53 results about "Symptom profiles" patented technology

The invention discloses an AI-based traditional Chinese medicine dialectical auxiliary diagnosis method and system and a medium thereof, and relates to the technical field of intelligent auxiliary diagnosis, and the method comprises the steps: collecting physiological monitoring data, tongue condition data and pulse condition signals of a patient, obtaining patient symptom information, mapping the patient symptom information to a preset traditional Chinese medicine pathogenesis classification model, and generating an initial symptom feature vector; calling a knowledge base containing traditional Chinese medicine prescription rules and compatibility medication taboo, performing data space-time alignment processing and dynamic combination calculation on the initial symptom feature vector, and generating a personalized candidate prescription set conforming to the traditional Chinese medicine compatibility taboo; according to dynamic combination calculation, a solution algorithm based on a constraint satisfaction problem is adopted, and multi-dimensional association rule matching is carried out in combination with the mapping relation between syndromes and modern medical symptoms; and outputting a prescription medication recommendation scheme containing traditional Chinese medicine compatibility, dosage and decoction methods based on the candidate prescription set. The method supports the formulation of an accurate personalized diagnosis and treatment scheme, and meets the requirements of high-quality traditional Chinese medicine personalized auxiliary diagnosis and treatment.

The invention provides a common mental disease intelligent diagnosis method and system based on multiple agents, and relates to the field of medical artificial intelligence. The method comprises the following steps: S1, extracting diagnosis standards and symptom characteristics of common mental disorders, and constructing a similar patient knowledge base after verification and evaluation of the similar patient knowledge base and expert calibration; s2, acquiring clinical data from a hospital information system, and performing large medical record structuring, clinical scale simplification and scale score analysis on the clinical data to form a similar patient database; and S3, performing symptom matching and scale performance analysis on the input clinical data, constructing a multi-agent mental disease diagnosis framework, and performing multi-agent diagnosis debate based on the multi-agent mental disease diagnosis framework. The technical problems of symptom overlapping and diagnosis subjectivity among common mental diseases are solved by constructing a multi-agent cooperative diagnosis framework, introducing particle size symptom analysis and dynamically integrating structured authoritative medical diagnosis standards.

The invention relates to the technical field of medical assistant systems, and discloses a comprehensive intelligent medical assistant system, which comprises an information acquisition unit used for acquiring user state information; the user state information comprises user static data, dynamic data and feedback data; the model construction unit is used for performing feature extraction according to the user state information and establishing data association indexes of physiology, environment and behaviors; the information processing unit is used for automatically capturing symptom characteristic information and carrying out diagnostic analysis on the input information in combination with user state information; the pushing unit is used for performing local decision processing on the analysis result, forming a diagnosis path diagram and pushing the diagnosis path diagram to a user side; and the learning optimization unit is used for optimizing a recommendation strategy according to the feedback data and integrating long-term health features to carry out optimization suggestions. According to the invention, the service mode of medical health is remodeled, the unique health characteristics of each user can be more accurately understood, the service quality and credibility of a medical assistant system are improved, and the occupancy rate of medical resources is reduced.

The invention belongs to the technical field of traditional Chinese medicine syndrome type classification, and discloses a traditional Chinese medicine syndrome type library construction method and system based on a convolutional neural network, and the method comprises the steps: constructing a corpus for mapping traditional Chinese medicine semantics and a dynamic semantic analysis framework, and carrying out the data enhancement preprocessing of the corpus; the method comprises the following steps: acquiring data, cleaning the acquired data, and removing repeated, missing or abnormal data; constructing a convolutional neural network, and processing and outputting the input data; and constructing a traditional Chinese medicine syndrome type library based on the output syndrome types, and deploying the trained convolutional neural network in an online diagnosis and treatment system for automatic classification and storage. Key features can be automatically extracted from traditional Chinese medicine clinical data, the traditional Chinese medicine symptoms are classified into the corresponding traditional Chinese medicine syndromes by constructing the mapping relation between the traditional Chinese medicine symptoms and the syndromes and utilizing the convolutional neural network to learn the symptom features, a perfect traditional Chinese medicine syndrome knowledge base is formed, and scientific and efficient auxiliary decision support is provided for traditional Chinese medicine clinical diagnosis and treatment.

The invention relates to the technical field of artificial intelligence, and discloses an interpretable depression detection method and system, and the method comprises the steps: retrieving a post related to a depressive symptom from a user social media history; on the basis of the post text corresponding to the symptom problem, a problem perception text representation is generated through fusion of a Longform encoder and an attention mechanism, and an optimal reasoning strategy is selected from a predefined reasoning strategy pool through a hybrid expert network; based on an inference strategy of question perception text representation and selection, selecting a most adaptive large language model from a predefined large language model pool through a hybrid expert network; deducing the severity of each depression symptom of the user according to an inference strategy and a large language model, and calculating the overall depression symptom severity of the user; according to the method, the reasoning strategy and the large language model are dynamically selected through the hybrid expert network, the optimal processing combination is adaptively matched for different symptom features and post contents, and the limitation of a fixed reasoning mode is overcome.

The invention provides a mood disorder assessment system based on multi-level feature fusion, and the system comprises a data collection unit which is used for collecting electroencephalogram signals of a plurality of brain regions of a to-be-assessed patient; the electroencephalogram feature extraction unit is used for extracting electroencephalogram features corresponding to the electroencephalogram signals of the brain regions; the multi-level feature extraction unit is constructed on the basis of the symptom features of the multiple testees and the corresponding electroencephalogram features, and is used for performing multi-level electroencephalogram feature latent variable extraction on the electroencephalogram features of the brain regions of the patient to be evaluated to obtain multi-level electroencephalogram feature latent variables; and the feature fusion and classification unit is used for carrying out classification prediction based on the electroencephalogram feature latent variables to obtain a mood disorder assessment result of the patient to be assessed. The method solves the problem that a mood disorder assessment system in the prior art adopts a single feature extraction and learning strategy and has no constraint of symptom information, so that the recognition capability of a model for mood disorders of different functional abnormality types is limited.

The invention relates to a diagnosis and treatment result prediction method fusing a time sequence and traditional Chinese medicine multi-stage diagnosis and treatment, belongs to the technical field of traditional Chinese medicine diagnosis and treatment prediction, and solves the problem of lack of accurate whole-process prediction in the prior art. The method comprises the following steps: acquiring the current doctor-seeing symptom and historical doctor-seeing time sequence data of a to-be-predicted patient; the historical treatment time sequence data comprises symptom, syndrome, therapy and prescription data of each time step; constructing a graph structure corresponding to each time step of the historical doctor-seeing time sequence data; extracting a symptom feature sequence, a syndrome feature sequence, a therapy feature sequence and a prescription feature sequence by adopting a trained graph neural network model based on the graph structure and the current treatment symptom; and based on the symptom feature sequence, the syndrome feature sequence, the therapy feature sequence and the prescription feature sequence, performing multi-stage diagnosis and treatment result prediction by adopting a trained recurrent neural network model to obtain the prediction results of the syndrome, the therapy and the prescription of the current doctor seeing of the to-be-predicted patient. And accurate whole-process prediction is realized.

The invention relates to the technical field of triage devices, in particular to a voice triage device, which comprises a voice acquisition module used for acquiring oral symptom information of a patient; converting the symptom information into audio data; the voice recognition module is in communication connection with the voice acquisition module; the symptom analysis module is in communication connection with the voice recognition module and generates symptom feature vectors based on the symptom keywords; the intelligent triage module is in communication connection with the symptom analysis module and receives the symptom feature vector; calculating the similarity between the symptom feature vector and each disease based on a preset disease symptom database; according to the similarity, generating a preliminary diagnosis result and a recommended doctor seeing department; the output module is in communication connection with the intelligent triage module and is used for receiving the preliminary diagnosis result and a recommended treatment department; the preliminary diagnosis result and the recommended diagnosis department are output in a text or voice form, and a comprehensive and efficient voice triage system is constructed by combining advanced technologies such as voice recognition, natural language processing, machine learning and the like.

The invention provides a special disease first-aid full-process auxiliary decision-making method based on multi-modal perception and AI, and relates to the technical field of medical first aid, and the method comprises the steps: obtaining first-aid field multi-modal data, constructing a feature dependence graph, and recognizing the type and symptom features of a special disease; indexing special disease diagnosis and treatment data based on the symptom feature vector, and determining a reference case and a treatment path; the action space is constructed in combination with clinical specifications, the expected income is predicted by applying Monte Carlo search, and the optimal treatment scheme is generated, so that the first-aid special disease recognition accuracy can be improved, the treatment decision time can be shortened, and the first-aid intervention effect can be improved.

The invention relates to the technical field of knowledge maps, in particular to a veterinary treatment big data knowledge map construction method, which comprises the following steps of: acquiring animal case symptom characteristics, physical indexes, medical history records and intervention stage data, normalizing the symptom characteristics and encoding medical history to generate a case characteristic vector set; mapping symptoms and medicine nodes to establish a semantic relationship to calculate association strength, embedding physique and medical history to update node confidence to generate a personalized knowledge graph model, dynamically correcting edge weights in combination with feedback and medicine response, and extracting an effective intervention path to construct an association index to generate a veterinary treatment big data knowledge graph. According to the method, through normalization and sequential processing of multi-source case data, feature quantification and tracking are achieved, dynamic association is established based on semantic mapping and graph attention, confidence attenuation and an attribute weighting mechanism are fused, a node relation is optimized and self-adaptive evolution is carried out, individual difference and drug response capture is enhanced, and the updating performance of diagnosis and treatment knowledge is improved; and accurate and intelligent diagnosis and treatment analysis is promoted.

The invention discloses an intelligent prescription recommendation method based on shared expression fusion, a medium and equipment, and the method comprises the steps: firstly obtaining original symptom text data of a patient, and generating a potential embedded expression through a pre-training model; global and local relation graphs are constructed through full connection, nearest neighbor and farthest neighbor composition modes, and global and local features with the same dimension are extracted through a graph convolutional neural network; and utilizing the shared encoder, the global decoder and the local decoder to reconstruct features, optimizing parameters of the shared encoder, and obtaining fusion symptom feature representation. And initializing the prescription embedding vector and extracting the characteristics of the prescription embedding vector, calculating a correlation score matrix fusing the symptom characteristics and the prescription characteristics, and outputting a preset number of prescriptions with the highest score as a recommendation result. According to the method, the complex relationship between symptoms can be effectively mined, and the accuracy and stability of prescription recommendation are improved.

Embodiments of the present application disclose an information recommendation method, device, equipment, system and storage medium. In the method, first, medical text materials of a target object are acquired. Then, symptom entities in the medical text materials are determined. Next, based on the medical text materials, symptom entity feature information and context feature information corresponding to the symptom entities are extracted. Then, the symptom entity feature information and the context feature information are fused to obtain fusion features corresponding to the symptom entities. Finally, information is recommended based on the fusion features corresponding to the symptom entities in the medical text materials. By extracting the symptom entity feature information and the context feature information corresponding to the symptom entities from the medical text materials, richer symptom-related semantics is used as the basis for the recommended information. Compared with the prior art, the technical solution of the present application enriches the basis category of the recommended information, improves the utilization rate of information in the medical text materials, and thus makes the recommended information more accurate.

The application provides a syndrome type classification method and device based on syndrome element decomposition, equipment and medium. The method analyzes the syndrome type name and syndrome type description of the to-be-classified syndrome type through a syndrome element prediction model, splits and predicts the main syndrome element and the secondary syndrome element of the to-be-classified syndrome type as the symptom characteristics of the to-be-classified syndrome type. The target feature vector of the to-be-classified syndrome type is subjected to similarity matching through the retrieval of the known feature vector of the known syndrome type, so that the known syndrome type similar to the feature of the to-be-classified syndrome type is searched in the known syndrome type library to complete the classification of the to-be-classified syndrome type. The application relates to the technical field of model prediction. The feature vector of the to-be-classified syndrome type is obtained through the syndrome element decomposition of the syndrome type, and the vector matching is performed with the known syndrome type, so that the matching between the syndrome types with different standard names and the same symptoms can be realized, the accuracy of the syndrome type matching is improved, and the classification accuracy between the syndrome types with different standards is improved.

The application discloses a kind of based on knowledge graph's simulation clinical experiment environment interaction method, specifically related to medical artificial intelligence and clinical simulation technical field;Initial disease entity node and its corresponding symptom feature set are acquired, and initial pathological state graph with time factor is constructed;Based on user interaction behavior extraction operation feature vector, utilize graph neural inference model to carry out multi-hop semantic path inference, generate post-interaction state graph;Further calculate the semantic shift degree caused by user operation, dynamically adjust graph inference weight;Extract relevant etiological entity and generate pathological evolution chain, calculate response difference degree in combination with user subsequent behavior, dynamically adjust virtual patient feedback, trigger path rollback operation if necessary;The application can realize the precise modeling and response control based on knowledge graph in clinical simulation environment, improve the interaction intelligence, explainability and stability of system, applicable to medical teaching, virtual diagnosis training and the like scene.

The application discloses a farm veterinarian question and answer and auxiliary diagnosis method and system based on a large language model, which comprises the following steps: standardizing a colloquial query to obtain structured query information; based on the information, mixed retrieval is carried out from a hierarchical veterinarian knowledge base to obtain a candidate disease list and a multi-source evidence set; a preliminary diagnosis answer is generated according to the multi-source evidence set, semantic and evidence alignment evaluation is carried out, and evidence sufficiency scores are generated; the differential diagnosis attributes of each disease in the candidate disease list are compared to identify key differences, and information missing items are identified by comparison with standard symptom profiles; based on the scores, key differences and information missing items, a multi-round diagnosis enhanced retrieval framework and user interaction are adopted, the candidate disease list and the multi-source evidence set are updated, and a diagnosis report is generated in combination with veterinary drug compliance rules. The application integrates hierarchical knowledge graphs, multi-evidence alignment and multi-round diagnosis logic, improves the accuracy of veterinarian question and answer, reduces knowledge illusion, and ensures drug compliance.

The invention discloses a time sequence classification method and system based on a multi-relation atlas, and the method comprises the steps: obtaining multivariable time sequence data through the sampling of a sensor, and defining the state of the sensor; related symptoms of each sensor state are mined through a large language model, and a sensor state relation graph is constructed for each symptom; a multi-graph gating network is constructed and trained, the multi-graph gating network is composed of a plurality of GNNs, a gating network and an MLP network, each GNN is learned by using a sensor state relation graph of one symptom, multivariable time sequence data is learned through the plurality of GNNs to obtain time sequence characteristics of the sensor state relation graph of each symptom, and the time sequence characteristics of the sensor state relation graph of each symptom are obtained; and aggregating into a total symptom feature through a gating network, and finally obtaining final classification output through an MLP network. The invention relates to the technical field of natural language processing, can combine a multi-relationship graph with multivariable time sequence data training, enables the construction of the relationship graph to be flexible, and effectively improves the classification accuracy.

The application discloses a pediatric emergency department hierarchical treatment guidance method based on symptom analysis and an electronic device, which comprises the following steps: acquiring age information of a target patient and detecting interaction data, wherein the interaction data comprises chief complaints and accompanying symptoms; based on the age information, a hierarchical evaluation rule library matched with the age information is called, and the interaction data is calculated by level through a preset logical judgment path in the hierarchical evaluation rule library, and a target pre-examination hierarchical result is output; the target pre-examination hierarchical result and the interaction data are combined, a preset pediatric clinical diagnosis and treatment mapping rule library is called for joint matching, a target examination item corresponding to the target pre-examination hierarchical result and the symptom characteristics is screened out, and a to-be-executed examination list is generated. In this way, the pre-examination hierarchical classification can be quickly and accurately performed, and the children and their families can be guided to efficiently complete the subsequent examination and treatment.

The application provides a disease-specific emergency whole-process auxiliary decision-making method based on multi-modal perception and AI, relates to the technical field of medical emergency, and comprises the following steps: acquiring multi-modal data of an emergency scene, constructing a feature dependency graph, and identifying disease types and symptom characteristics; indexing disease diagnosis and treatment data based on a symptom characteristic vector, determining reference cases and treatment paths; combining clinical norms to construct an action space, applying Monte Carlo search to predict expected returns, and generating an optimal treatment plan, which can improve the accuracy of emergency disease identification, shorten the treatment decision-making time, and improve the emergency intervention effect.

The invention discloses an LLM triage decision-making method based on animal injury, and the method comprises the steps: obtaining the related structural input information of animal injury, including animal types, exposure levels, basic information of patients and symptom description, and standardizing the symptom features through a natural language processing technology; multi-modal fusion is carried out on the large language model and directed acyclic medical logic map embedded features constructed according to diagnosis and treatment specifications, a Prompt input sequence containing medical logic constraints is generated, and the large language model is explicitly guided to carry out reasoning according to a medical decision path; according to the method, the path validity is dynamically tracked in the reasoning process, a structured log is generated, and finally the triage level and the processing suggestion conforming to the diagnosis and treatment specification are output, so that the standardization, the consistency and the traceability of the triage decision are improved, and the medical compliance and the clinical application value of the intelligent triage system are effectively enhanced.

The application discloses a traditional Chinese medicine prescription efficacy prediction method based on a prescription-symptom heterogeneous graph, first, the characteristics of traditional Chinese medicines are counted, the traditional Chinese medicine characteristics are initialized, the traditional Chinese medicine characteristics are aggregated based on a multiple attention mechanism, the prescription characteristics are initialized, the symptom characteristics are initialized based on a known prescription-symptom correlation matrix, and the dimensionality of the symptom characteristics is reduced through an encoder, then, a prescription-symptom heterogeneous network is constructed, feature learning is performed in the heterogeneous network by using a graph convolution, and finally, the efficacy is predicted by using the finally learned prescription and symptom characteristics. The method of the application uses a multiple attention mechanism, the feature representation of the prescription is more reasonable, the dimensionality of the symptom characteristics is reduced by using an encoder, the training and learning efficiency is improved, a prescription-symptom heterogeneous network is constructed, feature learning is performed by using a graph convolution, the efficacy of the prescription can be more intuitively and efficiently predicted, and the prescription efficacy prediction precision is improved.

The present application relates to a kind of fusion time series and traditional Chinese medicine multi-stage diagnosis and treatment diagnosis and treatment result prediction method, belong to traditional Chinese medicine diagnosis and treatment prediction technical field, solve the problem of lack of accurate whole process prediction in prior art.Method includes: obtaining the symptoms and historical visit time series data of the patient to be predicted current visit;Historical visit time series data includes the symptom, syndrome, therapy and prescription data of each time step;The graph structure corresponding to each time step of historical visit time series data is constructed;Based on the graph structure and the symptoms of current visit, symptom feature sequence, syndrome feature sequence, therapy feature sequence and prescription feature sequence are extracted using trained graph neural network model;Based on symptom feature sequence, syndrome feature sequence, therapy feature sequence and prescription feature sequence, multi-stage diagnosis and treatment result prediction is carried out using trained recurrent neural network model, and syndrome, therapy and prescription prediction results of the patient to be predicted current visit are obtained.Accurate whole process prediction is realized.

The invention discloses a lung cancer immunotherapy adverse reaction patient report management system, which relates to the technical field of medical information and comprises a data acquisition module, a phase deviation calculation module, a characteristic parameter calculation module, a real-time data processing module, a characteristic decomposition module and an evaluation generation module. The method comprises the following steps: firstly, acquiring a drug administration time sequence and multi-dimensional symptom data of a patient, calculating a phase offset at a symptom acquisition moment by using a drug administration period, constructing a periodic phase coordinate system, and mapping a symptom feature vector to the coordinate system, calculating a first characteristic parameter representing drug resonance intensity and a second characteristic parameter representing a time sequence topological relation between symptoms, constructing a multi-dimensional signal decoupling model, decomposing a symptom data vector into a first component vector and a second component vector, and generating a grading evaluation result according to module values of the two components; according to the invention, precise decoupling and identification of immune adverse reactions and tumor progression are realized, and the problem of misjudgment caused by confusion of signal sources is effectively solved.

The application discloses a traditional Chinese medicine recommendation method based on knowledge driving and residual attention network, and comprises the following steps: S1, a data collection and cleaning module: obtaining prescription text data, performing a standardization process on symptoms and traditional Chinese medicine terms in the prescription text data, and dividing the data set after the standardization process into a training set, a verification set and a test set; S2, an entity pre-training module: extracting symptom semantic features by using a Word2vec training model to extract feature of symptom entity in the prescription and obtain overall context semantic representation, constructing a traditional Chinese medicine attribute knowledge graph, and integrating natural attribute features of traditional Chinese medicine into a recommendation model as external knowledge; S3, a multi-graph construction and entity feature learning module: constructing a "symptom-traditional Chinese medicine" heterogeneous graph (SHHG), a "symptom-symptom" homogeneous graph (SSIG) and a "traditional Chinese medicine-traditional Chinese medicine" homogeneous graph (HHIG) according to the co-occurrence relationship between symptoms and traditional Chinese medicine, extracting symptom features, traditional Chinese medicine features and their interaction features from the "symptom-traditional Chinese medicine" heterogeneous graph (SHHG), the "symptom-symptom" homogeneous graph (SSIG) and the "traditional Chinese medicine-traditional Chinese medicine" homogeneous graph (HHIG) respectively by using a graph attention neural network, and enhancing entity features by using a residual structure; and S4, a feature fusion and traditional Chinese medicine recommendation module: fusing the symptom features and the traditional Chinese medicine features extracted from the "symptom-traditional Chinese medicine" heterogeneous graph (SHHG), the "symptom-symptom" homogeneous graph (SSIG) and the "traditional Chinese medicine-traditional Chinese medicine" homogeneous graph (HHIG) respectively, obtaining final symptom features and traditional Chinese medicine features, expressing syndrome features by using an MLP, and finally recommending a suitable traditional Chinese medicine set according to a given symptom set.

The invention belongs to the field of emergency treatment of infectious diseases, and particularly relates to an emergency treatment method and system for dealing with infectious diseases, and the method comprises the steps: extracting patient symptom features according to the treatment information of patients to form a symptom feature matrix; calculating a calculated Euclidean distance between the symptom feature matrix and the infectious disease feature vector, extracting a patient whose calculated Euclidean distance is less than a preset distance as a target patient, and calculating an infectious disease intensity coefficient; when the infectious disease intensity coefficient is greater than a preset coefficient, calculating a propagation index according to the activity track data set, and calculating an area proportion of the high-risk region according to the propagation index; when the area proportion is greater than the preset proportion, executing a second interference measure, and calculating an infection growth rate after the second interference measure is executed; and if the infection growth rate is greater than the preset growth rate, modifying the second interference measure according to the infection growth rate to obtain a third interference measure. Reasonable management can be carried out according to different infectious disease intensities and transmission areas, and manpower and material resources are saved.

The invention relates to the technical field of multi-modal perception, in particular to a medical scene dynamic interactive decision system and method based on multi-modal perception, and the system comprises a main node recognition module, a coverage judgment module, a reconstruction guide module, a factor construction module and a path rearrangement module. According to the method, frames with significant structures are screened through edge and texture changes between images, comparison between symptom keywords in case texts and lesion tags is combined, semantic omission is recognized, inquiry content is directionally completed, and the completed content comprises missing symptom features, uncovered part information and potential lesion description. An abnormal factor set is constructed on the basis of voice speed change, physiological waveform jump and expression tension change, factors comprise abnormal voice features, key physiological signal fragments and expression tension change directions, and semantic coverage integrity, interaction response accuracy and multi-modal fusion efficiency are improved on the basis, so that medical perception and reasoning effects are enhanced.

The invention discloses a traditional Chinese medicine syndrome differentiation language model training and reasoning method based on natural language processing, and particularly relates to the technical field of medical information processing. The method comprises the following steps: performing sentence segmentation and symptom statement segmentation on a traditional Chinese medicine medical record text of a patient to construct a symptom statement sequence data set, and analyzing a co-occurrence relation and occurrence position distribution of symptom statements in a patient narrative context to generate context association features of the symptom statements; identifying functional role differences of the same symptom in different narrative contexts according to the context association features of the symptom statements to generate symptom context role annotation data; and dynamically redistributing the participation degree of the symptom characteristics in different symptom type reasoning processes based on symptom context role labeling data, carrying out constraint updating on the traditional Chinese medicine syndrome differentiation language model, and inputting a traditional Chinese medicine medical record text of a to-be-analyzed patient into the trained traditional Chinese medicine syndrome differentiation language model in a reasoning stage. And outputting a corresponding traditional Chinese medicine syndrome type judgment result.

The invention provides an intelligent triage method and system based on face recognition, and the method comprises the steps: completing the identity verification through the comparison of face recognition and certificate information, and calling the medical history data of a patient; performing asymmetric fuzzification processing on currently acquired text chief complaint data, vital sign data and medical history data of the patient to generate a department related symptom feature set; constructing a symptom-department association rule base, and based on the symptom-department association rule base, generating department triage suggestions through a dynamic department decision model; and performing confidence coefficient optimization on the department triage suggestion, and outputting a final department triage report. According to the method, multi-symptom co-scene misjudgment and triage deviation of special crowds can be effectively reduced, a high-credibility and high-adaptability pre-examination triage solution is provided for intelligent medical treatment, and compared with traditional manual triage, the triage accuracy and emergency pre-examination efficiency can be greatly improved.

The invention is suitable for the technical field of medical intelligent diagnosis and machine learning, and provides a pneumonia screening and risk prediction model construction method based on a reverse neural network, and the method comprises the steps: firstly carrying out the preprocessing of a bacterial pneumonia clinical symptom data set, and dividing a multi-classification problem into a plurality of binary classification tasks; secondly, constructing a CPT algorithm based on a random forest and a convex hull theory, calculating a feature weight through information gain, and screening out high-contribution symptom features; and finally, inputting the screened features into the optimized BPNN, and obtaining a prediction model through repeated iterative training. The method has good classification accuracy, the number of the selected features is obviously reduced compared with a traditional model, and the method can be used as a clinical auxiliary diagnosis tool, is applied to clinical bacterial pneumonia infection screening and severe risk early warning, and provides decision support for timely treatment.

This invention discloses an electronic medical record data analysis system for children with fever, including a data acquisition module to acquire information from queried cases; and a data processing and analysis module for executing electronic medical record data analysis methods for children with fever, matching and ranking febrile diseases based on information from queried cases. The method includes: extracting candidate symptoms from electronic medical record data using an intelligent large model to generate a complete symptom dictionary; loading the complete symptom dictionary, filtering unstructured text, and generating structured symptom features for patients; calculating the mutual information value between symptoms and febrile disease classifications; calculating the point mutual information value between positive symptoms and febrile diseases, and generating an inverted index matching symptoms and febrile diseases; calculating the comprehensive distance between newly input patient electronic medical record data and candidate medical record samples based on structured and unstructured symptom features, and ranking the candidate medical record samples according to the comprehensive distance to obtain the matched febrile disease ranking.

The invention discloses a traditional Chinese medicine menstrual prescription clinical teaching evaluation method based on information entropy. The method comprises the following steps: constructing a conditional probability knowledge base; initializing a diagnosis space and a feature space, determining each diagnosis feature in the diagnosis space and each symptom problem distribution initial prior probability in the feature space based on a conditional probability knowledge base, and calculating to obtain an initial information entropy; acquiring an input symptom feature, calling a corresponding conditional probability according to a conditional probability knowledge base, executing Bayesian updating, and calculating a diagnostic posterior probability; after each Bayesian update, calculating and diagnosing spatial information entropy, and determining entropy decrement according to the initial information entropy; recording the diagnosis probability distribution and entropy decrement; and traversing the candidate symptom features which are not input, calculating expected information gains of the candidate symptom features, and outputting recommendation questions according to the expected information gains. According to the invention, objective quantitative evaluation of student thinking paths is realized, and dynamic optimization and guidance of inquiry strategies are realized through information gain calculation.