112 results about "Medical screening" patented technology

The invention discloses a multi-granularity knowledge graph auxiliary diagnosis method based on DeepSeek and Agent. The multi-granularity knowledge graph auxiliary diagnosis method comprises the following steps: step 1, receiving electronic medical record text data and medical image data of a patient; 2, constructing a knowledge graph; updating the knowledge graph every day to reflect the latest medical research result; step 3, analyzing the text data of the electronic medical record through DeepSeek-R1; 4, extracting spatial structure feature nodes of the medical image data through a multilayer three-dimensional convolution kernel; the method comprises the following steps: segmenting medical image data into sequence blocks through a Vision Transform; 5, the output of the DeepSeek-R1, the output of the multi-layer three-dimensional convolution kernel and the output of the Vision Transform are input into a multi-modal fusion module; step 6, outputting a high-confidence diagnosis conclusion and probability distribution; and step 7, generating an intelligent report of the structured text. According to the method, by combining natural language processing, computer vision and the knowledge graph technology, accurate and efficient medical examination is achieved.

The invention relates to the technical field of data processing, and discloses an old people health state assessment data processing system based on multi-modal data, and the system comprises a medical data integration module which obtains electronic medical record data and a medical examination report through an FHIR interface, and extracts a structured health index; the cross-modal causal fusion processing module is used for fusing the monitoring data and the medical text through an image, text and image interlayer architecture; the health state evolution modeling module is used for mapping the health feature vectors into physiological function, cognitive level and athletic ability three-dimensional state indexes; an evaluation report backtracking module; and a decision output module. Through an image, text and image interlayer architecture, deep semantic fusion of multi-modal features is realized under the constraint of medical pathology rules, feature weight adaptive distribution is dynamically guided based on a medical causal atlas, a high-dimensional fusion vector retaining key pathology information is generated, the semantic integration ability of health data is remarkably improved, and the health data fusion efficiency is improved. And the reliability of discrimination and decision making is improved.

A large language model-based medical examination conclusion generation method includes: obtaining a target manifestation text corresponding to a target medical examination; extracting medical examination inference knowledge that matches the target manifestation text from a medical examination inference knowledge base, where the medical examination inference knowledge includes a manifestation text and a conclusion text corresponding to a medical examination; constructing a sample based on the extracted medical examination inference knowledge, and constructing a prompt text based on the sample and the target manifestation text; and inputting the prompt text into a large language model, and outputting, by using the large language model, a target conclusion text that corresponds to the target medical examination and that is obtained by performing inference based on the target manifestation text and under guidance of the sample.

In a medical examination support system 1, speech information of conversation between a veterinarian and a pet owner is converted into text data by a text data conversion unit 106. The text data and a template which is instruction content for a large language model 205 are input to a medical examination support information creation unit 204 as input parameters, and medical examination support information is automatically created from the text data on the basis of the large language model 205. The created medical examination support information is displayed on a monitor 3 by a display device 30.

One or more embodiments of the invention provide a medical examination report interpretation method and device based on a large language model, and the method comprises the steps: obtaining a to-be-interpreted medical examination report image, and carrying out the optical character recognition of the medical examination report image, identifying a medical examination report text from the medical examination report image; performing information extraction on the medical examination report text to extract a target text related to a medical examination result from the medical examination report text, and organizing the target text into a structured text according to a preset structured text format; and inputting the structured text into a large language model, and reasoning based on the structured text by the large language model to generate a medical suggestion text corresponding to the medical examination result.

The invention provides a multi-agent medical examination recommendation system and method, and relates to the technical field of medical intellectualization. Comprising a medical examination recommendation data set building module used for extracting key medical entities and personal information of patients from electronic medical records of an intensive care medical information database, and generating enhanced patient sequence data by using the key medical entities and a preprocessing mode; the medical knowledge graph building module is used for building a medical knowledge graph according to the disease and the triple generation module based on the large language model; and the medical examination recommendation module is used for processing the enhanced patient sequence data and personal information by utilizing a plurality of intelligent agents and a medical knowledge graph to obtain a target medical examination item. In this way, structured medical examination data can be provided, and the quality of a data set is high; multiple agents are introduced, so that the flexibility and adaptability of the recommended target medical examination items are improved; and the reasonability of the recommendation result is improved by utilizing the established medical knowledge graph.

The invention discloses an information processing method and device for examination item recommendation, equipment and a medium, relates to the technical field of medical data processing, is applied to a computer device and comprises the steps that key feature vectors in health information of a target object are extracted; querying an initial disease name and an initial confidence coefficient corresponding to the vector from a medical knowledge graph; according to the initial disease name and the initial confidence coefficient, generating a health state evaluation list which corresponds to individual attribute information in the health information and comprises a target disease name and a corresponding target confidence coefficient; generating a preliminary recommendation table of the target object based on the health state evaluation list, wherein the recommendation table comprises initial medical examination items sorted based on the target confidence; and optimizing the preliminary recommendation table according to the evaluation information and the individual attribute information of each initial medical examination item to obtain a target recommendation table containing the target disease name and the corresponding target medical examination item. And personalized and high-accuracy medical examination item recommendation is realized.

The invention provides a drug recommendation system and method based on causal inference, and relates to the technical field of data mining, the system uses a deep learning model, and specifically comprises a patient state encoder, a medical examination auto-encoder and a recommendation module; the method comprises the following steps: inputting a patient feature X, and projecting the X to a low-dimensional embedding space by using a neural network encoder; reconstructing the medical examination data R by using a coder-decoder structure to obtain a substitute low-dimensional hidden variable ZR of the R, and calculating reconstruction loss; using comparative learning to optimize the low-dimensional hidden variable ZR, and calculating comparative learning loss; according to the patient characteristic X and the hidden variable ZR of the medical examination, predicting an appropriate drug, and calculating recommended loss; and the reconstruction loss, the comparison learning loss and the recommendation loss are jointly optimized to optimize parameters of the drug recommendation system, a causal relationship P (Ydo (X)) between the patient and the drug is established, and the recommendation ability of the drug recommendation system is improved. And finally, performing drug recommendation by using a drug recommendation system through combining the patient characteristics and the medical examination data.

The invention discloses a multi-agent medical intelligent diagnosis method and system based on an inference tree structure, electronic equipment and a storage medium. The method comprises the steps that a large language model is commanded to simulate multiple specialist physician roles through preset cue words; defining an inference tree structure, and requiring each agent to output a diagnosis result according to the structure; each agent analyzes the medical examination data of the corresponding field to generate a diagnosis result based on an inference tree structure; designing a multi-agent cross validation mechanism, and updating an inference tree through pairwise discussion of agents; and fusing the reasoning trees of all agents, and outputting final diagnosis including a diagnosis conclusion, a reasoning process and clinical evidence. According to the method, medical examination data in different fields are analyzed by utilizing a multi-agent method based on an inference tree structure, so that the diagnosis performance of a complex medical scene is improved.

The application relates to the technical field of data processing, and discloses an old person health state evaluation data processing system based on multi-modal data, which comprises a medical data integration module, an across-modal causal fusion processing module, a health state evolution modeling module, a backtracking evaluation report module and a decision output module. The medical data integration module acquires electronic medical record data and medical examination reports through a FHIR interface and extracts structured health indexes. The across-modal causal fusion processing module fuses monitoring data and medical texts through an image, a text and an image sandwich architecture. The health state evolution modeling module maps a health feature vector into three-dimensional state indexes of physiological functions, cognitive levels and motor abilities. The backtracking evaluation report module and the decision output module are used for backtracking evaluation and decision output. Through the image, the text and the image sandwich architecture, deep semantic fusion of multi-modal features is realized under the constraint of medical pathology rules, feature weight adaptive distribution is dynamically guided based on a medical causal graph, a high-dimensional fusion vector retaining key pathological information is generated, the semantic integration capability of health data is significantly improved, and the reliability of discrimination and decision is improved.

A stenosis assessment method and device based on the intracranial digital subtraction angiographic (DSA) imaging, including acquiring the intracranial DSA imaging and extracting two planar images containing the target blood vessel from the DSA imaging, wherein the two planar images have different shooting angles. According to the two planar images, a 3D model of the target vessel is established. Based on the established 3D model of the target vessel and the DSA imaging, the hemodynamic simulation of the target vessel is performed. The disclosure realizes the functional assessment of intracranial vascular stenosis, improves the diagnostic accuracy, and provides certain assistance for neurologists to determine intervention means. The disclosure of noninvasive FFR technology in the assessment of intracranial vascular stenosis can only rely on angiography for functional assessment, saving the medical examination cost of patients. It has more convenient operation and higher repeatability.

Provided herein are computerized system and method for full patient flow management through an emergency department process, integrating multi-agents LLM. The system and method utilize a plurality of LLM-based agents configured to perform one or more of: extract relevant medical information and generate a summarized medical history; interactively questioning the subject regarding its medical history and regarding the main complaint(s); provide recommendations regarding various medical examinations; process the summarized medical history and the results of the recommended medical examination(s) and; provide further summary, recommendations or instructions, regarding diagnosis and a decision regarding discharge or admission of the subject.

The invention relates to the technical field of medical instruments, and discloses a disinfection device for a reproductive medicine examination room, which comprises a flowing gas heating mechanism and a rotary reciprocating shaking mechanism, a lower movable disc which is positioned in the vertical disinfection barrel and can rotate, an upper movable disc which is positioned right above the lower movable disc and can generate a longitudinal reciprocating motion effect, and a storage movable plate which longitudinally moves along with the upper movable disc and can support an instrument are arranged in the vertical disinfection barrel. According to the disinfection device for the reproductive medicine examination room, an instrument is effectively disinfected through disinfection gas, the disinfection gas is gas and has the rapid movement and permeation functions, in addition, the instrument can shake in the disinfection process through the device, the instrument can generate a movement gap through shaking, and therefore the instrument can be disinfected conveniently. And the disinfection gas can generate a flowing disinfection effect along the whole surface of the instrument, so that the disinfection range of the instrument is expanded, and the infection risk of the instrument in the subsequent use process is reduced.

The invention discloses coronary heart disease tendency recognition equipment based on hand image features, and belongs to the technical field of medical image processing and deep learning. According to the method, a hand image is collected through a hand diagnosis instrument camera, image features are extracted and analyzed through a deep learning model, and whether a detected person has the tendency of coronary heart disease or not is judged. The method comprises the specific steps of collecting hand image data of a plurality of detected persons, preprocessing images to extract key features, constructing a deep learning model based on ResNet50 for training and classification, and finally outputting a prediction result of the coronary heart disease tendency. The accuracy of the method on a test set can reach more than 85%, and the method has the advantages of high efficiency, non-invasiveness and low cost, is suitable for scenes of family health monitoring, community medical screening, hospital auxiliary diagnosis and the like, and promotes early screening and prevention of coronary heart disease.

The invention provides a cognitive function evaluation method and system based on data fusion, and relates to the technical field of data processing. The method comprises the following steps: acquiring multiple medical examination data of a to-be-evaluated patient; extracting data features of the multiple medical examination data; fusing the data features of the multiple medical examination data through a linear perception fusion algorithm to obtain fused features; according to the fusion features, the cognitive function of the patient to be evaluated is evaluated through a quantum neural network. According to the method, the data features of the multiple medical examination data are fused, then the cognitive function of the patient to be evaluated is evaluated through the quantum neural network according to the fused features, the cognitive state of the patient can be reflected more comprehensively, and improvement of the accuracy of cognitive function evaluation is facilitated.

An examination device (10) for optical medical examinations, in particular a dermatoscope, comprises a camera unit (18) for recording at least one image of an examination area (58) of a patient and a control unit (78), wherein the camera unit (18) has a sensor element (72), a lens (74) and an adjustment device (76) for the lens (74), wherein the lens (74) is arranged in an observation beam path (70) of the camera unit (18) in front of the sensor element (72).The adjustment device (76) is configured to move the lens (74) along the optical axis of the lens (74) to different positions in order to focus on different examination planes in the examination area (58), wherein the control unit (78) is designed to control the adjustment device (76) and is connected to it, and information on two or more predefined examination planes (60, 62) in the examination area (58) with associated positions of the lens (74) is stored in the control unit (78). Furthermore, a method for capturing an image of an area under investigation is described.

The utility model discloses an auxiliary water supply device for medical probe medical ultrasonic endoscopy, which belongs to the technical field of medical examination devices.The auxiliary water supply device for medical probe medical ultrasonic endoscopy comprises a base, a water supply device main body and a water tank, a plurality of universal wheels are installed at the bottom end of the base, a support is fixedly connected to the base, and the water supply device main body is fixedly connected to the support. According to the scheme, a user can fix the water feeder body to the fixing block, a water tank is placed on the base, a water pipe used in cooperation with the water feeder body can be wound around the take-up rod, and the water feeder body can be fixed to the take-up rod; a handle is pushed to drive the whole device to move through a plurality of universal wheels, the portability of the water supply device is improved, the height of the water supply device body can be adjusted through the arrangement of an adjusting assembly, and therefore when a bedridden patient is treated, the height of the water supply device body can be adjusted according to the height of a bed, and the practicability of the water supply device is improved. And convenience is provided for the treatment process.

The invention discloses a full-cycle management method for an endometriosis patient, and relates to the technical field of medical informatization decision making, and the method comprises the steps: collecting the preliminary diagnosis disease staging information, lesion feature text and laboratory inspection data of the patient, and generating a case data set through medical term standardized conversion and text structured processing; constructing a recurrence risk prediction model, inputting the case data set into the recurrence risk prediction model, and generating a recurrence risk quantitative score; adjusting a follow-up period based on the recurrence risk quantitative score, setting follow-up time nodes and medical examination items, and combining to generate a follow-up plan; and performing graded reminding based on the follow-up visit plan, and collecting symptom scoring records, medicine use data and life quality evaluation results submitted by the patient to form a follow-up visit data set. The dynamic follow-up visit plan is generated by constructing the recurrence risk prediction model, individualized follow-up visit management is achieved, and the problem that follow-up visit depends on static experience and cannot be matched with a real risk level is solved.

An example system is described herein for a display device to couple with a handheld diagnostic tool allowing an optical device to be converted to digitally imaging and back and used for performing a medical examination by a clinician. The display device includes an interface that includes the ability to attach to an eyepiece of the diagnostic device. The display device includes a camera within the channel to align with the eyepiece and capture image data through the diagnostic device when the display device is coupled with the diagnostic device. The display device has the camera essentially centered along a length and width of the body such that the display device maintains the balance of the diagnostic device. The display device further includes sensors to determine an orientation of the display device to annotate image data with an indication of a reference frame.

To provide an endoscope for medical examination and / or treatment of a human or animal body or tissue sections thereof.SOLUTION: An endoscope (10) that is configured for imaging as well as for tissue analysis is disclosed. For this purpose, the endoscope (10) comprises an image sensor to which multiple optical devices are arranged in order to carry out different tasks with one and the same image sensor, particularly the task of imaging and measurement tasks concurrently or temporally graded.SELECTED DRAWING: Figure 1

A remotely interfaced medical screening assembly for remotely screening and diagnosing a user includes a plurality of garments, a relay module, and a user interface device. Each garment substantially covers a respective body part of the user and is equipped with one or more sensors and stimulators, each of which can assess or elicit a biological parameter or biological response, respectively. Connectors are operationally engaged to the relay module and can be selectively mutually attached to operationally engage the sensors and the stimulators to the relay module. The user interface device is in wireless communication with the relay module and a healthcare provider's electronic device so that commands, biological parameters, and biological responses are communicable between the relay module and the healthcare provider's electronic device, allowing the healthcare provider to evaluate the user and to formulate a diagnosis.

A method for determining items of object information in at least one of a medical examination or treatment arrangement with at least one object is provided. The at least one object is captured via at least one camera and an item of object information includes at least one of identification information or positional information relating to the at least one object. The item of object information is determined via a control device by evaluating camera data from at least one camera image obtained by the at least one camera, and the at least one object is equipped with a tracking device. The method comprises: determining, via the tracking device, an item of pose information describing at least one of a position or an orientation of the at least one object; and using the item of pose information to determine the item of object information.

An artificial tissue tube having a stem cell-derived smooth muscle layer and an endothelial cell layer is produced. Compared with conventional methods, it is possible to produce an artificial tissue tube that produces physiological contraction and relaxation reactions by using at least three times of stem cell-derived smooth muscle cells and further using stem cell-derived endothelial cells to produce an artificial tissue tube. An artificial blood vessel produced using an iPS cell derived from a patient with Viller's syndrome is shown to be an artificial blood vessel reflecting a pathological condition, and therefore an artificial tissue tube reflecting a pathological condition of a plurality of diseases can be produced using the iPS cell. The artificial tissue tube can be used for screening and transplanting medicines.

The application relates to the technical field of ultrasonic image analysis, and discloses a thyroid nodule evaluation system based on ultrasonic images. The system obtains medical record data and medical examination data of a patient through a multidimensional acquisition module, classifies and forms a data set, analyzes the thyroid function state of each patient through an intelligent evaluation module, generates a function coefficient, analyzes the picture quality of each group of ultrasonic images again, generates corresponding detection data group Jcsj, establishes a unified evaluation standard, quickly screens out key frames from a large amount of ultrasonic image data, has high multidimensional integration efficiency, sets a fixed range threshold value for the intelligent evaluation module, analyzes and generates a nodule volume and a nodule score in combination with a medical data set, and in combination with the function coefficient, the detection data group and the nodule score, evaluates the risk grade of the thyroid nodule and the picture quality of the ultrasonic image of the patient, screens out key frames of the ultrasonic image, and outputs a treatment suggestion; and the intelligent evaluation has high precision.

The application discloses a kind of compound screening method and system for regulating blood-brain barrier permeability, it is related to medical screening technical field, the specific steps of the method are as follows: S100, collect blood-brain barrier related cell multi-omics data to form original set;S200, data is preprocessed and standardized;S300, molecular network is constructed by cross-omics analysis, and key target is screened;S400, target information is integrated to establish structured target pool;S500, effective compound for regulating blood-brain barrier permeability is screened out by molecular docking and primary cell verification, the application constructs gene-protein-metabolite network by multi-omics integration and cross-omics analysis, accurately identifies blood-brain barrier key target, provides high credibility target pool;Combined with molecular docking and primary cell mixed culture verification, realize efficient screening and functional safety evaluation of candidate compound, significantly reduce research and development cost, provide efficient technical path for drug research and development.

The embodiment of the invention provides a physiological age prediction method and device, equipment and a storage medium, relates to the technical field of computers, can realize accurate prediction of physiological age by integrating external display images and internal medical examination data of human beings, and realizes efficient prediction calculation without contacting a detected person. The method provided by the embodiment of the invention comprises the following steps: acquiring face image data of a detected person, examination data of at least one human body physiological index and a real age; detecting a wrinkle area from the face image data, and determining an appearance aging factor of the detected person according to the detected wrinkle area; determining a body aging factor of the detected person according to the examination data; and obtaining a physiological age prediction result of the detected person according to the appearance aging factor, the body aging factor and the real age.

The present invention relates to a disposable nasal clip that helps to expand the nostrils to easily check the inside of the nose and perform medical examination or treatment in otolaryngology or the like, or for collecting specimens. A disposable nasal clip according to the present invention comprises an entry portion that can be entered into a nostril, a gripping portion connected to the entry portion and capable of being grasped by a user, and an elastic portion that elastically supports the gripping portion in a direction of mutual separation. The entry portion is formed such that the gap narrows when the gripping portion is pressed, and when the pressure is released, the entry portion also widens together with the gripping portion when the gripping portion is opened by the elastic portion.

An examination device (10) for optical medical examinations, in particular a dermatoscope, has a housing (12), a processor (42) and a heat sink (44), wherein the housing (12) encloses an interior space, the processor (42) being arranged in the interior space. The heat sink (44) has a heat source section (56) and a heat sink section (58), the heat source section (56) being arranged in the interior space and being in thermal contact with the processor (42), and wherein at least one side of the heat sink section (58) is arranged outside the interior space.

An image processing apparatus includes: a processor; and a memory connected to or built in the processor. The processor is configured to generate, as learning data used for training a machine learning model for medical images and examination results of medical examinations, new medical images from a first medical image and a second medical image among a plurality of the medical images according to a generation condition, and generate new examination results by performing calculation based on the generation condition on a first examination result of the medical examination corresponding to the first medical image and a second examination result of the medical examination corresponding to the second medical image.

According to an aspect of the present invention, there is provided computer-implemented method for forecasting near-term sudden cardiovascular events, comprising: pretraining a large language model transformer architecture using a processor with an associated computer memory device to recognize text associated with sudden cardiovascular events cases reporting sudden cardiovascular events following a medical exam appointment; obtaining relevant data regarding an asymptomatic individual comprising one or more of a coronary artery calcium (CAC) scan, a coronary CT angiography (CCTA), chest CT, blood markers, and electrocardiogram; providing the relevant data of the asymptomatic individual to the trained computer-implemented artificial neural network; receiving a forecast of the chance of near-term sudden cardiovascular events in the asymptomatic individual; and recommending the next diagnostic or therapeutic step for the asymptomatic individual.