70 results about "Clinical work" patented technology

The invention discloses a chest radiograph report generation and focus positioning method and system based on reinforcement learning, and belongs to the technical field of artificial intelligence and medical image analysis crossing. According to the method, firstly, a basic model is supervised and fine-tuned by using a multi-source chest radiograph image and a query text; and then optimizing the strategy model by adopting a GRPO reinforcement learning framework, introducing an indicator function guided by token entropy into a target function, and finally realizing parallel generation of an end-to-end chest radiograph report text and focus bounding box coordinates by the optimized strategy model. According to the method, visual positioning of the focus is realized while the generation quality of the chest radiograph report is improved, and the integrated output form of the method better fits the clinical actual working process.

A clinical workflow optimization system includes a data processing and analysis platform electrically connected or communicatively coupled to a user device and an HIS server, and a generative AI model set communicatively coupled to the data processing and analysis platform. The data processing and analysis platform provides one or more assistant tools. When the user device selects an assistant tool to execute a task instruction, the data processing and analysis platform uses one model of the generative AI model set to interpret and execute the task instruction. The analysis platform presents the execution result of the task instruction to the user device, wherein data required to execute the task instructions is recorded in the content of the task instructions or provided by the HIS server, the user device, or an external database. On the platform, users can independently develop and build clinical data processing tools using natural language.

The invention discloses a genetic disease pathogenic site sorting and diagnosis auxiliary method and system based on multi-modal artificial intelligence. The method comprises the following steps: firstly, collecting genetic disease data to construct a heterogeneous knowledge graph; the method comprises the following steps: acquiring patient data, and executing an analysis process: generating multi-modal feature representation of candidate pathogenic sites from four dimensions of variation features based on rules, a tissue specificity mechanism, a protein three-dimensional structure and real-time literature evidence; carrying out fusion sorting on the features by using a sorting model, and generating an interpretable report and a clinical examination suggestion based on the uncertainty of a sorting result; and after the doctor executes examination according to the suggestion and feeds back newly added data, the analysis process is repeated until a preset iteration target is achieved. According to the method, the limitation of a static analysis model is broken through, multi-dimensional evidence fusion and clinical workflow embedding are realized, and the interpretation accuracy and diagnosis efficiency of the pathogenic site of the genetic disease are remarkably improved.

Disclosed herein are methods for selecting and preparing patient data to facilitate the adoption and customized training of machine-learning models in clinical settings, particularly for radiation therapy treatment planning. The disclosed embodiments streamline the customized training process through an automated workflow that includes prefiltering patient metadata, retrieving relevant DICOM files, optional data anonymization, and generation of training data. The data is then organized into a format suitable for machine-learning training. The embodiments discussed herein reduce manual labor, minimize errors, and accelerate the integration of machine-learning into clinical workflows, enabling clinics to train and implement predictive models that replicate specific clinical practices, thereby enhancing treatment precision and improving patient outcomes.

A robotic surgical simulation system for clinical workplace simulation includes a virtual reality headset configured to display the clinical workplace simulation, a processor, and a memory. The memory includes instructions stored thereon, which, when executed by the processor, cause the robotic surgical simulation system to: generate a virtual operating room within a three-dimensional coordinate space. The virtual operating room includes a virtual surgical console. The instructions when executed by the processor further cause the system to compute, based on the captured image, a position of the user within the three-dimensional coordinate space relative to the virtual surgical console; and determine whether a user is engaged with or disengaged from the virtual surgical console based on the computed position.

The utility model relates to the technical field of medical instruments, and provides a sphygmomanometer cuff and a sphygmomanometer, the sphygmomanometer cuff comprises: a body used for surrounding the arm of a subject; a lining is arranged on at least part of the inner side face of the body, and grids used for generating friction with light and thin clothes on the arms of a subject are arranged on the lining. According to the sphygmomanometer cuff, the lining is arranged on at least part of the inner side face of the body, the grids used for generating friction with light and thin clothes on the arm of a subject are arranged on the lining, and due to the arrangement, displacement of the cuff can be reduced, falling can be prevented, clinical workload can be reduced, and the accuracy of a monitoring result can be improved.

The invention relates to the technical field of medical equipment and image guidance, and discloses a high-precision image guidance treatment supporting system, method and device, and the system comprises an image guidance module, a space distance measurement module, an artificial intelligence processing module, a closed-loop feedback control module, and a motor driving module. The method comprises the following steps: collecting coordinates of a tumor area and a treatment bed deformation model, combining real-time pose information, utilizing artificial intelligence to generate a pose compensation parameter, outputting a six-degree-of-freedom compensation control instruction, and driving a motor to realize accurate adjustment of the position and the pose of the treatment bed. Real-time accurate adjustment of the treatment bed under six degrees of freedom can be achieved, multi-source data fusion and an artificial intelligence compensation mechanism are combined, the positioning accuracy and the alignment stability of a tumor area are effectively improved, position errors caused by manual operation or deformation of the treatment bed are reduced, and the accuracy of the treatment bed is improved. And the safety, the accuracy and the clinical working efficiency of radiotherapy are remarkably improved.

This invention relates to the field of medical data processing technology, and discloses a method, system, device, and medium for calculating the synergistic control rate of drug infusion. The invention acquires the patient's real-time bispectral index (BSE) and determines its deviation from a preset target range. A control algorithm is then used to calculate the required total effect intensity adjustment. Based on a preset fixed ratio of propofol and remifentanil effect-site concentrations, the total effect intensity adjustment is allocated to the target effect-site concentrations of each drug. Finally, the target infusion rates of propofol and remifentanil are calculated backward using the Schnider and Minto models, respectively. This invention achieves synergistic closed-loop control of sedative and analgesic drugs based on a single BIS feedback, solving the clinical problem of unquantifiable analgesia control, ensuring a dynamic balance between sedation and analgesia, and incorporating a built-in safety verification mechanism. This significantly improves the accuracy, stability, and safety of anesthesia depth control, while reducing clinical workload.

Systems and methods for agentic clinical workflow governance with deterministic human escalation boundaries are disclosed. A hardware-isolated governance engine enforces consensus, risk, and regulatory constraints across multi-agent clinical workflows, deterministically freezing execution and escalating control to verified human oversight when required.

The invention discloses an ultrasonic report generation method, related equipment and a computer program product, and relates to the technical field of artificial intelligence. According to the method, streaming recognition is performed on the real-time spoken voice of the doctor in the ultrasonic detection process of the doctor, the current voice transcription text fragment is obtained, the large model is called to extract the ultrasonic detection parameters in the current voice transcription text fragment in a fast thinking mode, and the extracted ultrasonic detection parameters are output and previewed in real time, so that the accuracy of ultrasonic detection is improved. Therefore, real-time interaction with doctors is generated, and the result of the detection process is transparent to the doctors. After ultrasonic detection is finished, a large model is called to generate ultrasonic description and diagnosis based on an original complete voice transfer text in a slow thinking mode, ultrasonic detection parameters, the ultrasonic description and diagnosis are integrated to obtain a high-quality ultrasonic report, the clinical requirement of real-time interaction is met, the clinical working efficiency is improved, and the clinical experience is improved. And the quality of the finally obtained ultrasonic report can be ensured.

The present application relates to the medical care form technical field, propose a kind of medical care intelligent form generation method and system based on multimodal big model, comprising: collecting the physical examination of clinical business system in medical care patient, diagnosis record, diagnosis voice data and other multimodal data;Again, generate physical change sequence by multimodal big model in combination with physical examination data, construct diagnosis feature vector;Subsequently, the vector is mapped to medical quality index system, to generate visual form framework;Then, extract diagnosis record key elements and fill into framework, update form information in combination with diagnosis voice data;Finally, medical care intelligent form adapted to each system is output by multimodal big model, and is synchronized to medical care work terminal.The present application realizes the effective fusion of multimodal medical data, and the generated form can completely reflect the whole picture of diagnosis and treatment and the dynamic evolution of signs, improve the clinical work efficiency and medical quality.

The invention discloses a multi-dimensional physiological signal monitoring system for mental stress of nursing personnel. The system comprises a signal acquisition module, a context acquisition module, a processing analysis module and an output module. The signal acquisition module is used for acquiring multi-dimensional physiological data such as an electrocardiosignal, a motion signal and an environment signal of a nurse in real time; the context acquisition module acquires a clinical operation log from a hospital information system; the processing analysis module is used for distinguishing psychological pressure from physiological interference through a multi-modal signal fusion filtering technology, intelligently associating an effective pressure event with clinical operation and determining the context of a pressure source; and the output module is used for generating a personalized pressure analysis report and a management instrument panel containing the clinical work context. The problems that in the prior art, pressure monitoring specificity is poor, and a pressure source is unknown are solved, accurate monitoring and intelligent source tracing of the psychological pressure of nursing personnel in a real clinical environment are achieved, and a scientific basis is provided for individual pressure management and organization health intervention.

The invention discloses a clinical urinary catheterization device for urinary surgery and a use method, and belongs to the technical field of medical instruments. Comprising a base, a rotating platform is arranged on the upper surface of the base, a plurality of collecting mechanisms are arranged on the rotating platform, opening and closing mechanisms are arranged above the collecting mechanisms, and an L-shaped supporting plate is fixedly connected to the right side of the outer side wall of the base; urine is temporarily stored through a plurality of collecting barrels, when one collecting barrel is almost full, a motor only needs to drive a rotating platform, the unoccupied collecting barrel is rotated to the position below a butt joint mechanism to complete switching, frequent dumping operation is not needed, meanwhile, a lifting plate of the butt joint mechanism is matched with a pulling plate and a first spring, butt joint and separation of an inserting pipe and a connecting nozzle can be rapidly achieved, and the working efficiency is greatly improved. The time investment of nursing personnel on urine treatment is greatly reduced, so that the nursing personnel can apply more energy to core nursing work such as illness state observation and medication guidance, and the overall clinical working efficiency is remarkably improved.

This application provides a configuration method and apparatus for a heart sound processing model based on multimodal knowledge distillation. It introduces knowledge distillation technology on the basis of deep learning-based heart sound data processing and builds a novel model configuration scheme in a deep and adaptive manner. This realizes the integration of multimodal training and lightweight deployment of knowledge distillation, so as to comprehensively improve the accuracy, stability and engineering usability of diagnosis, and has good application prospects in clinical work.

The invention discloses a perioperative delirium risk classification method and system for unbalanced medical data, and relates to the field of computer data processing and machine learning. Comprising the following steps: extracting relevant data of examination and surgical anesthesia of a patient, and marking relevant data corresponding to delirium; constructing a delirium risk classification model, inputting the marked related data into the delirium risk classification model, and training the delirium risk classification model by utilizing a method for dynamically adjusting a category balance factor and a classification difficulty factor; and inputting to-be-evaluated perioperative period patient data into the trained delirium risk classification model, and performing classification prediction on the delirium risk in the perioperative period. The gradient calculation process is reconstructed on the basis of the gradient boosting tree, the problem of model training deviation caused by scarcity of positive samples in medical data is solved, and doctors are assisted in efficiently completing scientific research and clinical work.

Embodiments of the present disclosure relate to customized machine learning training of radiotherapy clinics. Disclosed herein are methods for selecting and preparing patient data to facilitate the employment and custom training of machine learning models in a clinical environment, particularly for radiotherapy treatment planning. The disclosed embodiments simplify the customized training process through an automated workflow that includes pre-filtering patient metadata, retrieving related DICOM files, optional data anonymization, and generating training data. And organizing the data into a format suitable for machine learning training. The embodiments discussed herein reduce manual labor, minimize errors, and accelerate the integration of machine learning into the clinical workflow, enabling clinics to train and implement predictive models replicating specific clinical practices, thereby improving treatment accuracy and improving patient outcomes.

A clinical workflow escalation and acknowledgment governance system converts AI-assisted clinical outputs into governed workflow items. The system enforces execution-time routing, tiered escalation, and acknowledgment thresholds and stores immutable audit records. The invention improves safety and accountability without autonomously diagnosing conditions or prescribing treatment actions.

The invention relates to a medical alarm management method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining patient physiological data, medical equipment state data, clinical workflow information and patient basic information in real time, and generating a multi-dimensional data sequence on a unified time axis; inputting the multi-dimensional data sequence into an adaptive decision engine, dynamically adjusting an alarm triggering condition according to clinical workflow information, and generating an original alarm event when the triggering condition is met; carrying out root analysis on the plurality of original alarm events in a preset time, defining root events of the plurality of original alarm events, marking other original alarm events as derivative alarms, and packaging to form a nested alarm object; and correspondingly sorting the nested alarms according to the clinical emergency degree and the event sequence. According to the medical alarm management method and device, the computer equipment and the storage medium, the problems of alarm fatigue, information overload, unclear source, difficulty in tracing and the like in a traditional system can be fundamentally solved.

A computer-implemented method for multi-modality medical image clinical workflow guidance comprises a step of receiving a user input (306-4) in relation to a first medical image data set (306-2) acquired by means of a first medical imaging modality (304-A). By means of a clinical-concept-to-medical-image linking algorithm (314), the received user input (306-4) is assessed in view of at least one second medical image data set (308-1) acquired by means of at least one second medical imaging modality (304-B). An indication of a clinical workflow guidance in relation to the at least one second medical image data set (308-1) is output.

A healthcare system accommodates spasmodic clinical workflows for populating a records database associated with a surgical platform or other digital healthcare platform. An interoperability engine receives data streams including events from various electronic health records systems that provide data events according to varying format, order, and timing dependent on their corresponding clinical workflows. The interoperability engine maps indeterminate events to expected events associated with a clinical workflow based on a clinical workflow management file, an industry standard model, a general parsing model, or a combination thereof. The interoperability engine may furthermore detect non-compliance of received events and may generate feedback indicative of a compliance assessment.

The invention provides a tool for intelligently evaluating the dystrophy risk of a patient with nasopharyngeal carcinoma, and the tool for evaluating the specific dystrophy of nasopharyngeal carcinoma is constructed by integrating indexes such as social demographic data, physique measurement, tumor staging, chemoradiotherapy conditions, recent adverse reactions and hematology indexes, so that high-precision risk evaluation is realized. Through single-factor and multi-factor analysis, the variable weight is optimized, and the discrimination capability and stability of the model are improved. An intelligent applet based on artificial intelligence is developed, patient data are extracted, nutrition risk calculation is completed within seconds, evaluation time is shortened, and clinical working efficiency is improved. The system also has the functions of dynamic monitoring and intelligent early warning, automatically updates the evaluation result along with the treatment progress of the patient, and provides individualized intervention suggestions. The defects that a traditional nutrition evaluation tool is high in subjectivity, low in efficiency, lack of tumor specificity and low in informatization degree are overcome, and an efficient, accurate and automatic intelligent evaluation solution is provided for clinic.

This invention provides an automated evaluation method, apparatus, storage medium, and computing device for intracranial collateral circulation. The method includes: obtaining cerebral blood flow images based on ASL images from multiple PLD times; segmenting the cerebral blood flow images to obtain regions of interest (ROIs) for arterial arrival artifacts; calculating quantitative parameters for evaluating intracranial collateral circulation based on the ROIs; and marking the ROIs and the quantitative parameters in the cerebral blood flow images. The method of this invention can more objectively evaluate the severity of arterial arrival artifacts, thereby evaluating collateral circulation and better assisting physicians in making clearer judgments and analyses of patients' conditions in clinical practice.

The embodiment of the invention discloses a three-dimensional myocardial scar visualization system. According to one specific embodiment, the system comprises a data processing end configured to perform heart structure and scar segmentation on target heart magnetic resonance data to obtain a binary tag graph for the heart and the myocardium; constructing an individualized ventricular network and a scar three-dimensional surface model based on the binary label graph; generating an initial myocardial scar three-dimensional model; generating lead implantation track information; generating a myocardial scar three-dimensional model according to the lead implantation track information; and the model application end is configured to perform model rendering on a target application page according to the model parameters corresponding to the myocardial scar three-dimensional model sent by the data processing end so as to provide an interactive operation function and generate a clinical report. According to the embodiment, accurate and visual three-dimensional visual decision support can be provided for preoperative planning and intraoperative navigation of heart diseases, so that the accuracy of surgical planning and the clinical working efficiency are remarkably improved.

The invention relates to the technical field of medical instruments, in particular to a standardized specimen integration device which comprises a main box body and a collection box. A first containing space used for containing the collecting box is formed in the main box body, an opening is formed in one side face of the main box body, the collecting box can move relative to the main box body through the opening, and a control center electrically connected with the collecting box is further arranged on the main box body; a second containing space used for containing specimens is arranged in the collecting box, and a pop-up structure is arranged at the bottom of the second containing space. And by arranging the control center, the movement and the ejection structure of the collecting box can be conveniently controlled through the control center, so that the operation is simpler and more accurate. The control center is added to control the collection box, so that bad consequences such as wrong detection results caused by untimely specimen collection due to busy clinical work delay can be reduced and even avoided.

A computerized system for personalized medical education, compliance verification, and clinical workflow automation uses sensor-based identification and multi-modal monitoring to verify user presence, engagement, and comprehension during delivery of educational modules and required disclosures. Artificial intelligence models interpret electronic medical record data to select and sequence patient-specific content, determine procedure-specific and jurisdiction-specific compliance requirements, and adapt presentation in real time through device-level control actions including pausing, prompting, repeating, and module recalibration when noncompliance is detected. The system further supports conducting interactive clinical encounters in lieu of or in conjunction with clinician visits, including structured intake, decision support, and generation of audit-ready, billable encounter documentation under clinician oversight and safety guardrails. The system generates time-stamped interaction logs, medical decision-making and time-on-task summaries, and electronic medical record-ready outputs with provenance and compliance verification, suitable for reimbursement and audit defensibility across multiple specialities.

A real-time clinical AI drift detection and regulatory evidence generation system continuously monitors AI-assisted clinical workflows for deviation from validated, regulator-aligned baselines. The system classifies regulatory relevance and produces auditable post-market surveillance evidence while preserving clinician authority. Continuous regulatory readiness is achieved without autonomously diagnosing conditions or prescribing treatment actions.

This invention belongs to the field of osteoarthritis management technology, specifically relating to an artificial intelligence-based osteoarthritis management system and a computer storage medium. This invention provides an artificial intelligence-based osteoarthritis management system. This system integrates an LLM-DL hybrid architecture, a multi-specialty module collaboration framework, and a RAG knowledge base system, covering the entire clinical process from initial patient diagnosis to treatment plan development. This system can comprehensively and accurately assess the patient's disease status, providing personalized disease progression predictions. It not only predicts 2-year and 4-year functional outcomes and radiological progression but also identifies patient-specific risk factors, providing a basis for precise intervention. The overall system design significantly improves clinical work efficiency and predictive accuracy, reduces reliance on specialist physicians and high-end equipment, enabling high-quality KOA management to be implemented even in resource-limited areas, thereby effectively reducing overall healthcare resource demands.

1. The name of the design product: treatment clothes. 2. The use of the design product: for back treatment and care in clinical work. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: perspective view.

The application discloses a kind of three-dimensional printing antibacterial hydrogel materials and preparation method and application thereof, which are made of the following components by weight fraction: carboxymethyl chitosan 10-20 parts, polylysine 1-10 parts, polyglycine 1-10 parts, gelatin 10-20 parts, water 20-40 parts.The application includes the preparation method of three-dimensional printing antibacterial hydrogel materials.The hydrogel material has the advantages of good biocompatibility, little damage to cells, antibacterial effect, stable performance of wound dressing obtained by three-dimensional printing, and can be used for skin, ligament and other soft tissue wound repair and other clinical work.

The invention relates to an analgesia pump drug delivery control method and device based on multi-dimensional pain indexes, and the method comprises the steps: obtaining multi-dimensional pain data, including physiological data and behavior data, of a target patient, building a pain calculation model containing the multi-dimensional pain indexes, importing the multi-dimensional pain data into the pain calculation model, and calculating the pain of the target patient according to the pain calculation model. Obtaining a pain value corresponding to the target patient, collecting a pain feedback value of the target patient in real time, and controlling the administration process of the analgesia pump in combination with the pain value. Through the core logic of multi-dimensional data acquisition, accurate model evaluation and real-time feedback regulation, the limitation of administration control of a traditional analgesia pump is broken through from the four dimensions of evaluation accuracy, administration individuation, administration safety and management efficiency, and finally the clinical goals of accurate analgesia, safe administration and efficient management are achieved. The method has important value for improving the pain diagnosis and treatment quality, guaranteeing the safety of patients and optimizing the clinical working process.