166 results about "Prognosis prediction" patented technology

The invention discloses a brain tumor multi-mode large model construction method, device and equipment and a storage medium, and is applied to the technical field of brain tumor imagines.The method comprises the steps that pixel-concept level alignment is conducted on a multi-mode MRI image and a pathological text; constructing a multi-modal feature fusion network for fusing image features and text features by adopting an attention mechanism of pathology perception and combining medical semantic information; training the multi-modal feature fusion network to generate an analysis report and a segmentation result; according to the technical scheme of multi-task cooperation, cross-modal pathological semantic accurate alignment, pathological knowledge graph injection and lightweight and continuous optimization parallelization, full-process coverage of brain tumor accurate segmentation, analysis report generation and prognosis prediction is achieved, the problems that a traditional model lacks pathological semantic support and is insufficient in clinical adaptability are solved, and the clinical adaptability of the traditional model is improved. And the deployment feasibility and the dynamic optimization capability are also considered.

The invention discloses a lung cancer lifetime prediction system based on prognosis factor multi-data fusion, and belongs to the technical field of lung cancer prognosis prediction, and the system comprises a multi-source data collection module which is used for collecting prognosis multi-source data of a patient; the multi-source data processing module is used for carrying out preprocessing and feature extraction on the prognosis multi-source data of the patient; the multi-source data fusion module is used for carrying out cross-modal alignment and fine-grained fusion on the extracted multi-modal feature vectors, and capturing a dependency relationship between modals based on a hierarchical attention mechanism to form patient prognosis fusion data; and the survival analysis and prediction module is used for analyzing the prognosis fusion data of the patient according to the lung cancer lifetime prediction model, automatically predicting the lifetime of the patient and displaying the lifetime in a visual form. The problems that existing lung cancer lifetime prediction is low in accuracy and cannot provide support for personalized treatment are solved. The lung cancer lifetime prediction accuracy can be improved, and support can be provided for personalized treatment.

The invention relates to the technical field of neurotrauma prognosis image analysis, and discloses a craniocerebral trauma prognosis prediction analysis system based on a three-dimensional model. According to the system, multi-scale segmentation and topology construction are carried out on a craniocerebral three-dimensional image of a patient, the morphological evolution rate of a trauma area is tracked, and key signal events in the trauma evolution process are accurately recognized in combination with an edema signal change curve. The system further quantitatively analyzes dynamic deviations associated with the integrity of normal brain tissue fiber bundles when a signal event occurs, thereby generating a lesion propagation path and mapping it to functional network nodes of a standard brain map, ultimately identifying a prognostic key brain network. According to the technical scheme, key event capture and path foresight prediction in the dynamic propagation process of the secondary injury after the craniocerebral trauma are realized, and the accuracy of prognosis evaluation is improved.

The invention provides a method and a system for predicting early gastric cancer prognosis by a circulating marker, and relates to the technical field of auxiliary diagnosis. The method comprises the following steps: performing multi-omics detection on a blood sample based on a preset sampling time sequence to obtain a multi-dimensional time sequence characteristic data set containing three groups of heterogeneous data of circulating tumor DNA, exosomes and protein markers; calculating a change slope and a fluctuation variance of the heterogeneous data in adjacent time sequence intervals, constructing a dynamic variation feature matrix in combination with a standard attenuation weighting factor, and deeply mining spatial cross-correlation and sequence dependence features of the matrix to generate a multi-modal fusion feature fingerprint; and performing regression operation on the feature fingerprints by using an integrated learning stack model to obtain a dynamic prognosis risk score, and further retrieving a risk hierarchical mapping table to generate a prognosis evaluation result containing a survival curve. According to the method, multi-modal heterogeneous data can be effectively fused, the biological dynamic characteristics in the tumor postoperative recovery phase are captured, and the accuracy and timeliness of early gastric cancer prognosis prediction are remarkably improved.

The invention relates to the technical field of tumor marker detection, in particular to a breast cancer lung metastasis related biomarker screening system which comprises a differential genetic factor mining module, a function association module, a verification screening module, an interference elimination module and an optimization integration module. According to the method, the candidate genetic factors highly associated with lung metastasis are extracted, and the expression fluctuation characteristics are combined to carry out difference analysis, so that the preliminary screening accuracy is improved, pathological information and pathway annotation are integrated to construct an action network, pathway weights are analyzed, and functional expressions of the candidate factors are quantitatively evaluated; an independent sample is called to verify transcription consistency and clinical relevance, interference factors with poor repeatability are eliminated, non-tumor tissue high-expression interference items are rejected in combination with background transcription characteristics, the specificity and adaptability of screening results are improved, and finally a marker set with metastasis mechanism indicating significance and prognosis prediction value is formed through comprehensive evaluation. And clinical transformation support is provided for identification of lung metastasis of breast cancer.

The invention relates to the technical field, in particular to a cerebral hemorrhage intelligent decision support system based on deep adaptive feature fusion, which comprises a multi-modal data standardization module, a cross-modal feature fusion module, a focus segmentation calculation module, a hemorrhage type identification module and an illness state grading output module. According to the method, deep association between fusion features and bleeding types is mined through an attention mechanism, related feature indexes are converted into standardized scores by referring to clinical common scoring standards, model attention weight distribution is optimized by combining actual prognosis result deviation, the suitability of illness state grading and the clinical scoring standards is improved, and the probability of illness state grading is lowered. An accurate grading result and prognosis prediction reference are provided for clinical treatment decision and rehabilitation intervention; effective data are screened from multiple types of brain images according to image quality related indexes, clinical text key information extraction and association labeling are combined, data integrity and consistency verification is carried out at the same time, and the standardization degree of multi-source data is improved.

Disclosed is an approach that uses artificial intelligence to make predictions regarding patient outcomes, and more specifically, to machine-learning models for inpatient prognosis prediction. A machine-learning classifier may be trained for predicting likelihoods of patients dying a number of days following inpatient admission. A training dataset may comprise, for subjects in a cohort, numerical and categorical values based on a set of tests, as well as demographic or biometric and / or historical values. The machine-learning classifier is trained so as to subsequently output likelihood of patients dying within the number of days following an admission at a healthcare facility.

An aspect of the invention is a prognosis prediction device including a prognosis prediction unit that predicts, using prognosis prediction information that indicates a relationship between graph tumor information that is information on an image of a tumor represented using an amount defined by a graph theory and a prognosis of a person or an animal having the tumor, a prognosis of an estimation target based on graph tumor information indicating an image of a tumor of the estimation target.

The application discloses an adaptive clustering federated learning modeling method for precision medicine, and relates to the technical field of precision medicine, and comprises the following steps: data collection and preprocessing and model construction and training; the application accurately determines the optimal number of the global model through adaptive clustering, and divides clustering groups according to the similarity of the client model parameters, realizes independent training of the groups, effectively improves the adaptability of the model to different client data characteristics, samples and label distribution differences, avoids the problem that a single model has poor performance in some clients, and significantly enhances the ability of the model to capture complex medical patterns; the model generalization is optimized through grouped training, so that the model can better cope with new data distribution, under the premise of ensuring the privacy and security of medical data, the accuracy and reliability of the model in precision medical scenes such as disease diagnosis and prognosis prediction are greatly improved.

The invention provides a method for merging expression values based on an MTX family and a kit for predicting prognosis of thyroid cancer, the kit detects the transcriptional level expression quantity of the MTX gene family by combining an RT-qPCR technology with a specific primer, and the expression quantity data is substituted into a prognosis prediction model, so that the prognosis of a thyroid cancer patient is realized. Particularly, the prognosis evaluation of BRAF V600E mutant thyroid cancer patients is realized. Experiments prove that the expression level of the MTX gene family is related to thyroid cancer driving gene BRAF V600E mutation, and the prognosis of a patient is influenced by influencing the electron transfer function of the BRAF V600E mutation thyroid cancer patient, so that the MTX gene expression level detection can be used as a prognosis prediction index of the BRAF V600E mutation thyroid cancer patient, and the prognosis of the BRAF V600E mutation thyroid cancer patient is influenced. And a basis is provided for selection of operation modes of thyroid cancer patients.

The application discloses a method for constructing a 4D FLOW-based hemodynamic evaluation pulmonary embolism prognosis prediction model and application, relates to the medical image technology field, and comprises the following steps: collecting 4D-Flow images of patients who have been diagnosed with pulmonary embolism from medical institutions to obtain image data A; pre-processing the image data A, and dividing the pre-processed image data A into a training set and a verification set according to a proportion; respectively performing imageomic feature extraction, clinical feature extraction and 4D FLOW hemodynamic feature extraction on the training set and the verification set; screening the imageomic features and the clinical features and 4D FLOW hemodynamic detection indexes to obtain key features; and based on the key features, establishing a multi-omics prediction model for pulmonary embolism prognosis prediction, thereby providing a new imaging reference for pulmonary embolism treatment.

The application discloses a kind of biomarkers for evaluating systemic lupus erythematosus to lupus nephritis progression, prediction model and application, belong to lupus nephritis prediction technical field.The application provides a kind of for evaluating systemic lupus erythematosus to lupus nephritis progression prediction model, the prediction model is according to the ratio of biomarker CD8 / CD4 and the κ / λ ratio of naive B cell, carries out binary Logistic regression analysis, obtains LogitP value, by comparing the high and low of the LogitP value and critical value 0.66938, predicts systemic lupus erythematosus to lupus nephritis progression situation.The prediction model constructed in the application aims to identify the individuals in lupus patients who may develop into lupus nephritis.This innovative model not only provides important guidance in the diagnosis, prognosis prediction and efficacy evaluation of the disease, but also provides a new perspective for the clinical management of lupus nephritis.

The application discloses a blood flow guiding dense mesh stent preoperative prognosis evaluation method and device based on hemodynamics, equipment and a storage medium, which comprises the following steps: constructing a three-dimensional blood vessel geometric model based on medical image data of a patient, performing hemodynamic simulation, obtaining a jet path in a tumor cavity, virtually implanting the blood flow guiding dense mesh stent in the three-dimensional blood vessel geometric model, obtaining a stent center line of the stent located in the tumor cavity, calculating a jet compliance index for prognosis evaluation based on the jet path in the tumor cavity and the stent center line, constructing a jet compliance comprehensive index based on the first jet compliance index, the second jet compliance index and the third jet compliance index, and performing prognosis evaluation on the preoperative curative effect of the blood flow guiding dense mesh stent according to the comprehensive index, so that the reliability of prognosis prediction is improved.

The present invention relates to a biomarker for diagnosing and prognostically predicting diabetes mellitus associated with pancreatic cancer and a use thereof, and more particularly, to a biomarker composition for diagnosing and prognostically predicting diabetes mellitus associated with pancreatic cancer, a kit and an information providing method, which comprise a preparation for determining the expression level of REG4 (REGEN 4) protein. Furthermore, the present invention relates to an information providing method for providing necessary information for the diagnosis and prognosis of diabetes-associated pancreatic cancer by measuring the level of REG4 in a biological sample isolated from a subject suffering from diabetes-associated pancreatic cancer, and for determining the prognosis of diabetes-associated pancreatic cancer by patient queue analysis, single-cell RNA sequencing (scRNAseq) analysis, and organoid methods. Provided is a complex prognostic prediction of REG4 against diabetes accompanied by pancreatic cancer. Therefore, an individualized treatment method can be provided for a patient, and prognosis prediction and treatment method determination can be more reasonably carried out on an object with diabetes mellitus accompanied by pancreatic cancer.

The invention relates to the technical field of medical equipment, in particular to a portable intelligent puncture detection device, system and method, and the device comprises a puncture module which is used for carrying out blood vessel puncture and obtaining a sample through infrared or ultrasonic guidance; the monitoring module is connected with the puncture module and is used for analyzing the sample and acquiring blood biological indexes of the blood; the monitoring module is also used for monitoring hemodynamic parameters through PICCO; the analysis module is used for carrying out analysis by adopting the constructed analysis model according to the blood biological indexes and the hemodynamic parameters to obtain analysis results, and the analysis results comprise illness condition severity program classification, treatment suggestion and prognosis prediction of the patient; the verification module is used for acquiring and displaying an analysis result; and the server is also used for acquiring an analysis result confirmation signal, confirming the analysis result and displaying a confirmation result. According to the scheme, multi-parameter and multi-index monitoring can be carried out, data analysis is carried out, the data utilization rate is increased, and medical workers are assisted to carry out treatment work.

The invention relates to the technical field of intelligent medical assistance, in particular to a stroke emergency prognosis prediction method, device and equipment and a medium, and the method comprises the steps: collecting historical emergency treatment data, historical basic health data and historical gene data of historical patients; based on the historical emergency treatment data, the historical basic health data and the historical gene data, determining historical data source cross features; on the basis of historical data source cross features, a deep learning algorithm and a random forest algorithm are adopted to construct a prediction model for predicting three aspects of conditions of the patient to obtain a historical prediction result; based on a historical prediction result, constructing a loss function based on three aspects of conditions of the patient; based on the loss function, optimizing the prediction model to obtain an optimized prediction model; acquiring multi-source target data of a target patient; by optimizing the prediction model, the target prediction result is obtained, the limitation of existing single target prediction is broken through, and the accuracy and reliability of prognosis prediction are improved.

The system according to this embodiment aims to design an optimal regeneration protocol based on the individual patient's condition and to dynamically adjust the treatment plan. [Solution] The system according to the embodiment comprises a data collection unit, an analysis unit, a design unit, an adjustment unit, and a prediction unit. The data collection unit collects patient data. The analysis unit analyzes the data collected by the data collection unit. The design unit designs an optimal regeneration protocol based on the analysis results obtained by the analysis unit. The adjustment unit dynamically adjusts the treatment plan based on the regeneration protocol designed by the design unit. The prediction unit simulates the recovery process based on the treatment plan adjusted by the adjustment unit and provides a prognosis prediction.

The invention provides an image-clinical characterization-combined multi-endpoint prognosis evaluation method for transjugular vein intrahepatic portal vein shunt, which comprises the following steps of: constructing a few-label portal vein segmentation module to obtain a preoperative CT portal vein label of a full-dose patient, and extracting deep learning features and radiomics features of the region; establishing a multi-modal interactive representation learning module for implementation, and performing cross-modal fusion with clinical features to form unified representation; and designing a multi-endpoint prognosis prediction module, inputting the data to a plurality of prognosis task decoders for postoperative survival, portal vein pressure gradient, hepatic encephalopathy prediction and the like, and adopting a multi-task learning optimization model to obtain a postoperative multi-endpoint prognosis evaluation result. According to the method, efficient fusion and multi-endpoint prognosis prediction of images and clinical information can be realized under limited labeling, clinical doctors can be assisted in preoperative patient screening and treatment scheme making, and the method has good clinical application value.

The invention relates to the technical field of biology, and provides a LanCL1 gene as a target for typing and prognosis of glioma. According to the application of the reagent for detecting LanCL1 gene expression in preparation of products for glioma molecular typing and prognosis prediction, molecular typing of glioma patients can be achieved, LanCL1 high expression is highly related to low malignancy and good prognosis, and clinical risk stratification, treatment decision and treatment assistance are facilitated.

The present application relates to the technical field of tumor prognosis prediction, and particularly relates to a tumor prognosis evaluation method and system based on clinical data analysis. Newly added clinical data is collected regularly to train incremental decision trees and add them to a random forest ensemble model; for each historical decision tree, based on the statistical stability of the feature distribution of the newly added data, the usability is evaluated, combined with the prediction bias to calculate a prognosis rule change index; the right-censored samples with definite outcomes in the newly added data are used to calculate an asymmetric misleading effect index; the weight of the historical decision tree is decayed and calibrated according to the two indexes, to reduce the interference of rule obsolescence and data defects; the prognosis of the patient is predicted based on the calibrated model. The present application effectively overcomes the interference of clinical practice evolution and data right-censored on the accuracy of prognosis evaluation, ensures that the ensemble model is always close to the latest clinical reality, and significantly improves the accuracy of tumor prognosis evaluation.

The application discloses application of CPSF7 as an ovarian cancer treatment and prognosis target, and relates to the technical field of biological medicine.The application research finds that overexpression of CPSF7 is related to poor prognosis of ovarian cancer, indicating that CPSF7 can be used as a prognosis index and potential treatment target of ovarian cancer.Further research shows that CPSF7 promotes malignant progression of ovarian cancer by promoting proliferation, migration and invasion of ovarian cancer cells, and inhibition of CPSF7 expression can significantly inhibit proliferation, migration and invasion of ovarian cancer cells.The application also finds that UBE2K is one of key downstream targets of CPSF7 in the ovarian cancer cell-mediated carcinogenic process, and inhibition of UBE2K expression can weaken the overexpression of CPSF7 induced enhancement effect of ovarian cancer cell proliferation, migration and invasion.The application provides a new target for treatment and prognosis prediction of ovarian cancer, and has important clinical application value.

The application discloses a lung inflammation lesion quantitative evaluation artificial intelligence model based on CT images and relates to the field of artificial intelligence models.The model comprises CT image preprocessing, self-supervised lesion segmentation and quantification, multi-modal joint pre-training coding and multi-task diagnosis and prognosis prediction module composition which are sequentially and communicatively connected, and realizes feature interaction through a unified feature embedding space.The model realizes self-supervised lesion segmentation and multi-dimensional quantification by adopting a three-dimensional generative reconstruction network, completes image-text feature fine-grained alignment through cross-modal contrast learning of an adversarial enhancement, and fuses multi-dimensional features.The model can complete multiple tasks such as ARDS diagnosis, non-invasive estimation of P / F ratio, severity grading and prognosis prediction in parallel, reduces dependence on artificial labeling, improves cross-center generalization capability and diagnosis precision, and provides a standardized intelligent tool for clinical evaluation of severe lung inflammation.

The present invention relates to a biomarker HLA-DOA for sepsis-related diseases and a use thereof. The present invention provides a use of HLA-DOA or an active fragment or functional fragment thereof in the preparation of a product for early diagnosis, risk assessment, immune status assessment, prognosis prediction and / or treatment regimen selection of sepsis-related diseases in a subject.

The invention relates to the field of oncology, in particular to application of a cancer immunotherapy target and a diagnosis and prognosis prediction biomarker. Wherein at least one marker in the EGFR / Wnt / beta-catenin-LINC00973-miRNA-CD55 / CD59 pathway can be used for evaluating the sensitivity or the prognosis of the cancer immunotherapy.

The invention discloses a disease prognosis prediction method and system, and the method comprises the steps: generating interpretation layer probability distribution and visual features according to pathological section image data; generating pathological section overall features according to the interpretation layer probability distribution and the visual features; generating magnetic resonance embedding features according to the magnetic resonance image data; similarity retrieval is carried out in the visual features according to the magnetic resonance embedding features, and proxy interpretation distribution is generated according to a retrieval result; generating prediction explanation distribution according to the magnetic resonance embedding features, and performing alignment processing on the magnetic resonance embedding features according to a distribution relation of the proxy explanation distribution and the prediction explanation distribution in an explanation layer space; and generating fusion features according to the aligned magnetic resonance embedding features, the pathological section overall features and the prediction interpretation distribution, and outputting prognosis prediction results of a plurality of time intervals according to the fusion features. According to the method, unified semantic modeling and prognosis prediction processing of the multi-modal medical image information are completed.

The invention belongs to the technical field of biomedicine and molecular diagnosis, and particularly relates to a combined marker and a risk scoring model for prognosis prediction of lung adenocarcinoma based on lactylation related genes as well as a construction method and application of the combined marker and the risk scoring model, and the combined marker comprises the following 12 genes: ANGPTL4, ITGA6, SOD1, CCL20, FKBP3, DECR1, SEMA3C, TRIM28, VEGFC, TNNC2, CRTAC1 and HGF. On the basis of sequencing data of large-scale lung adenocarcinoma samples, a group of lactylation related genes closely related to the total lifetime are systematically screened out, and a risk scoring model is constructed. According to the model, survival risk layering can be accurately carried out on the lung adenocarcinoma patient, and reliable reference is provided for clinical treatment strategy formulation and individualized management. In addition, the lactylation related genes are newly found, and the lactylation process in the lung adenocarcinoma can be understood.

The invention discloses a prognosis marker and a dynamic prognosis prediction method for colorectal cancer liver metastasis. The method comprises the following steps: S1, acquiring clinical pathological characteristic data of a patient with colorectal cancer liver metastasis and a longitudinal laboratory marker measured during post-operation follow-up visit; s2, extracting a change trend of the longitudinal laboratory marker by utilizing multivariable function principal component analysis to obtain a principal component score; s3, training a random survival forest model by using the principal component score and the clinical pathological feature data to obtain a dynamic prediction model; s4, dynamically updating the score of the principal component based on a newly collected laboratory marker of postoperative follow-up visit of the patient, and outputting dynamic risk assessment results of the progression-free lifetime and the total lifetime of the patient through a dynamic prediction model; according to the method, the prediction model capable of dynamically evaluating the survival risk of the patient is constructed and updated by fusing the dynamic longitudinal laboratory marker and the static clinical pathological characteristics.

One aspect relates to: a marker composition for diagnosis or prognosis of Alzheimer's disease, comprising microRNA-214 (miRNA-214); a marker composition for diagnosis or prognosis of Alzheimer's disease, comprising an agent for measuring an expression level of miRNA-214; a diagnostic or prognostic kit; and a method for providing information for diagnosis or prognosis. According to one aspect, data analysis for the diagnosis of Alzheimer's disease can be made to measure the expression level of miRNA-214 in blood, and as a biomarker for the prognosis of Alzheimer's disease, the microRNA can be advantageously used to predict the progression rate and treatment result of diseases.

The application provides a prognosis prediction method and system for chronic Doc patients, relates to the technical field of clinical prognosis evaluation, and collects multi-modal data such as neuroimaging, neuroelectrophysiological data, biochemical indexes and clinical data, carries out standardized processing and feature extraction, and fuses spatial features, time sequence features and key features.Combining a trained consciousness state grading evaluation model and a prognosis prediction model, a feature level data set is generated, and the consciousness state grading and prognosis development trend of the patient are accurately predicted.The application effectively integrates the complementary information of multi-modal data, improves the accuracy and reliability of prognosis prediction, and provides scientific support for clinical decision-making, individualized treatment and medical resource optimization.

The application relates to a biomarker for radiotherapy synergism and prognosis prediction of a solid tumor and application thereof, and the biomarker is arginine and / or proline. Compared with the prior art, the specificity of the arginine and / or proline is better, and the application is simple. The arginine and / or proline can be detected in patient serum, the detection means is more economical and simple, has more opportunities to be applied to the clinic, and has a good application prospect.