52 results about "Recurrence prediction" patented technology

The invention discloses an online lithium ion battery residual life predicting method based on relevance vector regression, belongs to the technical field of lithium ion battery life prediction, and solves the problem that the residual life of the existing lithium ion battery is predicted by an offline method with low precision. The method comprises the following steps: firstly selecting original samples, performing phase-space reconstruction to construct a training sample set; initializing the model parameters of RVM (relevance vector machine); performing RVM training to obtain a RVM prediction model; comparing the obtained prediction value with ynew, if yes, the constructed novel training set WS equal to WSUINS, retraining RVM, and updating the RVM prediction model; otherwise, keeping the RVM prediction model stable; performing recurrence prediction until the prediction value is smaller than the invalid threshold value U, and finishing the online prediction of the residual life of the predicted lithium ion battery. The method is suitable for prediction of the lithium ion battery residual life.

The invention provides a cerebral apoplexy recurrence prediction model establishing method and device. The method comprises the following steps of: obtaining a pathologic data set of each cerebral apoplexy patient in a plurality of cerebral apoplexy patients in a plurality of age groups; screening parameters remarkably associated with cerebral apoplexy recurrence from the pathologic data set of each cerebral apoplexy patient, and determining the parameters remarkably associated with the cerebral apoplexy reoccurrence and an attribute value corresponding to each parameter as pathologic data subsets of each cerebral apoplexy patient; and establishing a first cerebral apoplexy reoccurrence prediction model according to panel data corresponding to the pathologic data subsets. According to the method and device, the cerebral apoplexy reoccurrence prediction model can be established through the parameters of the cerebral apoplexy patients in a plurality of age groups, so that prediction can be carried out to judge whether cerebral apoplexy reoccurs to the patients or not, and then prevention and treatment can be carried out in advance.

The invention relates to the field of biomedicine, and discloses an early-stage non-small cell lung cancer recurrence model construction method based on DNA methylation. The invention aims to solve the problem of unreasonable non-small cell lung cancer recurrence prediction of a conventional non-small cell lung cancer recurrence model. According to the method, directed at methylation sites, the methylation sites with high correlation are searched and merged to form a corresponding methylation interval; then according to the types of methylation chips, methylation sites/intervals which can be detected by chip probes are selected as training data to establish a methylation risk score model containing one methylation interval and eight methylation sites, namely a non-small cell lung cancer recurrence model; and the methylation risk score model has a plurality of score thresholds that may match scores calculated by the methylation risk score model with one selected from a high score group,a medium score group and a low score group. The constructed model is suitable for predicting recurrence of non-small cell lung cancer.

The invention discloses a recurrence prediction model for coronary artery disease after interventional surgery and a modeling method and device thereof. The method includes the following steps: receiving a patient data set; processing the data of the patient data set, classifies and quantifies inspection diagnosis data according to the degree of severity, classifies and quantifies character type attribute data, and standardizes numerical examination data; judging whether there is difference in data attributes in the patient data set by means of statistical hypothesis test according to the processed data; and calculating the importance indexes of data attributes with difference, sorting the data attributes, and screening and adding the attributes with high importance to a recurrence prediction model; setting the network parameters of a neural network, taking the processed patient data set as a sample, using the neural network to train the sample, and building a recurrence prediction model.

The invention discloses a primary liver cancer recurrence prediction method based on the artificial intelligence technology. According to the invention, the method comprises the steps: through the powerful operational capability of a computer and an artificial intelligence algorithm, automatically capturing and learning fine difference characteristics of physiological indexes of different liver cancer patients from massive primary liver cancer patient data, and finding the potential risk factors for liver cancer recurrence; constructing a recurrence probability and recurrence period predictionmodel suitable for a primary liver cancer patient, and finally providing a client for a client to use in a software packaging mode or a webpage mode, and uploading a new case by a user through a computer or a smart phone to return a recurrence condition prediction result of the case after treatment.

The present invention discloses an approximation spectral clustering algorithm based method for predicting cancer metastasis and recurrence. The method is characterized by comprising: based on an approximation spectral clustering algorithm, constructing a cancer metastasis and recurrence prediction model by using cancer gene expression profile data as a training set sample; and using the prediction model for a test of a cancer metastasis and recurrence independent testing sample set, and classifying cancer patients into two types of patients: a metastasis and recurrence type and a non metastasis and recurrence type. According to the method provided by the present invention, it is predicted whether the cancer patients will be subjected to metastasis and recurrence, so that subsequent treatment of the cancer patients is more targeted.

The invention discloses a prognosis evaluation system for patients with early-stage LUAD and application thereof. According to the invention, disease-free survival data of 632 patients with early-stage LUAD in three independent queues are integrated, and an individual IBRS model for patients with early-stage LUAD is established and verified. The three independent queues include TCGA, GSE31210 and68 cases of frozen tissues. The IBRS model is composed of the following nine genes: DYNC1I2, THOC1, ADAM10, SERPINB6, CCL20, WNT2B, SLC11A1, MAPT and PSEN1. The establishment of the IBRS model for patients with early-stage LUAD is not only beneficial for understanding of the complex interaction mechanism between immune molecules, but also brings great help to the recurrence prediction of the patients with early-stage LUAD and the optimization of a treatment scheme.

The invention provides a local recurrence prediction device for head and neck cancer, and the device comprises a data collection module which is used for collecting data to form a training sample; Thegrouping module is used for grouping the training samples into a training set and a test set; The feature extraction module is used for performing feature extraction on the training set; The first training module is used for receiving the features extracted by the feature extraction module and carrying out random forest training to obtain a first random forest classifier; The first test module isused for inputting the test set into the first random forest classifier; The second training module is used for carrying out random forest training by taking the output of the first random forest classifier as an input to obtain a second random forest classifier; And the second test module is used for inputting the test set into the second random forest classifier.

The invention relates to the technical field of computer medicine, and discloses a method for predicting a biochemical recurrence risk after a radical prostatic cancer operation through an MRI image, and the method comprises the following steps: S1, collection and arrangement of prostatic cancer cases: firstly, carrying out the retrospective collection and arrangement of MRI data and clinical data of at least 300 patients subjected to the radical prostatic cancer operation according to a group entering standard, wherein 200 patients are used for constructing a radiomics model, and 100 patients are used for verifying and optimizing the radiomics model; according to the method, a retrospective and prospective combined mode is innovatively adopted, the optimized image group student recurrence prediction model is constructed and verified on the basis of a large number of prostate cancer cases which are collected in the past and are subjected to standardized scanning, and the accuracy of the model is tested by using prostate cancer radical cases collected prospectively, so that the reliability of the model is ensured. Meanwhile, retrospective and prospective data are creatively applied in the research, and the stability and repeatability of image features are evaluated by adopting multiple methods.

The invention discloses a method for establishing a cerebral apoplexy recurrence prediction model. The method comprises the steps of 1, establishing a comparison database; 2, establishing a cerebral apoplexy recurrence prediction system; and 3, integrating the comparison database established in the step 1 into an intelligent analysis module. The invention further discloses a cerebral apoplexy recurrence prediction device which comprises a computer, a heart rate tester, a blood pressure measuring instrument, an oximeter, a thermometer and a blood lipid instrument; the computer comprises a host,a display, a keyboard and a mouse; a cerebral apoplexy recurrence prediction model is installed in the host, and the display, the keyboard and the mouse are electrically connected with the host through data lines. The method and the device are proposed for elderly patients of 75 years old or above, are suitable for hospitals and families, can avoid troubles caused by the fact that the elderly patients need to frequently perform cerebral apoplexy recurrence prediction, solve life troubles, effectively guarantee the life rhythm of the elderly patients, and further improve the life quality of the elderly patients.

The invention provides a random survival forest-based liver cancer postoperative recurrence prediction method and a storage medium. The method comprises the following steps: acquiring clinical data and recurrence time of each case, the preset grouping dimension comprising basic factors of the patient, preoperative examination factors and postoperative pathological factors; obtaining a data set according to the clinical data, wherein the data set is composed of preset grouping dimensions corresponding to each case; and according to the data set and the recurrence time of each case, a random survival forest algorithm is adopted to construct a corresponding liver cancer postoperative early recurrence prediction model. According to the method, the postoperative recurrence probability of liver cancer of an individual patient can be accurately predicted, and the postoperative attention can be better determined; active prevention is facilitated; particularly, for medical institutions, medical staff can be helped to accurately screen out high-risk relapse patients after the liver cancer operation, intervention in the early relapse stage is facilitated, and postoperative follow-up visit and treatment are guided.

The invention discloses an automatic stroke detection method which comprises the following steps: acquiring a pathological data set of a stroke patient, the pathological data set comprising a plurality of pathological parameters associated with the patient; screening parameters significantly related to stroke recurrence from the pathological data set of each stroke patient, and determining the parameters as a pathological data subset; updating the pathological data subset of the stroke patient on the basis of hospitalization registration records, physical examination, outpatient reexaminationand the like of the stroke patient; and performing comparative analysis on the pathological data subset of each stroke patient and a recurrence prediction model in real time to obtain a correspondingdanger level, and informing the stroke patient for subsequent visit in time based on the danger level. The method has the advantages and effects that the risk coefficient of stroke of the patient canbe predicted, and the patient can timely go back for repeated diagnosis and treatment.

The invention relates to the field of biomedicine, discloses a lung cancer recurrence prediction method based on DNA methylation of a tissue-specific enhancement subregion, and is used for solving the problem that an existing non-small cell lung cancer recurrence model is unreasonable in non-small cell lung cancer recurrence prediction. The method comprises the following steps: firstly, extracting DNA of a lung cancer patient, and carrying out DNA methylation detection to obtain a beta value of a DNA methylation site of a tissue specific enhancer region; wherein the DNA (deoxyribonucleic acid) methylation sites comprise chr1: 170667082, chr12: 85280518, chr17: 76561412, chr11: 9759297, chr15: 91915828, chr16: 1079990, chr2: 226797988, and chr7: 150477419; and then substituting the beta value of the DNA methylation site into a pre-constructed lung cancer recurrence model, calculating a model score, and obtaining a prediction result according to the model score and a plurality of score thresholds. The method is suitable for predicting the recurrence of the early non-small cell lung cancer.

A loop control circuit and a loop control method that allow control on multiplexed loop operations to be executed with less overhead are provided. A loop control circuit comprises a means for address storage that stores in memory the address of a loop instruction at a second or subsequent stage in multiplexed loops or the address of the instruction immediately preceding the loop instruction when the loop instruction is executed for the first time, a means for loop instruction recurrence prediction that predicts a recurrence of the loop instruction at the second or subsequent stage by comparing the address of the loop instruction or the address of the instruction immediately preceding the loop instruction stored in memory with a value at a program counter and a means for loop instruction skipping that skips the loop instruction if it is predicted that the loop instruction is to occur next.

A tumor recurrence prediction device is provided, which includes a data extraction circuit, a memory, and a processor. The data extraction circuit extracts multiple patient clinical data and multiple slice image information; a memory stores multiple instructions; a processor is connected to the data extraction circuit and the memory, and is configured to load and execute the multiple instructions to: receive the multiple patient clinical data and the multiple slice image information; generate clinical feature information and tumor image feature information according to the multiple patient clinical data and the multiple slice image information; train a prediction model according to the clinical feature information and the tumor image feature information; and predict tumor recurrence for patient information of a patient using the prediction model. In addition, a tumor recurrence prediction method is also disclosed here.

The invention is suitable for the technical field of medical data processing, provides a data collecting and processing system for liver cancer recurrence prediction, is used for liver cancer recurrence data processing, and solves the problems that an existing recurrence prediction method mainly judges through experience of doctors, errors are large, and prediction results of different doctors are inconsistent. The system comprises: a parameter acquisition module used for acquiring pathological data of a liver cancer patient, integrating physical examination data of the patient, extracting the pathological data and the physical examination data of the liver cancer patient and preprocessing the data to obtain preprocessed parameters; a standard parameter presetting module; and a parameter analysis and comparison module. The system comprises the parameter acquisition module, the standard parameter presetting module and the parameter analysis and comparison module, the parameter acquisition module, the standard parameter presetting module and the parameter analysis and comparison module are executed to obtain a recurrence prediction model, a patient and a doctor are assisted in predicting the postoperative recurrence probability of the patient, and a periodic recurrence probability report is given.

The invention relates to establishment of an early gastric cancer recurrence prediction model, 25 potential genes related to early gastric cancer recurrence are screened out by using two batches of gene chip transcriptome data of GSE130823 and GSE55696, and the recurrence prediction model based on eight genes of AREG, LOC100507520, MMD, CH3L1, FOS, CCL20, CXCR2 and BATF3 is established. The model has excellent sensitivity, that is, all patients which are predicted to be not relapsed do not relapse, and the clinical prompting significance is that the reexamination follow-up diagnosis frequency of the patients can be adjusted according to the reexamination follow-up diagnosis frequency.

The invention provides a liver tumor early recurrence prediction method based on 3D CNN and LSTM. The method comprises the following steps: acquiring a CT image and clinical information of an HCC patient, and counting postoperative ER information of the HCC patient; carrying out image segmentation on the CT image, and then dividing obtained data samples into a training set and a test set; training by using the training set to obtain a 3D CNN model of a mapping relation between the CT image and the ER information; extracting iconography features of the data sample corresponding to the liver tumor area, performing dimension reduction on the extracted iconography features by using an LASSO logistic algorithm, and selecting out iconography features useful for ER prediction; carrying out statistical analysis on the clinical information, carrying out ER clinical factor univariate analysis by utilizing chi-square test, and selecting a clinical factor corresponding to a test level P less than 0.05; and training to obtain an optimal LSTM model by using features obtained by a 3D CNN model, imaging features useful for ER prediction and clinical factors corresponding to a test level P less than 0.05, and predicting the ER of an HCC patient by using the LSTM model.

The present invention provides diagnostic and disease progression or recurrence prediction methods based on osteopontin levels in a biological sample.

The invention relates to a LigtGBM model-based chronic obstructive pulmonary recurrence prediction method and device and a computer device. The method comprises the following steps of receiving the chronic obstructive pulmonary diagnosis data; extracting slow obstructive pulmonary diagnosis characteristics of the slow obstructive pulmonary diagnosis data; obtaining slow obstructive pulmonary sample characteristics matched with the slow obstructive pulmonary diagnosis characteristics in a slow obstructive pulmonary recurrence prediction model, wherein the chronic obstructive pulmonary recurrence prediction model is a model constructed based on LightGBM; extracting sample label contents of the slow obstructive pulmonary sample characteristics as slow obstructive pulmonary recurrence prediction results; and displaying the chronic obstructive pulmonary recurrence prediction result. By adopting the method, the accuracy of the chronic obstructive pulmonary recurrence prediction result can beimproved, and the accurate prediction of the chronic obstructive pulmonary recurrence is realized.

The invention relates to an application of a molecular marker LYPD1 gene in diagnosis of liver cancer, liver cancer differentiation and liver cancer prognosis, which comprises the following steps: selecting sequencing data and clinical information of a liver cancer patient from a TCGA database, selecting, classifying and analyzing the data to obtain a differential expression gene related to livercancer differentiation, and carrying out clinical experiment verification. Results show that the expression of the LYPD1 gene is highly related to liver cancer differentiation and liver cancer prognosis. The molecular marker closely related to liver cancer prognosis provided by the invention can be used for dynamically monitoring FOLFOX scheme treatment prognosis accepted by liver cancer patients,and has important clinical significance and application prospects.

The invention discloses an application of a CIT-H3 protein detection reagent in preparation of a liver cancer prognosis and/or recurrence prediction reagent, and provides an immunohistochemical detection kit for evaluating the prognosis and recurrence risk of a liver cancer patient. According to the principle of immunohistochemistry, the kit detects a marker CIT-H3 (citrullinated histone H3) of a neutrophile granulocyte extracellular trap net, has the characteristics of being objective, accurate, simple, convenient, intuitive, easy to operate and the like, and can be operated by common technicians in a hospital pathology room without the help of complex instruments; the prognosis and recurrence risk of the liver cancer patient can be effectively evaluated, so that a doctor is better helped to monitor the condition of the patient, proper treatment means are adjusted in time, the treatment effect is improved, and the survival time of the patient is prolonged.