16 results about "Clinical knowledge" patented technology

The application provides a medical image segmentation method and system based on concept guidance and cross-modal alignment, and belongs to the field of medical image processing. The method comprises the following steps: obtaining a medical image to be segmented and its corresponding clinical text description; generating clinical knowledge concepts related to the target disease by using a large language model, and constructing a concept set through clinical review; inputting the medical image, the clinical text description and the concept set into a trained concept-guided segmentation model to extract visual features, text features and concept labels; generating concept features aligned with the visual features through a concept-visual alignment module; dynamically adjusting the normalization process of the visual features through a concept modulation decoder, combining the features through multi-head cross attention, and outputting the final image segmentation result by using a segmentation head. The application effectively solves the problems of lack of effective clinical prior guidance in existing medical image segmentation, poor cross-modal feature alignment, and insufficient lesion segmentation accuracy.

The application relates to the technical field of sales support, and discloses a medicine sales data analysis method, which comprises the following steps: constructing a cognitive map model; performing clinical path complexity grading; applying a clinical path complexity grading algorithm to analyze clinical decision process data of a medical institution, and calculating a clinical path complexity index; implementing cognitive-clinical path matching; adopting a cognitive-clinical path matching algorithm to process sales representative cognitive state data and clinical path complexity data, and calculating a matching degree score; performing hierarchical progressive information presentation; based on a hierarchical progressive information presentation algorithm, processing the matching degree score and the clinical path data, dividing information into different priority levels, and outputting an optimized information presentation sequence; and providing personalized clinical knowledge navigation; the application significantly improves the accuracy and effectiveness of professional information transmission by intelligently adapting the cognitive ability of a sales representative to the complexity of a clinical path.

This invention relates to the field of data processing technology and specifically discloses a method for constructing a clinical terminology knowledge graph. The method includes: acquiring multi-source clinical data and medical domain dictionary data; determining the clinical entity set and data block dictionary set for each clinical data block of each medical clinical data from each data source; determining multiple business domain clustering data for each business domain label and the clustered medical entity set for each business domain clustering data; calculating the statistical entity relationship set and graph entity relationship set between every two medical entities in the clustered medical entity set of each business domain label; and constructing a clinical knowledge graph. This method enables deep collaboration between multi-source clinical data and medical dictionaries, improving the professionalism and reliability of medical entity associations, balancing the independence of business domain knowledge with the interoperability of global knowledge, and providing high-quality core support for intelligent medical assistance, medical research, and clinical knowledge transmission.

This invention relates to the interdisciplinary field of smart healthcare and digital twin technology, specifically to a dynamic medical twin system and interactive prediction method based on a physiological double helix driven and four-dimensional linkage modalities. The system continuously collects and fuses multi-source biophysical data through a physical entity helix, while a digital virtual helix solves a network of physiological equations coupled with metabolic and stress fields in real time. Both systems achieve endogenous synchronous mapping of gene loci and expressed proteins through a built-in base pairing engine. The four modalities of mirroring, deduction, intervention, and knowledge are responsible for high-fidelity real-time presentation, disease progression prediction, virtual intervention deduction, and clinical knowledge accumulation, respectively, forming a complete closed loop of "observation-deduction-intervention-learning." This invention elevates the system architecture from a static hierarchical stack to a dynamic life-body metaphor, supporting users to perform virtual operations on the twin and receive real-time feedback on multi-scale physiological responses across the entire system, achieving a leap from "morphological simulation" to "life mechanism simulation."

The invention discloses a traditional Chinese medicine disease diagnosis auxiliary system based on a clinical mapping knowledge domain, and relates to the technical field of traditional Chinese medicine diagnosis. Searching syndrome nodes associated with the symptoms and tongue picture features from a traditional Chinese medicine clinical knowledge map to form an initial syndrome set; calculating a matching degree between the pulse condition waveform data and typical pulse condition features of each syndrome node, and performing sorting and screening to form a focused syndrome set; extracting associated treatment methods and prescriptions to generate a preliminary diagnosis reasoning chain; and performing logic verification and optimization on the reasoning chain through a graph neural network syndrome evolution deduction model, outputting an optimized diagnosis path, and recording related data to a diagnosis and treatment file. The system can assist in traditional Chinese medicine diagnosis, improve diagnosis pertinence and reasoning preciseness, and perfect diagnosis and treatment records.

The invention discloses a text prompt type heart function intelligent evaluation method based on a visual language large model. The method comprises the following steps that 1, an echocardiography mark data set is constructed; 2, dividing four chambers of the heart; step 3, hierarchical feature learning; 4, performing multi-scale feature fusion; and 5, predicting the cardiac function (ejection fraction). According to the method, the heart can be modeled into a multi-scale semantic system, and features from macroscopic chamber dynamics to microstructure motion are captured through a hierarchical feature learning mechanism. Deep integration of imaging data and clinical knowledge is realized by aligning hierarchical visual features with professional medical descriptions in a shared semantic space. The method has excellent performance in the aspect of ejection fraction prediction.

This invention discloses an intelligent early warning system and method for infection control in intensive care units (ICUs), specifically relating to the fields of medical informatics and ICU infection control technology. Technical Problem: Addressing the issues of single data dimensions, rigid early warning thresholds, and disconnect between response and treatment in traditional ICU infection monitoring. Solution: Constructing a multi-source data fusion sensing network, employing a deep temporal model embedded with clinical knowledge to achieve dynamic risk assessment, triggering tiered early warnings based on individualized thresholds and intelligently linking with disinfection / isolation equipment, and continuously optimizing the model through a federated learning framework. Beneficial Effects: Achieving early detection of infection risks, individualized and accurate early warning, and automatic execution of prevention and control measures, improving the efficiency of closed-loop infection control management in the ICU.

The application relates to the technical field of medical informatics, and particularly relates to an AI voice recognition-based psychiatric electronic medical record generation device. A voice processing module collects doctor-patient conversation audio signals, generates a time-stamped text sequence through sound source separation and voice recognition. A semantic analysis module performs context modeling, entity recognition and relationship extraction on the text sequence, and outputs clinical entities and semantic relationships. A knowledge graph module performs graph reasoning based on psychiatric clinical knowledge data, and generates a diagnosis hypothesis. A template adaptation module selects a medical record template and fills in fields according to the analysis result and the diagnosis hypothesis, and generates a preliminary medical record document. A quality control module performs multistage checking on the document, and feeds back the checking result to each module to realize parameter optimization. Through data flow conversion and closed-loop feedback mechanism among the modules, the device realizes automatic conversion of unstructured doctor-patient conversation into standardized medical records, and effectively improves the accuracy and integrity of psychiatric medical record recording.

The application discloses a music-based psychological consultant matching method and system, which constructs a music-psychology mapping database, extracts music multi-level audio features to train a supervised learning model, and establishes a mapping relationship between the features and psychological dimensions. The music selection data of the visitor is obtained through an adaptive pairing comparison method, the presentation strategy is dynamically adjusted, the response delay is recorded, the psychological dimension vector of the selected music is weighted and aggregated, and a structured psychological portrait containing continuous value coordinates and clinical labels is decoded and generated. The psychological portrait and the consultant style vector are mixed and matched in a unified feature space, the cosine similarity and the Euclidean distance are combined to analyze the emotional resonance and the feature complementarity, the recommendation list is output after being filtered by the clinical knowledge weighting and the hard rule. The application can non-verbally capture the real-time and deep psychological state of the visitor through music preference, construct a multi-dimensional psychological vector, realize high-fitting-degree matching with the consultant, and improve the matching accuracy and the first consultation success rate.

The present application provides a radiology report generation method fusing clinical semantic modulation and hyperbolic prototype classification, which comprises: acquiring chest X-ray images and their associated clinical context knowledge, extracting visual features of the images using a visual encoder, extracting clinical semantic embedding using a medical language encoder, and retrieving relevant report features from a reference report database; constructing and utilizing a clinical semantic modulation module to generate modulated visual representation; constructing and utilizing a hyperbolic prototype classification module to generate diagnosis awareness prompts; inputting the modulated visual features and diagnosis awareness prompts into a decoder to complete the autoregressive generation of the radiology report. The present application can fully utilize the cross-modal fusion of clinical knowledge and visual features, and utilize the exponential expansion embedding capacity of hyperbolic space to improve the disease detection ability under the condition of class imbalance, and improve the clinical accuracy of radiology report generation.

The invention relates to the field of biomedical engineering technology and information processing, and discloses a trend prediction method and system based on multi-physiological signal fusion, a terminal and a storage medium, and the method comprises the steps: obtaining a venous pressure analog signal collected by a sensor or a radar, and carrying out the automatic calibration and digital processing of the venous pressure analog signal, obtaining central venous pressure data; processing the central venous pressure data based on a waveform feature automatic deconstruction algorithm to obtain hemodynamic feature parameters; and predicting the hemodynamic characteristic parameters according to a preset clinical knowledge rule to obtain clinical decision prompt information. According to the central venous pressure monitoring system and method, intelligent analysis and fusion prediction are conducted on the continuously-collected venous pressure signals, hierarchical clinical decision prompt information is obtained, and the automation, continuity and clinical decision support capacity of central venous pressure monitoring are greatly improved.

The present application relates to the technical field of medical data processing, and particularly relates to a pancreatic cystic lesion data processing method and system.In the present application, when encoding the multi-classification variable, the clinical knowledge is directly injected into the data features through the quantifiable risk progression matrix based on external evidence and the hierarchical risk weight, which is equivalent to providing a learning guide for the artificial intelligence model, so that the model does not need to start from scratch, thereby accelerating the convergence and improving the prediction accuracy; meanwhile, the encoding method provided by the present application has significantly different numerical characteristics, and such differences can be more effectively captured by the model, especially when dealing with highly unbalanced or highly different risk categories, the sensitivity of the model to high-risk categories can be significantly improved.

This invention discloses a method and system for monitoring and assessing neonatal vital signs based on multimodal information fusion, belonging to the field of vital sign monitoring technology. The method includes acquiring multimodal neonatal vital sign data, preprocessing the data to obtain multimodal feature data, identifying key factors affecting changes in neonatal health status, using a health status prediction model to predict future health changes and obtain health trend forecasts, assessing these trends, and providing health status response strategies and risk management recommendations based on the assessment results and in conjunction with a clinical knowledge base and historical cases. This invention can accurately predict future health changes and identify disease progression trends in advance, thereby providing nursing staff with timely warnings and intervention suggestions to ensure more effective protection of neonatal health.

The application relates to the technical field of medical diagnosis and artificial intelligence, and discloses a man-machine knowledge interaction type disease subtype diagnosis system, which comprises the following modules: a data acquisition and preprocessing module, which is used for acquiring multi-modal data of a to-be-diagnosed object and performing preprocessing, and outputs multi-modal fusion features; a clinical knowledge base module, which is used for storing a structured clinical knowledge graph; a man-machine knowledge interaction module, which is used for providing an interactive interface to receive input of a clinical expert, and quantifying the input into mathematical constraints that can be analyzed by a model; and a double-drive diagnosis model module, which injects the structured knowledge in the clinical knowledge base module into a neural network, performs fusion of the multi-modal fusion features under the guidance of the knowledge, constructs a patient-feature heterogeneous graph, mines potential knowledge from the multi-modal data, and generates an interpretable diagnosis result of a disease subtype. The application realizes high-precision and low-training-cost diagnosis of a disease subtype, and is suitable for accurate diagnosis of subtypes of non-infectious chronic diseases.

This invention discloses a privacy-preserving cloud-edge collaborative learning model for uterine ultrasound image analysis, belonging to the field of medical image processing technology. It constructs a dataset and divides it into cloud-based public data and edge-based private data. Employing a collaborative learning strategy of "cloud pre-training + edge fine-tuning," a semantically enhanced visual-language model is built in the cloud, using a clinical knowledge graph to construct a semantic similarity alignment mechanism for pre-training. At the edge, each client performs federated fine-tuning based on private data, using semantic matching loss to constrain local updates and resist model drift caused by non-independent and identically distributed data. Simultaneously, a differential privacy mechanism is introduced in the local model update, using gradient pruning and noise injection to prevent privacy leakage. In the context of strict data privacy requirements for consumer electronic devices, this invention effectively solves the problems of data silos and limited resources, achieving high-precision image processing comparable to centralized training while ensuring data privacy.

The present application relates to the technical field of intelligent medical treatment and health management, in particular to an intelligent dynamic adaptive lung transplantation postoperative rehabilitation management platform and method. It comprises a multi-source data sensing and fusion module, a dynamic risk assessment and decision module, a personalized intervention execution and feedback module, and a closed-loop learning optimization module. The platform generates panoramic state data by collecting multi-modal heterogeneous data of patients; performs real-time risk analysis using a first artificial intelligence model, outputs and predicts complications; predicts rehabilitation needs through a second artificial intelligence model; generates dynamically adaptive rehabilitation intervention instructions in combination with a clinical knowledge base; executes and collects feedback data through a user terminal; and finally optimizes model parameters in a closed loop using feedback data. The present application realizes intelligent, dynamic personalized and continuous self-optimization of lung transplantation postoperative rehabilitation management.