52 results about "Clinical exam" patented technology

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.

The invention discloses a system for evaluating coronary artery calcification points through photon CT non-electrocardiogram gated lung CT plain scanning, and relates to the technical field of coronary artery calcification point evaluation. Through the CT data acquisition module, the coronary artery calcification recognition module, the integral calculation evaluation module and the risk evaluation generation module, X-ray photons are directly counted, electronic noise is eliminated, the signal-to-noise ratio and the contrast noise ratio are improved, in conventional chest low-dose CT, electrocardio gating is not needed, and the cost is reduced. Automatic processing from low-dose lung CT flat scanning data acquisition to structured report generation is achieved, manual data transmission and intervention among all links are not needed, coronary artery calcification evaluation is fused into a conventional lung CT examination process, the extra burden caused by the fact that a patient needs to independently conduct coronary artery CT scanning is avoided, and the examination efficiency is improved; errors possibly caused by manual operation are reduced, consistency and reliability of evaluation results are ensured, and clinical examination and diagnosis processes are optimized.

Systems and methods for ophthalmic disease detection and risk assessment that combines digitally-augmented examination instruments with neural networks trained to analyze examination imagery across diverse patient populations and variable image qualities, enabling automated analysis and classification of eye conditions during routine clinical examinations.

1. Name of the product in this design: Wired oral endoscope. 2. Purpose of this design: For dental clinical examination, especially suitable for detailed observation and image acquisition of oral mucosal lesions. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The medical photodynamic multispectral electronic endoscope relates to the technical field of endoscopes and comprises an eyepiece seat and an objective lens, one end of the eyepiece seat is connected with a light transmitting bundle, the objective lens is mounted at one end, far away from the eyepiece seat, of the light transmitting bundle, a mounting cavity is formed in the eyepiece seat, one side of the mounting cavity is provided with an opening, and the opening is communicated with the eyepiece seat. A mounting cavity is formed in the eyepiece base, a mounting shell is clamped in the mounting cavity, through holes are formed in the two ends of the mounting shell, an eyepiece body is clamped in the mounting shell, sliding grooves are formed in the inner walls of the two ends of the side, away from the opening, of the eyepiece base, sliding rods are fixedly arranged in the sliding grooves, and the rod walls of the sliding rods are movably sleeved with sliding blocks. According to the utility model, the eyepiece quick-changing structure is arranged on the eyepiece seat body, so that a doctor can quickly change different eyepieces in a short time without complicated dismounting and mounting operations, the examination time is greatly saved, and the clinical examination efficiency is improved.

This invention discloses a multimodal respiratory disease-related data acquisition system and method. The data acquisition system includes a disposable oral-nasal breathing interface, an oral-nasal breath sound acquisition module, a bidirectional flow / differential pressure sensing module, a temperature and humidity auxiliary acquisition module, a chest and back multi-channel auscultation module, a channel auscultation front end, a trimodal respiratory data acquisition box, a mobile terminal annotation module, a clinical label association module, and a local storage module. The data acquisition method is as follows: Step 1, prepare the oral-nasal breathing interface and acoustic coupling patch; Step 2, start the trimodal respiratory data acquisition box; Step 3, the patient performs quiet breathing; Step 4, the patient performs a maximal inhalation followed by a forceful exhalation; Step 5, associate the clinical examination results with the acquired data; Step 6, output risk scores, abnormality prompts, or classification prompts. Beneficial effects: Reduces wind noise interference, allows acoustic signals and lung function data to be acquired at the same time reference, and reduces frictional noise and poor contact.

The application provides a kind of based on deep learning's absorbed dose prediction method, device, equipment and medium, it is related to medical image processing technical field, comprising: obtaining the treatment of patient's pre-test multi-modal data;According to clinical examination data and the mask map of the target tumor region and normal key organ region of pre-set drug, space coding is carried out, and the biomarker feature map of the patient to be tested is constructed;According to the pre-treatment medical image and biomarker feature map, a preset first deep learning model is used for prediction, to generate the simulated treatment initial medical image of the patient to be tested;According to the simulated treatment initial medical image, a preset second deep learning model is used for prediction, to generate the post-treatment predicted dosimetry parameter map of the patient to be tested.The application can improve the accuracy of nuclide absorbed dose prediction evaluation.

An intelligent homing type lens box comprises: a box body, which is internally provided with a chamber, and any side of which is provided with a lens recovery port; the try-on lens box is arranged on any side of the box body, and a plurality of lens grooves for accommodating lenses are formed in the try-on lens box; the feeding track is arranged in the cavity, and the feeding track is provided with an inlet end communicated with the lens recovery opening and a detection end used for positioning a to-be-returned lens; the detection mechanism is used for detecting parameters of the to-be-homed lens and is arranged corresponding to the detection end; and the sorting mechanism is used for transferring the to-be-homed lenses into the lens grooves matched with the parameters of the to-be-homed lenses in the try-on lens box based on the detection information acquired by the detection mechanism. According to the utility model, full-automatic identification and homing of the try-on lenses can be realized, manual searching for storage positions and degree comparison are not needed, and the sorting time is remarkably saved. The workflow automation degree of an optometry consulting room can be remarkably improved, non-diagnosis and treatment labor is reduced, and doctors can put more energy into clinical examination and analysis.

A multifunctional diagnostic system includes a reusable speculum with a modular head and a portable digital twin station. The speculum includes a set of heated blades configured to comfortably open the vaginal canal, a numbing spray nozzle to anesthetize the cervix, and an integrated light source to illuminate the internal anatomy for clinical examination. The same speculum head supports a vaginal sweep using embedded imaging components and sensors to capture interior anatomical data. The captured data is wirelessly transmitted to a companion digital twin system that includes a processor, memory, and smart display. The system implements multi-spectral imaging configured to generate a digital twin of the patient's anatomy, which may be used for assessment, diagnosis, treatment planning, education, and analysis with artificial intelligence and extended reality platforms. A portable housing station serves as both a charging dock and sanitization unit.

The invention is suitable for the technical field of image transmission, and provides an image stream transmission method and device and a computer program product. The method comprises the following steps: in response to a device binding operation of a user, starting a scanning function of a wearable display terminal to scan a device identification code of a medical device, and obtaining a network address and communication port information of the medical device; based on the network address and the communication port information, initiating a remote connection establishment request carrying the equipment authorization customer dependence information to the medical equipment so as to establish a remote procedure call connection with the medical equipment; based on the remote procedure call connection, sending a first media connection establishment parameter to the medical equipment, and receiving a returned second media connection establishment parameter; establishing point-to-point media transmission connection with the medical equipment according to the first media connection establishment parameter and the second media connection parameter; and based on the point-to-point media transmission connection, receiving and displaying the image stream pushed by the medical equipment, so as to improve the image access efficiency in the clinical examination process.

1. Name of the designed product: surgical microscope. 2. Use of the designed product: for clinical examination and surgery. 3. Design points of the designed product: in shape. 4. Picture or photo that best shows the design points: front view.

The application discloses a diabetes patient biological age calculation method based on glycosylation markers and a multi-task deep learning framework, and belongs to the technical field of bioinformatics and medical data processing technology, and the method comprises the following steps: obtaining glycomics feature data and clinical examination data of diabetes patients; preprocessing the data; obtaining a feature set by adopting a multi-method screening and fusion strategy; constructing a deep learning model comprising a multi-modal feature fusion module and a multi-task learning module for training, wherein the multi-task learning module comprises a main task of aging clock regression and at least one auxiliary task; and outputting biological age prediction values and age acceleration evaluation results of individuals by using the trained model. The method realizes deep fusion of multi-modal biological data and exclusive modeling for the diabetes population, can accurately quantify the biological aging process and the deviation degree relative to the calendar age, and provides an objective quantitative tool for clinical evaluation.

The invention provides a probiotic strain formula scheme screening method. The method comprises the following steps: establishing a disease model database according to a clinical examination result, performing standardization processing and data layering on the disease model database to obtain a layered database, scoring and grading diseases in the layered database, and establishing a disease model grading data matrix of patients; establishing a strain curative effect matrix according to the strain database and published clinical research data; and associating the disease model grading data matrix with the strain curative effect matrix, screening a relationship with high association strength, constructing a disease-microbial treatment response model, and obtaining different types and different levels of diseases and corresponding recommended bacterial systems through the disease-microbial treatment response model. And grading the synergistic effect of the disease and the recommended strain, filtering the score through a threshold value to screen out a scheme of a strain formula, and outputting the scheme of the strain formula through a user interface.

The present application relates to a kind of POVIC drug efficacy prediction method, the prediction method includes: obtaining prediction object, lung function index FEF 50％ And exhaled nitric oxide (FeNO), three data are processed by regression, obtain P value, when P value is less than or equal to preset value, predict the drug effective for treating POVIC as: compound methoxyphenamine and ICS / LABA joint;When P value is greater than preset value, predict the drug effective for treating POVIC as: compound methoxyphenamine is used alone.The present application also provides corresponding prediction device, computer readable storage medium and its electronic equipment.The two clinical examination indexes used can be obtained by hospital lung function result report, without carrying out complex additional examination, greatly reduce the examination times and examination cost of patient.

The invention relates to an intelligent clinical heat preservation device for newborns and a control method, and the intelligent heat preservation device comprises a box body, a mattress composed of a plurality of independent supporting units, lifting mechanisms correspondingly connected, a visual recognition device and a controller; recognizing the outline of the newborn through a visual device, driving the first target unit located in the area below the newborn to descend to form a downward concave area, and driving the second target unit close to the peripheral side of the newborn to ascend to form a surrounding structure. According to the intelligent heat preservation device, the shape of a bed surface is accurately controlled through visual feedback, profiling supporting and lateral limiting of a newborn are automatically achieved, the problems that manual fixing is unstable, image offset is likely to be caused, and operation is tedious are effectively solved, and the stability, safety and operation efficiency of posture limiting in clinical examination are remarkably improved.

The utility model relates to a child restraint device for bronchoscopy and an examining table. The child restraining device is installed on a bed board of the bronchoscopy bed and comprises fixing rods symmetrically arranged on the edges of the two sides of the bed board, two sliding supports are independently arranged on each fixing rod in a sliding mode, and fastening rotary knobs used for fixing the positions of the sliding supports are arranged on the sliding supports. A chest and abdomen restraint strap or a leg restraint strap is arranged between the corresponding sliding supports on the two sides in a penetrating mode. The child restraint device further comprises a head restraint assembly arranged on the bed board, and the head restraint assembly comprises a set of head limiting plates and a driving assembly used for driving the head limiting plates to be close to each other or away from each other. Compared with the prior art, the child restraint device has the advantages that through cooperation of the chest and abdomen restraint strap, the leg restraint strap and the head restraint assembly, turning over and twisting of a child patient can be effectively limited during bronchoscopy, and clinical examinations such as bronchoscopy and the like are facilitated.

The invention relates to a chronic liver disease assessment method based on a multi-classification model. The method comprises the following steps: acquiring clinical examination data of a patient to be diagnosed; the clinical examination data comprises blood routine data and biochemical data; inputting the clinical examination data into a pre-trained multi-classification hepatopathy auxiliary diagnosis model to obtain a chronic hepatopathy evaluation result; the chronic liver disease evaluation result comprises subdivided liver disease types and corresponding confidence and diagnosis result contribution characteristics; the multi-classification liver disease auxiliary diagnosis model is formed by sequentially connecting a first-stage large-class classifier, a second-stage exclusive feature activation layer and a second-stage fine classifier; and obtaining a chronic liver disease auxiliary diagnosis report according to the chronic liver disease evaluation result. By the adoption of the method, blood routine and biochemical data which are clinically and easily obtained can serve as input, subdivided liver disease types, confidence coefficients and contribution characteristics are rapidly output through the hierarchical multi-classification model, a structured auxiliary report is generated, diagnosis efficiency and precision are considered, all levels of medical scenes are adapted, and standard diagnosis and treatment and early intervention are assisted.

The embodiment of the invention provides a similarity calculation method and device based on multi-dimensional clinical data, equipment and a medium. The method comprises the steps of obtaining target patient data and to-be-compared patient data in a clinical database; a first similarity coefficient between the target patient data and the patient data to be compared is then calculated through a continuous attenuation function. According to the order level difference of the first clinical examination result between the target patient data and the patient data to be compared, a second similarity coefficient is obtained; then, calculating the toxicity vector similarity between the target patient data and the patient data to be compared to obtain a third similarity coefficient; and finally, performing weighted summation on the first similarity coefficient, the second similarity coefficient and the third similarity coefficient to obtain a comprehensive similarity score between the target patient data and the patient data to be compared. In this way, the accuracy and reliability of retrieving similar cases in the clinical database can be improved.

A method and apparatus for identifying a vulnerable coronary plaque based on a multimodal large language model (MM-LLM) are provided. The method includes: acquiring a target 3D coronary computed tomography angiography (CCTA) image and a target straightened curved planar reformation (SCPR) image; acquiring plaque mask information of a blood vessel based on the target SCPR image; acquiring basic plaque data based on the plaque mask information; acquiring fluid dynamics data of each plaque area based on the SCPR image; acquiring basic clinical testing information; standardizing above image data, structural data, and textual data separately, and performing, by a regression mapping network, feature fusion to acquire a first fusion feature; acquiring a trained vulnerable plaque identification LLM; and inputting the first fusion feature into the vulnerable plaque identification LLM to acquire an identification result. The method solve problems of poor single-image feature expression ability and low identification performance in traditional technologies.

A decision support system that aids healthcare practitioners in making more informed clinical decisions and avoiding errors related to diagnosis and treatment of diseases. The system utilizes several data points from the patient history and clinical findings input by the patient and the doctor, to help the doctor make a more accurate diagnosis and develop a more informed treatment plan that incorporates not just drugs and procedures, but also dietary and lifestyle interventions. A system of the present disclosure comprises dosage calculator, symptom checker, differential diagnosis, drug interaction checker, side effect checker, nutritional analyzer and drug-food interaction checker input pathways and corresponding database compartments. Output data is generated in correspondence with patient input data and stored on a database server, where it is correlated with patient outcomes over time and improved through machine learning.

The invention relates to the technical field of tooth inlay repair, in particular to an inlay repair quality intelligent grading evaluation method and system. Clinical examination data at different times after a target tooth is repaired and an SEM image under a multi-angle light source are obtained, a microscopic 3D image is constructed based on an image recognition and segmentation technology, key microscopic parameters are calculated, then the microscopic parameters and the clinical data are fused into feature vectors, and the feature vectors are used as feature vectors. Comprehensive evaluation and risk classification of the future health state of the inlay are achieved through a time sequence prediction model, the repair quality grade is finally output, micro-morphology data and macroscopic clinical evaluation indexes are systematically fused, the problem that evaluation is inconsistent due to the fact that traditional methods depend on subjective experience of doctors is solved, and the method is suitable for popularization and application. Through quantitative analysis, the objectivity of evaluation is remarkably improved, and manual operation deviation is reduced; the technical problems that an existing inlay repair quality intelligent evaluation method has subjectivity and is difficult to quantify, and microscopic and macroscopic information is not fused are solved.

The application provides a medical cell detection method, comprising: S1: collecting a cell image for preprocessing; S2: performing structural processing and encoding processing on multi-modal data; S3: performing feature extraction on the cell image and the multi-modal data; S4: fusing the cell image and the multi-modal data; S5: inputting the fused feature vector into a segmentation head of FastSAM; S6: generating a segmentation mask of the image; S7: judging whether the cell is abnormal; S8: for the cell with the abnormality, resampling and culturing the cell; S9: collecting a cell image in a cell culture device in real time for preprocessing; and S10: inputting the cell image into a FastSAM model, and analyzing indexes of the cell based on the generated segmentation mask; the application combines the cell image and multi-modal data such as a case and a clinical examination result, more comprehensively understands characteristics of the cell, and improves detection accuracy.

This invention discloses a syncope medical history collection system, terminal, computer equipment, and storage medium. The medical history collection system includes: an automatic collection module, a recording module, an information filtering module, a structured storage module, an automated etiology discrimination module, a testing and analysis module, and a guidance and suggestion module. This invention, through a syncope medical history auxiliary collection system, combines the needs of clinical diagnosis, treatment selection, and scientific research management. It records, collects, and structures the information related to the admission of syncope patients. The testing and analysis module calls an existing XGBoost training model to automatically discriminate the etiology of syncope in new users. Finally, the predicted etiology results from the testing and analysis module pop up the next set of test kits, guiding the next etiology diagnosis and clinical examination plan, and assisting doctors in investigating the cause of syncope in patients and in clinical diagnosis and treatment.

The application introduces a kind of blood vessel diameter automatic measurement method for fundus OCT image.Retinal blood vessel diameter measurement is an important clinical examination method, which can be used for the diagnosis and monitoring of ophthalmic diseases and cardiovascular diseases.The traditional half-peak full-width measurement method has higher requirements for the medical level of operators and limited applicability, while the present method realizes efficient and accurate measurement through a two-stage model.In the first stage, the approximate area of the blood vessel is obtained by using U-Net network, and in the second stage, the edge attention network (EAT) is used for accurate segmentation of the blood vessel area.The feature fusion module uses different fusion methods to meet the requirements of measurement speed and accuracy.The method has high efficiency and accuracy, and reduces the influence of human error.The neural network model trained by a large amount of data can accurately identify and measure retinal blood vessels of different shapes and diameter ranges, and is suitable for the diagnosis and monitoring needs of various ophthalmic and cardiovascular diseases.

This invention concerns a centralized control panel device for monitoring and controlling multi-station clinical examination rooms, specifically for the implementation of Objective Structured Clinical Examination (OSCE). The invention consists of a main control panel connected to modules in each examination room via a data communication system. Each room module integrates information technology readiness indicators, logistics readiness indicators, and emergency (panic) condition indicators that automatically send status information to the main control panel in real time. The main control panel displays the identity of each room and its operational status so that operators can monitor all examination rooms simultaneously from a single monitoring point. The system is also equipped with a centralized time synchronization mechanism to standardize the implementation of examinations across all stations and an alarm priority mechanism that automatically identifies the location of the room in the event of an emergency.This configuration allows for faster, more precise, and integrated coordination of exam implementation, monitoring of each room's readiness, and handling of operational disruptions. This invention enhances the effectiveness of supervision, expedites emergency response, and increases the efficiency of multi-station clinical skills exam administration.

This invention provides a perinatal full-cycle intelligent intervention method based on multi-source heterogeneous data fusion, comprising: step S100, simultaneously collecting subjective self-reported data from pregnant women, real-time physiological data from wearable devices, and heterogeneous clinical examination data to construct a multi-dimensional spatiotemporal data pool; step S200, establishing a unified time base axis with gestational age and absolute time as dual coordinate axes, and extracting feature vectors from the data in the multi-dimensional spatiotemporal data pool at fixed time steps; step S300, calculating the real-time global comprehensive risk index RI based on the feature vectors; step S400, when RI exceeds the first dynamic threshold T1, the system triggers a level-one warning; when RI exceeds the second dynamic threshold T2 and a preset acute-critical feature operator is identified, the system triggers a level-two warning, and simultaneously generates an admission preparation list and sends a rescue instruction to the hospital's emergency dispatch system.

The application discloses a photon CT non-electrocardiogram gating lung CT plain scanning coronary artery calcification score evaluation system and relates to the technical field of coronary artery calcification score evaluation.The CT data acquisition module, the coronary artery calcification identification module, the score calculation and evaluation module and the risk evaluation generation module directly count X-ray photons, eliminate electronic noise, improve the signal-to-noise ratio and the contrast-to-noise ratio, in the conventional chest low-dose CT, without electrocardiogram gating, realize the automatic processing from the low-dose lung CT plain scanning data acquisition to the structured report generation, without manual data transmission and intervention among the links, integrate the coronary artery calcification evaluation into the conventional lung CT examination process, avoid the additional burden of the patient needing to separately perform coronary artery CT scanning, improve the examination efficiency, reduce the error possibly introduced by manual operation, ensure the consistency and reliability of the evaluation result and optimize the clinical examination and diagnosis process.

This utility model discloses a portable ocular surface imaging device, relating to the field of clinical testing technology. The portable ocular surface imaging device includes a housing with an opening on one side for placing a camera inside the housing, and a Placido disk assembly. The Placido disk assembly includes a Placido disk mounted on the housing and is conical in shape. The top of the Placido disk has a through hole, and the lens of the camera is located within the projected area of ​​the through hole. By reducing the overall size of the housing, the operator can hold the device with one hand during the imaging process, making it more portable and flexible in different environments. It is more suitable for clinical examinations or home use, reducing the user's cost and difficulty of use.

The embodiment of the invention discloses a mammal ovulation prediction method and system based on multi-source clinical information fusion, and the method comprises the steps: obtaining the medical image data of a target animal generated in a conventional clinical examination process, and carrying out the preprocessing of the obtained medical image data; performing analysis according to the follicle image to obtain reference ovulation remaining time and a reference ovulation state in a preset time window; analyzing according to the cervical image to obtain an ovulation stage evaluation result; analyzing according to the uterus image to obtain the corresponding ovulation condition for reflecting the state change of the uterus tissue; and generating a comprehensive ovulation prediction result of the target animal according to the ovulation remaining time, a reference ovulation state in a preset time window, an ovulation stage evaluation result, a result obtained by uterus image analysis and an artificial experience evaluation result. Therefore, an ovulation prediction result which is available in small samples, easy to deploy, high in interpretability, accurate in prediction result and stable can be provided based on conventional clinical data.

The periodontal probe comprises a detection mechanism, a pressure measuring device and a handle. The detection mechanism is arranged at the far end of the handle; the pressure measuring device comprises a pressure detection probe and a pressure prompting mechanism; the pressure detection probe is arranged on the working part of the detection mechanism, the pressure prompting mechanism is arranged on the handle, and the pressure applied to the gingiva by the working part is prompted in real time on the pressure prompting mechanism after being detected by the pressure detection probe. According to the periodontal probe, after force applied to the working part is detected through the pressure measuring device, real-time prompting is carried out in the modes of pressure value prompting, and / or pressure range prompting, and / or pressure state prompting and the like, so that it is guaranteed that probing and diagnosing force applied by probing and diagnosing personnel in clinical application is always controlled within a proper pressure range, and the probing and diagnosing efficiency is improved. Therefore, the working part can detect the bottom of the periodontal pocket, gingivae cannot be punctured due to too large force, and effective and safe clinical examination is guaranteed.