloses an intelligent recommendation method and system for clinical pathways in cerebral hemorrhage based on knowledge graphs. It constructs a pathway knowledge graph and a disease severity classification system by analyzing treatment guidelines, identifying key nodes in pathway execution and disease severity level switching boundaries, and configuring differentiated decision rules for single and mixed disease severity areas. It collects multi-source disease data from patients in a dimensional manner, extracts disease features, and monitors dynamic indicator trends. Through weighted feature extraction and dynamic early warning analysis, it generates disease descriptions and calculates the matching degree between the current disease severity and candidate pathways. When a deviation in pathway execution is detected, it locates the source node of the deviation through cross-stage transitivity analysis and reverse tracing, generating targeted pathway correction instructions. Through node integrity verification and mandatory constraint correction, it ensures the standardization of the adjustment plan, outputting clinical pathway recommendation results adapted to the patient's actual condition, thus improving the adaptability and accuracy of clinical pathway recommendations.

The invention belongs to the technical field of intelligent medical treatment, and provides a digital intelligent medical service providing method and system. The method comprises the following steps: receiving basic medical information input by a patient, and carrying out matching analysis on the basic medical information and an illness state description guiding knowledge base to generate a personalized symptom guiding framework; performing semantic analysis and integrity verification on symptom description information fed back by the patient through the personalized symptom guide framework, and identifying missing core symptom dimension information; generating a supplementary guide instruction for the missing core symptom dimension information, and further obtaining complete symptom description data; and performing standardization processing on the complete symptom description data based on the symptom description specification term library to generate a structured illness state abstract, and pushing the structured illness state abstract to a doctor side. The method can effectively solve the problems of non-professional expression of the patient and information missing, shortens the inquiry time, reduces the information transmission error, assists the doctor to quickly capture the key illness state, improves the doctor-patient communication efficiency and diagnosis accuracy, and optimizes the medical experience.

The invention relates to the technical field of data analysis, in particular to a plant state evaluation method and system based on a multi-modal thinking chain technology, and the method comprises the steps: firstly obtaining a plant disease image, a disease description text, an environment parameter and a target crop type, and then associating the target crop type with the disease description text; the method comprises the following steps: acquiring a plant disease image, inputting associated data into a pre-trained language model, calculating semantic features of a disease description text, inputting the plant disease image and environmental parameters into a preset reinforcement learning and interpretability enhancement model, respectively calculating to obtain an image quality score and a pathological constraint reward parameter of the plant disease image, and finally, obtaining the image quality score and the pathological constraint reward parameter of the plant disease image. And inputting the pathological constraint reward parameters, the image quality score and the semantic features into a preset multi-modal thinking chain reasoning model, and calculating to obtain an evaluation result of the plant disease image. Compared with the prior art, the evaluation result of the method is more accurate.

The invention discloses a multi-modal small sample plant disease identification method, which comprises the following steps: acquiring a plant disease image through collection, and carrying out data preprocessing on the image; a VSF model is provided and comprises a semantic upgrading module, and plant disease definitions are upgraded by using a large language model and prompt words to generate more real disease descriptions conforming to an agricultural scene; a two-stage modal fusion module is designed, so that the consistency and discrimination capability of cross-modal information are effectively improved; inputting the preprocessed image data into the model for training and verification to obtain an optimal model; and finally, inputting a to-be-classified image into the optimal model to obtain a classification result. The multi-modal small sample plant disease identification method provided by the invention can ensure that the plant diseases can be rapidly identified and correct types can be obtained, and has a good application prospect.

The invention discloses a training method and device of a medical aid decision-making model. The method comprises the following steps: for each case text in a training sample set, calculating the similarity between the case text and all multi-granularity disease description texts by an initial auxiliary decision model, and screening K target disease description texts with the highest similarity score from N multi-granularity disease description texts according to the similarity; taking K target disease description texts corresponding to the case text as negative samples and taking actual disease description texts corresponding to the case text as positive samples by the initial aid decision model; and performing parameter adjustment on the initial auxiliary decision-making model according to the case text, the positive sample corresponding to the case text and the K negative samples to obtain the medical auxiliary decision-making model. According to the scheme, by introducing a comparative learning mechanism based on strong negative sample mining, the recognition capability of the model on easily-confused disease descriptions is effectively enhanced, the accuracy of decision suggestions output by the model is improved, and reliable support is provided for high-precision diagnosis and treatment recommendation.

The invention provides a disease probability prediction method and apparatus, and an electronic device. The method comprises the steps of obtaining at least one target keyword associated with a target disease and disease description information of a target patient; for each target keyword, marking the target keyword according to whether the target keyword exists in the disease description information or not to obtain a first marking result; and inputting the disease description information and the first marking result corresponding to each target keyword into a pre-trained BRF model to output the probability that the target patient suffers from the target disease, in this way, at least one target keyword associated with the target disease is pre-determined, and the probability that the target patient suffers from the target disease is determined on the basis of the disease description information of the target patient. After each target keyword is marked, the first marking result corresponding to each target keyword and the disease description information are jointly used as the input of the BRF model, so that the comprehensiveness and accuracy of evaluating whether the target patient suffers from the target disease can be improved.