In the analysis of censored survival data,it is crucial to consider the heterogeneity of treatment effects in order to avoid biased inferences.The deep neural network-based heterogeneous partially linear Cox model off...In the analysis of censored survival data,it is crucial to consider the heterogeneity of treatment effects in order to avoid biased inferences.The deep neural network-based heterogeneous partially linear Cox model offers a flexible and robust solution by incorporating both heterogeneous linear and homogeneous nonlinear components.The authors propose a novel approach to subgroup detection for this model under right-censoring,using deep neural networks to approximate nonlinear effects.To simultaneously estimate parameters and identify subgroups,the authors employ a concave pairwise penalty and the alternating direction method of multipliers(ADMM)algorithm.Furthermore,the authors demonstrate that the proposed estimator possesses oracle properties and achieves model selection consistency.Through simulation studies and empirical data analysis on breast cancer,the authors illustrate the effectiveness of the proposed method.展开更多
This study has provided a starting point for defining and working with Cox models in respect of multivariate modeling. In medical researches, there may be situations, where several risk factors potentially affect pati...This study has provided a starting point for defining and working with Cox models in respect of multivariate modeling. In medical researches, there may be situations, where several risk factors potentially affect patient prognosis, howbeit, only one or two might predict patient’s predicament. In seeking to find out which of the risk factors contribute the most to the survival times of patients, there was the need for researchers to adjust the covariates to realize their impact on survival times of patients. Aside the multivariate nature of the covariates, some covariates might be categorical while others might be quantitative. Again, there might be cases where researchers need a model that has <span style="font-family:Verdana;">the capability of extending survival analysis methods to assessing simulta</span><span style="font-family:Verdana;">neously the effect of several risk factors on survival times. This study unveiled the Cox model as a robust technique which could accomplish the aforementioned cases.</span><span style="font-family:;" "=""> </span><span style="font-family:;" "=""><span style="font-family:Verdana;">An investigation meant to evaluate the ITN-factor vis-à-vis its </span><span style="font-family:Verdana;">contribution towards death due to Malaria was exemplified with the Cox model. Data were taken from hospitals in Ghana. In doing so, we assessed hospital in-patients who reported cases of malaria (origin state) to time until death or censoring (destination stage) as a result of predictive factors (exposure to the malaria parasites) and some socioeconomic variables. We purposefully used Cox models to quantify the effect of the ITN-factor in the presence of other risk factors to obtain some measures of effect that could describe the rela</span><span style="font-family:Verdana;">tionship between the exposure variable and time until death adjusting for</span><span style="font-family:Verdana;"> other variables. PH assumption holds for all three covariates. Sex of patient was insignificant to deaths due to malaria. Age of patient and user status </span></span><span style="font-family:Verdana;">were</span><span style="font-family:Verdana;"> both significant. The magnitude of the coefficient (0.384) of ITN user status depicts its high contribution to the variation in the dependent variable.</span>展开更多
Starting with the Aalen （1989） version of Cox （1972） ＇regression model＇ we show the method for construction of ＂any＂ joint survival function given marginal survival functions. Basically, however, we restrict o...Starting with the Aalen （1989） version of Cox （1972） ＇regression model＇ we show the method for construction of ＂any＂ joint survival function given marginal survival functions. Basically, however, we restrict ourselves to model positive stochastic dependences only with the general assumption that the underlying two marginal random variables are centered on the set of nonnegative real values. With only these assumptions we obtain nice general characterization of bivariate probability distributions that may play similar role as the copula methodology. Examples of reliability and biomedical applications are given.展开更多
OBJECTIVE To retrospectively analyze clinical data of patientsfrom our hospital who underwent radical surgery for esophagealcarcinoma and for adenocarcinoma of the gastric cardia,as well asto investigate prognostic fa...OBJECTIVE To retrospectively analyze clinical data of patientsfrom our hospital who underwent radical surgery for esophagealcarcinoma and for adenocarcinoma of the gastric cardia,as well asto investigate prognostic factors affecting the long-term survival ofthe patients.METHODS Data from the patients eligible for our study,admitted to the 4th Hospital of Hebei Medical University fromJanuary 1996 to December 2004,were randomized,and 12distinctive clinicopathologic factors influencing the survival rateof those who underwent radical surgery for esophageal carcinomaor carcinoma of the gastric cardia were collected.Univariate andmultivariate analysis of these individual variables were performedusing the Cox proportional hazard model.RESULTS It was shown by univariate analysis that age,tumorsize,pathologic type,lymph node status,TNM staging,depthof infiltration and encroachment into local organs,etc.,were thefactors that markedly influenced the prognosis of patients(P<0.01).Multivariate analysis showed that pathologic type,numberof the lymph node metastases,involvement of local organs,andTNM staging were independent prognostic factors(P<0.05).CONCLUSION The independent factors influencing theprognosis of patients with esophageal cancer and carcinoma ofthe gastric cardia include pathologic type,number of lymph nodemetastases,involvement of local organs and TNM staging.Themain prognostic factors affecting the patient's survival are patientage,tumor size and depth of infiltration.In addition,patients withinvolvement of the local organs have a worse prognosis,and theyshould be closely followed up.展开更多
基金partially supported by the National Nature Science Foundation of China under Grant Nos.12171328,12326613,and 12031016Beijing Natural Science Foundation under Grant No.Z210003Beijing Outstanding Young Scientist Program under Grant No.JWZQ20240101027。
文摘In the analysis of censored survival data,it is crucial to consider the heterogeneity of treatment effects in order to avoid biased inferences.The deep neural network-based heterogeneous partially linear Cox model offers a flexible and robust solution by incorporating both heterogeneous linear and homogeneous nonlinear components.The authors propose a novel approach to subgroup detection for this model under right-censoring,using deep neural networks to approximate nonlinear effects.To simultaneously estimate parameters and identify subgroups,the authors employ a concave pairwise penalty and the alternating direction method of multipliers(ADMM)algorithm.Furthermore,the authors demonstrate that the proposed estimator possesses oracle properties and achieves model selection consistency.Through simulation studies and empirical data analysis on breast cancer,the authors illustrate the effectiveness of the proposed method.
文摘This study has provided a starting point for defining and working with Cox models in respect of multivariate modeling. In medical researches, there may be situations, where several risk factors potentially affect patient prognosis, howbeit, only one or two might predict patient’s predicament. In seeking to find out which of the risk factors contribute the most to the survival times of patients, there was the need for researchers to adjust the covariates to realize their impact on survival times of patients. Aside the multivariate nature of the covariates, some covariates might be categorical while others might be quantitative. Again, there might be cases where researchers need a model that has <span style="font-family:Verdana;">the capability of extending survival analysis methods to assessing simulta</span><span style="font-family:Verdana;">neously the effect of several risk factors on survival times. This study unveiled the Cox model as a robust technique which could accomplish the aforementioned cases.</span><span style="font-family:;" "=""> </span><span style="font-family:;" "=""><span style="font-family:Verdana;">An investigation meant to evaluate the ITN-factor vis-à-vis its </span><span style="font-family:Verdana;">contribution towards death due to Malaria was exemplified with the Cox model. Data were taken from hospitals in Ghana. In doing so, we assessed hospital in-patients who reported cases of malaria (origin state) to time until death or censoring (destination stage) as a result of predictive factors (exposure to the malaria parasites) and some socioeconomic variables. We purposefully used Cox models to quantify the effect of the ITN-factor in the presence of other risk factors to obtain some measures of effect that could describe the rela</span><span style="font-family:Verdana;">tionship between the exposure variable and time until death adjusting for</span><span style="font-family:Verdana;"> other variables. PH assumption holds for all three covariates. Sex of patient was insignificant to deaths due to malaria. Age of patient and user status </span></span><span style="font-family:Verdana;">were</span><span style="font-family:Verdana;"> both significant. The magnitude of the coefficient (0.384) of ITN user status depicts its high contribution to the variation in the dependent variable.</span>
文摘Starting with the Aalen （1989） version of Cox （1972） ＇regression model＇ we show the method for construction of ＂any＂ joint survival function given marginal survival functions. Basically, however, we restrict ourselves to model positive stochastic dependences only with the general assumption that the underlying two marginal random variables are centered on the set of nonnegative real values. With only these assumptions we obtain nice general characterization of bivariate probability distributions that may play similar role as the copula methodology. Examples of reliability and biomedical applications are given.
基金supported by the Hebei Provincial Program for the Subjects with High Scholarship and Creative Research Potential,China.
文摘OBJECTIVE To retrospectively analyze clinical data of patientsfrom our hospital who underwent radical surgery for esophagealcarcinoma and for adenocarcinoma of the gastric cardia,as well asto investigate prognostic factors affecting the long-term survival ofthe patients.METHODS Data from the patients eligible for our study,admitted to the 4th Hospital of Hebei Medical University fromJanuary 1996 to December 2004,were randomized,and 12distinctive clinicopathologic factors influencing the survival rateof those who underwent radical surgery for esophageal carcinomaor carcinoma of the gastric cardia were collected.Univariate andmultivariate analysis of these individual variables were performedusing the Cox proportional hazard model.RESULTS It was shown by univariate analysis that age,tumorsize,pathologic type,lymph node status,TNM staging,depthof infiltration and encroachment into local organs,etc.,were thefactors that markedly influenced the prognosis of patients(P<0.01).Multivariate analysis showed that pathologic type,numberof the lymph node metastases,involvement of local organs,andTNM staging were independent prognostic factors(P<0.05).CONCLUSION The independent factors influencing theprognosis of patients with esophageal cancer and carcinoma ofthe gastric cardia include pathologic type,number of lymph nodemetastases,involvement of local organs and TNM staging.Themain prognostic factors affecting the patient's survival are patientage,tumor size and depth of infiltration.In addition,patients withinvolvement of the local organs have a worse prognosis,and theyshould be closely followed up.
