Incidence of prostate, colorectal and male breast cancers in relation with statins and testosterone replacement therapy: SEER-Medicare 2007-2015.

INTRODUCTION: Statins and testosterone replacement therapy (TTh) have been inconsistently associated with a reduced risk of hormone-related cancers (HRCs, prostate [PCa], colorectal [CRC], and male breast cancers [BrCa]). Yet, the joint association of statins and TTh with the incidence of these cancers, and whether these associations vary by race, remains poorly understood. The objective of this retrospective cohort study is to examine the independent and joint effects of pre-diagnostic use of statins and TTh on the risk of HRCs, including PCa, CRC, and male BrCa. MATERIALS: and Methods: In 105,690 men (≥65 yrs) identified using the SEER-Medicare 2007-2015 data, we identified 82,578 White and 10,256 Black men. Pre-diagnostic prescription of statins and TTh was ascertained for this analysis and categorized into four groups (Neither users, statins alone, TTh alone and Dual users). Multivariable Time-varying Cox proportional hazards and Accelerated Failure Time (AFT) models were performed. RESULTS: We found inverse joint associations of statins and TTh with incident HRCs before (aHR: 0.39; 95 % CI: 0.35-0.44) and after 3 years of follow-up (aHR: 0.74; 95 % CI: 0.67-0.82). This included a lower risk for advanced stage HRC (only <3 years follow-up). Similar joint associations were identified with incident PCa, aggressive PCa, incident CRC, and its specific right- and left-sided CRC (only <3 years follow-up). In general, the inverse associations persisted among White (mainly <3 years follow-up) and Black men (high-grade HRC and <3 years follow-up). Findings from the AFT analysis were similar. DISCUSSION: Pre-diagnostic use of statins and TTh were, independently and jointly, associated with reduced risks of HRC and specific cancer sites at three years of follow-up overall, and among White and Black men. Greatest associations of HRCs risk reduction were observed among dual users (statins plus TTh). Further studies are needed to validate these findings, including larger samples of Black men, and male BrCa sites.

Group lasso priors for Bayesian accelerated failure time models with left-truncated and interval-censored data.

An important task in health research is to characterize time-to-event outcomes such as disease onset or mortality in terms of a potentially high-dimensional set of risk factors. For example, prospective cohort studies of Alzheimer's disease (AD) typically enroll older adults for observation over several decades to assess the long-term impact of genetic and other factors on cognitive decline and mortality. The accelerated failure time model is particularly well-suited to such studies, structuring covariate effects as "horizontal" changes to the survival quantiles that conceptually reflect shifts in the outcome distribution due to lifelong exposures. However, this modeling task is complicated by the enrollment of adults at differing ages, and intermittent follow-up visits leading to interval-censored outcome information. Moreover, genetic and clinical risk factors are not only high-dimensional, but characterized by underlying grouping structures, such as by function or gene location. Such grouped high-dimensional covariates require shrinkage methods that directly acknowledge this structure to facilitate variable selection and estimation. In this paper, we address these considerations directly by proposing a Bayesian accelerated failure time model with a group-structured lasso penalty, designed for left-truncated and interval-censored time-to-event data. We develop an R package with a Markov chain Monte Carlo sampler for estimation. We present a simulation study examining the performance of this method relative to an ordinary lasso penalty and apply the proposed method to identify groups of predictive genetic and clinical risk factors for AD in the Religious Orders Study and Memory and Aging Project prospective cohort studies of AD and dementia.

Reply to "Matters arising: cost-effectiveness of first-line immunotherapy combinations with or without chemotherapy for advanced non-small cell lung cancer: a modelling approach".

In this article, we read with great attention the correspondence by Bullement et al., regarding our published study on cost-effectiveness of first-line immunotherapy combinations with or without chemotherapy for advanced non-small cell lung cancer. We referred to a few the most important comments from Bullement et al. in our opinion, including proportional hazard (PH) assumption, accelerated failure time (AFT) model, and health utility, and made some explanations.

Bayesian semi-parametric inference for clustered recurrent events with zero inflation and a terminal event.

Recurrent events are common in clinical studies and are often subject to terminal events. In pragmatic trials, participants are often nested in clinics and can be susceptible or structurally unsusceptible to the recurrent events. We develop a Bayesian shared random effects model to accommodate this complex data structure. To achieve robustness, we consider the Dirichlet processes to model the residual of the accelerated failure time model for the survival process as well as the cluster-specific shared frailty distribution, along with an efficient sampling algorithm for posterior inference. Our method is applied to a recent cluster randomized trial on fall injury prevention.

Choice of baseline hazards in joint modeling of longitudinal and time-to-event cancer survival data.

Longitudinal time-to-event analysis is a statistical method to analyze data where covariates are measured repeatedly. In survival studies, the risk for an event is estimated using Cox-proportional hazard model or extended Cox-model for exogenous time-dependent covariates. However, these models are inappropriate for endogenous time-dependent covariates like longitudinally measured biomarkers, Carcinoembryonic Antigen (CEA). Joint models that can simultaneously model the longitudinal covariates and time-to-event data have been proposed as an alternative. The present study highlights the importance of choosing the baseline hazards to get more accurate risk estimation. The study used colon cancer patient data to illustrate and compare four different joint models which differs based on the choice of baseline hazards [piecewise-constant Gauss-Hermite (GH), piecewise-constant pseudo-adaptive GH, Weibull Accelerated Failure time model with GH & B-spline GH]. We conducted simulation study to assess the model consistency with varying sample size (N = 100, 250, 500) and censoring (20 %, 50 %, 70 %) proportions. In colon cancer patient data, based on Akaike information criteria (AIC) and Bayesian information criteria (BIC), piecewise-constant pseudo-adaptive GH was found to be the best fitted model. Despite differences in model fit, the hazards obtained from the four models were similar. The study identified composite stage as a prognostic factor for time-to-event and the longitudinal outcome, CEA as a dynamic predictor for overall survival in colon cancer patients. Based on the simulation study Piecewise-PH-aGH was found to be the best model with least AIC and BIC values, and highest coverage probability(CP). While the Bias, and RMSE for all the models showed a competitive performance. However, Piecewise-PH-aGH has shown least bias and RMSE in most of the combinations and has taken the shortest computation time, which shows its computational efficiency. This study is the first of its kind to discuss on the choice of baseline hazards.

Accelerated failure time modeling of in-lane street hawkers' lane entry and exit behaviors at signalized intersections.

In-lane street hawking is the intermittent entry of signalized intersections by traders to sell groceries to drivers and passengers. Studies have shown that hawkers get exposed to traffic injuries but the lack of quantitative analysis of their lane entry and exit behaviors in signalized intersections makes it difficult to improve traffic safety. This study analyzes the significant predictors of in-lane street hawkers' (1) lane entry within 30 s after the red signal illumination, (2) lane exit within 30 s after the green signal illumination, and (3) probability of getting injuries during the green signal time. Drone-based trajectory data were collected from a selected signalized intersection in Accra, Ghana. A Weibull accelerated failure time duration model incorporating Gamma frailty was used to evaluate hawkers' behaviors. Overall, the majority of hawkers exhibited red-light running behaviors exposing them to traffic injuries. An increase in traffic speed, especially beyond 20 km/h, exposed hawkers to injury risks significantly. Notably, hawkers' lane entry decreased significantly as the traffic speed increased. Their lane exit duration was significantly predicted by the queue lengths and traffic volumes. Accordingly, safety practitioners can enhance traffic regulation and control methods in addition to pro-poor social interventions to demotivate hawking at signalized intersections.

An Accelerated Failure Time Model to Predict Cause-Specific Survival and Prognostic Factors of Lung and Bronchus Cancer Patients with at Least Bone or Brain Metastases: Development and Internal Validation Using a SEER-Based Study.

BACKGROUND: This study addresses the significant challenge of low survival rates in patients with cause-specific lung cancer accompanied by bone or brain metastases. Recognizing the critical need for an effective predictive model, the research aims to establish survival prediction models using both parametric and non-parametric approaches. METHODS: Clinical data from lung cancer patients with at least one bone or brain metastasis between 2000 and 2020 from the SEER database were utilized. Four models were constructed: Cox proportional hazard, Weibull accelerated failure time (AFT), log-normal AFT, and Zografos-Balakrishnan log-normal (ZBLN). Independent prognostic factors for cause-specific survival were identified, and model fit was evaluated using Akaike's and Bayesian information criteria. Internal validation assessed predictive accuracy and discriminability through the Harriel Concordance Index (C-index) and calibration plots. RESULTS: A total of 20,412 patients were included, with 14,290 (70%) as the training cohort and 6122 (30%) validation. Independent prognostic factors selected for the study were age, race, sex, primary tumor site, disease grade, total malignant tumor in situ, metastases, treatment modality, and histology. Among the accelerated failure time (AFT) models considered, the ZBLN distribution exhibited the most robust model fit for the 3- and 5-year survival, as evidenced by the lowest values of Akaike's information criterion of 6322 and 79,396, and the Bayesian information criterion of 63,495 and 79,396, respectively. This outperformed other AFT and Cox models (AIC = [156,891, 211,125]; BIC = [158,848, 211,287]). Regarding predictive accuracy, the ZBLN AFT model achieved the highest concordance C-index (0.682, 0.667), a better performance than the Cox model (0.669, 0.643). The calibration curves of the ZBLN AFT model demonstrated a high degree of concordance between actual and predicted values. All variables considered in this study demonstrated significance at the 0.05 level for the ZBLN AFT model. However, differences emerged in the significant variations in survival times between subgroups. The study revealed that patients with only bone metastases have a higher chance of survival compared to only brain and those with bone and brain metastases. CONCLUSIONS: The study highlights the underutilized but accurate nature of the accelerated failure time model in predicting lung cancer survival and identifying prognostic factors. These findings have implications for individualized clinical decisions, indicating the potential for screening and professional care of lung cancer patients with at least one bone or brain metastasis in the future.

What characteristics of dogs help them stay shorter in shelters? Evidence from a polish animal shelter.

Staying in animal shelters can be stressful for dogs because of exposure to noise, unfamiliar environment, and social separation. Consequently, the wellbeing of sheltered dogs could be improved through reduction of length of stay in a shelter (LOS). To help inform the development of interventions aimed at LOS reduction, we analyze dogs' characteristics affecting their LOS. We use econometric modeling to identify the characteristics's influence by simultaneously controlling for multiple factors. We use data from Poland's largest animal shelter (11805 observations from the years 2000-2020). We compare two modeling approaches: a Cox survival model, commonly used in animal welfare studies, and an accelerated failure time model, theoretically better fitted to studying time-dependent factors but not yet applied in the context of LOS. We conclude that the latter approach is preferable for studying factors affecting LOS. Male sex, mixed-breed, dark fur, large size, and older age appear to be associated with longer time to adoption for dogs. To our knowledge, this is the first econometric examination of factors affecting LOS in a country in Central and Eastern Europe.

Characterizing quantile-varying covariate effects under the accelerated failure time model.

An important task in survival analysis is choosing a structure for the relationship between covariates of interest and the time-to-event outcome. For example, the accelerated failure time (AFT) model structures each covariate effect as a constant multiplicative shift in the outcome distribution across all survival quantiles. Though parsimonious, this structure cannot detect or capture effects that differ across quantiles of the distribution, a limitation that is analogous to only permitting proportional hazards in the Cox model. To address this, we propose a general framework for quantile-varying multiplicative effects under the AFT model. Specifically, we embed flexible regression structures within the AFT model and derive a novel formula for interpretable effects on the quantile scale. A regression standardization scheme based on the g-formula is proposed to enable the estimation of both covariate-conditional and marginal effects for an exposure of interest. We implement a user-friendly Bayesian approach for the estimation and quantification of uncertainty while accounting for left truncation and complex censoring. We emphasize the intuitive interpretation of this model through numerical and graphical tools and illustrate its performance through simulation and application to a study of Alzheimer's disease and dementia.

Maximum approximate likelihood estimation in accelerated failure time model for interval-censored data.

The approximate Bernstein polynomial model, a mixture of beta distributions, is applied to obtain maximum likelihood estimates of the regression coefficients, the baseline density and the survival functions in an accelerated failure time model based on interval censored data including current status data. The estimators of the regression coefficients and the underlying baseline density function are shown to be consistent with almost parametric rates of convergence under some conditions for uncensored and/or interval censored data. Simulation shows that the proposed method is better than its competitors. The proposed method is illustrated by fitting the Breast Cosmetic and the HIV infection time data using the accelerated failure time model.

Misclassification simulation extrapolation method for a Weibull accelerated failure time model.

The problem of misclassification in covariates is ubiquitous in survival data and often leads to biased estimates. The misclassification simulation extrapolation method is a popular method to correct this bias. However, its impact on Weibull accelerated failure time models has not been studied. In this paper, we study the bias caused by misclassification in one or more binary covariates in Weibull accelerated failure time models and explore the use of the misclassification simulation extrapolation in correcting for this bias, along with its asymptotic properties. Simulation studies are carried out to investigate the numerical properties of the resulting estimator for finite samples. The proposed method is then applied to colon cancer data obtained from the cancer registry at Memorial Sloan Kettering Cancer Center.

An econometric approach to aggregating multiple cardiovascular outcomes in German hospitals.

OBJECTIVE: Development of an aggregate quality index to evaluate hospital performance in cardiovascular events treatment. METHODS: We applied a two-stage regression approach using an accelerated failure time model based on variance weights to estimate hospital quality over four cardiovascular interventions: elective coronary bypass graft, elective cardiac resynchronization therapy, and emergency treatment for acute myocardial infarction. Mortality and readmissions were used as outcomes. For the estimation we used data from a statutory health insurer in Germany from 2005 to 2016. RESULTS: The precision-based weights calculated in the first stage were higher for mortality than for readmissions. In general, teaching hospitals performed better in our ranking of hospital quality compared to non-teaching hospitals, as did private not-for-profit hospitals compared to hospitals with public or private for-profit ownership. DISCUSSION: The proposed approach is a new method to aggregate single hospital quality outcomes using objective, precision-based weights. Likelihood-based accelerated failure time models make use of existing data more efficiently compared to widely used models relying on dichotomized data. The main advantage of the variance-based weights approach is that the extent to which an indicator contributes to the aggregate index depends on the amount of its variance.

A connection between survival multistate models and causal inference for external treatment interruptions.

Recently, treatment interruptions such as a clinical hold in randomized clinical trials have been investigated by using a multistate model approach. The phase III clinical trial START (Stimulating Targeted Antigenic Response To non-small-cell cancer) with primary endpoint overall survival was temporarily placed on hold for enrollment and treatment by the US Food and Drug Administration (FDA). Multistate models provide a flexible framework to account for treatment interruptions induced by a time-dependent external covariate. Extending previous work, we propose a censoring and a filtering approach both aimed at estimating the initial treatment effect on overall survival in the hypothetical situation of no clinical hold. A special focus is on creating a link to causal inference. We show that calculating the matrix of transition probabilities in the multistate model after application of censoring (or filtering) yields the desired causal interpretation. Assumptions in support of the identification of a causal effect by censoring (or filtering) are discussed. Thus, we provide the basis to apply causal censoring (or filtering) in more general settings such as the COVID-19 pandemic. A simulation study demonstrates that both causal censoring and filtering perform favorably compared to a naïve method ignoring the external impact.

Social integration predicts survival in female white-faced capuchin monkeys.

Across multiple species of social mammals, a growing number of studies have found that individual sociality is associated with survival. In long-lived species, like primates, lifespan is one of the main components of fitness. We used 18 years of data from the Lomas Barbudal Monkey Project to quantify social integration in 11 capuchin (Cebus capucinus) groups and tested whether female survivorship was associated with females' tendencies to interact with three types of partners: (1) all group members, (2) adult females, and (3) adult males. We found strong evidence that females who engaged more with other females in affiliative interactions and foraged in close proximity experienced increased survivorship. We found some weak evidence that females might also benefit from engaging in more support in agonistic contexts with other females. These benefits were evident in models that account for the females' rank and group size. Female interactions with all group members also increased survival, but the estimates of the effects were more uncertain. In interactions with adult males, only females who provided more grooming to males survived longer. The results presented here suggest that social integration may result in survival-related benefits. Females might enjoy these benefits through exchanging grooming for other currencies, such as coalitionary support or tolerance.

An Accelerated Failure Time Cure Model with Shifted Gamma Frailty and Its Application to Epidemiological Research.

Survival analysis is a set of methods for statistical inference concerning the time until the occurrence of an event. One of the main objectives of survival analysis is to evaluate the effects of different covariates on event time. Although the proportional hazards model is widely used in survival analysis, it assumes that the ratio of the hazard functions is constant over time. This assumption is likely to be violated in practice, leading to erroneous inferences and inappropriate conclusions. The accelerated failure time model is an alternative to the proportional hazards model that does not require such a strong assumption. Moreover, it is sometimes plausible to consider the existence of cured patients or long-term survivors. The survival regression models in such contexts are referred to as cure models. In this study, we consider the accelerated failure time cure model with frailty for uncured patients. Frailty is a latent random variable representing patients' characteristics that cannot be described by observed covariates. This enables us to flexibly account for individual heterogeneities. Our proposed model assumes a shifted gamma distribution for frailty to represent uncured patients' heterogeneities. We construct an estimation algorithm for the proposed model, and evaluate its performance via numerical simulations. Furthermore, as an application of the proposed model, we use a real dataset, Specific Health Checkups, concerning the onset of hypertension. Results from a model comparison suggest that the proposed model is superior to existing alternatives.

Efficiency of Naive Estimators for Accelerated Failure Time Models under Length-Biased Sampling.

In prevalent cohort studies where subjects are recruited at a cross-section, the time to an event may be subject to length-biased sampling, with the observed data being either the forward recurrence time, or the backward recurrence time, or their sum. In the regression setting, assuming a semiparametric accelerated failure time model for the underlying event time, where the intercept parameter is absorbed into the nuisance parameter, it has been shown that the model remains invariant under these observed data set-ups and can be fitted using standard methodology for accelerated failure time model estimation, ignoring the length-bias. However, the efficiency of these estimators is unclear, owing to the fact that the observed covariate distribution, which is also length-biased, may contain information about the regression parameter in the accelerated life model. We demonstrate that if the true covariate distribution is completely unspecified, then the naive estimator based on the conditional likelihood given the covariates is fully efficient for the slope.

Semiparametric analysis of a generalized linear model with multiple covariates subject to detection limits.

Studies on the health effects of environmental mixtures face the challenge of limit of detection (LOD) in multiple correlated exposure measurements. Conventional approaches to deal with covariates subject to LOD, including complete-case analysis, substitution methods, and parametric modeling of covariate distribution, are feasible but may result in efficiency loss or bias. With a single covariate subject to LOD, a flexible semiparametric accelerated failure time (AFT) model to accommodate censored measurements has been proposed. We generalize this approach by considering a multivariate AFT model for the multiple correlated covariates subject to LOD and a generalized linear model for the outcome. A two-stage procedure based on semiparametric pseudo-likelihood is proposed for estimating the effects of these covariates on health outcome. Consistency and asymptotic normality of the estimators are derived for an arbitrary fixed dimension of covariates. Simulations studies demonstrate good large sample performance of the proposed methods vs conventional methods in realistic scenarios. We illustrate the practical utility of the proposed method with the LIFECODES birth cohort data, where we compare our approach to existing approaches in an analysis of multiple urinary trace metals in association with oxidative stress in pregnant women.

Prediction of the generalization of myasthenia gravis with purely ocular symptoms at onset: a multivariable model development and validation.

Background: About half of myasthenia gravis (MG) patients with purely ocular symptoms at onset progress to generalized myasthenia gravis (gMG). Objectives: To develop and validate a model to predict the generalization of MG at 6 months after disease onset in patients with ocular-onset myasthenia gravis (OoMG). Methods: Data of patients with OoMG were retrospectively collected from two tertiary hospitals in Germany and China. An accelerated failure time model was developed using the backward elimination method based on the German cohort to predict the generalization of OoMG. The model was then externally validated in the Chinese cohort, and its performance was assessed using Harrell's C-index and calibration plots. Results: Four hundred and seventy-seven patients (275 from Germany and 202 from China) were eligible for inclusion. One hundred and three (37.5%) patients in the German cohort progressed from OoMG to gMG with a median follow-up time of 69 (32-116) months. The median time to generalization was 29 (16-71) months. The estimated cumulative probability of generalization was 30.5% [95% CI (confidence interval), 24.3-36.2%) at 5 years after disease onset. The final model, which was represented as a nomogram, included five clinical variables: sex, titer of anti-AChR antibody, status of anti-MuSK antibody, age at disease onset and the presence of other autoimmune disease. External validation of the model using the bootstrap showed a C-index of 0.670 (95% CI, 0.602-0.738). Calibration curves revealed moderate agreement of predicted and observed outcomes. Conclusion: The nomogram is a good predictor for generalization in patients with OoMG that can be used to inform of the individual generalization risk, which might improve the clinical decision-making.

Examining Risk Factors Accelerating Time-to-Chronic Obstructive Pulmonary Disease (COPD) Diagnosis among Asthma Patients.

Asthma patients may have an increased risk for diagnosis of chronic obstructive pulmonary disease (COPD). However, risk factors accelerating time-to-COPD diagnosis are unclear. This study aims to estimate risk factors associated with the incidence of COPD diagnosis in asthma patients. Canada's Population Data BC (PopData BC) was used to identify asthma patients without prior COPD diagnosis between January 1, 1998, to December 31, 1999. Patients were assessed for time-to-incidence of COPD diagnosis from January 1, 2000, to December 31, 2018. The study estimated the effects of several risk factors in predicting the incidence of COPD in asthma patients during the 18-year follow-up period. Patient factors such as Medication Adherence (MA) were assessed by the proportion of days covered (PDC) and the medication possession ratio (MPR). The log-logistic mixed-effects accelerated failure time model was used to estimate the adjusted failure time ratios (aFTR) and 95% Confidence Interval (95% CI) for factors predicting time-to-COPD diagnosis among asthma patients. We identified 68,211 asthma patients with a mean age of 48.2 years included in the analysis. Risk factors accelerating time-to-COPD diagnosis included: male sex (aFTR: 0.62, 95% CI:0.56-0.68), older adults (age > 40 years) [aFTR: 0.03, 95% CI: 0.02-0.04], history of tobacco smoking (aFTR: 0.29, 95% CI: 0.13-0.68), asthma exacerbations (aFTR: 0.81, 95%CI: 0.70, 0.94), frequent emergency admissions (aFTR:0.21, 95% CI: 0.17-0.25), longer hospital stay (aFTR:0.07, 95% CI: 0.06-0.09), patients with increased burden of comorbidities (aFTR:0.28, 95% CI: 0.22-0.34), obese male sex (aFTR:0.38, 95% CI: 0.15-0.99), SABA overuse (aFTR: 0.61, 95% CI: 0.44-0.84), moderate (aFTR:0.23, 95% CI: 0.21-0.26), and severe asthma (aFTR:0.10, 95% CI: 0.08-0.12). After adjustment, MA ≥0.80 was significantly associated with 83% delayed time-to-COPD diagnosis [i.e. aFTR =1.83, 95%CI: 1.54-2.17 for PDC]. However, asthma severity significantly modifies the effect of MA independent of tobacco smoking history. The targeted intervention aimed to mitigate early diagnosis of COPD may prioritize enhancing medication adherence among asthma patients to prevent frequent exacerbation during follow-up.

Scalable algorithms for semiparametric accelerated failure time models in high dimensions.

Semiparametric accelerated failure time (AFT) models are a useful alternative to Cox proportional hazards models, especially when the assumption of constant hazard ratios is untenable. However, rank-based criteria for fitting AFT models are often nondifferentiable, which poses a computational challenge in high-dimensional settings. In this article, we propose a new alternating direction method of multipliers algorithm for fitting semiparametric AFT models by minimizing a penalized rank-based loss function. Our algorithm scales well in both the number of subjects and number of predictors, and can easily accommodate a wide range of popular penalties. To improve the selection of tuning parameters, we propose a new criterion which avoids some common problems in cross-validation with censored responses. Through extensive simulation studies, we show that our algorithm and software is much faster than existing methods (which can only be applied to special cases), and we show that estimators which minimize a penalized rank-based criterion often outperform alternative estimators which minimize penalized weighted least squares criteria. Application to nine cancer datasets further demonstrates that rank-based estimators of semiparametric AFT models are competitive with estimators assuming proportional hazards in high-dimensional settings, whereas weighted least squares estimators are often not. A software package implementing the algorithm, along with a set of auxiliary functions, is available for download at github.com/ajmolstad/penAFT.