196 results about "Disease severity" patented technology

The invention relates to the technical field of crop disease recognition, in particular to a crop early disease recognition method and system based on time sequence feature fusion, and the method comprises the steps: obtaining an RGB image and a temperature feature image of a target leaf, and collecting multispectral feature data through a spectral imaging device; based on the time sequence image sequence, generating a coordinate transformation matrix of the first frame image by using a PnP algorithm, and aligning subsequent images according to the coordinate transformation matrix; multi-modal features are extracted by using a deep neural network, and the deep neural network comprises a 3D convolutional layer and an adaptive attention mechanism and is used for extracting features of space and time dimensions; realizing cross-modal feature fusion through a graph convolutional network based on the spectral data and the multi-modal features; inputting the fused features into a classifier, and generating the disease category and the disease severity of the target leaf based on the output of the classifier; outputting the disease transmission risk and the early warning result, and capturing the tiny dynamic change in the disease development process.

The invention relates to the technical field of computer vision, in particular to a plant leaf disease severity assessment method based on position-guided focus characterization learning, which comprises the following steps: acquiring a disease leaf image; the disease leaf image is input into a hierarchical lesion fusion evaluation network model, a leaf disease severity evaluation result is obtained, the hierarchical lesion fusion evaluation network model is obtained based on training of a real training set, the real training set is a leaf image marked with the disease severity, and the leaf disease severity evaluation result is obtained; the hierarchical lesion fusion evaluation network model comprises a feature encoder with priori knowledge, a hierarchical lesion feature fusion module and an evaluation module, the feature encoder with priori knowledge is obtained by inputting an image pair into a position-guided lesion characterization learning network for training, the image pair refers to health and disease states of the same leaf, and the evaluation module refers to the position-guided lesion characterization learning network. The leaf disease state is a lesion leaf generated from a healthy leaf through a diffusion model. According to the invention, more accurate positioning and severity evaluation can be carried out on the focus area.

The invention relates to the technical field of road maintenance and management, in particular to a pavement internal disease analysis method and system based on artificial intelligence. Five core processes of multi-layer sensor network real-time data acquisition, multi-modal data fusion and deep learning feature extraction, dynamic environment and use mode combined disease prediction and analysis, intelligent prediction and decision support system, and real-time disease condition evaluation and report generation are carried out. Through the technical means, comprehensiveness and timeliness of data acquisition, accuracy of disease identification and prediction, scientificity of a maintenance strategy and optimization of resource allocation are realized; the finally generated disease current situation report provides a detailed disease distribution diagram, disease type analysis and disease severity evaluation, comprehensive, accurate and timely disease information is provided for maintenance personnel, and the efficiency and effect of pavement maintenance and management are remarkably improved.

Presented herein are systems and methods that provide for improved detection and characterization of lesions within a subject via automated analysis of nuclear medicine images, such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) images. In particular, in certain embodiments, the approaches described herein leverage artificial intelligence (AI) to detect regions of 3D nuclear medicine images corresponding to hotspots that represent potential cancerous lesions in the subject. The machine learning modules may be used not only to detect presence and locations of such regions within an image, but also to segment the region corresponding to the lesion and / or classify such hotspots based on the likelihood that they are indicative of a true, underlying cancerous lesion. This AI-based lesion detection, segmentation, and classification can provide a basis for further characterization of lesions, overall tumor burden, and estimation of disease severity and risk.

The present disclosure provides systems and methods for machine learning classification and assessment of COVID-19 disease based on gene expression data, including prediction of disease severity. In an aspect, a method for determining a COVID-19 disease state of a subject may comprise: (a) assaying a biological sample obtained or derived from the subject to produce a data set comprising gene expression measurements of the biological sample of each of a plurality of COVID-19 disease-associated genes; (b) computer processing the data set to determine the COVID-19 disease state of the subject; and (c) electronically outputting a report indicative of the COVID-19 disease state of the subject.

The invention discloses a medical auxiliary diagnosis method and system based on a convolutional neural network, and relates to the field of medical big data analysis, and the method comprises the steps: collecting various types of medical data, which comprise medical image data, electronic medical record text data and vital sign monitoring data; constructing a convolutional neural network model with a multi-branch structure; preparing a training data set containing labeled samples, wherein labeled information comprises disease diagnosis results and disease severity grades; training the convolutional neural network model by using the training data set, dynamically adjusting the learning rate in the training process by adopting a stochastic gradient descent optimization algorithm and combining a learning rate attenuation strategy, and introducing a regularization method; inputting to-be-diagnosed medical data into the trained convolutional neural network model, and outputting disease diagnosis probability distribution and disease severity prediction results through forward propagation calculation of the model; and generating a medical auxiliary diagnosis report according to the output prediction result.

The invention discloses an examination item scheduling system and method based on patient examination demand optimization, and relates to the technical field of medical first aid, and the system comprises an information obtaining module which is used for obtaining the basic information and the emergency examination demand of a patient; the priority evaluation module is used for evaluating the priority of the patient based on the vital signs and the disease severity of the patient; the scheduling generation module is used for generating an optimized examination item scheduling table so as to ensure that high-priority patients are examined preferentially; the state monitoring module is used for monitoring the state of the patient in real time and dynamically adjusting the examination item scheduling table according to the state change, and the result sending module is used for sending the final examination item scheduling table to the corresponding medical equipment and the doctor terminal; according to the examination item scheduling system and method based on patient examination demand optimization, the problem that in the prior art, when critical patients in the emergency department are rapidly shunted, first-aid response is slow due to priority judgment errors is solved.

The invention relates to the technical field of atmospheric pollution monitoring, and discloses an atmospheric pollution safety alarm system, which comprises a pollutant monitoring unit used for receiving and analyzing pollutant concentration data of each monitoring point in a plurality of monitoring points in a target area, and determining excessive pollutants and early warning monitoring points. The user management unit is divided into a healthy user portrait data set and a disease user portrait data set according to the health state; obtaining a first user portrait data set according to the age of the healthy user portrait data set; and obtaining a corresponding early warning disease type and a disease severity level according to the disease description information of the disease user portrait data set. In the safety alarm unit, the early warning range is determined according to the standard exceeding grade of the standard exceeding pollutants and the position information of the early warning monitoring points; and screening user portrait data in the early warning range from the first user portrait data group to obtain a fixed user terminal identifier, and sending early warning information to a corresponding user terminal. Therefore, an alarm is given to a user when the atmospheric pollutants exceed the standard.

The invention relates to a hierarchical diagnosis and treatment resource allocation system based on an AI priority pre-auditing mechanism, and belongs to the technical field of medical resource allocation, and the system comprises a user input module which is used for receiving initial information of a patient based on an AI applet, and the initial information at least comprises a symptom description, a medical history record, examination data and a diagnosis and treatment stage; the AI intelligent pre-inquiry module is used for performing multiple rounds of questions and answers on the patient according to the initial information to extract an illness state index, inputting the illness state index into a preset risk layering model, and determining an illness state severity / urgency index of the patient; the resource distribution module comprises a special number source pool reserved for experts, and the resource distribution module is used for opening expert numbers for the patients whose illness condition severity / emergency index is greater than an illness condition threshold value; and the referral guidance module is used for recommending a replacement doctor seeing scheme for the patient who does not accord with the open expert number. According to the invention, the technical problem of insufficient fairness and efficiency of an illness state emergency degree registration distribution mechanism caused by structural mismatching of expert resources is solved.

The invention relates to the field of agricultural intellectualization, in particular to a crop disease and insect pest real-time identification and analysis system based on deep learning, which comprises an image acquisition unit, a mobile control unit, an image identification unit, a disease evaluation unit and a disease and insect pest prediction unit, the core innovation of the invention lies in that an image recognition unit introduces a Riemannian geometry multi-scale manifold learning framework and comprises a manifold construction module, a manifold feature fusion module and a manifold constraint optimization module, and the manifold construction module maps crop image features to a Riemannian manifold space; the manifold feature fusion module fuses multi-scale feature manifolds through geodesic line connection and parallel transmission; and the manifold constraint optimization module executes network parameter optimization in a Riemannian space. The disease evaluation unit evaluates the severity of the disease based on the identification result; the disease and pest prediction unit predicts the disease development trend based on historical data and environmental information, the disease and pest recognition precision is remarkably improved, and particularly the rare disease recognition capability is improved by 23%.

The invention discloses a turbid water area bridge pile pier disease intelligent detection method based on fluorescence radiography, and the method comprises the steps: obtaining a sound wave reflection signal, and judging whether a bridge pile pier has a disease or not; constructing an injection parameter prediction model of the fluorescence injection device, and determining injection parameters of the fluorescence injection device; obtaining a fluorescence distribution image of the surface of the bridge pile pier, and extracting a region contour of a disease region in the fluorescence distribution image; constructing a disease diagnosis model of the disease area, and judging the disease type and the disease severity of the disease area of the bridge pile pier; constructing a structural risk assessment model of the disease aggregation region, and assessing the structural risk degree of the disease aggregation region; calculating a disease area development rate, and generating a preventive maintenance strategy; and according to the bridge pile pier maintenance result, the early warning threshold value and the monitoring strategy are continuously adjusted. By combining a nondestructive testing technology, a fluorescent spraying technology and intelligent analysis, efficient detection and maintenance optimization of bridge pile pier diseases are realized.

The invention relates to a bridge degradation identification and maintenance decision support method and system based on a knowledge graph, belongs to the technical field of traffic infrastructure intelligent operation and maintenance and engineering information processing, and solves the defects of weak data fusion capability, opaque causal modeling and non-traceable decision support in the prior art. The method comprises the following steps: acquiring and preprocessing multi-source heterogeneous data to generate a standardized data set; semantic alignment is carried out, and candidate entities and relations are extracted; constructing a knowledge graph body and loading the knowledge graph body into a knowledge graph; a self-adaptive quantile threshold value is adopted to binarize the factor intensity and the disease severity sequence, and a smooth point mutual information and a Spearman correlation coefficient are fused to learn a causal weight; complementing the influence relation of factors on the bridge through graph reasoning and calculating the weight; and finally, calculating a bridge degradation risk score, and outputting a high-confidence influence path based on a shortest path algorithm. According to the method, multi-source data fusion and degradation causal chain explicit modeling are realized, and a scientific basis is provided for a bridge maintenance decision.

The present invention uses ex vivo human airway cultures to assess the human transmissibility and replication competence of influenza and coronavirus strains. By comparing pandemic influenza A subtype H1N1 and highly pathogenic avian influenza H5N1 as reference strains, the transmissibility risk of various viruses was evaluated and categorized. Additionally, an in vitro model evaluated virus-induced impairment of alveolar fluid clearance (AFC) as an indicator of disease severity. The study revealed correlations between bronchus viral replication, human transmission, AFC impairment, and clinical disease severity across different influenza and coronavirus strains.

The invention discloses a multi-classification auxiliary prediction method and system for metabolism-related fatty liver diseases, electronic equipment and a storage medium, belongs to the field of medical data processing, and is used for solving the problem that a traditional MAFLD binary prediction model cannot fully reflect continuous pedigree of disease severity. The method comprises the following steps: acquiring clinical data related to classification prediction of metabolism-related fatty liver diseases; performing label coding, missing value filling and feature screening on the clinical data; and inputting the screened features into a TabNet classification model optimized by a particle swarm algorithm, and outputting a risk classification result of the metabolism-related fatty liver disease. According to the method, the severity of the fatty liver can be more accurately evaluated, the liver health condition of a patient is comprehensively reflected, and more accurate treatment guidance is provided for clinical diagnosis.

The invention belongs to the technical field of biomedicine, and particularly relates to application of GPR161 as an acute distress syndrome diagnostic marker and a therapeutic target. Experiments prove that the expression level of GPR161 in peripheral blood mononuclear cells of a patient with the acute respiratory distress syndrome is remarkably increased, and the expression quantity of the GPR161 is positively correlated with the severity of the disease, so that the GPR161 gene or GPR161 protein can be used as a molecular marker for screening or diagnosis or prognosis evaluation of the acute respiratory distress syndrome; a reagent for inhibiting GPR161 gene expression or protein activity can be used for preparing a medicine for treating the acute respiratory distress syndrome. The invention provides a new strategy for diagnosis, monitoring and targeted drug development of ARDS, and has important clinical application value.

Provided herein are systems and methods for identifying a disease or disorder of a patient, identifying if a patient is likely to respond to a treatment for the disease or disorder, and / or predicting the clinical outcome of the disease or disorder of a patient. Systems and methods described herein may be directed to patients with different chronic conditions, inflammatory conditions, and / or autoimmune conditions. Systems and methods described herein may be directed to patients with a dermatological condition.

The invention provides a new bunyavirus neutralizing antibody screening method based on single cell BCR sequencing. The new bunyavirus neutralizing antibody screening method comprises the following steps: S1, collecting peripheral blood B cells of acute stage and recovery stage patients and healthy volunteers of new bunyavirus infected persons; s2, carrying out CD19 < + > CD38 < + > CD138 < + > magnetic bead separation to obtain a single-cell suspension; s3, constructing a single cell transcriptome and a BCR library, separating single cells by using a microfluidic system, and performing high-throughput sequencing; s4, analyzing a B cell subset, a BCR cloning amplification mode and a VJ gene pair enrichment characteristic through bioinformatics analysis; and S5, screening a specific BCR clone type related to the severity of the disease as a neutralizing antibody candidate target. The method provided by the invention provides powerful support for immune monitoring and vaccine design of new bunyavirus infection, and is expected to provide new strategies and methods for clinical treatment and prevention.

The invention provides an airway atomization flow intelligent drug delivery control method and system, and relates to the technical field of medical instruments.The method comprises the steps that basic information of the age, the weight and the illness state severity of a patient is obtained, and physiological parameters of the respiratory rate and the tidal volume of the patient are collected in real time through a sensor; inputting the basic information and the physiological parameters into a fuzzy adaptive control algorithm, and initializing an individual administration rule base according to the basic information; based on the real-time change trend of the respiratory rate and the tidal volume, three initial control index values including an atomization flow value, a drug concentration value and a time interval are dynamically generated through a membership function. According to the invention, through the full-process design of data acquisition, intelligent modeling, accurate execution and data closed loop, intelligentization of atomization treatment is realized.

The invention relates to the field of biological medicine, and discloses application of LPC, PC and AA in children sepsis diagnosis and prognosis product development. According to the invention, a high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS / MS) technology is used, plasma samples of a child sepsis patient and a healthy control group are compared, the relationship between lipidome change and pSOFA score is analyzed, and specific lipid molecules closely related to disease severity and prognosis are identified. According to the invention, the following lipid molecules are highlighted as key biomarkers: lysophosphatidylcholine (LPC), phosphatidylcholine (PC) and arachidonic acid (AA). The change of the lipid molecules is closely related to the physiological state of a child sepsis patient, and the lipid molecules can be used for early diagnosis and evaluation of the state of the child sepsis, so that the treatment effect and the accuracy of prognosis evaluation are improved, and a new treatment strategy and a new management method are provided for clinic.

17-Beta-hydroxysteroid dehydrogenase type 13 (17β-HSD13) plays an important role in the pathogenesis and progression of Non-alcoholic fatty liver disease (NAFLD), also known as Metabolic dysfunction-associated steatotic liver disease (MASLD), and Alcohol-related liver disease (ARLD). Loss-of-function variant of 17β-HSD13 has been associated with a significantly reduced risk of NAFLD (MASLD), cirrhosis associated with nonalcoholic steatohepatitis (NASH (MASH)), alcoholic-related liver disease, alcoholic cirrhosis, hepatocellular carcinoma (HCC), hepatitis C chronic liver disease, pediatric liver disease, NASH (MASH) disease severity, ballooning degeneration, lobular inflammation, and fibrosis. The present invention relates to hydantoin compounds useful as inhibitors of 17β-HSD13 and methods for their preparation and use for treatment and prevention of above mentioned liver diseases.

The invention discloses a potato late blight severity grading calculation system and method based on YOLOv8-UNet3Plus, and the system comprises an image collection module which is used for collecting a shadow-free potato leaf image through employing a bidirectional light source and a fixed pose camera; the leaf positioning module is used for optimizing a YOLOv8 network by using a space and channel redundant convolution ScConv and a bidirectional feature pyramid network BiFPN, positioning a plurality of potato leaves in the potato leaf image by using the optimized YOLOv8 network, and outputting bounding box information of each leaf; the scab segmentation module is used for optimizing the UNet3Plus network to obtain a lightweight UNet3Plus network, performing pixel-level segmentation on each leaf area by using the lightweight UNet3Plus network, and distinguishing a healthy area from a disease area; the grading calculation module is used for calculating the disease spot area proportion and dividing the disease severity grade of each leaf; according to the method, lightweight construction of the leaf positioning and scab segmentation network is realized, and the model parameter quantity, the calculation quantity and the terminal deployment cost are remarkably reduced.

The invention discloses an electrical stimulation therapeutic apparatus for ear vagus nerves, which comprises a USB power supply, a battery management module, an LDO voltage reduction and stabilization module, an MCU module, a Boost module, two stimulation current driving modules, an ear electrode and an ear electrode detection module, and is characterized in that the power supply management module is composed of a TP4056 chip, an external element, a power supply input USB Type-C interface and a battery connection interface; the external element is used for setting charging current, filtering and other functions, the power supply input interface can be connected with a USB power supply, the USB power supply is a lithium ion battery, and the battery connection interface is connected with the lithium ion battery. The therapeutic apparatus has flexible stimulation parameter adjusting functions including stimulation intensity, stimulation frequency, current direction, pulse width and the like so as to adapt to different diseases, different disease severity degrees and tolerance and reactivity differences of different individuals to stimulation, and accurate personalized treatment is achieved.

The invention belongs to the technical field of biological medicines, and particularly relates to bifidobacterium longum subsp.infantis and application of a microecological preparation of the bifidobacterium longum subsp.infantis in preparation of products for preventing and treating irritable bowel syndrome. The bifidobacterium longum subsp. Infantis disclosed by the invention is bifidobacterium longum subsp. Infantis B8762, and the preservation number is CGMCC (China General Microbiological Culture Collection Center) No.22765. The strain and the microecological preparation thereof can be used for improving the severity score of an IBS-SSS disease of a patient, improving the IBS-QOL life quality of the patient, reducing the score of a psychological assessment somatic symptom group scale PHQ-15 and reducing the score of a non-gastrointestinal somatic symptom scale PHQ-12, so that the disease severity of the patient is improved, and the life quality is improved; the strain and the microecological preparation thereof can be used for preparing products for preventing, relieving and / or treating irritable bowel syndrome.

The application provides a tobacco virus classification model construction method based on tobacco leaf hyperspectrum, and belongs to the technical field of tobacco virus classification models. Fractional differential spectrum enhancement processing is adopted, persistent homology eigenvalues and Betti number sequence values are calculated through spectrum topological manifold embedding of enhanced spectrum data, dimension reduction is performed through kernel principal component analysis to obtain topological embedding feature vectors, fusion feature vectors are output through a multimodal attention fusion module in combination with thermal infrared temperature field data and chlorophyll fluorescence kinetic curve data, data enhancement is performed on minority class samples by using a spectral generative adversarial network, the fusion feature vectors are input into a virus classification and recognition model adopting a focal loss function and a dynamic network adjustment mechanism for training, virus type classification and disease severity grade recognition of tobacco leaves to be tested are realized, and the problem that different types of tobacco viruses cannot be accurately recognized and distinguished in the early stage of disease is solved.

This invention relates to a grading method for diabetic retinopathy based on a local-global interactive dual-branch network, belonging to the fields of deep learning, medical image analysis, and computer-aided diagnosis. It includes: inputting the generated initial feature sequence into a global scanning module; using dilated reparameterized convolution to capture multi-scale structural prior information; inputting the feature map with structural prior information into a core dual-branch LoGo module; the local flow extracting fine-grained lesion features through depthwise separable convolution; the global flow generating spatially variable convolution kernels based on the global context through contextual hybrid dynamic convolution; and performing bidirectional cross-modulation through an adaptive multi-scale feature interaction aggregation module to sharpen local details for global semantics and filter local noise from the global context, ultimately outputting a disease severity grade. This invention explicitly simulates the cognitive strategies of clinicians, significantly improving grading accuracy while maintaining computational efficiency.

Embodiments of computerized deep-learning systems and methods for processing medical videos to assess disease severity of a patient are disclosed. In one or more embodiments, an encoder is configured for encoding a plurality of video frames corresponding to the medical videos to obtain respective frame embeddings corresponding to respective frames of the plurality of video frames, wherein the encoder has been pre-trained using self-supervised learning. One or more video frame classifiers, each comprising an attention-based deep learning network, processes the respective frame embeddings and computes, on a frame-by-frame basis, respective frame-level inferences corresponding to the respective frames. A video analyzer comprises an attention-based deep learning network and uses the respective frame-level inferences and the respective frame embeddings to calculate at least one disease severity assessment of the patient.

The present invention discloses an intelligent TCM ear diagnosis auxiliary system, comprising: an ear data acquisition module for collecting pathological image data, temperature percentage data, and humidity percentage data from the patient's ear and performing preprocessing; a pathological image data analysis module for matching and analyzing the pathological image data to generate disease diagnosis data; a temperature and humidity percentage data analysis module for integrating and analyzing the temperature percentage data and the humidity percentage data to generate disease severity data; an accuracy analysis module for integrating and analyzing the disease diagnosis data and disease severity data to generate accuracy data; and a disease output module for outputting a diagnosis result and error level based on the disease diagnosis data and accuracy data. The present invention improves the authenticity and accuracy of diagnosis and reduces the incidence of misdiagnosis.

Provided herein are gene replacement approaches to restore HOXA11AS in the colon for patients with IBD, e.g., UC. Further, since HOXA11os levels inversely correlate with disease severity this lncRNA can also be used as a sensitive colon specific disease relevant biomarker.

The present invention discloses a set of diagnostic markers for aortic dissection and their applications. The markers include the genes MMP8, ALOX15, HP, FXYD2, SIGLEC8, and CCL2. The genes MMP8, ALOX15, HP, FXYD2, SIGLEC8, and CCL2 protected by the present invention can be used as biomarkers for AD and as indicators for assessing disease severity in AD patients, enabling efficient diagnosis of patients with aortic dissection.

The application relates to the technical field of pest and disease identification, in particular to a dynamic early warning and prevention and control system based on forestry pest and disease identification, which obtains crown layer leaf attribute data of target forest area tree species and excitation source physical characteristic parameters of a patrol unmanned aerial vehicle, determines aerodynamic pressure required for turning over of the crown layer leaves according to the leaf attribute data, determines aerodynamic excitation control parameters in combination with the excitation source physical characteristic parameters and a final parameter mapping model, controls the unmanned aerial vehicle to force the leaves to turn over by using a downward airflow to obtain leaf back image data, and adaptively corrects the control parameters according to an effective leaf back exposure rate; image recognition is performed on the leaf back image data to obtain pest and disease characteristic data, and a leaf stiffness index is calculated through time domain analysis; pest and disease severity is generated according to the pest and disease characteristic data and the leaf stiffness index, and a graded early warning is performed; the application can effectively obtain leaf back image information, and realizes early and accurate identification and dynamic early warning of pests and diseases.