30 results about "Guideline" patented technology

The invention discloses an intelligent medical image diagnosis system and method based on hierarchical cross-modal conversion and dynamic feature tracking. The system adopts three-step cross-modal conversion: a first-layer small model for converting user questions to realize medical ontology matching; the second-layer multi-modal model extracts image features, and outputs text states such as JSON data with focus coordinates, density and other features; and the third-layer large model fuses the medical history and the image features to generate diagnosis suggestions, and credibility verification is carried out. A dynamic focus tracking engine is introduced, a focus evolution rule of multiple scanning is analyzed through a convolutional network, and an optical flow field is adopted to compensate artifacts. The system also integrates a multi-expert voting mechanism to simulate a clinical consultation process, and outputs consensus diagnosis and objection viewpoints. A hierarchical routing algorithm is designed for emergency treatment scenes, so that the recognition response time of emergencies such as pneumothorax is shortened. Further, the system automatically generates a full chain of evidence report that conforms to medical regulations, including a model version, a guide reference, and a data hash value.

The invention relates to a medical diagnosis method and system based on multi-modal retrieval enhancement and guide guidance. The method comprises the steps that text information including reports and / or electronic health records and medical image information are obtained; encoding the medical image information and the text information by using an image encoder and a text encoder respectively to obtain visual features and text features; respectively utilizing a guide branch decoder and a label branch decoder, taking diagnosis guide features and disease type labels of samples in the training stage as queries of a Transform structure, taking splicing features obtained by splicing text features and visual features as keys and values, and decoding to obtain first prediction probability distribution and second prediction probability distribution of disease types, so as to obtain first prediction probability distribution and second prediction probability distribution of the disease types; and a final disease prediction result is obtained. According to the method, disease specificity knowledge is dynamically retrieved based on a multi-source medical knowledge base, redundancy and noise are removed through a large language model, a standardized and structured diagnosis guide is generated, and explicit guidance of the knowledge is achieved.

This invention discloses a knowledge graph-based intelligent question-and-answer method for audit guidance, relating to the field of digital auditing. Through knowledge graph framework design and ETL data warehouse technology, this invention extracts, cleans, and transforms audit business data relevant to business environment optimization audits, achieving the fusion of various business data to provide data support for intelligent question-and-answer. By constructing an intelligent question-and-answer system, and designing a multi-task-oriented approach based on real-world audit scenarios, it utilizes word segmentation, matching, and query modules to achieve knowledge graph-based intelligent question-and-answer for business environment optimization audit guidance. This reduces the workload of the audit process, freeing auditors from tedious and repetitive tasks, allowing them to focus more on risk identification, problem analysis, and root cause analysis, effectively improving audit efficiency and quality.

The invention relates to the technical field of medical data processing, in particular to a VTE intelligent monitoring system supporting a multi-role demand, and provides the following scheme: a doctor role end constructs an evidence hypergraph based on multi-source clinical data, generates an evidence association vector through partial sequence conflict lattice merging, and stores the evidence association vector into a database; and searching in the guide version dictionary tree to obtain a current effective node, and outputting prevention and treatment suggestions and version pointing information to form a traceable evidence chain. The nursing role end receives and analyzes the tracing chain, screens matched prevention and treatment schemes from an intervention measure set in combination with real-time monitoring data, generates a nursing execution instruction and performs dynamic adjustment and feedback according to an intervention effect, so that closed-loop cooperation of risk assessment, intervention execution and result certification among multiple roles is realized, and the risk assessment efficiency is improved. And the timeliness, the traceability and the execution consistency of the prevention and treatment suggestions are ensured.

The application provides a clinical conclusion generation method and device, comprising: obtaining a clinical query request; generating a candidate clinical assertion list based on the clinical query request; for each candidate clinical assertion in the candidate clinical assertion list, simultaneously initiating an independent retrieval request to a preset clinical guideline library, a preset evidence-based literature library and a preset patient medical record library to obtain an evidence triple retrieval result corresponding to each candidate clinical assertion; verifying the integrity of the evidence triple corresponding to each candidate clinical assertion, and if the evidence triple of the candidate clinical assertion is complete, generating a corresponding clinical conclusion based on the complete evidence triple; the application realizes the binding of the clinical conclusion and the multi-source evidence, effectively solves the problems of soft coupling, single evidence source and lack of evidence integrity verification in the prior art retrieval and generation, reduces the illusion risk of the medical large model, and can meet the actual application requirements of clinical decision support.

The application discloses an online medical intelligent doctor guiding system based on text graph embedding and belongs to the technical field of medical doctor guiding. Through fine-grained medical entity recognition and ambiguity resolution on online medical consultation texts, fine-grained entities can be accurately recognized, and the problem of fine semantic granularity can be solved. Through matching of a medical dictionary and context, the ambiguity generated by the entity can be effectively eliminated. Through a dynamic updating mechanism, the latest medical knowledge can be ensured to be incorporated into the graph, and the knowledge can be prevented from being outdated. From text preprocessing to graph construction, a complete link is formed, which can provide a high-quality knowledge base for subsequent graph embedding and doctor guiding reasoning. The entity vector obtained through processing contains graph structure, deep semantics and clinical logic, and can effectively solve the defects of single mode of traditional embedding. Through a constraint loss function, the vector can be ensured to conform to the path rules of authoritative clinical guidelines, clinical logic consistency can be realized, and vectors that violate medical common sense can be avoided.

We provide the system. [Solution] A means of learning necessary items and formats by analyzing existing documents, A means of providing learned templates when creating a new document, A means for comparing documents in multiple different formats and detecting differences, A means of generating annotations based on legal requirements and guidelines and suggesting their appropriate location within a document, An information processing system that includes means for verifying the legal requirements of generated documents and providing real-time warnings.

The application relates to the technical field of medical data processing, and particularly relates to a VTE intelligent monitoring system supporting multi-role requirements. The following scheme is provided: a doctor role end constructs an evidence hypergraph based on multi-source clinical data, generates an evidence correlation vector through partial order conflict grid merging, searches in a guideline version dictionary tree to obtain a current effective node, outputs prevention and treatment suggestions and version pointing information to form a traceable evidence chain. A nursing role end receives and analyzes the traceable chain, screens matched prevention and treatment schemes from an intervention measure set in combination with real-time monitoring data, generates nursing execution instructions and dynamically adjusts and feeds back according to intervention effects, and realizes closed-loop cooperation of risk assessment, intervention execution and result back-checking among the multi-roles, so that the timeliness, traceability and execution consistency of the prevention and treatment suggestions are guaranteed.

The application provides a chronic disease personalized diagnosis and treatment scheme recommendation method and system based on multi-source data fusion and an AI model, a medium, the method comprising: acquiring a personalized health portrait of a patient, and matching continuous health trajectory data of the patient; performing inference analysis on the continuous health trajectory data of the patient according to a preset decision recommendation model, and outputting a first recommended scheme and a first confidence score; outputting a second recommended scheme and a second confidence score according to an inference engine of a clinical guideline rule; selecting a recommended scheme with a high score as a leading scheme, integrating a recommended scheme with a low score as an intervention suggestion to the leading scheme to obtain a final treatment scheme; if the first confidence score and the second confidence score are both less than a preset confidence threshold, triggering manual review; and through analysis of the continuous health trajectory data of the patient, different recommended schemes are matched, and confidence evaluation is performed on the recommended schemes, thereby improving diagnosis and treatment effects.

The invention discloses a medical record time axis-based respiratory disease interactive processing analysis method and system, which can construct a real medical record-based respiratory system disease interactive intelligent auxiliary diagnosis and treatment system and improve the accuracy and practicability of respiratory system disease auxiliary diagnosis and treatment. The method comprises the following steps: (1) merging and sorting electronic medical record data of a patient into a text format for storing key-value pairs; (2) arranging the medical records into a timeline-based core information JSON file by utilizing a large language model; (3) classifying the data into a vector knowledge base by adopting a hierarchical processing architecture; (4) querying a timeline knowledge base and returning a matching result, and performing a first round of single case summarization; after summarizing, carrying out a second round of thinking and multi-case experience summarization; a return result serves as a prompt word of the final question-answer; (5) collecting guide evidences and transmitting into a large model for summarization and analysis; and (6) submitting results of multi-case summarization and guide analysis to a large language model for final question and answer, and outputting previous case summarization and experience summarization, guide recommendation summarization and comprehensive recommendation suggestions.

We provide the system. [Solution] Information processing means for receiving information about activities and daily life obtained from users, An analytical means for analyzing information related to the aforementioned activities and lifestyle and evaluating the user's condition, Based on the aforementioned evaluation, a guideline generation means for providing users with appropriate exercise and dietary guidelines, A means of communication for conveying the aforementioned guidelines to users, An adjustment means for adaptively adjusting the guidelines based on responses to the guidelines obtained from users, A means of analyzing health data across the entire city and providing health promotion guidelines to individual users based on the results, A system that includes this.

The present invention relates to a method and system for automatically incorporating conversation session content into project guidelines. The method according to the present invention comprises the steps of: specifying a target project among a plurality of projects; obtaining conversation content from a conversation session that does not belong to the target project; extracting guideline candidate information from the conversation content using a learned language model; determining whether there is duplication or conflict by comparing the extracted guideline candidate information with existing project guidelines; generating project guideline data based on the determination result and adding or updating it to existing project guidelines; and applying the updated guidelines to subsequent conversation sessions within the target project. According to the present invention, useful information formed from conversations that do not belong to a specific project can be automatically, accurately, and safely transferred to separate project guidelines, thereby reducing the manual workload required for project guideline management and maintaining the consistency and alignment of the guidelines.

Provided herein are computer implemented methods and systems for assessing long-term quality of management of patients in health care facilities. In particular, the methods and systems disclosed herein allow calculating guideline(s) adherence score, based on a calculated compliance score of a plurality of procedures of the guidelines(s), to thereby facilitate assessment of the quality of the long-term treatment of the patients.

The invention discloses an AI collaborative logic auditing multi-dimensional risk scoring system and method for tuberculosis, and the system integrates an authoritative diagnosis and treatment guide and an artificial intelligence collaborative reasoning technology, and constructs a structured weight scoring matrix and multi-model logic tracking technology dual-core architecture. Through structured scoring of five-dimension indexes and thinking chain auditing of a Gemini 3 series large model, logic contradiction recognition, offset correction and fusion risk score calculation of clinical data are realized, and meanwhile, visual decision logic, agreement processing suggestions and scientific research data closed-loop management functions are generated. According to the method, an expert-level analysis report can be quickly output, the screening sensitivity and the diagnosis and treatment homogenization level are remarkably improved, and the method is suitable for tuberculosis early screening, clinical decision assistance and scientific research data mining of primary and specialized medical institutions and has extremely high clinical application value and scientific research potential.

The invention relates to a breast cancer whole-course intelligent follow-up visit management system and method based on an evidence-based guide. The system comprises a patient file module used for acquiring an electronic health record of a patient and preprocessing the electronic health record to obtain a patient health file; the evidence-based guide module is used for performing knowledge acquisition on an evidence-based guide text based on a text extraction technology to obtain an evidence-based guide follow-up visit template; the follow-up visit personalization module is used for generating a personalized follow-up visit plan according to the patient health archive by adopting executable rule reasoning based on the evidence-based guide follow-up visit template; the interaction module is used for generating a patient interaction task and a corresponding pushing instruction according to the personalized follow-up visit plan; and the multi-modal risk assessment module is used for updating the follow-up visit health data to the patient health archive and performing risk assessment according to the updated patient health archive to obtain a multi-dimensional concurrent risk vector. By adopting the method, whole-course, personalized and intelligent follow-up visit management can be carried out on the breast cancer patient.

The invention discloses a stoma state intelligent evaluation method and related equipment. The method comprises the following steps: inputting a stoma key area image into a visual Transform multi-label classification model subjected to medical data fine adjustment, and outputting a label set for representing a stoma state and corresponding confidence; and inputting the tag set and the confidence coefficient thereof into a medical knowledge base enhanced risk decision engine, and generating a structured risk assessment result based on a guide entry retrieval result associated with the abnormal tag and a preset grading processing rule, the structured risk assessment result comprises a risk level and a disposal path corresponding to the risk level; and inputting the structured risk assessment result, the tag set, the confidence of the tag set and at least one piece of basic information of the target patient into a medical big language model to generate an inquiry grading prompt. The problems that a traditional management mode highly depends on self-judgment of a patient, accuracy is low, and slight abnormity is prone to being neglected or misjudged can be solved.

A stroke recurrence risk assessment and personalized management method and system, the system comprises an application server, the application server comprises a database module, a recurrence risk dynamic prediction model module and a personalized management strategy generation module. The recurrence risk dynamic prediction model module is used to determine a long-term static risk index reflecting the inherent risk of the patient based on the clinical data stored in the database module, determine a short-term dynamic risk adjustment index reflecting the instantaneous risk contribution based on the dynamic feature sequence in the self-management data; by executing a risk coupling algorithm, the long-term static risk index and the short-term dynamic risk adjustment index are fused and calculated by using a weight coefficient to obtain a total risk index; the personalized management strategy generation module is used to convert the total risk index into a query vector, retrieve a matched guideline segment in a stroke management knowledge base; input the guideline segment as a constraint condition into a large language reasoning model to generate a personalized intervention scheme.

This invention discloses a method and system for cross-guideline recommendation consistency detection based on structured features. First, it collects clinical practice guideline texts from multiple sources, parses and processes the recommendations within these texts to generate structured clinical semantic data. Then, based on this structured clinical semantic data, recommendations from different sources are paired to construct recommendation pairs, and a structured feature representation is generated for each pair, resulting in a set of candidate recommendation pairs with potential relationships. Next, using these recommendation pairs as consistency analysis objects, consistency inference analysis is performed under the constraints of structured semantic information. The results of the consistency relationship determination between recommendations and their corresponding analytical basis are output, along with a credibility assessment and rollback control of the output. This invention provides interpretable and controllable intelligent support for clinical guideline knowledge integration, guideline version comparison, evidence conflict identification, and intelligent decision support systems.

This invention relates to the fields of artificial intelligence and natural language processing, and particularly to a method for filtering fake entities based on guide learning and dual-view gating retrieval. The method includes constructing an example library, generating guide rules, and building a guide library; sampling and correcting training prediction results, generating new guide rules for unsuccessful corrections, scoring each guide rule, and updating the guide library; constructing dual views of entities in the test prediction results and entities in the example library, determining the density reliability corresponding to the dual views, obtaining a fusion similarity through gating weights, and obtaining retrieval examples; filtering fake entities in the test prediction results based on the updated guide library and the retrieval examples to obtain post-processed test prediction results. This invention also relates to a fake entity filtering system, apparatus, device, medium, and program product based on guide learning and dual-view gating retrieval.

The application discloses a family health management system based on guideline knowledge base reasoning driving, and particularly relates to the field of health service and management information processing for family scenes, and is used for solving the problem that the reminder and management action are dislocated due to the difficulty in stable alignment of the guideline time condition under the shift and night shift work-rest conditions; the sleeping time and the getting-up time are collected through a user terminal, and the sleep midpoint is obtained, the work-rest reference time is generated in a data collection and storage module, the guideline clauses with time conditions are extracted from a health knowledge base by an intelligent agent module, and are converted into clause time windows relative to the work-rest reference time to generate a relative time task table, an event sequence is recorded by a task and reminder module, the sleep segment intersection and the phase deviation minute are calculated by the intelligent agent module, and a rearrangement coefficient is generated through a comprehensive analyzer, a treatment decision is formed according to the rearrangement coefficient to trigger the minimum clarification interaction or update the work-rest reference time and synchronously update the relative time task table.

Techniques for evaluating adherence to clinical guidelines using large language models (LLMs) are described. A computer-implemented method comprises extracting information from clinical guideline data describing a clinical guideline for providing medical care to patients using a LLM generating a prompt decision tree (PDT) representative of the clinical guideline using the information, and employing the PDT to perform a question and answering session for a patient, comprising sequentially selecting prompt questions from the PDT based on respective answers to immediately preceding prompt questions and sequentially applying each of the prompt questions as input to the LLM or another LLM to extract the respective answers for each of the prompt questions from patient data for the patient. The method further comprises determining adherence information regarding whether and to what degree the patient received the medical care in accordance with the clinical guideline based on the prompt questions and the respective answers.

We provide the system. [Solution] A means of learning from past information data and generating guidance guidelines tailored to the organization and position, A means for receiving information settings entered by the user and automatically correcting them based on the aforementioned guidelines, A means for receiving progress information toward a goal, analyzing the progress status, and generating warnings, A means of calculating evaluation feedback and providing that feedback to the user, A means of presenting short-term goals and improvement measures based on progress analysis, A means of jointly managing goals set individually by residents and administrative departments, and providing integrated information, A system that includes this.

The invention discloses a medical insurance policy and clinical guideline interpretation system based on natural language processing, and relates to the technical field of medical insurance policy interpretation and clinical guideline application, and the system comprises a double-source knowledge graph module which collects and converts data, and constructs a dynamically updated integrated knowledge graph; the bidirectional conflict classification module detects conflicts, classifies the conflicts and outputs a report; the conflict self-healing scheme module generates compliance substitution and other schemes; the multi-scene reasoning adaptation module analyzes a user demand and generates a customized decision; the interpretable interaction optimization module visually displays the basis and collects and feeds back the optimization system; according to the method, the medical insurance and clinical DRG integrated knowledge graph is constructed, accurate detection is performed, medical insurance and clinical conflicts are classified, a self-healing scheme is given, various user scene requirements are analyzed, a customized decision result and a visual display basis are generated, dynamic updating and optimization are performed, experience and efficiency are improved, compliance and efficient resource utilization are promoted, and medical insurance payment reform is supported.