59 results about "Patient model" patented technology

The invention discloses an artificial intelligence-assisted standard artificial temporomandibular joint automatic placement method. The method comprises the following steps: training a three-dimensional reconstruction model used for extracting a mandible and zygomatic bone zygomatic arch joint prosthesis placement area; based on an improved 3D U-Net neural network, carrying out segmentation extraction on the interested areas of the glenoid fossa and the mandibular branch, and obtaining a space geometric structure for prosthesis installation; the method comprises the following steps: extracting outer bone surface point cloud data of a zygomatic arch and a mandibular ramus on the basis of a space geometric structure of prosthesis installation, identifying anatomical key points, and generating a standard prosthesis fitting surface through geometric fitting and constrained optimization; determining the relative position relation between the maxillary joint fossa prosthesis and the mandibular branch prosthesis, and determining the installation direction, the hole position definition and the assembly reference point; and determining a contact area, a posture direction and a placement position of the prosthesis, and completing three-dimensional positioning and posture matching of the prosthesis in the patient model as a surgical planning scheme.

The invention discloses a medical training evaluation method and system based on an intelligent simulation patient, and relates to the field of artificial intelligence technology and medical simulation, and the method comprises a virtual patient model construction step, a multi-modal perception step, an intelligent interaction step and an intelligent evaluation step. By integrating voice recognition, natural language understanding, facial expression recognition, gesture recognition and virtual reality technologies, a high-simulation and high-interactivity intelligent patient model is constructed for medical students or clinical medical staff to perform diagnosis and treatment training and skill operation assessment. The virtual patient model supports custom information such as age, gender, race, medical history, living habits and the like, different virtual patient images and different pathophysiological states are generated, and personalized learning requirements of users are met. In addition, targeted training suggestions are provided, the training difficulty and content can be adjusted according to the performance of the user, and different training requirements are met.

Methods, systems, and apparatuses are described for associating dielectric properties with a patient model.

The invention relates to the technical field of data analysis, in particular to a VR-based CT room operation virtual training method and system. The method comprises the following steps: acquiring an equipment model and a patient model in current CT training operation; analyzing a relative position relationship between the equipment model and the patient model at the initial position to obtain an initial abnormal value; analyzing posture changes of a plurality of limb parts of the patient model before and after the limb adjustment operation to obtain a plurality of posture anomaly indexes; according to the initial abnormal value, analyzing the change of an overlapping region between a plurality of limb parts of the patient model and the equipment model in the examination process of the current CT training operation, and obtaining a plurality of position abnormal indexes; and obtaining an operation evaluation result of the current CT training operation according to the plurality of attitude anomaly indexes and the plurality of position anomaly indexes. According to the invention, the evaluation accuracy of the abnormal operation condition of the CT training operation can be improved.

The invention relates to a urine sugar quantitative analysis system and belongs to the technical field of detection systems. The quantitative analysis system for urine sugar comprises a model generation unit, a quantitative analysis unit and a curve generation unit. On the basis of establishing a patient model, a quantitative analysis result of urine sugar of a patient is calculated according to the change condition of physical sign data of the patient and the patient model, and a urine sugar change curve is generated. The urine sugar quantitative analysis result is obtained without depending on laboratory detection equipment, the urine sugar information of a patient can be expressed in a centesimal system, and the urine sugar data precision is further improved to about 0.2 mmol / L. Compared with traditional urine sugar qualitative detection, the patient can more accurately know the urine sugar state, a change curve is drawn based on high-precision urine sugar data, and the accuracy of the urine sugar quantitative analysis result is improved. The change trend of urine sugar is accurately displayed. The urine sugar quantitative analysis system can be conveniently realized through a mobile phone, a tablet computer and other mobile terminals, and is particularly suitable for daily household urine sugar monitoring by a patient by using the system provided by the invention.

A system, and related method, operable on a processor and memory for predicting and prescribing a treatment to a disease for a patient, configured to collect population data about the disease, build a population and patient model based on the population data, record patient factors of the patient associated with the disease, and anonymize the patient factors by creating synthetic data of the patient factors. The system is also configured to merge the patient factors into the population and patient model, prescribe the treatment to the disease for the patient based on predicted outcomes from the population and patient model, and store the treatment to the disease for the patient in the memory.

The present disclosure provides systems and methods for providing neurostimulation therapy according to gait features. The gait features may be analyzed to develop a patient model between gait features and optimal settings for a neurostimulation therapy using machine learning operations. The model is used to control ongoing neurostimulation therapy for the patient.

The present disclosure provides systems and methods for providing neurostimulation therapy according to patient features. The patient features may be analyzed to develop a patient model between physiological and / or patient reported features and optimal settings for a neurostimulation therapy using machine learning operations. The model is used to control ongoing neurostimulation therapy for the patient.

The invention relates to the technical field of breathing machines, in particular to a real-time breathing machine parameter optimization system based on a digital twinning technology, which comprises a patient modeling module for acquiring sensor data of an external sensor and establishing a patient digital model according to the sensor data; the breathing condition analysis module is used for analyzing the breathing machine data according to the patient digital model to obtain an analysis result; and the parameter adjusting module is used for adjusting the control parameters of the breathing machine according to the analysis result. Aiming at the problem of poor control effect of a respirator in the prior art, a patient modeling module is arranged in the scheme, a patient digital model is constructed through a digital twinning technology, and then a breathing condition analysis module analyzes respirator data according to the patient digital model to obtain a more accurate analysis result; and the subsequent parameter adjustment process is more in line with the actual situation of the user.

The invention provides an illness state tracking and early warning system based on a knowledge database, and the system comprises a data module which is responsible for collecting and integrating clinical knowledge and patient data information in the cardiovascular field; the survival rate prediction analysis module is used for extracting pathological features from the patient model, performing survival rate prediction analysis by using a deep learning algorithm and a neural network model, and displaying a prediction result to a physician in a visual report form; and the illness state auxiliary tracking, studying and judging module monitors the illness state change of the patient in real time, analyzes the illness state development trend and risk factors in combination with a knowledge graph and a patient model, and provides treatment scheme recommendation and early warning notification functions. Through the beneficial effects of integrating medical resources, improving data security, accurately predicting the survival rate of a patient, monitoring and early warning in real time, widely applying a knowledge graph, being friendly to user interaction, feedback circulation and continuous optimization and the like, powerful support is provided for prevention, diagnosis and treatment of cardiovascular diseases.

A three-dimensional (3D) digital image of an individual patient marked with target therapeutic locations on a skin surface of the patient is used for locating those treatment locations on a patient's skin for fascial manipulation and other treatments. The 3D image may be obtained by merging an unmarked 3D digital patient model image converted from a 2D optical image with a “generic” musculoskeletal digital model having optimized target therapeutic locations distributed over a skin surface thereof. The generic musculoskeletal digital model may be obtained from a library of such images.

For patient weight estimation in a medical imaging system, a patient model, such as a grid, is fitted to a depth image. One or more feature values are extracted from the fitted patient model, thereby reducing noise and clutter in the values. The weight estimation is regressed based on the extracted features.

The invention belongs to the technical field of diabetes diagnosis and treatment training, and provides a diabetes standardized digital intelligence patient diagnosis and treatment training platform based on a knowledge graph, and the platform comprises a knowledge graph construction module which is used for collecting diabetes related data in multiple channels; the digital intelligent patient model generation module is used for creating a dynamic digital intelligent patient model based on the knowledge graph; the diagnosis and treatment training function module provides a vivid clinical diagnosis and treatment interface; an evaluation feedback module; the comprehensive and accurate knowledge graph is constructed, and the dynamic digital intelligent patient model is created, so that the platform not only effectively integrates diabetes related data acquired in multiple channels, but also provides vivid clinical diagnosis and treatment training and rich case learning resources for medical staff; and meanwhile, through automatic and comprehensive evaluation feedback, the platform is helpful for the medical personnel to timely discover own defects and seek a promotion way, so that the efficiency and the quality of diabetes diagnosis and treatment training are improved, and powerful support is provided for occupational development of the medical personnel.

A patient's health is modeled through multiple scenarios. A base model incorporates rules that govern a response by a human being to one or more diseases, as well as a relation between health metrics and the diseases. Health attributes of the patient are obtained. From the base model and the health attributes, a patient model is generated. The patient model is modeled under different parameters to generate health metrics. From an analysis of the parameters and the resulting health metrics, occurrence probabilities for each of the sets of parameters are determined. Risks are identified, which indicate a likelihood of the patient transitioning from the initial state to an adverse outcome such as a diseased state. A report provides a diagnosis of the patient and one or more remedies / interventions that are predicted, based on the plural sets of parameters and resulting health metrics, to avoid or prevent an adverse outcome.

System (SYS) and delated methods for supporting an imaging operation of an imaging apparatus (IA) capable of assuming different imaging geometries. The system comprises an input interface (IN) for receiving a current image acquired by the imaging apparatus (IA) of a current region of interest (ROI_1) at a current imaging geometry (p). A pre-trained machine learning component (MLC) computes output data that represents an imaging geometry change (Δp) for a next imaging geometry (p′) in relation to a next region of interest (ROI_2). An output interface (OUT) outputs a specification of the imaging geometry change.

The invention relates to the technical field of virtual simulation, in particular to a child electronic bronchoscope operation emergency rescue simulation training system which comprises a VR device used for presenting a virtual scene of one or more emergency conditions of a virtual patient in a child electronic bronchoscope operation; the patient model is used for being operated and used by an operator; the camera is used for collecting emergency rescue operation executed by an operator aiming at the virtual scene of one or more emergency conditions of the virtual patient; the processing module is connected with the VR equipment and the camera, and is used for judging whether the emergency rescue operation is correct or not, obtaining a judgment result, prompting an operator based on the judgment result, providing a changeable emergency rescue training environment through a virtual scene presented by the VR equipment, providing a more real simulation training feeling for the training of the operator, and improving the training experience of the operator. Therefore, the effectiveness of sudden emergency rescue training in the child electronic bronchoscope operation is improved.

The application discloses a kind of real-time non-rigid registration method and system of surgical navigation image based on deep learning, comprising: calibration the space transformation matrix between RGB-D camera and medical imaging equipment;RGB-D camera real-time capture patient whole body optical image and depth information;Medical imaging is carried out to patient, while reconstructing the initial model of patient based on SMPL based on human posture estimation neural network of deep learning;Medical image is point cloud, and the point-to-plane spatial position matching relationship between medical image and the initial model of patient is established;Neural network reconstructs the dynamic change of patient model in operation in real time, and the non-rigid deformation field of medical image is solved by matching relationship;Registration medical image, update display.The application can realize the real-time non-rigid registration of surgical navigation medical image to different body posture patient, solve the movement, deformation of organ, soft tissue caused by patient posture change in surgical navigation, thereby cause the problem of medical image failure, help to improve the accuracy of surgical navigation.

A computer-implemented method for generating, by one or more computer processors, a three dimensional model for use in assisted navigation of a patient's oral cavity is provided.SOLUTION: Receiving 302 a first dataset comprising surface boundary information, generating 304 a digital patient model from at least a portion of the first dataset, performing 306 a 3D surface scan of a portion of an intraoral cavity using a 3D scanner, the 3D surface scan comprising a region of interest, aligning 308 the acquired 3D surface scan to at least a portion of the digital patient model, determining 310 a spatial transformation configured to align or register the acquired 3D surface scan and the 3D digital patient model, and using at least the transformation: Determining 312 position and orientation information of the 3D scanner relative to the digital patient model and generating 314 a second dataset comprising the position and orientation information of the 3D scanner relative to the 3D patient model.SELECTED DRAWING: Figure 2A

Methods, systems, and apparatuses are described for associating dielectric properties with a patient model.

The present disclosure shows a generated, large-scale and realistic patient dataset that mimics real patient data distributions, supports multiple treatments, and provides ground truth for the effects of these treatments. The datasets generated are of synthetic patients modeled on a large nationwide cohort of real patient data including their history of diagnoses, medications, and laboratory values. A data generation process is designed by adapting an Anonymization Through Data Synthesis Using Generative Adversarial Networks (ADS-GAN) model for fictitious patient information generation and using a neural network for treatment outcome generation. The synthetic dataset demonstrates strong similarity to the original dataset as measured by the Wasserstein distance. In addition, privacy of the original patients is preserved so that the dataset can be made available to the research community to evaluate causal inference models.

The application discloses a doctor-patient joint decision-making method based on LLM-Agent multidisciplinary dynamic cooperation and relates to the technical field of doctor-patient joint decision-making. The method comprises the following steps: acquiring a disease description, extracting symptoms and signs by an LLM, assigning a department according to the symptoms and signs by the LLM, acquiring a multidisciplinary team composed of doctor agents of the corresponding department, independently analyzing the disease description by each doctor agent, generating a scheme, then integrating the schemes, and determining whether to adopt the scheme as a treatment scheme by a voting review mechanism. Patient preferences are extracted from the disease description based on a predefined preference format and a pre-constructed lightweight LLM. Then, a patient model is constructed based on the patient preferences and the disease description. Potential conflicts between the treatment scheme and the patient preferences are identified by an LLM. The patient agent quantitatively evaluates whether the treatment scheme is satisfactory according to the potential conflicts. If not, the next iteration is entered, otherwise the negotiation is stopped. The treatment scheme when the negotiation is stopped is output.

The invention relates to the technical field of medical instruments, and discloses a lung ultrasonic teaching and training simulation system and a use method. The system comprises a simulation probe, a patient model, a storage module and an ultrasonic image acquisition module, the simulation probe comprises a first positioning module and an angle checking module, and the patient model comprises a second positioning module; the first positioning module and the second positioning module determine the position information of the simulation probe on the patient model; the storage module is used for storing lung ultrasonic images of the plurality of simulation plates and position information generated by the first positioning module and the second positioning module; and the ultrasonic image acquisition module is used for acquiring and displaying a corresponding ultrasonic image in combination with the position information and the current simulation plate. According to the invention, the lung ultrasonic examination process can be effectively simulated, long-term special learning can be conveniently arranged by learners, and the training cost can be reduced.

The invention discloses a simulated patient construction method and system for intelligent diagnosis and treatment evaluation, and the method comprises the steps: constructing a data specification of a standard patient, and dividing the standard patient data into basic layer data and behavior layer data; processing according to the doctor-patient dialogue data in the real scene and the corresponding medical record data to obtain seed data of large-model synthesis dialogue data; carrying out standard patient model training; the basic layer information and the behavior layer information are input into the evaluation system, the patient is simulated to start multiple rounds of dialogues with the intelligent diagnosis and treatment model, and evaluation indexes include fluency, safety and accuracy, question-seeking reasonability, friendliness and context relevance. The dynamic standard patient construction method oriented to the large model intelligent diagnosis and treatment system can be effectively realized, and the performance of the intelligent diagnosis and treatment model in dynamic dialogues can be effectively evaluated by simulating multiple rounds of dialogue behaviors of a real patient.

The invention belongs to the technical field of biological diagnosis, and provides an application of histone H3K27 acetylation in early diagnosis of non-infectious uveitis, which is characterized in that the histone H3K27 acetylation level is used as a judgment marker of early non-infectious uveitis. According to the invention, the acetylation expression level of histone H3K27 in cross-model and cross-species non-infectious uveitis is evaluated by establishing an EAU mouse model, an IL-17A induced human RPE cell model and an NIU patient model; the result shows that the acetylation level of the histone H3K27 is obviously reduced in three non-infectious uveitis models, and the histone H3K27 can be used as a diagnostic marker of the non-infectious uveitis.

The invention discloses a dynamic optimization method and device for medical treatment resource reservation, equipment and a medium. The method comprises the following steps: acquiring and preprocessing multi-dimensional panoramic data; constructing a bimodal patient model of static clinical portrait and dynamic state evolution, and combining a dynamic weight clinical index evaluation and clinical priority dynamic quantification method to obtain clinical features of the patient; obtaining an inspection time length prediction result, and constructing an inspection operation constraint matrix to obtain an inspection operation constraint rule; an MADDPG multi-agent resource scheduling model under the CTDE framework is constructed, and a resource scheduling joint optimization strategy is obtained through multi-agent joint training; and generating a reservation scheme based on the resource scheduling joint optimization strategy, and performing rolling updating on the reservation scheme based on a look-ahead rolling rescheduling mechanism. The invention belongs to the field of diagnosis strategy optimization. According to the invention, a more reasonable doctor-seeing appointment strategy can be provided for the doctor-seeing personnel.

The application discloses a somatosensory interaction tactile feedback fusion training system for nursing teaching and belongs to the technical field of nursing teaching, and specifically comprises the following steps: establishing a student operation behavior vector library; analyzing the operation behavior vector library and constructing a parameterized virtual patient model; extracting palpation depth deviation values and pressure distribution deviation amounts, integrating the same into an inference deviation parameter set; deconstructing a physiological parameter space to identify inference deviation, establishing an adversarial variation instance generation rule; inferring the deviation parameter set and corresponding physiological parameter adjustment amount based on a historical training cycle of an application rule, training an output parameter change strategy; obtaining the inference deviation parameter set based on real-time operation behavior vectors and inputting the parameter change strategy, and generating an adversarial variation patient instance as a distribution instance for a subsequent training cycle. Through directional generation of the adversarial variation instance, the application realizes accurate matching of student operation weaknesses and training content, and improves the migration efficiency of skills to a real clinical environment.

An automatic checkpoint identification system receives a user input including patient health information or pre-operative images. The system generates, as an output of a patient model estimator, a 3D patient model with one or more anatomical checkpoints from the user input. The system receives, from an external imaging system, one or more imaging frames tracking a medical procedure. The system detects, by a controller, progress of the medical procedure based on a proximity of an intravascular device to one of the one or more anatomical checkpoints. The system generates, by a controller, an action recommendation based on the proximity.

A system for providing visualization during a medical procedure of a patient or a simulated medical procedure of a patient model, the system comprising: a. Means for receiving imaging data of a body of the patient or a first region of the patient model; b. Means for receiving tracking data of one or more instruments inserted in a second region of the patient's body or of the patient model; characterized in that: c. The system comprises means for receiving model data of a fourth region of the patient's body or of the patient model, and processing means adapted to collectively register the tracking data and the model data; d. The system comprises a display for simultaneous visualization of the co-registered data and the imaging data; e, the tracking data comprises three or more tracking points, and the three tracking points are not collinear; and / or one or more tracking points and roll, pitch and yaw angles or a set of Euler angles or a set of quaternion or angle-axis representations or a rotation matrix or a homogeneous transformation matrix; and / or a point cloud representation for at least one of the one or more instruments; f. The tracking data is used to determine the position and / or shape and / or orientation of at least one of the one or more instruments; and g. The visualization comprises a representation of the shape and / or position and / or orientation of at least one of the one or more instruments; and an associated method.

Provided is a computer-implemented method for creating a synthetic patient model comprising a synthetic patient image. The method comprises: obtaining a data set comprising medical information, wherein the medical information comprises an anatomical description comprising at least information specifying an anatomical structure to be depicted in the synthetic patient image, and imaging information specifying image formation characteristics of the synthetic patient image, and wherein the medical information optionally comprises anamnesis and physical examination descriptions; generating an anatomical map of the anatomical structure by means of anatomy modelling using the anatomical description as an input; conditioning a generative model using the anatomical map; embedding a subset of the medical information, the subset comprising textual information and including at least the imaging information, in the generative model; creating the synthetic patient model including a synthetic patient image by means of the generative model.

A patient's health is modeled through multiple scenarios. A base model incorporates rules that govern a response by a human being to one or more diseases, as well as a relation between health metrics and the diseases. Health attributes of the patient are obtained. From the base model and the health attributes, a patient model is generated. The patient model is modeled under different parameters to generate health metrics. From an analysis of the parameters and the resulting health metrics, occurrence probabilities for each of the sets of parameters are determined. Risks are identified, which indicate a likelihood of the patient transitioning from the initial state to an adverse outcome such as a diseased state. A report provides a diagnosis of the patient and one or more remedies / interventions that are predicted, based on the plural sets of parameters and resulting health metrics, to avoid or prevent an adverse outcome.