scholarly journals Comparison of the marginal hazard model and the sub-distribution hazard model for competing risks under an assumed copula

2019 ◽  
Vol 29 (8) ◽  
pp. 2307-2327 ◽  
Author(s):  
Takeshi Emura ◽  
Jia-Han Shih ◽  
Il Do Ha ◽  
Ralf A Wilke
Keyword(s):  
Competing Risks ◽  
Hazard Function ◽  
Cox Regression ◽  
Cox Model ◽  
Hazard Model ◽  
Numerical Comparison ◽  
Hazard Functions ◽  
Different Types ◽  
Competing Risks Data ◽  
The Relationship

For the analysis of competing risks data, three different types of hazard functions have been considered in the literature, namely the cause-specific hazard, the sub-distribution hazard, and the marginal hazard function. Accordingly, medical researchers can fit three different types of the Cox model to estimate the effect of covariates on each of the hazard function. While the relationship between the cause-specific hazard and the sub-distribution hazard has been extensively studied, the relationship to the marginal hazard function has not yet been analyzed due to the difficulties related to non-identifiability. In this paper, we adopt an assumed copula model to deal with the model identifiability issue, making it possible to establish a relationship between the sub-distribution hazard and the marginal hazard function. We then compare the two methods of fitting the Cox model to competing risks data. We also extend our comparative analysis to clustered competing risks data that are frequently used in medical studies. To facilitate the numerical comparison, we implement the computing algorithm for marginal Cox regression with clustered competing risks data in the R joint.Cox package and check its performance via simulations. For illustration, we analyze two survival datasets from lung cancer and bladder cancer patients.

An issue of identifying longitudinal biomarkers for competing risks data with masked causes of failure considering frailties model

2019 ◽  
Vol 29 (2) ◽  
pp. 603-616
Author(s):  
Feng-shou Ko
Keyword(s):  
Competing Risks ◽  
Failure Time ◽  
Score Test ◽  
Joint Modeling ◽  
Repeated Measurements ◽  
Failure Time Data ◽  
Time Data ◽  
Hazard Functions ◽  
Competing Risks Data ◽  
Causes Of Failure

In this paper, we consider joint modeling of repeated measurements and competing risks failure time data to allow for more than one distinct failure type in the survival endpoint. Hence, we can fit a cause-specific hazards submodel to allow for competing risks, with a separate latent association between longitudinal measurements and each cause of failure. We also consider the possible masked causes of failure in joint modeling of repeated measurements and competing risks failure time data. We also derive a score test to identify longitudinal biomarkers or surrogates for a time-to-event outcome in competing risks data which contain masked causes of failure. With a carefully chosen definition of complete data, the maximum likelihood estimation of the cause-specific hazard functions and of the masking probabilities is performed via an expectation maximization algorithm. The simulations are used to explore how the number of individuals, the number of time points per individual, and the functional form of the random effects from the longitudinal biomarkers considering heterogeneous baseline hazards in individuals influence the power to detect the association of a longitudinal biomarker and the survival time.

scholarly journals Prognostic factors in patients with thyroid carcinoma: a competing-risks analysis

2020 ◽  
Author(s):  
Junhu Wang ◽  
Lisong Heng ◽  
Jie Yang ◽  
Feng Tian ◽  
Xiaojun Liang ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Prognostic Factors ◽  
Thyroid Carcinoma ◽  
Competing Risks ◽  
Hazard Function ◽  
Cox Regression ◽  
Multivariate Analyses ◽  
Regional Lymph Nodes ◽  
Cox Regression Analysis ◽  
Competing Risks Analysis

Abstract Background Cox proportional-hazards models are widely used to describe survival trends and identify prognostic factors for thyroid carcinoma, but they have significant limitations and deficiencies. This study therefore used a competing-risks model to identify the significant prognostic factors for thyroid carcinoma. Methods We identified 38,444 eligible patients in the SEER (Surveillance, Epidemiology, and End Result) database. The potential prognostic factors for thyroid carcinoma were analyzed by competing-risks analysis using both univariate and multivariate analyses. Results The univariate analysis showed that age, sex, race, marital state, insurance status, tumor size, whether regional lymph nodes were examined, AJCC stage, histology, surgery status, radiation status, chemotherapy status, bone metastasis, brain metastasis, liver metastasis, and lung metastasis were prognostic factors for death caused by thyroid carcinoma. The multivariate analyses that comprised Cox regression analysis, the cause-specific hazard function analysis, and subdistribution hazard function (SD) analysis produced different results, identifying age, being unmarried, no regional lymph nodes examined, AJCC stages II, III, and IV, having follicular, medullary, and anaplastic carcinomas, no surgery, no radiation, liver metastasis, and lung metastasis as the significant risk factors for thyroid carcinoma, while being female and not receiving chemotherapy were protective factors. The results from the three multivariate models for being black, tumor size >1 cm, and brain metastasis were inconsistent. Conclusion This study had produced information about the significant prognostic factors for thyroid carcinoma using a competing-risks model that is more accurate than that obtained using Cox regression analysis. The SD model seems to be preferable for establishing a more accurate prognostic model of this disease aimed at guiding clinical treatments and improving prognoses.

scholarly journals Prognostic factors in patients with thyroid carcinoma: a competing-risks analysis

2020 ◽  
Author(s):  
Junhu Wang ◽  
Lisong Heng ◽  
Jie Yang ◽  
Feng Tian ◽  
Xiaojun Liang ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Thyroid Cancer ◽  
Prognostic Factors ◽  
Thyroid Carcinoma ◽  
Competing Risks ◽  
Tumor Size ◽  
Hazard Function ◽  
Cox Regression ◽  
Regional Lymph Nodes ◽  
Cox Regression Analysis

Abstract Background: Cox proportional-hazards models are widely used to describe survival trends and identify prognostic factors for thyroid carcinoma, but the prognostic model is not accurate enough. This study therefore used a competing-risks model to identify the significant prognostic factors for different types of thyroid carcinoma.Methods: We identified 38,444 eligible patients in the SEER (Surveillance, Epidemiology, and End Result) database. The potential prognostic factors for thyroid carcinoma were analyzed by Cox regression analysis, cause-specific hazard function (CS) analysis, and subdistribution hazard function (SD).Results: Cox regression analysis, CS analysis and SD analysis found identifying age, being unmarried, no regional lymph nodes examined, AJCC-6 II, III, IV vs I , having follicular, medullary, anaplastic vs Papillary carcinomas, no surgery, no radioiodine, liver metastasis, and lung metastasis as the significant risk factors for thyroid carcinoma, while being female was protective factor. However, the results from the three multivariate models for being black, tumor size >1 cm, and brain metastasis were inconsistent.Conclusion: In addition to finding that age, pathological type, tumor size, AJCC-6 stage, surgery status, radioiodine status, metastasis as common factors affected the prognosis, we also found that women, being unmarried and had their regional lymph nodes examined can improve the prognosis of thyroid cancer. The discovery of these factors will provide evidences for the prevention and treatment of thyroid cancer.

scholarly journals High Mean Platelet Volume Associates with In-Hospital Mortality in Severe Pneumonia Patients

2020 ◽  
Vol 2020 ◽  
pp. 1-9 ◽  
Author(s):  
Jieru Chen ◽  
Yihao Li ◽  
Yingsi Zeng ◽  
Yu Tian ◽  
Yueqiang Wen ◽  
...  
Keyword(s):  
Hospital Mortality ◽  
Mean Platelet Volume ◽  
Cox Regression ◽  
Cox Model ◽  
Predictive Ability ◽  
Severe Pneumonia ◽  
Platelet Volume ◽  
Kaplan Meier ◽  
Increased Risk ◽  
The Relationship

Background. Although mean platelet volume (MPV) appears to be associated with poor outcome of pneumonia, the relationship between MPV and in-hospital mortality is unclear in severe pneumonia (SP) patients. Methods. In this retrospective cohort study, 115 SP patients from June 1st, 2016, to September 29th, 2019, were included and divided into two groups. The primary outcome was in-hospital mortality. The receiver operating characteristic (ROC) curve was performed to assess the predictive ability for in-hospital mortality. Kaplan-Meier cumulative incidence curves were applied to observe the incidence of mortality. Multivariable Cox regression analyses were used to evaluate the hazard ratios (HRs). Besides, a formal test for interaction was investigated to analyze the relationship between MPV and sex. Results. During the course of hospitalization, 63 cases of mortality were recorded. ROC analysis suggested that MPV had a modest power for predicting in-hospital mortality (AUC=0.723, 95% CI: 0.628-0.818, P<0.001). Yet the cutoff value of MPV was 10.5 (sensitivity=73.02%; specificity=73.08%). Compared to the low-MPV group, the high-MPV group had significantly increased in-hospital mortality (log-rank test=13.501, P<0.001), while the adjusted Cox model indicated that the high-MPV group was associated with an elevated risk of in-hospital mortality (HR: 2.267, 95% CI: 1.166-4.406, P=0.016). Moreover, analyses of in-hospital mortality suggested a significant interaction between optimal MPV level and sex (P=0.011). In a multivariate Cox model which included females only, a high MPV level was associated with increased risk of in-hospital mortality (HR: 11.387, 95% CI: 1.767-73.380, P=0.011). Conclusion. High MPV level is an independent risk factor for in-hospital mortality in patients with SP.

THEORY OF LAW AND PHILOSOPHY OF LAW AS THEORETICAL DISCOURSES: SPECIFICS AND RELATIONSHIP

2020 ◽  
pp. 9-17
Author(s):  
Вадим Леонидович Афанасьевский
Keyword(s):  
Scientific Knowledge ◽  
Scientific Theory ◽  
Theoretical Concept ◽  
Philosophy Of Law ◽  
The West ◽  
Scientific Creativity ◽  
Key Characteristics ◽  
Different Types ◽  
Theory Of Law ◽  
The Relationship

В статье анализируется проблема взаимоотношений философии права и научной теории права. Рассматриваемая проблема стала особенно актуальной в российском образовательном пространстве в связи с введением после длительного перерыва в государственный образовательный стандарт магистратуры по юриспруденции учебной дисциплины «Философия права». Автор статьи в качестве базисного принимает тезис, согласно которому философия права, являясь сферой философской мысли, и теория права как область научного социогуманитарного знания представляют собой разные типы теоретического дискурса. Исходя из этого, в статье выстраивается теоретическая концепция, согласно которой задачей философии права как философского типа мышления является конструирование или экспликация онтологических, эпистемологических, аксиологических, феноменологических оснований для формирования и функционирования научных теоретико-правовых и историко-правовых построений. Для реализации поставленной в статье задачи подробно рассматриваются ключевые характеристики как теории философского типа, так и идеалов, норм и характеристик научного знания. Выявленное различие экстраполируется на взаимоотношение теории права как продукта научного творчества и философии права как конструкции, задающей базовые мировоззренческие смыслы. В качестве примера выработанных философией права и государства оснований научных теорий прогресса, государства, морали и права, автор приводит взгляды мыслителей западноевропейской философской классики: Т. Гоббса, Ж.-Ж. Руссо, И. Канта, Г.В.Ф. Гегеля. Именно их философские концепции предопределили образы теоретико- и историко-правовых учений XVIII, XIX, XX и даже начала XXI в. Таким образом, отношение философии права и теории права выстраивается по «вертикали»: от онтологического основания к возведению теоретико-правовых и историко-правовых научных построений. The article analyzes the problem of the relationship between the philosophy of law and the scientific theory of law. The problem under consideration has become especially urgent in the Russian educational space in connection with the introduction of the Philosophy of Law discipline master's degree in law after a long break. The author of the article takes as the basis the thesis that the philosophy of law, being the sphere of philosophical thought, and the theory of law as a field of scientific socio-humanitarian knowledge are different types of theoretical discourse. Based on this, the article builds a theoretical concept according to which the task of the philosophy of law as a philosophical type of thinking is the construction or explication of ontological, epistemological, axiological, phenomenological grounds for the formation and functioning of concrete scientific theoretical and legal and historical and legal constructions. To implement the task posed in the article, the key characteristics of both a theory of a philosophical type and ideals, norms and characteristics of scientific knowledge are examined in detail. The revealed difference is extrapolated to the relationship between the theory of law as a product of scientific creativity and the philosophy of law as a construction that sets basic philosophical meanings. As an example of the foundations of the scientific theories of progress, state, morality and law developed by the philosophy of law and the state, the author gives the views and thinkers of the West European philosophical classics T. Hobbes, J.-J. Russo, I. Kant, G.V.F. Hegel. It was their philosophical concepts that predetermined the images of theoretical and historical-legal doctrines of the XVIII, XIX, XX and even the beginning of the XXI centuries. Thus, the attitude of the philosophy of law and the theory of law is built along the «vertical»: from the ontological foundation to the construction of theoretical and historical and historical legal scientific constructions.

Characteristics of Different Types of Childhood Violence and the Risk of Revictimization

2019 ◽  
Vol 25 (14) ◽  
pp. 1696-1716 ◽  
Author(s):  
Ida Frugaard Stroem ◽  
Helene Flood Aakvaag ◽  
Tore Wentzel-Larsen
Keyword(s):  
Childhood Abuse ◽  
Telephone Survey ◽  
Regression Analyses ◽  
Multiple Forms ◽  
Different Types ◽  
Children And Young Adults ◽  
Childhood Violence ◽  
Forms Of Violence ◽  
The Relationship

This study investigates the relationship between the characteristics of different types of childhood violence and adult victimization using two waves of data from a community telephone survey (T1) and a follow-up survey, including 505 cases and 506 controls, aged 17-35 years (T2). The logistic regression analyses showed that exposure to childhood abuse, regardless of type, was associated with adult victimization. Exposure to multiple types of abuse, victimization both in childhood and in young adulthood, and recency of abuse increased these odds. Our findings emphasize the importance of assessing multiple forms of violence when studying revictimization. Practitioners working with children and young adults should be attentive to the number of victimization types experienced and recent victimization to prevent further abuse.

Sign in / Sign up

Export Citation Format

Share Document