37 results about "Clinical decision support system" patented technology

The present invention relates to a cognitive computing-assisted clinical decision support system designed to enable personalized neurological rehabilitation. The system acquires structured user data across clinical, anatomical, radiological, etiological, pathological, and rehabilitation domains to create individualized profiles. These profiles are mapped against a repository of historical cases using analog matching and similarity scoring to generate stratified, evidence-based rehabilitation recommendations. Real-time monitoring of rehabilitation progress is performed using global recovery and function outcome indicators, allowing for dynamic adjustment of treatment plans. Clinician intervention modules ensure safety, interpretability, and context-aware customization. The system incorporates a continuous feedback mechanism to refine future predictions and recommendations, making it increasingly adaptive over time. The invention improves rehabilitation outcome prediction accuracy, reduces recovery variability, and optimizes functional outcomes by transforming static rehabilitation models into intelligent, responsive, and personalized care pathways.

The invention provides a medical information retrieval enhancement method and device based on a large model and related equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: in response to a medical information query request, executing double-path joint retrieval of keywords and semantics in a pre-constructed medical knowledge base to obtain a candidate data set containing at least one medical information query result, the medical knowledge base is a database which analyzes the multi-modal medical data based on a multi-modal medical data deep analysis large model and is constructed according to the analyzed medical text data; and adopting a plurality of sorting tools to resort the medical information query results in the candidate data set, and performing fusion processing on a plurality of resorting results obtained by resorting to obtain a medical information query result after retrieval enhancement. According to the method and the device, the precision improvement and response efficiency optimization of medical knowledge retrieval can be realized, a high-credibility knowledge enhancement service is provided for a clinical decision support system, and the method and the device have important application value.

The invention discloses an interpretable clinical decision support system based on label generation and a knowledge graph. The method comprises the following steps: based on a breast cancer domain knowledge enhanced version Qwen-BrCaAdapt of a general large language model Qwen, analyzing an unstructured medical record text of a patient, and generating a structured result containing tags, values, evidences and explanations; calculating a reasoning label through a path matching engine by utilizing an editable structured path rule table, and matching a candidate treatment scheme according to the reasoning label; and taking the matched treatment scheme as a central node, calling a medical knowledge graph to bind entity information including clinical evidence, recommendation levels, medical insurance information, medication risks, usage and dosage, and generating a traceable JSON structure and a visual report. The method has the beneficial effects that the accuracy and efficiency of tag generation in the breast cancer field are improved, the rule maintenance cost is reduced, the interpretability and traceability of a clinical decision scheme are enhanced, and the acceptability of a doctor to a recommendation result is improved.

The invention provides an AI doctor assistant agent medical information processing method based on voice interaction and large model driving, and relates to the technical field of intelligent medical treatment, and the method comprises the steps: obtaining the audio information of a doctor-patient conversation and a voice instruction through a voice collection module, and converting the audio information into a text in real time based on a real-time voice conversion module, the intelligent transfer service module is used for carrying out intention classification on texts and distinguishing doctor-patient conversations and voice instructions, the AI medical big model intelligent agent service module is used for generating structured medical information for the doctor-patient conversations, the structured medical information is automatically recorded into the electronic medical record system, and the voice instructions are automatically recorded into the electronic medical record system. And analyzing and executing corresponding desktop operation through the instruction response module and the desktop analysis large model service module. The method can consider performance, cost and data security, improves the accuracy and credibility of medical information, is suitable for electronic medical record input, clinical decision support, system operation automation and other actual scenes, and can help medical institutions improve the diagnosis and treatment efficiency and quality.

The application discloses a similar case recommendation method and system, belongs to the technical field of clinical decision support system, and aims to solve the technical problem that the implementation difficulty of similar case recommendation is extremely great and the feasibility is not high by using a deep learning algorithm and a natural language processing technology.The technical scheme is as follows:the method is specifically as follows: data preprocessing: extracting the symptom and diagnosis information of the case admission record electronic medical record; and processing the case into a standard symptom and standard diagnosis list, and extracting the treatment information of the case for storage in a dictionary to assist in subsequent acquisition of the similarity degree of the case; wherein, the treatment information comprises age and department; obtaining the symptom weight: based on the knowledge graph of the symptom and disease related knowledge, extracting the weight of the symptom in the disease diagnosis; obtaining the similarity degree of the case: according to the symptom and diagnosis list of the target case, and fusing the weight to obtain the similarity degree of other cases and the target case; similar case recommendation.

The invention discloses a clinical decision support system fusing structured knowledge and generative intelligence. A guide map generation module is used for converting an unstructured authoritative clinical guide into a machine-readable and executable structured knowledge map; the medical record information extraction module is used for processing an unstructured medical record original text written by a clinician and extracting a clinical event sequence with a timestamp from the unstructured medical record original text; the decision reasoning module is used for receiving the structured knowledge graph and the clinical event sequence and driving a large language model to perform multi-step logical reasoning under the guidance of the structured knowledge graph so as to plan a diagnosis and treatment path; and the interactive display module is used for displaying the diagnosis and treatment path and the decision basis corresponding to each decision node on the diagnosis and treatment path in a visual mode. According to the method, the unstructured medical record information and the structured guide knowledge can be deeply fused, and normative and highly personalized decision support is provided for clinicians.

The invention relates to the technical field of medical artificial intelligence, in particular to a one-question multi-certificate task-oriented special retrieval embedding method, which comprises the following steps of S1, constructing a one-question multi-certificate training data set: systematically collecting authoritative medical guide document data from a plurality of authoritative channels, and establishing a corresponding document meta-information index table based on the collected data; analyzing a document chapter structure by adopting an OCR (Optical Character Recognition) algorithm in combination with font characteristics, a serial number structure and paragraph indentation and line feed rules, and constructing a chapter tree; inputting each structured TXT guide into a GPT-4 or other language model, adopting a customized prompt word Prompt to guide the structured TXT guide to complete multiple rounds of question and answer generation, and forming structured question and answer pairs Qamp in a uniform form; structure A; an automatic sampling mechanism is established, each time N documents are processed, the method can be seamlessly connected with an existing RAG framework, and rapid deployment and iteration in scenes such as electronic medical records and clinical decision support systems are facilitated.

The invention relates to the technical field of anaesthesia machines, in particular to an anaesthesia machine control parameter optimization method and a clinical decision support system, and the method comprises the steps: setting a safety interval of each control parameter of an anaesthesia machine; observation parameters and action space are determined, a reward function is designed, and a reinforcement learning model is constructed and trained; inputting observation parameters at each moment in the operation of the patient into the strategy network of the trained reinforcement learning model to obtain probability distribution of control parameters at each moment, and determining the value of each control parameter according to the safety interval; and sending the obtained values of the control parameters to a microcontroller of the anaesthesia machine so as to complete updating of the control parameters. By automatically optimizing the control parameters of the anesthesia machine, the workload of an anesthetist is reduced, and the physiological parameters of a patient are maintained within an expected range.

The present disclosure provides an AI-based clinical decision support system comprising an input module configured to receive clinical information comprising brain scan data, an analysis module configured to parse the clinical information using statistical measures from functional connectivity analysis with counterfactual explanations to identify brain connectivity patterns associated with brain disorders, and an output module configured to present a recommended diagnosis and explanation comprising attribution information identifying connectivity features contributing to the diagnosis. The brain scan data comprises functional magnetic resonance imaging, electroencephalography, and magnetoencephalography data. The statistical measures comprise functional connectivity analysis and graph theory metrics including degree metrics, betweenness centrality measures, and clustering coefficients. The analysis module comprises a functional connectivity engine configured to process brain scan data and generate connectivity features, a feature bank configured to store connectivity features, and modeling backbones configured to analyze connectivity features using machine learning techniques.

The invention discloses a clinical decision support system for treating pelvic adhesive infertility through combination of traditional Chinese medicine and western medicine, relates to the technical field of medical health and artificial intelligence crossing, and assists doctors in formulating personalized schemes, covering screening, diagnosis, scheme generation, curative effect evaluation, adaptation to gynecology of hospitals at the second level and above, acquisition of western medicine images, laboratory and gynecology data and diagnosis and treatment of pelvic adhesive infertility. Performing preprocessing filling missing values, marking abnormal values, western medicine disease differentiation, traditional Chinese medicine syndrome differentiation and correlation to form a combined diagnosis report, and marking a basis; matching traditional Chinese and western medicine schemes, and combining individual difference adjustment to generate a scheme containing a period and review time; and review data grading evaluation is carried out, reasons of invalid patients are analyzed, and a scheme is optimized. The system integrates traditional Chinese and western medicine diagnosis and treatment, improves diagnosis accuracy and scheme suitability, identifies drug interaction in advance to guarantee medication safety, dynamically evaluates the curative effect and adjusts the scheme, realizes full-period management, provides reference for doctors, adapts to different medical scenes, and improves the treatment effect.

Embodiments of the present disclosure pertain to methods and clinical decision support systems for distinguishing between a first and a second condition in a subject. Additional embodiments of the present disclosure pertain to computer-implemented methods of distinguishing between the first and the second condition in a subject. Further embodiments of the present disclosure pertain to computing devices that are operable to distinguish between the first and the second condition in a subject.

The invention discloses a primary osteoporosis traditional Chinese medicine clinical decision support system, and relates to the field of traditional Chinese medicine artificial intelligence, and the system comprises a data processing module which is used for carrying out the term standardization processing and syndrome element extraction of original traditional Chinese medicine literature data, and constructing a structured traditional Chinese medicine syndrome and treatment database; the dialectical reasoning module is constructed based on a machine learning model and is used for outputting a traditional Chinese medicine syndrome element diagnosis result according to the input four diagnosis information; and the prescription recommendation module is constructed based on a knowledge graph and is used for recommending corresponding treatment methods and rules and traditional Chinese medicine prescriptions according to the traditional Chinese medicine syndrome element diagnosis results and / or the specific clinical symptoms. According to the scheme, objectivity and consistency of syndrome element differentiation are remarkably enhanced, the defect that a traditional method is insufficient in composite syndrome type processing capacity is overcome, and the self-adaptive capacity of prescription recommendation along with dynamic evolution of clinical practice is achieved.

This invention discloses a method and system for predicting the risk of malignant cerebral edema after mechanical thrombectomy in ischemic stroke, aiming to address the pain points of existing prediction tools, such as insufficient accuracy, lack of clinical interpretability, and difficulty in directly supporting decision-making. The core solution involves: stably extracting key predictive variables from multi-source clinical and laboratory data through a multi-algorithm consensus feature selection mechanism (LASSO, Boruta algorithm); employing eight machine learning algorithms to select the best high-performance prediction model, and using repeated cross-validation and grid search for robust optimization; innovatively and deeply integrating the SHAP interpretability framework to achieve global, local, and individualized interpretation of the model predictions; and finally deploying it as an integrated clinical decision support system, outputting a visual report that combines risk probability, risk classification, and decision-making basis. This method significantly improves the early risk identification capability of malignant cerebral edema, and the model exhibits excellent discrimination and calibration.

The present invention is characterized in that it comprises: an initial evaluation unit that calculates the severity and risk of an infectious disease using patient information and determines a treatment type among home treatment, inpatient treatment, and ICU (Intensive Care Unit) by inputting the calculated severity and risk of the infectious disease into an artificial intelligence model or comparing it with preset criteria; a treatment guide unit that determines monitoring guidelines and treatment guidelines for a patient determined to receive home treatment based on patient information, the calculated severity and risk of the infectious disease, and the results of a medical history interview; and a monitoring unit that performs monitoring of the patient receiving home treatment according to the monitoring guidelines determined by the treatment guide unit.

Techniques for evaluating user interactions with a clinical decision support (CDS) system are disclosed. User interaction data is received associated with a user response to an advice item generated by the CDS system. The user interaction data is evaluated, such as to determine a user trust level associated with the advice item and / or the CDS system. A corrective action is generated based on the evaluation of the user interaction data. In some examples, the disclosed techniques identify and correct for user under-trust or over-trust in artificial intelligence (Al)-based CDS systems.

The invention discloses a multi-dimensional prognosis risk assessment method for hematopoietic stem cell transplantation, a clinical decision support system and a storage medium. The multi-dimensional prognostic risk assessment method for hematopoietic stem cell transplantation comprises the following steps: acquiring test data including microorganism data, immune data, medication data and time synchronization data; and according to the test data, carrying out multi-dimensional prognostic risk assessment solution through a pre-trained multi-dimensional prognostic risk assessment model to obtain multi-dimensional prognostic risk assessment. The invention discloses a multi-dimensional prognosis risk assessment method for hematopoietic stem cell transplantation, a clinical decision support system and a storage medium. The hematopoietic stem cell transplantation patient prognosis risk assessment or individualized intervention guidance can be realized by integrating multi-source heterogeneous medical data and adopting an intelligent prediction method of dynamic feature screening, time sequence effect modeling and interpretable output.

A clinical decision support system for retinal diseases processes OCT retinal scan images to enhance certain aspects of speckle, which has been found to include relevant information that can be used to enhance the diagnosis and classification of the severity and progression of any disease found in the retina scan image. A copy of the original OCT retinal scan image is processed using a shifted window transformer block to enhance the relevant speckle information, and combine it with the original image, which is then evaluated by a trained system to classify the retinal features, including the speckle.

The present application belongs to the field of pneumonia prognosis prediction, and in particular to a severe pneumonia post-pulmonary fibrosis prognosis prediction method and system based on multi-modal artificial intelligence. The present application constructs a database for storing clinical medical record texts, laboratory examination results and image CT data. Data acquisition is realized by connecting with a hospital information system, data preprocessing is carried out by using natural language processing, standardization processing and feature extraction, important features are selected after feature integration, a model is constructed and trained by selecting a suitable algorithm, and the model is verified and evaluated. Finally, the prediction results are integrated into a clinical decision support system, a personalized prediction report is generated and associated with clinical data, and a friendly front-end interface is provided for doctors to query, thereby providing a more accurate, efficient and clinically valuable solution for severe pneumonia post-pulmonary fibrosis prognosis prediction.

The present invention relates to a clinical decision support system comprising a processing unit in communication with a memory. The processing unit is configured to receive and process clinical data associated with a patient, which comprises medical records, biometric or physiological data, and / or currently prescribed medication information. The system computes personalized target lipid profile ranges based on the clinical data and medical guidelines stored in the memory. Preferably, the system receives pharmacogenetic analysis data and measured lipid profile values from patient blood tests. The processing unit compares the measured lipid values with the personalized target ranges and, if deviations are found, computes a list of potential medication treatments. This list is sorted based on the estimated effects of each treatment on the lipid profile values, the different between measured and objective lipid profile values, on the clinical data and / or on the pharmacogenetic analysis. The system further outputs data related to the personalized lipid ranges, the comparison of measured values, and / or the suggested medication treatments.

Systems, methods and computer-readable media are provided for facilitating clinical decision support and managing patient population health by health-related entities including caregivers, health care administrators, insurance providers, and patients. Embodiments of the invention provide decision support services including providing timely contextual patient information including condition risks, risk factors and relevant clinical information that are dynamically updatable; imputing missing patient information; dynamically generating assessments for obtaining additional patient information based on context; data-mining and information discovery services including discovering new knowledge; identifying or evaluating treatments or sequences of patient care actions and behaviors, and providing recommendations based on this; intelligent, adaptive decision support services including identifying critical junctures in patient care processes, such as points in time that warrant close attention by caregivers; near-real time querying across diverse health records data sources, which may use diverse clinical nomenclatures and ontologies; improved natural language processing services; and other decision support services.

The application discloses an intelligent clinical decision support system based on a knowledge graph and voice interaction and an implementation method thereof.The system comprises a voice interaction terminal, a knowledge graph construction module, a natural language understanding module, a dialogue management module, a graph query and reasoning module and a clinical knowledge base.The application converts the dialogue content of doctors and patients collected through voice into structured medical entities and intentions, and generates a diagnosis prompt, an examination suggestion or a drug safety reminder based on path reasoning and probability calculation of a large-scale medical knowledge graph.The system supports active questioning type interaction, makes up for missing key information and provides a clinical auxiliary suggestion with a confidence level.The application can improve the clinical decision efficiency and accuracy, reduce medical errors and is especially suitable for voice interaction scenes such as ward rounds, emergency treatment and primary medical treatment.

The invention relates to the technical field of biology and information, and discloses an anti-infection clinical decision support system, which comprises the following modules: a various antibacterial drug characteristic module (1); an antibacterial drug pharmacokinetic module (2); a renal insufficiency dose adjustment module (3), wherein the renal insufficiency dose adjustment module (3) comprises a renal insufficiency dose adjustment-free drug module (31) and a creatinine clearance rate calculation module (32); a liver insufficiency dose adjustment module (4), wherein the liver insufficiency dose adjustment module (4) comprises a liver function impairment Child-Pugh grading module (41) and a liver insufficiency dose adjustment-free drug module (42); a national bacterial drug resistance statistics module (5); and a drug antibacterial spectrum query module (6). According to the anti-infection clinical decision support system, through cooperative operation of the six modules, all-around support is provided for clinical anti-infection diagnosis and treatment.

A clinical decision support system and method allows a user to display, review, and analyze health data. One or more algorithms can be used to analyze health data in order to produce a score. The score is presented graphically along with related examination parameters for review by a user. The criticality of examination parameters is also displayed graphically.

The application relates to the technical field of medical artificial intelligence and clinical decision support systems, and provides an acute abdominal disease diagnosis system and method based on feature mapping and dynamic game arbitration. The system extracts a standardized global abnormal feature vector by using a multi-modal perception and mapping module, independently reasons corresponding N different acute abdominal disease types by using a multi-agent parallel reasoning engine to obtain output states, and uses a conflict detection and arbitration agent to monitor the N output states, triggers a game arbitration mechanism when a diagnosis conflict exists, discriminates scores of the conflicting output states by using a threshold weighted feature discrimination matrix, and further determines a diagnosis result, effectively alleviates a logical conflict problem in multi-label classification, realizes "white box" and interpretability of a diagnosis process, simultaneously realizes a "gray" decision in line with clinical thinking, the diagnosis process is closer to uncertainty decision requirements of a real medical scene, and the diagnosis result credibility is improved.

The application discloses a kind of multi-agent high blood pressure clinical decision-making auxiliary system and method based on data driving, belong to medical artificial intelligence and clinical pharmacy cross field.Aiming at the low blood pressure control rate (11.0%) of 2.45 million high blood pressure patients in China, lack of precision medicine tool for primary doctors, adverse reactions caused by low blood pressure caused by drug are easily ignored and other clinical pain points, the application innovatively proposes "real world drug warning data→risk signal automatic identification→clinical decision-making rule conversion→multi-agent collaborative decision-making→clinical feedback closed loop" complete technical route.System core innovation includes: (1) drug warning signal three-level hierarchical automatic conversion engine, establish signal intensity quantization model, automatically generate red / orange / yellow three-level differential early warning rule;(2) patient characteristic driven dynamic threshold adjustment algorithm, according to age, combined disease, organ function and other risk factors, real-time calculation individualized early warning threshold;(3) five-agent decoupled pipeline architecture (A1 information structure→A2 similar case retrieval→A3 safety warning→A4 decision generation→A5 quality control), adopt rule engine and large language model dual-engine collaborative mechanism;(4) four-layer anti-illusion verification system, through hard rule verification, guideline compliance verification, LLM self-evaluation, literature reference authenticity verification to ensure output reliability;(5) clinical feedback driven continuous learning mechanism, construct "decision→application→follow-up→labeling→fine-tuning" data closed loop.This system fills the technical gap between drug warning and clinical decision support system.

The invention relates to a visual clinical decision support system based on EMRS data. The system comprises a data acquisition module used for acquiring vital sign data, inspection parameter data, image abstract data and parameter self-defined thresholds of a user; the feature extraction module is used for comprehensively analyzing features of the vital sign data, the inspection parameter data and the image abstract data to obtain a comprehensive feature vector; the feature analysis module is used for analyzing the influence of the vital sign data, the inspection parameter data and the image abstract data on the user based on the comprehensive feature vector to obtain a comprehensive risk vector; the report generation module is used for generating a visual clinical reference graph based on a preset historical diagnosis and treatment scheme library, the comprehensive risk vector, the comprehensive feature vector and a parameter self-defined threshold value; the historical diagnosis and treatment scheme library comprises treatment schemes, comprehensive risk vectors and vital sign data of historical patients. By adopting the system, the accuracy and timeliness of early warning of critical and severe cases can be improved.

Various methods and systems are provided for a longitudinal patient history timeline and predictive clinical decision support system. In one example, a computing device comprising a display screen displays a menu listing one or more electronic medical records (EMRs) of one or more patients, and additionally is configured to display a patient timeline graphical user interface (GUI) accessible from the menu while the one or more EMR systems are in an un-launched state. The patient timeline GUI displays patient data as longitudinal medical history event elements and includes elements representing predicted outcomes generated by one or more artificial intelligence (AI) algorithms based on the patient data and one or more activity items generated from the patient data. The event elements and the predicted outcome elements are selectable to launch respective pop-up windows with additional information relating to the selected element.

The invention discloses a Parkinson's disease patient subtype intelligent typing method based on machine learning, and the method comprises the steps: integrating the multi-dimensional data of a patient, including demographic information, motor and non-motor symptoms, iconography and biomarkers, and utilizing a technical means of combining unsupervised learning and supervised learning, and carrying out the subtype intelligent typing of the Parkinson's disease patient. The Parkinson's disease classification method has the advantages that fine layering of Parkinson's disease patients is achieved, the limitation problems of roughness and single dimension of a traditional classification method are solved, disease heterogeneity can be revealed more accurately, and a scientific basis is provided for formulating an individualized treatment strategy; the disease subtypes with different clinical features and prognosis differences are recognized through clustering analysis, then the supervised learning model is used for conducting rapid and accurate subtype classification on new patients, the classification result is integrated into a clinical decision support system, comprehensive and personalized patient management suggestions are provided for doctors, and the life quality of the patients is improved.

Various methods and systems are provided for a longitudinal patient history timeline and predictive clinical decision support system. In one example, a computing device including a display screen displays a menu listing one or more electronic medical records (EMRs) of one or more patients, and additionally is configured to display a patient timeline graphical user interface (GUI) accessible from the menu when one or more EMR systems are in an unlaunched state. A patient timeline GUI displays patient data as longitudinal medical history event elements and includes elements representing predictions generated by one or more artificial intelligence (AI) algorithms based on the patient data and one or more activity items generated from the patient data. The event element and the predictor element can be selected to initiate a respective pop-up window with additional information related to the selected element.

The embodiment of the invention relates to a blood coagulation analyzer, a fibrinogen analysis method and a clinical decision support system. The blood coagulation analyzer comprises a sample preparation part which is used for preparing a determination sample by using to-be-detected plasma from a to-be-detected blood sample and a detection reagent; the detection part is used for detecting the test sample; the controller is used for acquiring detection information representing reduction of fibrinogen in the to-be-detected plasma, and responding to the detection information: controlling the sample preparation part to prepare a first determination sample at a first dilution ratio and a second determination sample at a second dilution ratio, and controlling the detection part to respectively detect the first determination sample and the second determination sample, and determining the cause of fibrinogen reduction in the to-be-detected plasma at least according to the first coagulation time and the first dilution ratio, the second coagulation time and the second dilution ratio and a reference curve, and the reference curve represents the relationship between the coagulation time and the dilution ratio of the reference plasma.