96 results about "Survival analysis" patented technology

The present invention provides a method and system for valuing patent assets based on statistical survival analysis. An estimated value probability distribution curve is calculated for an identified group of patent assets using statistical analysis of PTO maintenance fee records. Expected valuations for individual patent assets are calculated based on a the value distribution curve and a comparative ranking or rating of individual patent assets relative to other patents in the group of identified patents. Patents having the highest percentile rankings would be correlated to the high end of the value distribution curve. Conversely, patents having the lowest percentile rankings would be correlated to the low end of the value distribution curve. Advantageously, such approach brings an added level of discipline to the overall valuation process in that the sum of individual patent valuations for a given patent population cannot exceed the total aggregate estimated value of all such patents. In this manner, fair and informative valuations can be provided based on the relative quality of the patent asset in question without need for comparative market data of other patents or patent portfolios, and without need for a demonstrated (or hypothetical) income streams for the patent in question. Estimated valuations are based simply on the allocation of a corresponding portion of the overall patent value “pie” as represented by each patents' relative ranking or position along a value distribution curve.

The present invention provides a fault prediction and condition-based repair method of an urban rail train bogie. An optimum service life distribution model of a framework, a spring device, a connecting device, a wheel set and axle box, a driving mechanism, and a basic brake device of a bogie is determined by adopting a method based on survival analysis; a reliability characteristic function of each subsystem is obtained; then, a failure rate of each subsystem of the bogie is calculated by adopting a neural network model optimized by an evolutionary algorithm; and finally, proportional risk modelling is conducted by taking the failure rate and safe operation days of each subsystem of the bogie as concomitant variables; and on the basis of cost optimization, thresholds and control limits for condition-based repair of a bogie system are obtained.

The present invention provides a method and system for valuing patent assets based on statistical survival analysis. An estimated value probability distribution curve is calculated for an identified group of patent assets using statistical analysis of PTO maintenance fee records. Expected valuations for individual patent assets are calculated based on a the value distribution curve and a comparative ranking or rating of individual patent assets relative to other patents in the group of identified patents. Patents having the highest percentile rankings would be correlated to the high end of the value distribution curve. Conversely, patents having the lowest percentile rankings would be correlated to the low end of the value distribution curve. Advantageously, such approach brings an added level of discipline to the overall valuation process in that the sum of individual patent valuations for a given patent population cannot exceed the total aggregate estimated value of all such patents. In this manner, fair and informative valuations can be provided based on the relative quality of the patent asset in question without need for comparative market data of other patents or patent portfolios, and without need for a demonstrated (or hypothetical) income streams for the patent in question. Estimated valuations are based simply on the allocation of a corresponding portion of the overall patent value “pie” as represented by each patents' relative ranking or position along a value distribution curve

The present invention applies classical survival analysis to genome-wide gene expression profiles of prostate cancers and preoperative prostate-specific antigen levels from prostate cancer patient, to identify prognostic markers of disease relapse that provide additional predictive value relative to prostate-specific antigen concentration. The present invention provides a method of determining prognosis of prostate cancer and predicting prostate cancer outcome of a patient. The method comprises the steps of first establishing the threshold value of at least one prognostic gene of prostate cancer. Then, the amount of the prognostic gene from a prostate tissue of a prostate cancer patient is determined. The amount of the prognostic gene present in that patient is compared with the established threshold value of the prognostic gene, whereby the prognostic outcome of the patient is determined.

The invention belongs to the technical field of lung adenocarcinoma prediction, and specifically relates to an identification of early diagnosis markers of lung adenocarcinoma based on co-expression similarity, and a constructing method of a risk prediction model. The constructing method includes the steps of: data remodeling and grouping, data standardization, phase specific gene extraction, geneco-expression correlation analysis, unsupervised cluster analysis, specific and non-specific co-expression network analysis, functional pathway gathering, significant variation pathway identification, screening of early screening marker genes by using an REE algorithm, establishment of a classification model based on early screening risk genes, survival analysis verification, and the like. The identification of early diagnosis markers of lung adenocarcinoma based on co-expression similarity, and the constructing method of a risk prediction model can realize the early diagnosis of lung cancer,and can identify gene markers which change significantly with the progress of lung cancer at the same time.

The invention discloses a breast cancer prognosis survival rate prediction method based on a dynamic Cox model, and belongs to the technical field of a tumor mortality risk regression model algorithm.The method includes: using a log probability regression model to estimate the patient's positive lymph node ratio LNR level; combining the ratio with other features to fit a Cox regression model of Bayesian method based dynamical estimation model parameters; and predicting a survival rate-time characteristic curve of the patient. The simulation results show that the Cox regression model of the Bayesian method based dynamical estimation model parameters of two logarithmic pseudo-marginal LPML indexes of the combined model is superior to the conventional Cox proportional risk model using LNR index features; and the Cox regression model of the dynamical estimation parameters can further improve the prediction precision of a survival analysis model, the computational complexity is within an acceptable range, and the prediction effect is relatively accurate.

An embodiment in accordance with the present invention provides a method of forecasting a demand for a particular hospital unit. The method can be executed by programming the steps into a computer readable medium. One step includes logging a total number of beds in the particular hospital unit and available nursing slots to determine a capacity for the particular hospital unit. The method also includes analyzing data for patients scheduled to stay in the particular hospital unit data to predict stochastic arrivals in order to estimate a total inflow. A length of stay of a patient in the particular hospital unit is predicted using a survival analysis based on physician orders to estimate a total outflow. Additionally, the method includes executing an algorithm designed to use the capacity, total inflow, and total outflow to determine the demand for the particular hospital unit.

The present invention discloses a bus travel time model construction method based on survival analysis parameter distribution. The method comprises: acquiring travel time of each bus in three sections: upstream, a bus stop and downstream of an area adjacent to the bus stop and corresponding influence variable data; comparing the travel time to a duration in survival analysis; supposing that the duration approximately obeys parameter distribution, taking each independent variable into a model for solution; and selecting a probability density function of an optimal model to perform integration to obtain an expected function as a bus travel time evaluation model and verifying accuracy of the model. The method provided by the present invention is easy and feasible, and is capable of calculating travel time of a bus and comparing and evaluating actual bus travel time, so as to provide theoretical basis for operation managers to implement control measures for influence variables to offer bus competitiveness; and the method has actual project application value for evaluating travel time of the bus in the adjacent area of the bus stop.

Methods, systems, and non-transitory computer readable storage media are disclosed for determining and applying digital content transmission times using machine-learning. For example, in one or more embodiments, the disclosed system trains a recurrent neural network based on past electronic messages for a user that have been partitioned into a plurality of time bins. Additionally, in one or more embodiments, the system utilizes the trained recurrent neural network to generate predictions of engagement metrics (e.g., a hazard metric based on survival analysis or interaction probability metric) for sending a new electronic message within the plurality of time bins. The system then executes the digital content campaign by selecting a time bin based on the predicted engagement metrics and then sending the new electronic message at a send time corresponding to the selected time bin.

A statistical methodology is disclosed to provide time-to-event estimates for oilfield equipment performance data and considers parameters interactions without recourse to data thinning. The analysis explicitly accounts for items of equipment that are still operational at the time of analysis. A method according to the present invention may also be utilized to apply survival analysis to any oilfield equipment components where time-to-event information has been recorded. The method of the present invention allows comparative reckoning between different components present in the system comprising several or many individual components and allows analysis of these components either individually or simultaneously, i.e., in the presence of other components.

The vulnerability of network devices may be predicted by performing a survival analysis on big data. A prediction algorithm may be built by considering historical data from heterogeneous data sources. The operating state of the network devices on a network may be predicted. The services potentially affected by a predicted outage may be determined and displayed. Alternatively or in addition, the number of clients potentially affected by a predicted outage may be determined and displayed.

A computer-implemented method for privacy-preserving data mining to determine cancer survival rates includes providing a random matrix B agreed to by a plurality of entities, wherein each entity i possesses a data matrix Ai of cancer survival data that is not publicly available, providing a class matrix Di for each of the data matrices Ai, providing a kernel K(Ai, B) by each of said plurality of entities to allow public computation of a full kernel, and computing a binary classifier that incorporates said public full kernel, wherein said classifier is adapted to classify a new data vector according to a sign of said classifier.

The invention relates to a diagnostic marker for malignant glioma and belongs to the technical field of molecular biology. Particularly, the marker is an NES gene and an expression product thereof. The diagnostic marker has the advantages that comprehensive genomics and proteomics analysis is carried out on a GBM, and through gene expression analysis based on a gene chip and RNA sequencing and proteome analysis of LC / MS / MS, the mRNA level and protein level of the NES gene are regulated up. Through survival analysis on the NES, over-expression of the NES is related to poor prognosis of a GBM patient, so that the NES can be used as a GBM biomarker and a potential therapeutic target. The NES gene is used for encoding nestin protein, is mainly applied to nerve cell expression, and can be used as the GBM biomarker and the potential therapeutic target.

The invention provides an analytical method for prognosis survival case of non-small cell lung cancer. The analytical method for prognosis survival case of non-small cell lung cancer designs an experiment to perform prognosis survival analysis and research on a non-small cell lung cancer patient, constructs a prognostic analysis model for the non-small cell lung cancer based on CT image omics characteristics, according to a traditional imaging omics research framework, performing tumor segmentation, characteristic extraction, characteristic screening, and modeling of a correlation analysis andprognosis survival analysis model for image omics characteristics and the prognosis survival case on the data of the non-small cell lung cancer patient to obtain an image omics prognostic factor andprognosis survival analysis model correlated with prognosis survival significance of the patient with the non-small cell lung cancer, so as to provide the doctor with data information including the survival time of the patient and a series of late lesion development situations, and at the same time, to evaluate the performance of the prognosis survival model to ensure the accuracy of the prognosissurvival model.

The invention discloses a disease prognosis prediction system based on deep semi-supervised multi-task learning survival analysis. The disease prognosis prediction system comprises a data acquisitionmodule, a data preprocessing module, a prediction model construction module and the like. On the basis of a deep neural network model, a survival analysis problem is converted into a multi-task learning model composed of a semi-supervised learning problem of multi-time-sequence-point survival probability prediction; the model directly models the survival probability, does not depend on proportional risk hypothesis, can fit a time-dependent effect, and has better interpretability; a semi-supervised loss function and a sorting loss function are utilized to fit the data, complete data and deleteddata are fully utilized, and a traditional survival analysis problem and a survival analysis problem considering competition risks can be solved; according to the model, through multi-task learning of multiple time sequence points, data sharing among multiple prediction tasks is achieved, mutual constraint among the multiple prediction tasks is achieved, and the generalization ability of the model is improved.

The invention discloses a time sequence deep survival analysis system with active learning. The system comprises a data acquisition module, an active learning module and a time sequence deep survivalanalysis module. The data acquisition module is used for acquiring survival data of a to-be-analyzed object; the active learning module selects part of right deletion data to mark survival time in combination with an active learning method; and the time sequence deep survival analysis module constructs a time sequence deep survival analysis neural network model, and takes the undeleted data and the right deleted data as model inputs to obtain a survival time prediction result of the to-be-analyzed object. According to the method, the right deletion data and the time sequence characteristics inthe survival data can be fully utilized. Compared with a traditional survival analysis model, the system has the advantages that the problem that high-dimensional data is difficult to process is solved, and the problem that the model is poor in performance under the condition that only a small amount of data is not deleted in survival analysis is solved; meanwhile, extraction and utilization of data time dimension features are increased, the application range of the model is expanded, and the expression effect of the model is improved.

The invention discloses a method for survival time analysis fusing DNA methylation characteristics. Three kinds of characteristic data are obtained from a TCGA database, some characteristics which are of great importance to cancers are obtained by performing characteristic selection on the three kinds of characteristic data through a K-split Lasso-based characteristic selection algorithm, and then COX regression is performed on these characteristics to obtain a regression model. When new characteristic data is available, the survival time probability of a cancer patient can be obtained only by inputting these characteristic data into the regression model, and thus the method is of great significance for cancer prognosis.

The invention discloses a consumption staging default probability model based on survival analysis. The model is characterized in that the number of consumption staging repayment periods is regarded as discrete survival time, the discrete survival time is added into the user attribute characteristics and then the discrete survival time is fused into a default model, the relationship between a sample survival result and the survival time and the user attribute characteristics is researched, and a model capable of predicting the default probability of the consumption staging loan user in any future period is established by using an xgboost algorithm; a danger function of survival analysis is obtained through the default probability model, the default probability of any loan user in any period is predicted based on the danger function, and the future default risk of the loaned user is evaluated at the same time. According to the invention, the possibility that the user is overdue betweenthe end of the observation period and the full period neglected by the traditional model is covered, so that the future risk is estimated more accurately, and the financial institution can develop theconsumption staging business more healthily and continuously.

The invention provides a comprehensive risk scoring method for multiple myeloma, comprising the following steps: S1, obtaining a gene expression profile GSE24080 of an MM patient from a GEO database,and pre-treating genes in the gene expression profile GSE24080 to obtain the first 25% of the 5413 genes with the largest variance of expression value; S2, subjecting the 5413 genes to WGCNA gene co-expression network analysis to identify co-expressed functional modules; S3, evaluating the correlation between the functional modules and clinical information through Pearson correlation test to determine the most significant modules; S4, performing univariate survival analysis on the genes in the most significant modules by using a Cox proportional hazard model, and screening out a ten-gene scoring model composed of the 10 best genes through LASSO regression; and S5, setting the rule that each factor scores 1 point when the ten-gene scoring model or serum [beta]2M or LDH is higher than a cut-off value and otherwise 0, and establishing a comprehensive risk scoring system.

The invention relates to a method for predicting the pipe explosion risk of a water supply pipe network based on Bayesian survival analysis, and the method comprises the following steps: (1), buildinga pipe explosion database through the collected pipe explosion historical data, and extracting key information as a concomitant variable; (2), carrying out the spatial clustering analysis of a pipe explosion point, quantifying the spatial distribution information of the pipe explosion point as a new concomitant variable, and adding the new concomitant variable to the pipe explosion database; (3),constructing a pipe explosion risk prediction model based on the pipe explosion database through employing the Bayesian survival analysis method; (4), predicting the pipe explosion risk of a pipe through the pipe explosion risk prediction model. Compared with the prior art, the method is more accurate and reasonable in prediction result.

The invention discloses a method for pushing information based on scenes. The method for pushing information comprises the following steps: firstly extracting scene characteristics of user sessions, then predicting survival time via a survival analysis model based on the extracted scene characteristics, and finally determining predicted information pushing time according to the predicted survival time and the scene ending time of the user sessions. The method for pushing information further comprises the following steps: determining actual information pushing time according to the predicted information pushing time and access time sets corresponding to users; and updating the survival analysis model according to feedback data of the users. The method takes the user scenes as learning targets, pushes the information based on the scenes, and can predict more accurate information pushing time; the user experience is improved; the more efficient information pushing service is supplied to the users.

The invention discloses an integrated avionics equipment fault intelligent diagnosis system, and aims to provide a diagnosis system which is accurate in fault positioning, high in fault identificationcapability and strong in robustness. The system is realized through the following technical scheme: a data preprocessing module converts acquired equipment data into a difference value of equipment fault timestamps, and the two columns of data are stored into a first database as a fault event sequence; a Hawkes process module periodically sends a detection signal, judges whether the system has afault and the type of the system fault, diagnoses the fault type, the fault part and the reason, and sends the detected fault signal to a survival analysis and prediction module to identify the faultsize and the time-varying characteristic, a time dependent variable is introduced, a proportional risk regression model COX regression model is constructed by taking survival outcome and survival timeas dependent variables, a survival function is obtained from the Hawkes process module, and fault analysis is performed according to units of different fault timestamps to complete a fault diagnosistask.

The invention discloses an employee demission behavior prediction method based on survival analysis. The method comprises the following steps: step 1, performing demission behavior feature extractionon an employee to be predicted; step 2, performing prediction through a prediction algorithm to obtain important features; and step 3, analyzing the important features to obtain a conclusion. According to the life analysis-based demission prediction method, the probability statistics technology of survival analysis and the integrated learning of the random forest are fused; the survival rate obtained by statistics of events and time is utilized, and the problems are classified into the traditional supervised binary classification problems, so that the problems can be compared with a large number of mature machine learning algorithms, and the final classification effect is better than that of the existing demission prediction algorithm.

The invention relates to a survival analysis risk function prediction method based on a gradient survival promotion tree. The method comprises the following steps: S1, obtaining survival analysis sample data, and carrying out the preprocessing; s2, constructing a gradient boosting tree prediction model based on a greedy segmentation algorithm; s3, training the gradient boosting tree prediction model by using the training data; and S4, inputting the preprocessed survival analysis sample data into a gradient boosting tree prediction model, and outputting a risk function obtained by prediction. Compared with the prior art, the method has the advantages of accuracy, generalization performance, interpretability and the like.

The invention discloses a night stay parking demand predicting method based on survival analysis. The night stay parking demand predicting method includes the steps that parking lot continuous parkingdata and some external factor data are obtained; the day time period for parking and the night time period for parking are divided according to parking feature analysis, and night parking demands areconverted into a stay part for day vehicle parking; a parking event is expressed with a survival event, corresponding data processing is conducted, and thus the form of the parking event is applied to a survival analysis method; a semi-parametric model method is adopted to establish a Cox proportional risk model with multiple factors affecting the parking time; and according to a model result, the probability of different parking time of the day driven-in vehicles under different conditions is predicted, and predicted night parking demands are further obtained. According to the new night parking demand predicting microcosmic method, good prediction precise is achieved. According to the night stay parking demand predicting method, the basis can be provided for night demand management of aparking lot, and the night stay parking demand predicting method can be used for the aspects such as pricing, shared parking space opening, and parking partition in fine management.

The invention relates to a marker associated with the diagnosis of malignant glioma, and belonges to the technical field of molecular biology, specifically, the marker is a TNC gene and the expression product of the TNC gene. The invention also provides application of the marker. The marker has the advantages of carrying out a comprehensive genomics and proteomics analysis of GBM, and by gene expression analysis and LC-MS / MS protein mass spectrometry analysis based on gene chips and RNA sequencing, finding that the TNC gene is up-regulated at the mRNA level and protein level. Survival analysis of TNC shows that the overexpression of TNC is related to the poor prognosis of GBM patients, indicating that TNC can be used as a GBM biomarker and a potential therapeutic target.

The invention discloses a kit for prognosis and postoperative treatment response prediction of breast cancer. Five miRNAs (miR-205, miR-320a, miR-665, miR-188-5p and miR-198), which are obviously related to the survival prognosis of patients, are discovered by the inventor, wherein two of the miRNAs are protective and the other three miRNAs are dangerous. By virtue of the five miRNAs molecular tags, the patients are classified into patients of high risk and patients of low risk; and overall survivals of the two groups are compared based on survival analysis, discovering that a significant difference exists between the overall survivals of the high-risk group and the low-risk group (p=0.001). The reagent is effective for guiding the clinical treatment of the breast cancer and is capable of conducting appropriate adjuvant therapy on the patients of high risk in prognosis, so that the survival quality of the patients is improved; and meanwhile, unnecessary treatment on the patients of low risk can be avoided.