220 resultados para Survival data
em University of Queensland eSpace - Australia
Resumo:
We consider a mixture model approach to the regression analysis of competing-risks data. Attention is focused on inference concerning the effects of factors on both the probability of occurrence and the hazard rate conditional on each of the failure types. These two quantities are specified in the mixture model using the logistic model and the proportional hazards model, respectively. We propose a semi-parametric mixture method to estimate the logistic and regression coefficients jointly, whereby the component-baseline hazard functions are completely unspecified. Estimation is based on maximum likelihood on the basis of the full likelihood, implemented via an expectation-conditional maximization (ECM) algorithm. Simulation studies are performed to compare the performance of the proposed semi-parametric method with a fully parametric mixture approach. The results show that when the component-baseline hazard is monotonic increasing, the semi-parametric and fully parametric mixture approaches are comparable for mildly and moderately censored samples. When the component-baseline hazard is not monotonic increasing, the semi-parametric method consistently provides less biased estimates than a fully parametric approach and is comparable in efficiency in the estimation of the parameters for all levels of censoring. The methods are illustrated using a real data set of prostate cancer patients treated with different dosages of the drug diethylstilbestrol. Copyright (C) 2003 John Wiley Sons, Ltd.
Resumo:
A mixture model incorporating long-term survivors has been adopted in the field of biostatistics where some individuals may never experience the failure event under study. The surviving fractions may be considered as cured. In most applications, the survival times are assumed to be independent. However, when the survival data are obtained from a multi-centre clinical trial, it is conceived that the environ mental conditions and facilities shared within clinic affects the proportion cured as well as the failure risk for the uncured individuals. It necessitates a long-term survivor mixture model with random effects. In this paper, the long-term survivor mixture model is extended for the analysis of multivariate failure time data using the generalized linear mixed model (GLMM) approach. The proposed model is applied to analyse a numerical data set from a multi-centre clinical trial of carcinoma as an illustration. Some simulation experiments are performed to assess the applicability of the model based on the average biases of the estimates formed. Copyright (C) 2001 John Wiley & Sons, Ltd.
Resumo:
We investigate whether relative contributions of genetic and shared environmental factors are associated with an increased risk in melanoma. Data from the Queensland Familial Melanoma Project comprising 15,907 subjects arising from 1912 families were analyzed to estimate the additive genetic, common and unique environmental contributions to variation in the age at onset of melanoma. Two complementary approaches for analyzing correlated time-to-onset family data were considered: the generalized estimating equations (GEE) method in which one can estimate relationship-specific dependence simultaneously with regression coefficients that describe the average population response to changing covariates; and a subject-specific Bayesian mixed model in which heterogeneity in regression parameters is explicitly modeled and the different components of variation may be estimated directly. The proportional hazards and Weibull models were utilized, as both produce natural frameworks for estimating relative risks while adjusting for simultaneous effects of other covariates. A simple Markov Chain Monte Carlo method for covariate imputation of missing data was used and the actual implementation of the Bayesian model was based on Gibbs sampling using the free ware package BUGS. In addition, we also used a Bayesian model to investigate the relative contribution of genetic and environmental effects on the expression of naevi and freckles, which are known risk factors for melanoma.
Resumo:
BACKGROUND: Recent studies have demonstrated that exercise capacity is an independent predictor of mortality in women. Normative values of exercise capacity for age in women have not been well established. Our objectives were to construct a nomogram to permit determination of predicted exercise capacity for age in women and to assess the predictive value of the nomogram with respect to survival. METHODS: A total of 5721 asymptomatic women underwent a symptom-limited, maximal stress test. Exercise capacity was measured in metabolic equivalents (MET). Linear regression was used to estimate the mean MET achieved for age. A nomogram was established to allow the percentage of predicted exercise capacity to be estimated on the basis of age and the exercise capacity achieved. The nomogram was then used to determine the percentage of predicted exercise capacity for both the original cohort and a referral population of 4471 women with cardiovascular symptoms who underwent a symptom-limited stress test. Survival data were obtained for both cohorts, and Cox survival analysis was used to estimate the rates of death from any cause and from cardiac causes in each group. RESULTS: The linear regression equation for predicted exercise capacity (in MET) on the basis of age in the cohort of asymptomatic women was as follows: predicted MET = 14.7 - (0.13 x age). The risk of death among asymptomatic women whose exercise capacity was less than 85 percent of the predicted value for age was twice that among women whose exercise capacity was at least 85 percent of the age-predicted value (P<0.001). Results were similar in the cohort of symptomatic women. CONCLUSIONS: We have established a nomogram for predicted exercise capacity on the basis of age that is predictive of survival among both asymptomatic and symptomatic women. These findings could be incorporated into the interpretation of exercise stress tests, providing additional prognostic information for risk stratification.
Resumo:
Bioenergetics differ between males and females of many species. Human females apportion a substantial proportion of energy resources towards gynoid fat storage, to support the energetic burden of reproduction. Similarly, axial calcium accrual is favoured in females compared with males. Nutritional status is a prognostic indicator in cystic fibrosis (CF), but girls and young women are at greater risk of death despite equivalent nutritional status to males. The aim of this study was to compare fat (energy) and calcium stores (bone density) in males and females with CF over a spectrum of disease severity. Methods: Fat as % body weight (fat%) and lumbar spine (LS) and total body (TB) bone mineral density (BMD) were measured using dual absorption X-ray photometry in 127(59M) control and 101(54M) CF subjects, aged 9–25 years. An equation for predicted age at death had been determined using survival data and history of pulmonary function for the whole clinic, based on a trivariate normal model using maximum likelihood methods (1). For the CF group, a disease severity index (predicted age at death) was calculated from the derived equations according to each subjects history of pulmonary function, current age, and gender. Disease severity was classified according to percentile of predicted age at death (‘mild’ ≥75th, ‘moderate’ 25th–75th, ‘severe’ ≤25th percentile). Wt for age z-score was calculated. Serum testosterone and oestrogen were measured in males and females respectively. Fat% and LSBMD were compared between the groups using ANOVA. Results: There was an interaction between disease severity and gender: increasing disease severity was associated with greater deficits in TB (p=0.01), LSBMD (p
Resumo:
The aim of this study was to apply multifailure survival methods to analyze time to multiple occurrences of basal cell carcinoma (BCC). Data from 4.5 years of follow-up in a randomized controlled trial, the Nambour Skin Cancer Prevention Trial (1992-1996), to evaluate skin cancer prevention were used to assess the influence of sunscreen application on the time to first BCC and the time to subsequent BCCs. Three different approaches of time to ordered multiple events were applied and compared: the Andersen-Gill, Wei-Lin-Weissfeld, and Prentice-Williams-Peterson models. Robust variance estimation approaches were used for all multifailure survival models. Sunscreen treatment was not associated with time to first occurrence of a BCC (hazard ratio = 1.04, 95% confidence interval: 0.79, 1.45). Time to subsequent BCC tumors using the Andersen-Gill model resulted in a lower estimated hazard among the daily sunscreen application group, although statistical significance was not reached (hazard ratio = 0.82, 95% confidence interval: 0.59, 1.15). Similarly, both the Wei-Lin-Weissfeld marginal-hazards and the Prentice-Williams-Peterson gap-time models revealed trends toward a lower risk of subsequent BCC tumors among the sunscreen intervention group. These results demonstrate the importance of conducting multiple-event analysis for recurring events, as risk factors for a single event may differ from those where repeated events are considered.
Resumo:
We surveyed a sample of 204 individuals selected from the public in Brisbane, Australia, to ascertain the extent to which they like or dislike 24 species of wildlife present in tropical Australia. The species belong to three classes: mammals, birds and reptiles. We calculated likeability indices for each of these species. We also asked respondents if they favoured the survival of each of these species and so the percentage of respondents favouring survival of each of these species could be calculated. Thus, using linear regression analysis, the percentage of respondents favouring survival of each of the species was related to their indices of likeability. In addition, the data enables the average likeability of species in the three classes (mammals, birds and reptiles) to be compared with the average support for survival of species in each of these three classes. As a result, we are able to assess how important stated likeability seems to be for preferences for survival of species, and to reconsider the hypothesis in the literature that there is likely to be more public support for the survival of mammals than for birds than for reptiles.
Resumo:
Regression analyses of a long series of light-trap catches at Narrabri, Australia, were used to describe the seasonal dynamics of Helicoverpa armigera (Hubner). The size of the second generation was significantly related to the size of the first generation, to winter rainfall, which had a positive effect, and to spring rainfall which had a negative effect. These variables accounted for up to 96% of the variation in size of the second generation from year to year. Rainfall and crop hosts were also important for the size of the third generation. The area and tonnage of many potential host crops were significantly correlated with winter rain. When winter rain was omitted from the analysis, the sizes of both the second and third generations could be expressed as a function of the size of the previous generation and of the areas planted to lucerne, sorghum and maize. Lucerne and maize always had positive coefficients and sorghum a negative one. We extended our analysis to catches of H. punctigera (Wallengren), which declines in abundance after the second generation. Winter rain had a positive effect on the sizes of the second and third generations, and rain in spring or early summer had a negative effect. Only the area grown to lucerne had a positive effect on abundance. Forecasts of pest levels from a few months to a few weeks in advance are discussed, along with the improved understanding of the seasonal dynamics of both species and the significance of crops in the management of insecticide resistance for H. armigera.
Resumo:
A two-component survival mixture model is proposed to analyse a set of ischaemic stroke-specific mortality data. The survival experience of stroke patients after index stroke may be described by a subpopulation of patients in the acute condition and another subpopulation of patients in the chronic phase. To adjust for the inherent correlation of observations due to random hospital effects, a mixture model of two survival functions with random effects is formulated. Assuming a Weibull hazard in both components, an EM algorithm is developed for the estimation of fixed effect parameters and variance components. A simulation study is conducted to assess the performance of the two-component survival mixture model estimators. Simulation results confirm the applicability of the proposed model in a small sample setting. Copyright (C) 2004 John Wiley Sons, Ltd.
Resumo:
OBJECTIVE - The purpose of this paper is to estimate the impact of diabetes on survival among patients with first acute myocardial infarction, using data from the World Health Organization (WHO) Monitoring Trends and Determinants of Cardiovascular Disease (MONICA) Project in Newcastle, New South Wales, Australia. RESEARCH DESIGN AND METHODS - The WHO MONICA Project is a community-based surveillance system that monitors coronary heart disease morbidity and mortality. All patients with suspected coronary events were observed for 28 days after the onset of symptoms. RESULTS - Of 5,322 patients with acute myocardial infarction and no previous history of ischemic heart disease (3,643 men and 1,679 women), 333 men (9%) and 224 women (13%) had a history of diabetes. The age-adjusted 28-day case fatality for women with diabetes (25%) was significantly higher than for women without diabetes (16%); relative risk 1.56 (95% CI: 1.19-2.04). The difference for men was also significant (25% with diabetes and 20% without diabetes); relative risk 1.25 (95% CI: 1.02-1.53). Age-specific case fatality increased significantly with age in both men and women without diabetes, but systematic age effects were not so apparent in patients with diabetes. Case fatality significantly decreased over the study period in patients without diabetes, but not among the diabetic patients. CONCLUSIONS - The increased risk of death in the diabetic patients remained after accounting for their poorer risk factor profiles; even if they reached the hospital alive, diabetic patients were also less likely to survive than nondiabetic patients. The relative impact of diabetes on survival is greater in women than in men.
Resumo:
This study of breast cancer survival is based on analysis of five-year relative survival of 38 362 cases of invasive breast cancer in New South Wales (NSW) women, incident between 1972 and 1991, with follow-up to 1992, using data from the population-based NSW Central Cancer Registry. Survival was ascertained by matching the registry file of breast cancers against NSW death certificates from 1972 to 1992, mainly by automated probabilistic linkage. Absolute survival of cases was compared with expected survival of age- and period-matched NSW women. Proportional hazard regression analysis was used for examination of the effects on excess mortality of age, period of diagnosis and degree of spread at diagnosis. Relative survival at five years increased from 70 per cent in 1972-1976 to 77 per cent in 1987-1991. Survival improved during the 1970s and in the late 1980s. Regression analysis suggested that part of the improved survival in the late 1980s was due to lesser degree of spread at diagnosis, whereas the improved survival during the 1970s may have been due to treatment. Survival was better for those aged 40-49 years (RR = 0.86) and worse for those aged greater than or equal to 70 years (RR = 1.22) compared with the referent group (60-69 years). Excess mortality was much less for those with invasive localised disease than those with regional spread (RR = 3.1) or metastatic cancer (RR = 15.5) at diagnosis. For the most recent period (1987-1991), relative five-year survival was 90, 70 and 18 per cent, respectively, for the three degree-of-spread categories.
Resumo:
Breast cancer five-year relative survival was calculated for 16 urban and rural regions in New South Wales (NSW) for cases incident in 1980-1991. Survival analysis employed cancer registry data linked with the death register, and age- and period-matched regional mortality of NSW women, Proportional hazard regression analysis was used to compare excess mortality in breast cancer cases in each region. The effect of region was significant (P < 0.05) in the analysis, after age and the follow-up variable (and their intel action) were adjusted for, although no region was significantly different from the referent group (chosen because of average relative five-year survival). When degree of spread and its interactions were entered into che model, the effect of region became nonsignificant. A significant linear trend (P < 0.05) in the adjusted relative risk for excess mortality in breast cancer cases was noted when regions were divided into quartiles based on socioeconomic status, with higher relative risk in low-socioeconomic-status groups; this effect also disappeared with adjustment for degree of spread at diagnosis. There was no general effect of rurality versus capital city or other metropolitan centres. This study demonstrates a small effect of region of residence and implied socioeconomic status on breast cancer survival in NSW women, but this becomes nonsignificant when the data are adjusted for degree of spread at diagnosis, This suggests that earlier diagnosis would he of benefit in reducing minor inequalities in breast cancer survival in NSW women.
Resumo:
We show here that the neurotrophin nerve growth factor (NGF), which has been shown to be a mitogen for breast cancer cells, also stimulates cell survival through a distinct signaling pathway. Breast cancer cell lines (MCF-7, T47-D, BT-20, and MDA-MB-231) were found to express both types of NGF receptors: p140(trkA) and p75(NTR). The two other tyrosine kinase receptors for neurotrophins, TrkB and TrkC, were not expressed. The mitogenic effect of NGF on breast cancer cells required the tyrosine kinase activity of p140(trkA) as well as the mitogen-activated protein kinase (MAPK) cascade, but was independent of p75(NTR). I, contrast, the anti-apoptotic effect of NGF (studied using the ceramide analogue C2) required p75(NTR) as well as the activation of the transcription factor NF-kB, but neither p140(trkA) nor MAPK was necessary. Other neurotrophins (BDNF, NT-3, NT-4/5) also induced cell survival, although not proliferation, emphasizing the importance of p75(NTR) in NGF-mediated survival. Both the pharmacological NF-KB inhibitor SN50, and cell transfection with IkBm, resulted in a diminution of NGF anti-apoptotic effect. These data show that two distinct signaling pathways are required for NGF activity and confirm the roles played by p75(NTR) and NF-kappaB in the activation of the survival pathway in breast cancer cells.