26 results about "Disease progress" patented technology

The invention provides an osteoporosis prediction method and system based on a centrum CT image, and the method comprises the steps: obtaining a patient centrum CT image, and carrying out the preprocessing of the image, and obtaining standardized three-dimensional voxel data; performing spatial resampling on the original data to a uniform resolution; constructing a hierarchical feature extraction network for centrum bone structure perception, and designing a non-uniform sampling mechanism for centrum density distribution; constructing an intervertebral biomechanical conduction diagram network; designing an osteoporosis specific loss function; and outputting a grading prediction result containing confidence, generating probability distribution of each grade through a softmax function, and generating a visual thermodynamic diagram of the lesion area. Through time sequence consistency constraint, the system can analyze image changes of the same patient at different time points and evaluate the treatment effect and the disease progress. The dynamic monitoring ability provides a powerful tool for long-term management of chronic osteoporosis, and is helpful for timely adjustment of treatment schemes and improvement of prognosis of patients.

The invention relates to a training method of a respiratory tract infection disease progress and prognosis prediction model. The training method comprises the following steps: extracting mRNA from peripheral blood of a target patient, and carrying out transcriptome sequencing to obtain a sequencing result; based on the ferroptosis related gene set, comparing ferroptosis score differences of two groups of patients with community-acquired pneumonia and sepsis, and screening corresponding ferroptosis related genes with statistical significance from a sequencing result; screening out genes meeting preset conditions from the ferroptosis related genes based on LASSO regression; and establishing an RTI clinical outcome prediction model through logistic regression by taking whether the patient is sepsis or not as an outcome dichotomy variable and taking the screened gene expression quantity as a prediction variable. According to the invention, after the prediction model is subjected to machine learning screening such as LASSO and the like, the core feature with the highest prediction value is reserved, so that the risk of over-fitting of the model on training data is reduced.

A method may include applying a cell classification model to identify, based at least on an image of a biological sample, one or more cell types present in the biological sample. The cell classification model may be trained to differentiate between a plurality of cell types including a first cell type whose likelihood of being a macrophage satisfies a threshold and a second cell type whose likelihood of being the macrophage fails to satisfy the threshold. A composition profile for the biological sample may be generated based on the one or more cell types identified in the biological sample. At least one of a disease diagnosis, a disease progress, a disease burden, and a treatment response for a patient associated with the biological sample may be determined based on the composition profile of the biological sample. Related systems and computer program products are also provided.

The invention belongs to the technical field of osteoarthritis management, and particularly relates to an osteoarthritis management system based on artificial intelligence and a computer storage medium. The invention provides an osteoarthritis management system based on artificial intelligence. The system integrates an LLM-DL hybrid architecture, a multi-specialist module cooperation framework and an RAG knowledge base system, and can cover a complete clinical process from patient preliminary diagnosis to treatment scheme formulation. The system can comprehensively and accurately evaluate the disease state of a patient, provides personalized disease progress prediction, not only predicts 2-year and 4-year functional results and iconography progress, but also can identify specific risk factors of the patient, and provides a basis for accurate intervention. Through the design of the whole system, the clinical working efficiency and the prediction accuracy are remarkably improved, the dependence on specialist doctors and high-end equipment is reduced, high-quality KOA management can also be implemented in resource limited areas, and therefore the overall medical resource requirement is effectively reduced.

The invention discloses an intelligent health early warning system based on deep learning, and relates to the technical field of medical health, and the system employs a causal convolutional network and a gating circulation unit double branch to extract long and short term features, generates a dynamic threshold value through adaptive weight fusion in combination with a dynamically updated personalized health baseline and a disease knowledge graph, and carries out the early warning of the health. The method has the advantages that long-scale health trend features are mined through the long-period feature extraction module, short-scale sudden abnormal features are captured through the short-period feature extraction module, and two types of feature weights are dynamically distributed and fused based on a medical risk level judgment rule in combination with the self-adaptive weight fusion module; and a personalized dynamic early warning threshold adaptive to the health state of the user is generated by combining a dynamic threshold generation module with a disease progress pathology knowledge graph, so that the defects that an existing system cannot separate long and short-term health signals and depends on a fixed threshold, so that an early hidden risk signal is covered, early warning is lagged and the false alarm and missing report rate is high are effectively overcome.

The invention discloses a Crohn disease postoperative bad outcome prediction method combining knowledge base construction and an experience-driven self-asking mechanism, and solves the problems of insufficient interpretability, insufficient clinical data utilization, weak generalization ability and the like of an existing prediction method. The method comprises the following steps: constructing a Crohn disease special medical knowledge base, extracting disease progress related factors from medical literatures and real medical records, and carrying out expert score weighting processing to form searchable knowledge entries; retrieving related knowledge injection context from a knowledge base based on a medical record input by a user, and generating preliminary prediction by using a large language model; structured reasoning is guided through a multi-layer prompt engine, diagnosis tasks are decomposed through the thinking chain technology, and self-check before reasoning is achieved by driving a self-asking mechanism through experience. And generating an introspection problem chain according to historical error cases, iteratively optimizing the reasoning process, and finally outputting a bad outcome prediction result and a detailed analysis report. According to the method, both traceable interpretability and prediction accuracy are considered, and reliable assistance is provided for postoperative clinical management of Crohn's disease.

The embodiment of the invention discloses a Crohn disease longitudinal queue course prediction system based on time perception Transform, and relates to the technical field of medical data processing, the system comprises a data preprocessing module, an input embedding layer, a Transform encoder and a multi-task multi-time window prediction header, the system breaks through the limitation that only baseline data is used for prediction of a traditional model, and the prediction efficiency is improved. According to the method, the full-cycle longitudinal data (such as inflammation indexes and medication records of each treatment) of the patient from the morbidity to the prediction can be integrated, and the disease progress, operation and medication risks of 1 year / 3 years / 5 years can be dynamically output. And reference is provided for clinicians.

The invention relates to the technical field of biology, in particular to a construction method of an Elmod3 gene mutation mouse model. Based on clinical data of hereditary deafness family patients, ELMOD3c.512Agt is found; g abnormal mutation can cause delayed progressive sensorineural deafness of a patient. According to the invention, a molecular marker with Elmod3c.512Agt is constructed; the G point mutation mouse model is consistent with the mutation site of a patient, and after the mouse is born, the disease progresses under the normal feeding environment and the natural growth rule, so that the experiment conditions of the disease research of the model mouse are closer to the real disease development of family patients, and a researcher can deeply research how the ELMOD3 gene mutation causes deafness. And a foundation is laid for functional research and subsequent gene therapy research of the ELMOD3 in an inner ear auditory system.

Provided are multi-layer bioreactors for growing, maintaining, stimulating, monitoring and testing organoids and tissues derived from or representing hollow organs in organoid chambers. Also provided are uses of those bioreactors in modeling a disease process for monitoring disease progress and / or for assessing a biological effect, such as therapeutic efficacy and / or toxicity, e.g., organotoxicity. Also disclosed are bioreactors comprising organoid chambers that are useful as systems for measuring the volume, pressure, contractility, pump function, or electrophysiology of an organoid chamber as well as systems for controlling the pressure experienced by an organoid or tissue in an organoid chamber.

The invention relates to the technical field of plant disease control, and particularly discloses a screening method of a cruciferous crop clubroot control agent, which comprises the following steps: after accelerating germination of cruciferous crop seeds, transplanting the cruciferous crop seeds into a 1 / 2 MS solution, and culturing the cruciferous crop seeds to a two-leaf one-core stage to obtain seedlings; soaking the roots of the seedlings in a mixed system containing plasmodiophora brassicae spores and a medicament to be detected, and inoculating; and transplanting the inoculated plants into a newly prepared 1 / 2 MS solution for continuous culture, and regularly investigating morbidity and prevention and control effects to screen out the medicament with prevention and control effects on the clubroot of the cruciferae crops. According to the method provided by the invention, continuous and non-destructive dynamic observation on the same plant can be allowed, the disease progress is accurately monitored, and the medicament screening cost is greatly reduced.

The utility model relates to an auxiliary observation device for an abdominal cavity drainage bag, relates to the technical field of medical equipment, and is used for solving the problem that in the prior art, the color and the amount of liquid in the drainage bag cannot be clearly and accurately checked in a dark environment, so that the disease progress and the treatment effect of a patient cannot be accurately judged. Comprising a transparent placing box, an induction lighting piece, a weighing piece and a mounting frame used for being fixedly mounted on a wall, the weighing piece is fixedly mounted on the mounting frame, and the transparent placing box is detachably hung on the weighing piece; the transparent placing box is used for placing a drainage bag, the induction lighting part used for lighting is arranged below the transparent placing box, a light beam of the induction lighting part is arranged upwards, and a limiting part used for fixing the drainage bag is arranged on the transparent placing box.

The invention relates to an interpretable Alzheimer's disease deep learning prediction method and system. The method comprises the following steps: acquiring multi-modal data of a candidate AD patient, wherein the multi-modal data comprises sMRI images and clinical and lifestyle data; processing the multi-modal data by using a pre-trained multi-modal deep fusion prediction model to obtain an AD risk level and a disease progress probability; wherein multi-modal features are extracted through the sub-modal feature extraction layer, deep fusion is carried out on the multi-modal features through the fusion modeling layer to obtain a global fusion feature vector, the global fusion feature vector is processed through the result output layer, and a risk level classification result and a disease progress probability in future preset time are obtained. By adopting the method, multi-modal heterogeneous data can be effectively fused, qualitative risk grading and quantitative disease course prediction are provided, and the diagnosis comprehensiveness is improved.

The invention discloses an apple leaf ring spot early diagnosis and chlorophyll content prediction method based on hyperspectral imaging and a CNN-LSTM mixed model. According to the method, hyperspectral images of apple leaves within the range of 400-1000 nm are collected through a hyperspectral imaging system, characteristic wave bands related to the disease progress and chlorophyll change are screened through a competitive adaptive reweighted sampling (CARS) and a continuous projection algorithm (SPA), and a convolutional neural network and long-short term memory network (CNN-LSTM) mixed model is input; early recognition of diseases and synchronous prediction of chlorophyll content are realized. And the chlorophyll prediction model is used for pixel-by-pixel prediction of the leaf spectral image, so that a spatial distribution visual image of the chlorophyll content of the apple leaf is realized, and lossless, rapid and quantitative evaluation of the health state of the apple leaf is realized.

The invention discloses a predictive marker as well as a related product and application thereof, and relates to the field of tumor diagnosis. The invention finds that WNT5A can be used as a marker of any one or more of disease risk, prognosis risk, disease progress, treatment effect, residual focus and metastatic focus of squamous-cell carcinoma, is beneficial to accurate diagnosis and treatment of squamous-cell carcinoma, and accelerates the research and development of new drugs.

The invention discloses a microbial agent based on the synergistic effect of bifidobacterium pseudolongum and bifidobacterium animalis and application, and belongs to the technical field of biological medicine. The active ingredient of the microbial agent is a viable bacterium mixture of bifidobacterium pseudolongum and bifidobacterium animalis, or a metabolite co-cultured by the bifidobacterium pseudolongum and the bifidobacterium animalis. According to the microbial agent provided by the invention, an intestinal flora-butyric acid-peripheral / central immune axis is adjusted through a metabolic synergistic effect of the two strains, A beta deposition and neuroinflammation can be intervened from a pathologic source so as to intervene the progress of the Alzheimer's disease, and the safety is good. The synergistic effect of the bifidobacterium pseudolongum and the bifidobacterium animalis is applied to regulation of intestinal flora and intervention or auxiliary improvement of memory of the Alzheimer's disease, and a novel biological preparation and a technical path are provided for prevention and treatment of neurodegenerative diseases such as the Alzheimer's disease.

The invention relates to an interpolation method for missing data in Alzheimer's disease progress prediction, which comprises an integrated feature selection module and a missing value interpolation module, and is characterized in that the integrated feature selection module adopts an isomorphic and heterogeneous integrated feature selection method for time heterogeneity and phenotypic heterogeneity respectively to screen out features closely related to disease progress; the missing value interpolation module obtains irregular missing time sequence information by calculating a real interval between follow-up visit data of each patient, takes specific individual features of the patient as intervention condition input of a variational auto-encoder, and learns conditional distribution of the features by using a conditional variational auto-encoder; according to the method, more refined conditional distribution modeling is carried out, and finally, missing data is generated by the model, so that the problems that the distribution characteristics of data are not fully considered and conditional dependence information behind a missing mechanism is difficult to capture in the current traditional interpolation method based on AD patient multi-source longitudinal data are solved, and the accuracy and reliability of Alzheimer's disease progress prediction are remarkably improved.

The invention discloses a method for evaluating sepsis lung injury by detecting the crosslinking degree of type VI collagen, and relates to the technical field of medical diagnosis and monitoring. The method at least comprises the following steps: S1, firstly, carrying out sample collection and multi-index detection; s2, performing imaging feature extraction, and automatically identifying fine structure changes in the chest CT image by using a deep learning algorithm; and S3, based on the feature extraction in the S2, establishing a corresponding quality control algorithm, a basic damage scoring model, a dynamic progress prediction model and a comprehensive risk assessment model. The accurate, early-stage and dynamic sepsis lung injury assessment method is provided through multi-dimensional biomarker detection, iconography feature extraction and a dynamic algorithm model, the early diagnosis rate of sepsis lung injury can be remarkably improved, the disease progress can be effectively monitored, the treatment effect can be effectively assessed, and the application prospect is wide. The method has remarkable clinical application prospects and economic benefits, and particularly has important value in intensive care and formulation of personalized treatment schemes.

This application discloses an intelligent medical management system for patients with bone injuries, including the following modules: a scanning module for acquiring imaging images of the affected area of ​​bone injury patients, including CT images, X-ray images, and ultrasound images; adjustable scanning parameters to adapt to the scanning needs of bone injuries in different locations and at different stages of the disease; and an image analysis module that automatically performs denoising, enhancement, and precise segmentation processing on the original scan images to achieve accurate quantitative assessment of the bone injury condition, generate standardized processed images and feature parameter reports, effectively reduce the workload of medical staff, improve diagnostic and treatment efficiency, and provide objective data support for clinical diagnosis and treatment. The prediction module calls historical case data and current patient disease progress data from the data storage module to identify high-risk groups for complications in advance and output targeted intervention suggestions, effectively avoiding poor patient rehabilitation, secondary injury, and aggravation of complications, thereby improving the quality of patient rehabilitation.

The invention relates to the technical field of medical care, and particularly discloses a core tube of a nursing strategy generation method for a hepatocellular carcinoma interventional post-operation, which comprises the following steps: systematically acquiring clinical parameters of a patient at multiple time points after a TACE operation and a patient report outcome, including symptom expression, complication and life quality data; performing multi-dimensional analysis on the symptom trajectory, the complication severity and the disease progress risk based on a preset rule, and dynamically evaluating the recovery risk level of the patient; and then, according to the risk level and the specific stage of the post-operation, a corresponding structured nursing strategy template is intelligently matched from a knowledge base constructed based on evidence, personalized fine adjustment is carried out on the template in combination with the individual condition of the patient, and a comprehensive nursing document containing symptom management, nutrition, activity, psychology and social support is generated and safely output to a medical system. By implementing closed-loop management of evaluation, strategy generation and dynamic adjustment, the accuracy, systematicness and individuation level of postoperative care are effectively improved.

The present invention relates to a biomarker for predicting the reoccurrence or prognosis of diabetic foot ulcer, according to specific methylation of at least one gene selected from the group consisting of MORN1, NCOR2, and LINC00504. The present invention identifies a specific pattern of reoccurrence or prognosis of diabetic foot ulcer, discovers major biomarkers that account for the pattern, by machine learning of gene data, and thus, not only can predict the reoccurrence or prognosis of diabetic foot ulcer by using blood analysis-based clinical biomarkers, and but can also be used in the future to develop mechanisms for preventing or treating diabetic foot ulcer. By the discovery of factors that account for vital signs, the prediction of treatment or prognosis of diabetic foot ulcer is possible, and thus, a system capable of preemptively controlling disease progress can be established.

The invention discloses a proliposome loaded with astaxanthin and a preparation method of the proliposome, and belongs to the cross technical field of food science and biological medicine application. The preparation method of the proliposome loaded with the astaxanthin comprises the following steps: forming a mixed solution from phospholipid and the astaxanthin, and then adding sugar alcohol powder into the mixed solution to obtain the proliposome loaded with the astaxanthin; the proliposome loaded with astaxanthin prepared by the method has good biocompatibility, has inhibition and alleviation effects on Lo-2 cell oxidative stress, inflammatory injury and abnormal fat accumulation caused by hydrogen peroxide, can significantly improve and alleviate the disease progress of C57 / BL6 mouse non-alcoholic steatohepatitis, and has good application prospects. The method has a very good application prospect in the industries of medicines and health care products.

The invention discloses a light symptom SFTS risk prediction method and system based on machine learning, and the method comprises the steps: obtaining light symptom SFTS clinical data, carrying out the preprocessing, carrying out the variable screening of the preprocessed data, determining an optimal regularization parameter, obtaining a key prediction factor, building a Cox proportional risk scoring model of two time points based on the key prediction factor, and carrying out the calculation of the Cox proportional risk scoring model. Calculating individual risk scores and constructing a column graph, determining risk levels based on a risk layering threshold value, realizing risk prediction, finally generating a visual heat map according to the combination of the key prediction factors, marking critical disease risk probabilities under different key prediction factor combinations, and completing risk prediction of different key prediction factor combinations. The objective of the method for constructing the risk prediction model of the mild SFTS based on machine learning is to realize accurate risk prediction of early-stage SFTS critical disease progress through double-time-point modeling, dynamic risk layering and visualization of a heat map.

The invention relates to the related technical field of periodontal disease monitoring and diagnosis, and discloses a digital periodontal disease monitoring and diagnosis system, which comprises an intraoral scanning module, a multispectral imaging probe, a pressure sensing probe, a data processing terminal and a cloud analysis platform, the intraoral scanning module is used for acquiring three-dimensional structure data of teeth and gingiva and comprises a high-precision optical lens and an infrared positioning sensor. Through cooperative arrangement of the intraoral scanning module, the multispectral imaging probe and the pressure sensing probe, a complete soft tissue real-time detection, scanning and acquisition closed-loop structure can be formed; the objective quantitative diagnosis of periodontal pocket depth, attach loss and inflammatory activity can be realized through the visual interaction terminal and cloud platform data; the limitation of a single detection mode is eliminated through multi-source data fusion; through setting of a periodontal disease grading deep learning model in the cloud analysis platform, a traceable digital disease progress model can be constructed.

The application discloses application of UFC1 as a biomarker in preparation of reagents for diagnosing and / or treating prostatic hyperplasia. In the technical scheme, the cell experiment result shows that UFC1 can significantly inhibit the proliferation ability of WPMY-1 and BPH-1 cells, and can effectively promote the apoptosis of the cells. The finding reveals the core driving role of UFC1 in BPH progress, that is, maintaining the imbalance between the proliferation and apoptosis of prostate cells, and promoting the tissue hyperplasia. The mechanism indicates the precise intervention direction of the targeted treatment: if the activity or expression of UFC1 can be specifically inhibited, the abnormal proliferation of prostate cells can be blocked from the source, the normal apoptosis program of the cells can be restored, and the proliferation progress can be reversed by realizing the "two-way regulation". Compared with the existing alpha receptor blockers which can only relieve the obstruction symptoms, and the 5 alpha-reductase inhibitors which need long-term medication and can cause sexual dysfunction, the treatment strategy of targeting UFC1 directly attacks the biological nature of the hyperplastic cells, and is expected to more effectively control the disease progress.

The invention belongs to the technical field of biomedical detection and tumor molecular diagnosis, particularly relates to a plasma exosome mass spectrum metabolic fingerprint, and further discloses a method for separating and purifying plasma exosome based on exclusion chromatography and screening prostate malignant tumor biomarkers in combination with solid-phase mass spectrum metabonomics. The invention also discloses application of the compound in preparation of a prostatic cancer biomarker. Plasma mass spectrum metabolism fingerprint detection is carried out based on an SEC + LDI-MS platform, a metabolism marker with stable diagnosis performance is screened out, six plasma exosome metabolism markers for prostatic cancer are screened out, the difference between a healthy group and an experimental group is remarkable (p is smaller than 0.05), and the sensitivity is high. Discovery of the prostate cancer marker is crucial to disease diagnosis and disease progress monitoring, and the defect that high-accuracy diagnosis performance cannot be achieved through an existing metabolic marker is effectively overcome.