39 results about "Early disease" patented technology

The invention provides a wheat stripe rust remote sensing change information-driven early disease prediction method and system, and the system comprises a multi-source data progressive fusion module which enables a natural image and a multispectral image to be spliced step by step into corresponding hierarchical features, and carries out the fusion and outputting of deep fusion features; the frequency domain decoupling-based change detection module is used for outputting a change probability graph of adjacent moments; constructing a plurality of groups of training samples and inputting the training samples into a conditional diffusion prediction model for training; to-be-predicted wheat remote sensing image data and corresponding meteorological data are collected, a change probability graph is obtained, the change probability graph, the corresponding meteorological data and diffusion mode prior data are fused to serve as a condition vector, the condition vector and random Gaussian noise are input into the trained condition diffusion prediction model together for denoising, and prediction denoising data are obtained; then a prediction change probability graph is obtained through a visual decoder; and on the basis, obtaining a prediction result of the severity and distribution range of the wheat stripe rust disease on the d-th day. The method can be used for predicting the early wheat stripe rust.

The invention discloses a vegetable disease incubation period detection method and system based on bimodal time sequence collaborative fusion, and the method comprises the steps: obtaining a leaf image through building an acquisition environment, constructing a training sample data set, and constructing a downy mildew incubation period spectral feature adaptive enhancement (AW-FPF) module; the method comprises the following steps: decomposing a hyperspectral signal into low-frequency and high-frequency components through spectrum time sequence adaptive wavelet decoupling, obtaining an enhanced feature tensor through spectrum multi-scale pathological feature frequency-time dual-path aggregation fusion frequency domain and time domain paths, and obtaining a first feature sequence through weighted screening by using a multi-head attention mechanism; a downy mildew incubation period prediction (HyChl-TFNet) model containing a hyperspectral branch, a chlorophyll fluorescence parameter branch, a feature fusion branch and a classifier is constructed, bimodal features are processed and fused to output a day number prediction result, accurate recognition of the downy mildew incubation period is achieved, the detection precision can be controlled to the day number level, and the detection accuracy is improved. And an accurate time basis is provided for early prevention and control of diseases.

The invention discloses a veterinary knowledge injection-based multi-modal live pig early disease early warning method, which comprises the following steps of: acquiring multi-modal data of a pig, the multi-modal data comprising text data, image data, audio data and sensor data of a veterinary diagnosis report and clinical symptoms; different single-mode data are preprocessed, feature extraction and conversion are carried out on the preprocessed single-mode data, and an embedded vector of each type of single-mode data is obtained; standardizing the embedded vector of each type of single-mode data and unifying the dimension to obtain single-mode feature representation with consistent scale and dimension; inputting all the single-modal feature representations after the dimensions are unified into a multi-modal reasoning large model for unified fine tuning training, and performing multi-modal fusion reasoning by using the multi-modal reasoning large model after fine tuning; and outputting and early warning by using a multi-modal fusion reasoning result. According to the invention, multi-mode collaborative analysis and domain knowledge guidance are utilized, so that the early warning precision is remarkably improved.

The invention relates to the technical field of medical data mining and mode recognition, in particular to a special child early disease prediction method based on double-layer granular ball knowledge representation BGBK and three-way role arbitration TRA. The method comprises the following steps: firstly, converting original special child data into multi-granularity granular ball representation through an unsupervised granular ball generation algorithm; a BGBK structure is constructed, and coarse-grained particle ball information and fine-grained sample information are fused; a three-boundary neighborhood rough set theory is utilized to endow semantic roles to the granular balls, wherein the semantic roles comprise a core region, an abnormal boundary and a transition boundary; designing a TRA strategy, and calculating a sample abnormal score in combination with the role influence factor; and finally, constructing an abnormal factor by fusing the abnormal scores under the multi-attribute subspace, and realizing accurate early prediction of the special child disease. The method can effectively process complex special child data, has the advantages of high detection precision, strong robustness, good interpretability and the like, and significantly improves the accuracy of early prediction of special child diseases.

This invention discloses a medical problem consultation system and method based on a large model. It includes a dialogue consultation module that processes input text and inputs it into a finely tuned large model for inference, outputting medical advice; a professional knowledge base module that processes input text and documents and inputs them into a framework based on the large model for further processing, outputting medical advice and related professional knowledge; an image analysis module that receives medical images and inputs them into an image classification model to obtain the corresponding disease name, then inputs the disease name into the finely tuned large model, which generates corresponding medical knowledge based on the disease name; and an image classification model that receives the input medical images, performs feature extraction, fusion, weighting, and classification to obtain the corresponding disease name. This system can simultaneously address the problems of young people lacking time for in-person consultations and the elderly lacking awareness of early disease symptoms, enabling early prevention, early detection, early diagnosis, and early treatment of diseases.

The invention discloses a method for constructing a multi-modal live pig early disease early warning model based on spatio-temporal information enhancement, and the method comprises the steps: collecting the multi-modal data of a pig, including an image, an audio, a sensor, a spatial layout and the day age information of the pig; constructing a time-space aligned multi-modal data set; extracting embedded vectors of different single-mode data to obtain spatio-temporal information; performing multi-modal feature interaction to obtain weighted information of different-modal feature interaction; performing feature fusion on weighted information of different modal feature interaction to obtain fused feature representation, and performing deep extraction on the fused feature representation to obtain feature representation; performing end-to-end training on the multi-modal model by using the training set; inputting the data of the test set into the trained multi-modal model to obtain feature representation, and identifying and positioning abnormal pigs and judging disease types. According to the method, potential health problems can be found earlier, the misdiagnosis rate is reduced, and a solid guarantee is provided for pig health management and sustainable development of animal husbandry.

The present application relates to a high-sensitivity flexible electrochemical sensor and its preparation method and application, the preparation method comprises the following steps: step S1: preparation of NS-TiO2@M-HG composite material; step S2: preparation of rGO modified silk screen printing electrode rGSPE; step S3: NS-TiO2@M-HG composite material is modified on the working electrode of rGSPE, and NS-TiO2@M-HG / SPE is obtained. Compared with the prior art, the sensor array has a wide detection range, low detection limit and high sensitivity, while maintaining mechanical flexibility, anti-interference ability and repeatability. Through in-situ sweat biomarker detection during exercise, the sensor effectively tracked the fluctuations of ascorbic acid (AA), dopamine (DA) and uric acid (UA) levels in the volunteers. This practical application highlights the potential of the sensor in continuous health monitoring, early disease detection and personalized medical monitoring, making it a promising tool in the field of modern healthcare.

The application relates to the technical field of image recognition, and provides a Gastrodia elata disease and pest image recognition method and system. By applying a specific frequency of sound wave vibration to the Gastrodia elata to be detected, the tiny characteristic differences caused by early diseases and pests can be amplified, and multi-spectral image and video data can be accurately captured, so that the limitation that only middle and late diseases and pests can be recognized in the prior art is broken, and early accurate early warning is realized. Spectral response characteristics representing physiological states are extracted from multi-spectral images, vibration response characteristics representing structural properties are extracted through video light flow processing, and dynamic response characteristics are fused and constructed, so that disease and pest abnormalities and environmental abnormalities can be effectively distinguished, and the misjudgment rate can be greatly reduced.

AI-BASED MEDICAL DEVICE FOR EARLY DISEASE DETECTION

The application discloses a kind of based on supervised learning prediction patient auxiliary examination item method, comprising the following steps: obtaining the electronic medical record of inpatient, it and corresponding hospitalization number are stored as the source data of inpatient in the form of Excel table, the source data of inpatient obtained is preprocessed, to obtain the preliminary prediction result of auxiliary examination item of inpatient after preprocessed source data, and the preliminary prediction result is decoded using the auxiliary examination coding table established in advance, to obtain the final prediction result of auxiliary examination item of inpatient.The application can solve the technical problems that the existing LSTM model cannot predict the auxiliary examination item of patient's early disease due to the complexity of training, relying on a large number of historical time series data.

The invention provides a wearable early-stage deterioration early warning system and application, and belongs to the technical field of medical auxiliary equipment. A first electrode group, a second electrode group, a photoelectric volume pulse wave sensor and an inertial measurement unit are integrated on a wearable vest of the system, and the wearable vest is used for synchronously collecting thoracic impedance, thoracic and abdominal movement impedance, oxyhemoglobin saturation and trunk movement data; the edge computing gateway carries out signal preprocessing; the feature extraction module is used for extracting respiratory rate, tidal volume trend, thoracico-abdominal respiration asynchronism index, blood oxygen trend and activity state; the hospital information system interface obtains a medication record; the context-aware risk assessment module fuses the multi-dimensional parameters and the clinical context to generate a risk score; and the early warning generation module triggers graded early warning according to the score and automatically integrates the graded early warning to the hospital clinical workflow. According to the method, the early-stage decompensation trend of the non-asthmatic respiratory failure can be continuously and specifically recognized, closed-loop management from risk recognition to intervention is realized, and the clinical response efficiency is improved.

Methods of using spectral data to diagnose a disease, such as breast cancer, in a biological sample are described. The method relates to a computer-implemented method that converts spectral vibrations of a sample into a map and scores the map using a set of reference maps. Based on the score and a threshold, it may be determined whether the subject obtaining the sample is diseased, and if the subject is diseased, the degree of diseased is determined. The methods may also detect early and pre-illness states of a subject by detecting a low concentration analyte signal indicative of the early or pre-illness state. The method is non-invasive, non-subjective, highly specific and sensitive. The method provides an application of a single standard of diagnostic accuracy, independent of whether there is a pathology expert.

The invention discloses a diseased silkworm detection method based on spectral imaging and a diseased silkworm database, and the method comprises the steps: capturing the fine change of spectral fingerprints of diseased silkworms, and achieving the precise and early disease diagnosis through big data and an artificial intelligence algorithm. According to the method, diagnosis can be made before the diseased silkworms have macroscopic symptoms, and the early chemical component change can be sensitively captured through spectral imaging.

The invention belongs to the field of early disease diagnosis, and particularly relates to a core-shell nanoparticle labeled portable dual-mode immunoassay platform based on dynamic driving, which comprises an antibody-gold nanoparticle biological coupling system, an amplification system, a color development system and a colorimetric-atomic emission spectrum detection system. The Au-coated Cu core-shell nano-particles are dynamically driven to realize signal amplification, colorimetric preliminary screening and atomic emission accurate quantification are combined, CEA (0.02 ng / mL), cTnI (0.35 fg / mL) and A beta (10.3 pg / mL) can be detected in an ultra-sensitive manner, and the Au-coated Cu core-shell nano-particles are suitable for bedside detection of early diseases.

In order to solve the problems that an existing viral pneumonia related prediction model lacks accurate distinguishing of disease grading, model construction depends on laboratories and iconography data, and interpretability is insufficient, the invention provides an instant interpretable viral pneumonia disease grading distinguishing model construction method based on symptoms and signs. Comprising the following steps: acquiring clinical information of a subject, and constructing a sample data set; determining N preliminary clinical manifestation variables, and screening out M variables as clinical symptom sign feature vectors; respectively constructing a plurality of machine learning models, and determining an optimal model; the M clinical symptom sign feature vectors are incorporated into an optimal model, and a viral pneumonia condition grading discrimination model is established; carrying out SHAP interpretability analysis on the optimal model; and constructing an ordered logistic regression model, drawing a normogram, and displaying scores corresponding to different clinical symptom sign feature vectors and illness state grading discrimination probabilities according to the normogram, so as to realize accurate identification of early illness states and clinical convenience operability.

The invention relates to the technical field of image recognition, and provides a gastrodia elata disease and insect pest image recognition method and system, which can amplify tiny feature differences caused by early diseases and insect pests by applying sound wave vibration with a specific frequency to gastrodia elata to be detected, and accurately recognize the disease and insect pests through accurate capture of multispectral images and video data. The limitation that only middle and late stage diseases and insect pests can be identified in the prior art is broken through, and early-stage accurate early warning is realized; according to the method, spectral response characteristics representing physiological states are extracted through multispectral images, vibration response characteristics representing structural properties are extracted through video light stream processing, and dynamic response characteristics are fused and constructed, so that pest and disease damage abnormalities and environmental abnormalities can be effectively distinguished, and the misjudgment rate is greatly reduced.

The invention discloses an auxiliary decision-making system for early diagnosis and progress prediction of cerebral small vascular diseases. The system comprises a data acquisition module, a data processing module, a comprehensive analysis module and a data storage module, the data acquisition module is used for acquiring proteomics detection data of a patient; the data processing module is used for analyzing the detection data of the patient to obtain analysis results of different detection data; the comprehensive analysis module is used for carrying out comprehensive analysis on analysis results of different detection data and generating auxiliary decision prompt information; and the data storage module is used for storing the data of the patient. Through comprehensive analysis of iron metabolism imbalance detection data and protein detection data of a patient, the disease early diagnosis sensitivity and disease early prediction accuracy are improved, and meanwhile, the accuracy of a diagnosis report auditing result is improved.

An accurate and early disease detection method to improve the treatment and prognosis of individuals with diseases such as cancer. [Solution] The present invention provides methods such as multi-omics methods for evaluating diseases such as cancer. Multi-omics methods can integrate proteomics data, transcriptomics data, genomics data, lipidomics data, or metabolomics data. Methods for screening diseases or conditions are also described herein. Methods for screening diseases or conditions from biological samples are also described herein. These methods may include evaluating whether nodules, tumors, or cysts are cancerous.

The application discloses a health data anomaly detection method based on a generative adversarial network and belongs to the technical field of health data anomaly detection, which comprises a forward evolution generation module, a reverse evolution generation module, a bidirectional consistency discrimination module and a dynamic adaptive turning point detection module; the forward evolution generation module is used for receiving individual current health state data, generating a disease state prediction of the individual under the condition that the individual continuously evolves in the disease direction; the dynamic adaptive turning point detection module is used for tracking the dynamic evolution trend of the closed-loop evolution loss function value, establishing and continuously refreshing the individual's exclusive closed-loop integrity baseline, triggering an early warning when the closed-loop integrity decline rate exceeds the historical normal fluctuation range of the individual, accurately capturing early disease signal of the index value being normal but the evolution logic being abnormal, and greatly reducing the risk of missing judgment in the prodromal period.

The portable device for early disease identification allows in situ detection of the disease by analyzing the plant's leaf directly and visually identifying the degree of disease spread in the plant.

The invention is suitable for the technical field of biological data processing, and provides a method for evaluating the immune state and the immune age of a human body, and the method comprises the steps: firstly, based on a preset T cell receptor immune group library, rapidly obtaining multi-dimensional feature set information, then inputting the multi-dimensional feature set information into a preset multi-task deep learning model, and obtaining the immune age of the human body. And evaluation result set information is accurately generated. The problem of signal confusion can be solved, disease specific interference is effectively distinguished and stripped, a purer and more accurate immune age prediction result is obtained, meanwhile, the classification accuracy of the health state under the complex immune background is improved, the generalization ability and robustness of the model are remarkably enhanced, and the method is suitable for popularization and application. A brand-new and integrated solution is provided for early warning of diseases, dynamic monitoring of health status and evaluation of anti-aging intervention curative effect.

The invention provides a marker combination for predicting thyroid cancer metastasis and application thereof. Specifically, the invention provides application of a gene, mRNA, cDNA and protein of the risk marker combination for thyroid cancer metastasis judgment or a detection reagent of the gene, the mRNA, the cDNA and the protein, and is used for preparing / establishing a diagnostic reagent or a kit / equipment for judging the thyroid cancer metastasis occurrence risk. Researches show that the thyroid cancer metastasis risk marker combination can be used as a marker for early judgment of thyroid cancer metastasis of a thyroid cancer patient, has high sensitivity and specificity, can quickly diagnose thyroid cancer metastasis at a relatively early disease progress stage, and provides powerful assistance for early treatment intervention of diseases.

The invention provides a low-cost bridge structure health monitoring and intelligent sensing method based on multivariate data fusion, and relates to the technical field of bridge structure health monitoring. VMD parameters are adaptively optimized by using a fruit fly optimization algorithm to realize vibration signal noise reduction, key features are extracted in combination with kernel principal component analysis, and a Fisher discriminant analysis model is constructed to realize intelligent diagnosis; the method can effectively improve the accuracy of bridge disease recognition, has the advantages of low deployment cost, high algorithm adaptability, stable diagnosis effect and the like, and is suitable for long-term monitoring and early disease recognition of a bridge structure.

The invention discloses a mango anthracnose early detection method based on hyperspectral imaging and deep learning, and belongs to the field of spectral analysis. According to the method, a hyperspectral image of an infection process is collected, and a three-dimensional sub-cube and a one-dimensional spectrum of a region of interest are extracted and are respectively used for training a 3D-CNN model and a 1D-CNN model; generating a space thermodynamic diagram and a spectrum activation curve based on an output prediction category of the optimal 3D-CNN model; superposing the space thermodynamic diagram to a corresponding original mango RGB image to form a superposed thermodynamic diagram, and identifying a key space region; identifying a key wavelength from the spectral thermodynamic diagram according to a preset threshold value, and independently identifying the key wavelength based on the optimal 1D-CNN model; judging the key space region as an actual position of an early disease on the corresponding pericarp; and determining key biochemical component change caused by anthracnose early infection according to the key wavelength. The early-stage mango anthracnose can be effectively detected, and the disease identification accuracy is improved.

This application discloses a method, device, equipment, and storage medium for early warning of critical states in biological systems, relating to the field of bioinformatics. It quantifies the degree of local network disturbance using network topology indicators, enabling the sensitive detection of abnormal turning signals in the cell network topology before disease symptoms appear, providing a basis for early disease warning. The method includes: obtaining a cell feature matrix; constructing a cell-related network for each stage of the disease process based on cell expression characteristics in the cell feature matrix; defining local cell networks within the cell-related network of each stage of the disease process; determining a global evaluation indicator for each stage of the disease process based on the topology evaluation indicators of all local cell networks in the disease process stage; and identifying the stage of the disease process where the global evaluation indicator first reaches a maximum value as a critical state, thereby providing disease warning through the critical state.

A method for disease risk assessment using multiple data sources, and a computer program for implementing the same. The present invention relates to a method for improving the accuracy of early cancer detection by a priori identifying a PRS and then combining it with biomarkers to improve accuracy. The method comprises the following steps: i) calculating an individual's genetic risk, including a polygenic risk score (PRS); ii) measuring biomarkers (including proteins and metabolites); and iii) (optionally) updating the calculated risk to take into account additional clinical variables, including age, sex, and history of infectious diseases or environmental exposures (e.g., smoking).

This invention relates to the field of disease assessment technology, providing a method and system for disease assessment based on clinical indicators. The method includes assessing disease based on routine clinical vital signs parameters, defining normal, intermediate, and abnormal ranges for each parameter at the corresponding physiological stage based on the patient's age, establishing an abnormality judgment benchmark suitable for the individual, and avoiding the adaptation bias of general standards. Time-series data is decomposed into continuous, equal-duration minimum fluctuation units. Fluctuation characteristics are extracted and abnormal trigger units falling into the intermediate range are marked, accurately capturing early disease anomalies and overcoming the lag limitations of traditional monitoring. Abnormal trigger units are chained together according to time rules to form a transmission relationship chain. The time lag difference is calculated and linked to treatment plans to generate an emergency treatment library, reconstructing the disease development path and establishing standardized treatment comparison criteria. Real-time monitoring enables rapid alarms for critical situations, and early risk classification warnings and precise matching of treatment plans for early anomalies, improving the timeliness of disease assessment.

The invention discloses a human body biological characteristic-based electromagnetic pulse diagnosis method, which comprises the following steps of: aiming at an original signal set, removing noise interference by adopting a self-adaptive filtering algorithm to obtain a de-noised signal set; extracting electromagnetic response characteristics of each organ from the de-noised signal set, and decomposing the signals based on a wavelet transform algorithm to obtain a time-frequency characteristic set; according to the independent signal set, a time sequence analysis algorithm is adopted to calculate time delay and intensity differences of all organ signals, and a time sequence feature vector is obtained; extracting multi-organ coordination parameters from the time sequence feature vectors, and aligning signal time sequences based on a dynamic time warping algorithm to obtain a coordination index set; for the coordination index set, if indexes deviate from a normal range, classifying through a support vector machine algorithm, and judging early disease features; and according to a judgment result, integrating the multi-organ time sequence characteristics by adopting a data fusion algorithm to obtain comprehensive diagnosis parameters.

The invention discloses a clock drawing task-driven Alzheimer's disease early recognition method, and belongs to the technical field of disease early screening, and the method comprises the steps: collecting a static image and eight types of process signal data of a subject in a clock drawing test, and carrying out the preprocessing of the static image and eight types of process signal data; image space structure features and process signal dynamic features are extracted through a double-flow feature extraction module composed of an improved VGGNet16 network and an MLP; generating a joint feature vector through channel attention weighting and full connection layer fusion; and a polynomial loss function optimization model is adopted, and a recognition result is output through a Softmax layer. According to the method, deep fusion of static and dynamic multi-modal features is realized, key features are effectively highlighted, redundant information is inhibited, samples difficult to classify are focused, the recognition accuracy on a DARWIN data set reaches 92.59%, and the method is simple and convenient to operate, low in cost, capable of being deployed on portable equipment and suitable for clinical screening and primary medical popularization.

The invention relates to the technical field of biological medicine, in particular to a proteome-based protein combination for chronic liver disease incidence prediction, a prediction model and application. According to the invention, an Olink proteomics technology, a machine learning algorithm and a discovery-internal verification research strategy are integrated, and a group of chronic liver disease prediction models containing 10 plasma protein markers (VCAM1, CD48, NUDT5, MILR1, TNFSF8, DDAH1, IL17RB, NFASC, FCN2 and RTN4R) are successfully screened and verified. Through cross fusion of system biology and artificial intelligence technology, a new thought of full-period prediction from early disease screening to dynamic risk monitoring is developed, and an innovative scheme is provided for accurate prevention and control of chronic liver diseases.