42 results about "Prognostic factor" patented technology

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 discloses a preoperative risk stratification system based on hepatic resection after transformation treatment in the technical field of biomedicine, and the system comprises a sample module which is used for selecting a proper hepatocellular carcinoma patient as a sample, distributing the patient sample to a training queue and an internal verification queue, and building an external verification queue; the treatment module is used for providing a treatment strategy for the patient based on whether liver resection is performed or not after conversion treatment; the tracking module is used for carrying out regular follow-up visit on the patient subjected to the liver resection or not subjected to the liver resection after the conversion treatment; and the data analysis module is used for determining prediction factors related to recurrence-free survival in the training queue by adopting a minimum absolute contraction and selection operator regression analysis method, further analyzing and screening out independent prognosis factors through multivariable Cox regression, and constructing a column graph based on the factors to predict the postoperative recurrence rate. Through verification of the internal and external verification queues, the method can effectively guide and select a patient who is most likely to benefit from the liver resection operation after transformation treatment.

Systemic lupus erythematosus (SLE) is an autoimmune disease in which circulating immune complexes can cause different types of glomerulonephritis, according to immune deposits and to the type of glomerular cell injury. Proliferative lesions represent the most severe form of lupus nephritis (LN) and often lead to kidney failure and death. Mucosal-associated invariant T (MAIT) are a subset of innate-like T cells that recognize microbial-derived ligands from the riboflavin synthesis pathway. Now the inventors analyzed the phenotype and function of peripheral blood MAIT cells by flow cytometry in 26 patients with LN and in a control group of 16 healthy volunteers. The inventors found that MAIT cell frequencies are markedly reduced in blood of LN patients. More particularly, among LN patients, baseline MAIT cell frequency, Ki-67 expression evaluating proliferative activity and granzyme B production measuring cytotoxicity represent promising prognostic factors of renal response one year after induction therapy. In conclusion, the inventors showed that baseline frequency and cytotoxic profile of MAIT cells may represent a promising prognostic factor of renal remission one year after induction therapy.

The invention discloses an application of Hsa-miR-24-3p in construction of a pancreatic ductal adenocarcinoma postoperative total lifetime prediction model. According to the invention, the expression of Hsa-miR-24-3p in preoperative serum of a PDAC patient is analyzed, and the total lifetime of a patient with increased level of Hsa-miR-24-3p (miR-24) is obviously reduced (Plt; 0.0001) of the method for manufacturing the same; multi-factor analysis shows that miR-24 is a prognosis factor independent of the age, gender and clinical pathological characteristics of a patient, and the prediction efficiency of miR-24 is remarkable; the area under the ROC curve reaches 0.82, which is superior to the area under the CA19-9 (0.61), the area under the CA125 (0.59), the area under the CA50 (0.51) and the area under the CEA (0.56); when the miR-24 and the TNM are staging, and the CA19-9 and the CA125 are integrated into the column diagram model, the prognosis prediction accuracy is further improved.

The invention discloses an HIV (human immunodeficiency virus) combined hepatocellular carcinoma risk stratification model and a construction method thereof, the construction method comprises the following steps: obtaining clinical data of an HIC-HCC patient, the clinical data comprising demographic information, clinical feature information and treatment and outcome information; taking the total lifetime of the patient as an outcome, performing single-factor analysis on the clinical data, and screening out a plurality of risk factors influencing the total lifetime of the patient; performing multi-factor analysis on the plurality of risk factors to obtain independent prognosis factors of the total lifetime of the patient; the independent prognosis factors comprise organ fatigue and multiple tumors; and establishing a risk layering model based on the independent prognosis factors.

The invention belongs to the technical field of biological medicine, and particularly relates to application of GLUT5 serving as a colorectal cancer biomarker in development of an in-vitro detection kit, a prognosis model and an inhibitor. The GLUT5 is highly expressed in colorectal cancer tumor-related fibroblasts (CAFs), the expression level of the GLUT5 is remarkably related to poor prognosis of a patient, and the GLUT5 can be used as a molecular basis for auxiliary diagnosis and an independent prognosis factor. In mechanism, the GLUT5 promotes tumor progression by mediating fructose metabolism reprogramming of the CAFs. A full-chain solution from early diagnosis and precise prognosis to targeted therapy is provided for colorectal cancer, and the clinical transformation value is remarkable.

The invention discloses application of a lactic acid modified gene ENO1 inhibitor in preparation of a medicine for treating nasopharynx cancer, and relates to the technical field of biological medicines. A head and neck squamous cell carcinoma prognosis model containing seven lactylation related genes is constructed by analyzing a TCGA database, the model can effectively distinguish patient risks, the total lifetime of a high-risk group is remarkably shortened, and a risk score is an independent prognosis factor; the functions of the key gene ENO1 are deeply studied through in-vitro experiments, and experimental results show that silencing of the ENO1 gene in nasopharynx cancer 5-8F cells causes up-regulation of cell pan-lactylation level, up-regulation of MMP2 expression and down-regulation of E-cadherin expression, and migration and invasion ability of tumor cells is significantly enhanced. The prognosis model provided by the invention has an important clinical prediction value, inhibition of ENO1 can promote tumor progression through abnormal lactylation, and a new thought is provided for taking ENO1 as a treatment target.

The invention relates to the technical field of medical prognosis evaluation, in particular to a sex-specific advanced young non-small cell lung cancer prognosis model construction method, which collects clinical data of young metastatic non-small cell lung cancer patients, including sex, age, body mass index, D-2 polymer level, gene mutation state, metastasis site, tumor marker and hematology index. Data are divided into male and female queues, male specific prognostic factors (body mass index, gene mutation state and liver metastasis state) and female specific prognostic factors (D-2 polymer level and gene mutation state) are identified through Cox proportional risk regression analysis, and male and female column map prognostic models are respectively constructed based on the factors. All prognosis factors are converted into risk scores, the corresponding relation between the total score and the survival probability is established, finally, the model can output individualized survival probability prediction results of patients of different genders, and important reference is provided for clinical treatment and prognosis evaluation.

The application relates to the technical field of postoperative early warning, and particularly discloses a postoperative risk early warning method and system based on machine learning, which belongs to the technical field of postoperative early warning, and the method comprises the following steps: acquiring historical patient data of a plurality of patients who have undergone a to-be-early-warned operation, determining an adverse prognosis set of the to-be-early-warned operation and adverse data of each adverse prognosis in the adverse prognosis set; determining an influence factor vector of each adverse prognosis in the adverse prognosis set and an independent prognosis factor set; determining a plurality of preset non-independent factor sets of each adverse prognosis in the adverse prognosis set; determining a non-independent prognosis factor set of each adverse prognosis in the adverse prognosis set; and realizing postoperative risk early warning. The postoperative risk early warning method can comprehensively cover the postoperative risk influence dimension, accurately capture data correlation, realize intelligent transformation from data to risk prediction, provide more accurate and comprehensive postoperative risk early warning for the clinic, and improve the scientificity, accuracy and reliability of postoperative risk early warning.

The application discloses a colorectal cancer IHC staining image tumor infiltration front immune grading method, system and storage medium, and the method comprises the following steps: acquiring a colorectal cancer IHC staining image; classifying the staining image by using a trained convolutional neural network classifier to obtain nine types of tissues, namely tumor epithelium, tumor interstitium, tumor necrosis, mucus, muscle, normal gland, lymph aggregation, fat and background; merging the nine types of tissue categories into five categories to automatically determine a tumor infiltration front and a tumor center area; performing cell segmentation and counting on the above-mentioned areas to obtain CD3 and CD8 positive cell densities, and then performing immune grading; the application quantifies the CD3 and CD8 positive cell densities in the tumor infiltration front and the tumor center area by automatically determining the tumor infiltration front and the tumor center area, evaluates the CD3 and CD8 positive cell densities in the tumor infiltration front as a prognostic factor, and thus assists pathologists in diagnosing and treating colorectal cancer patients.

The application provides a gout recurrence risk assessment method and system based on a neutrophil-to-lymphocyte ratio, comprising: data acquisition, data preprocessing, and generating gout recurrence risk assessment sample data through data standardization processing; establishing a joint model of a Cox proportional hazards regression model and a competing risk model to evaluate the correlation between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence; adding NLR as a characteristic variable of a prognosis factor of gout recurrence risk to a baseline model to construct multiple gout recurrence risk candidate prediction models; screening to obtain a target gout recurrence risk assessment model; generating an evaluation result; and visual display. The method can effectively handle the problems of incomplete and skewed distribution of clinical data, improve the quality and stability of the data, improve the accuracy of evaluation and prediction by screening out an effective target gout recurrence risk assessment model, and provide reliable auxiliary decision support for clinicians.

The invention provides a gout recurrence risk assessment method and system based on the ratio of neutrophil to lymphocyte. The method comprises the steps of data collection, data preprocessing and generation of gout recurrence risk assessment sample data through data standardization processing; establishing a combined model of a Cox proportional risk regression model and a competitive risk model, and evaluating the correlation between the ratio NLR of neutrophil to lymphocyte and gout recurrence; taking the NLR as a characteristic variable of a gout recurrence risk prognosis factor, adding the NLR into the baseline model, and constructing a plurality of gout recurrence risk candidate prediction models; screening to obtain a target gout recurrence risk assessment model; generating an evaluation result; and performing visual display. According to the method, the problems of incomplete and skewed distribution of clinical data can be effectively solved, the quality and stability of the data are improved, the accuracy of evaluation and prediction is improved by screening out the effective target gout recurrence risk evaluation model, and reliable auxiliary decision support is provided for clinicians.

The invention relates to the technical field of biomedicine, and discloses application of an FASN inhibitor in preparation of a medicine for treating KAT2B low-expression renal cell carcinoma. According to the invention, development of a lipid metabolism related biomarker is realized, it is determined that the biomarker is an independent prognosis factor KAT2B in RCC, high methylation of a KAT2B promoter region causes down-regulation of expression of the biomarker, then lipid generation and development of the RCC are enhanced, a mechanism of KAT2B / HDAC5 / LSD1 / FASN axis for inhibiting the lipid generation and development of the RCC in vivo is proposed for the first time, KAT2B is acetylated at a K726 site of HDAC5, and KAT2B and LSD1 / FASN are used for inhibiting the lipid generation and development of the RCC. The FASN inhibitor can be used for inhibiting cancer cell targeting and promoting extranuclear transport of the FASN inhibitor, so that the FASN inhibitor and LSD1 cannot form a compound in a cell nucleus, the histone methylation level is increased, FASN expression is reduced, and a new thought is provided for research and development of products for inhibiting cancer cell targeting through the FASN inhibitor.

The invention provides a kit for a method for predicting or evaluating the prognosis of a glioma patient. In combination with immune-related genes, a group of characteristic genes capable of stably predicting the prognosis of the diffuse glioma is found; by adopting the system disclosed by the invention, the prognosis of the diffuse glioma can be well predicted; single-factor and multi-factor Cox proportional risk regression analysis is further carried out, and it is proved that the immune risk score can be really used as an independent prognosis factor of the diffuse glioma.

The invention relates to the technical field of medical artificial intelligence and prognosis prediction, and discloses a construction method of a prognosis risk prediction model for prostate cancer patients. According to the method, a diagnosis and treatment state transition topology is formed by creating a hierarchical knowledge network and mining diagnosis and treatment path time sequence dependence, and a whole disease course time sequence data segment of a patient is depicted according to the topology. Synchronously operating a feature selection cycle of simulated annealing optimization, and performing dynamic interactive training with a depth prediction architecture containing a multi-scale time sequence attention mechanism to realize online adaptive screening of feature subsets; and constructing a feature influence propagation graph according to a feature selection process, identifying a key feature cluster, and performing guided correction on the attention weight of the model according to the key feature cluster. And integrating the components to form a prediction model, and establishing an online self-adaptive fine tuning loop. According to the method, feature combination can be effectively optimized, the focusing capability and prediction robustness of the model for key prognosis factors are improved, and increment adjustment according to new data is supported.

The invention relates to the technical field of biomedicine, and discloses a rectal cancer prognosis model construction method based on deep learning, and the method comprises the following steps: identifying disease characteristics of a rectal cancer patient, and defining prognosis requirements of the rectal cancer patient according to a baseline standard of the disease characteristics; determining focus types and iconography characteristics of the rectal cancer patients, and analyzing key prognosis indexes of the rectal cancer patients in combination with the focus types and the iconography characteristics; analyzing prognosis influence factors of the rectal cancer patient, and extracting characteristic data of the medical data; key prognosis features of the rectal cancer prognosis features are extracted, and derived features are determined; and setting a survival analysis result of the rectal cancer patient, and constructing a prognosis model of the rectal cancer patient in combination with the key prognosis characteristics, the derived characteristics and the survival analysis result. The use efficiency and generalization ability of the prognosis model can be improved.

The invention relates to the technical field of medical information, and discloses a non-small cell lung cancer immunotherapy prognosis risk assessment method and system and a medium, and the method comprises the steps: obtaining clinical data including clinical variables, progression-free lifetime (PFS) and total lifetime (OS); taking each clinical variable as a hierarchical index to divide patient subgroups, and screening out hierarchical indexes with significant differences; then, aiming at each subgroup divided by the screened hierarchical indexes, quantifying prognosis influence of other clinical variables on the corresponding subgroup by adopting a risk regression model; and finally, screening out determinants with prognosis values according to a quantification result, dividing the determinants into different prognosis recommendation levels, and constructing a risk assessment matrix. According to the method, through a two-stage screening strategy of firstly identifying the effective hierarchical indexes and then analyzing the prognosis factors, evaluation deviation caused by generalization of local effective factors or neglecting of global non-significant factors is avoided, so that the accuracy and clinical practicability of prognosis evaluation are remarkably improved.

The invention provides a method for evaluating a prognosis curative effect of drug treatment of a liver cancer patient based on radiomics, and belongs to the technical field of biomedical detection. According to the method, the body composition is evaluated through L3 level CT scanning, sarcopenia (Sarcopenia) is defined by skeletal muscle index (SMI), and muscle steatosis (Myosteatosis) is defined by skeletal muscle density (SMD). Progression-free lifetime (PFS) and overall lifetime (OS) are evaluated, and single-factor and multi-factor Cox regression analyses are performed to identify prognostic factors. Experimental results show that sarcopenia and muscle fatty degeneration are important predictive factors for poor prognosis of HCC patients receiving HAIC combined targeted therapy and immunotherapy, especially sarcopenia, and are independent risk factors of OS. Therefore, the body component detection method plays an important role in prognosis evaluation and treatment decision, and can be well used for prognosis curative effect evaluation of drug treatment of the liver cancer patient.

The invention relates to the technical field of postoperative early warning, particularly discloses a postoperative risk early warning method and system based on machine learning, and belongs to the technical field of postoperative early warning. Determining a bad prognosis set of the operation to be pre-warned and bad data of each bad prognosis in the bad prognosis set; determining an influence factor vector of each bad prognosis in the bad prognosis set and an independent prognosis factor set; determining a plurality of preset non-independent factor sets of each bad prognosis in the bad prognosis set; determining a non-independent prognosis factor set of each bad prognosis in the bad prognosis set; and post-operation risk early warning is realized. According to the method, the postoperative risk influence dimension can be comprehensively covered, data association can be accurately captured, intelligent conversion from data to risk prediction is realized, more accurate and comprehensive postoperative risk early warning is provided for clinic, and the scientificity, accuracy and reliability of postoperative risk early warning are improved.

This invention discloses a risk stratification assessment model, device, and construction method for RUNX1::RUNX1T1-positive children with acute myeloid leukemia. The construction method includes: acquiring sample clinical data; assessing the correlation between clinical predictors and overall survival (OS) and event-free survival (ORS); for continuous variables, determining the optimal risk cutoff value for predicting poor prognosis; converting the continuous variables into binary variables; performing univariate Cox proportional hazards regression analysis to screen for factors significantly associated with OS and ORS; and incorporating these factors into a multivariate Cox proportional hazards regression model to confirm independent prognostic factors. This invention systematically integrates the clinical variable MRD1 and the percentage of peripheral blood blasts at diagnosis as core predictors, constructing a model capable of accurately assessing ORS. + A prognostic model for pAML risk was developed and rigorously validated. This model demonstrated superior predictive performance, effectively and accurately identifying patients with a high actual risk of relapse and death from the traditionally low-risk patient population.

This invention belongs to the field of biomedical technology and discloses the application of exosomal lncOSLMT in the diagnosis and treatment of osteosarcoma lung metastases. This invention discloses the application of reagents for detecting lncOSLMT in the preparation of products for risk diagnosis or prognostic assessment of osteosarcoma lung metastases. Through research, this invention found that lncOSLMT selectively accumulates in exosomes released by osteosarcoma cells with high metastatic potential. Its elevated expression is positively correlated with the incidence of lung metastasis and serves as an independent prognostic factor for poor prognosis in osteosarcoma patients. This invention elucidates the regulatory role of lncOSLMT in the pre-metastatic microenvironment of osteosarcoma lung metastases and its effect on lung metastasis, clarifying that targeting lncOSLMT has significant clinical translational value for targeted treatment of osteosarcoma lung metastases, especially in osteosarcoma liquid biopsy and early metastasis prediction, and is of great importance in ensuring adequate clinical safety.

The invention discloses a combination of melanoma biomarkers found on the basis of transcriptomics data of lesion sites of melanoma and vitiligo. The biomarker combination is composed of two genes, namely BCAN and OCA2. The invention also discloses a method for extracting reverse expression gene characteristics based on transcriptomics data of melanoma and vitiligo lesion sites. Meanwhile, the invention also discloses application of a melanoma prognosis model constructed by using the group of markers in prognosis evaluation of melanoma patients and a model construction method. The risk scoring model can be used as an independent prognosis factor of melanoma patients, and proves that patients in a high-risk group are related to poor prognosis, and the prognosis prediction accuracy is good.

Tumor budding (TB) is defined as a cluster of one to four tumor cells at the tumor invasive front. Though promising as a prognostic factor for colorectal cancer, its routine clinical use is hampered by high inter-and intra-observer disagreement on routine H&E staining. Therefore, automated methods are provided that minimize the inter-and intra-observer disagreement for tumor bud detection on images of H&E-stained tissue sections.

The invention discloses a cerebral hemorrhage clinical data multi-dimensional mining and knowledge discovery method and system, and the method comprises the steps: carrying out the standardization and integration of multi-source heterogeneous data, and constructing a unified clinical data feature set; multi-dimensional feature extraction is carried out on the clinical data feature set, time window association rule mining is carried out, and an association rule knowledge base is formed through association mode screening and evaluation; prognosis-oriented patient subgroup clustering is carried out based on the association rule knowledge base, treatment scheme feature components are extracted through treatment scheme similarity calculation, and a treatment mode map is constructed; then, an individualized factor weight threshold value is determined through factor interaction effect detection, and factor importance ranking is executed to form a prognosis key factor combination; and finally, the follow-up visit data is used for verifying and correcting the prognosis key factor combination and implementing evidence-based grade labeling, and a clinical decision support result is output, so that systematic identification and individualized evaluation of the prognosis factors are realized, and the clinical decision accuracy is improved.

The invention discloses an application of a CGREF1 inhibitor in preparation of a medicine for preventing and / or treating colorectal cancer metastasis and an application of CGREF1 in prognosis prediction of a colorectal cancer patient. It is found that inhibition of CGREF1 expression has no significant influence on proliferation of colorectal cancer cells, but migration and invasion of the colorectal cancer cells can be significantly inhibited. Besides, it is found for the first time that high expression of the CGREF1 is related to remarkable shortening of the survival time of the colorectal cancer patient, univariate analysis and multivariate Cox regression analysis both show that the expression of the CGREF1 is an independent prognosis factor for survival of the colorectal cancer patient, and the above discovery prompts that the CGREF1 is potentially applied to prognosis prediction of the colorectal cancer patient as a biomarker, and the application prospect is wide. Clinical doctors can be assisted in judging the prognosis of the patient, so that a personalized treatment scheme is formulated.

The invention provides a method of detecting or predicting a relapse of multiple sclerosis in an individual having a form of multiple sclerosis, comprising: (a) providing a blood sample of the individual; (b) testing the blood sample to determine a protein activity or protein level, wherein the protein is Factor VIII, von Willebrand Factor, or Protein C; and (c) detecting or predicting a relapse of multiple sclerosis in the individual if the protein activity or protein level is elevated compared to the protein activity or protein level in an individual not having the form of multiple sclerosis and the patient's own baseline value. The invention also provides a method of treating an individual having multiple sclerosis who is experiencing a relapse or is predicted to experience a relapse, comprising treating the individual by administering a dose of a steroid or an anticoagulant compound effective to reduce symptoms of multiple sclerosis.

The invention discloses application of ALYREF in treatment and prognosis prediction of multiple myeloma, and belongs to the field of biomedicine. According to the application disclosed by the invention, high expression of the ALYREF in myeloid tissue of a patient with multiple myeloma is found, and differential expression analysis and survival analysis of the ALYREF find that the ALYREF is an independent prognosis factor of the patient with multiple myeloma, and high expression of the ALYREF is related to poor prognosis of multiple myeloma. Then starting from a multiple myeloma cell strain, through targeted down-regulation of expression of ALYREF, it is found that down-regulation of the expression level of ALYREF can inhibit the multiplication capacity of multiple myeloma cells and promote death of tumor cells, and finally multiple myeloma is improved or treated. Therefore, the invention provides effective treatment and prognosis evaluation molecules for multiple myeloma.

The invention discloses a children pneumonia prognosis condition prediction system and method based on a BP neural network, and relates to the technical field of data processing, and the system comprises a multi-source data fusion module which is used for receiving electronic medical records, laboratory data, imaging features and environment features, and building a multi-source fusion data set; the self-adaptive feature selection module is used for extracting key prognosis factors based on hybrid feature screening; the construction optimization module is used for training a prognostic risk scoring model by using the key prognostic factors and optimizing the prognostic risk scoring model through a gradient direction correction strategy; and the prediction module is used for performing child risk scoring and prognosis management. The technical problems that the prior art depends on a simple model and single data, illness state changes cannot be dynamically tracked, and the accuracy and timeliness of prognosis evaluation are poor are solved, and the technical effects that personalized prognosis management is carried out through the BP neural network optimized through multi-source data fusion, and the accuracy and timeliness of prognosis risk evaluation are improved are achieved.

The application relates to the technical field of medical artificial intelligence and prognosis prediction, and discloses a construction method of a prostate cancer patient prognosis risk prediction model. The method forms a diagnosis and treatment state transition topology by creating a hierarchical knowledge network and mining diagnosis and treatment path time sequence dependence, and accordingly depicts a patient whole-course time sequence data segment. A simulated annealing optimization feature selection cycle is synchronously run, and a deep prediction architecture containing a multi-scale time sequence attention mechanism is dynamically interactively trained, so that online adaptive screening of a feature subset is realized; a feature influence propagation graph is constructed according to the feature selection process, key feature clusters are identified, and guided correction of attention weights of the model is carried out accordingly. The above components are integrated to form a prediction model, and an online adaptive fine-tuning loop is established. The method can effectively optimize feature combination, improve the focusing ability and prediction robustness of the model on key prognosis factors, and support incremental adjustment according to new data.