Leilei Zeng

A Multistate Model for Bivariate Interval‐Censored Failure Time Data

SUMMARY Interval-censored life-history data arise when the events of interest are only detectable at periodic assessments. When interest lies in the occurrence of two such events, bivariate-interval censored event time data are obtained. We describe how to fit a four-state Markov model useful for characterizing the association between two interval-censored event times when the assessment times for the two events may be generated by different inspection processes. The approach treats the two events symmetrically and enables one to fit multiplicative intensity models that give estimates of covariate effects as well as relative risks characterizing the association between the two events. An expectation-maximization (EM) algorithm is described for estimation in which the maximization step can be carried out with standard software. The method is illustrated by application to data from a trial of HIV patients where the events are the onset of viral shedding in the blood and urine among individuals infected with cytomegalovirus.

Who is stressed? Comparing cortisol levels between individuals

Cortisol is the most commonly used biomarker to compare physiological stress between individuals. Its use, however, is frequently inappropriate. Basal cortisol production varies markedly between individuals. Yet, in naturalistic studies that variation is often ignored, potentially leading to important biases.

Transition Models for Multivariate Longitudinal Binary Data

In many settings with longitudinal binary data, interest lies in modeling covariate effects on transition probabilities of an underlying stochastic process. When data from two or more processes are available, the scientific focus may be on the degree to which changes in one process are associated with changes in another process. Analysis based on independent Markov models permits separate examination of covariate effects on the transition probabilities for each process, but no insight into between-process associations is obtained. We propose a method of estimation and inference based on joint transitional models for multivariate longitudinal binary data using GEE2 or alternating logistic regression that allows modeling of covariate effects on marginal transition probabilities as well as the association parameters. Consistent estimates of regression coefficients and association parameters are obtained, and efficiency gains for the parameters governing the marginal transition probabilities are realized when the association between processes is strong. Extensions to deal with multivariate longitudinal categorical data are indicated.

A longitudinal evaluation of the relationship between first morning urinary and salivary cortisol

Cortisol is one of the most frequently used stress biomarkers in humans. Urine and saliva are the matrices of choice to longitudinally monitor cortisol levels. Salivary and urinary cortisol are often discussed as though they provide similar information. However, the relationship between “free” cortisol levels in urine (nonconjugated) and saliva (non‐protein‐bound) has yet to be properly evaluated using naturalistic designs.

The association between diurnal variation of optic nerve head topography and intraocular pressure and ocular perfusion pressure in untreated primary open-angle glaucoma.

PurposeTo investigate the hypotheses that the topography of the optic nerve head (ONH) significantly changes during the day in untreated primary open-angle glaucoma (uPOAG) and healthy volunteers; and that there is a significant association with diurnal variations of intraocular pressure (IOP) and mean ocular perfusion pressure (MOPP). MethodsFourteen uPOAG and 14 age-matched normals were included. IOP, blood pressure, and ONH topography were measured between 7:00 AM and 10:00 PM. MOPP was calculated. A mixed-effect repeated measures analysis was done. Variance component analysis was done for glaucoma and normal groups separately based on the mixed-effect models. ResultsThe cup volume, rim volume, and cup shape measure in the temporal (T) and temporal-inferior (TI) sectors were significantly different between the 2 groups (P<0.05). The highest variance component was owing to “patients” whereas “time” had the smallest contributed percentage. Cup volume (T and TI) and reference height (RH) showed a significant (P<0.001) diurnal change in uPOAG. Rim volume (T and TI) showed a significant diurnal change in normals (P⩽0.01). There was no significant (P>0.05) association between the change in IOP, MOPP, and ONH topography in either group. There was a significant association between cup volume and RH in both groups (P<0.001, global and T). There was a significant association between MOPP and RH in both groups (P<0.001). ConclusionThe ONH topography significantly changed during the day in both groups. The change in ONH topography was associated with the change in reference height, which in turn was associated with MOPP. These findings suggest that the time of the day and the level of perfusion pressure should be considered when evaluating ONH topography using the HRT. Repeated measures are recommended when evaluating ONH topography.

Bias in progression‐free survival analysis due to intermittent assessment of progression

Cancer clinical trials are routinely designed to assess the effect of treatment on disease progression and death, often in terms of a composite endpoint called progression‐free survival. When progression status is known only at periodic assessment times, the progression time is interval censored, and complications arise in the analysis of progression‐free survival. Despite the advances in methods for dealing with interval‐censored data, naive methods such as right‐endpoint imputation are widely adopted in this setting. We examine the asymptotic and empirical properties of estimators of the marginal progression‐free survival functions and associated treatment effects under this scheme. Specifically, we explore the determinants of the asymptotic bias and point out that there is typically a loss in power of tests for treatment effects. Copyright

Regression analysis with a misclassified covariate from a current status observation scheme.

Naive use of misclassified covariates leads to inconsistent estimators of covariate effects in regression models. A variety of methods have been proposed to address this problem including likelihood, pseudo-likelihood, estimating equation methods, and Bayesian methods, with all of these methods typically requiring either internal or external validation samples or replication studies. We consider a problem arising from a series of orthopedic studies in which interest lies in examining the effect of a short-term serological response and other covariates on the risk of developing a longer term thrombotic condition called deep vein thrombosis. The serological response is an indicator of whether the patient developed antibodies following exposure to an antithrombotic drug, but the seroconversion status of patients is only available at the time of a blood sample taken upon the discharge from hospital. The seroconversion time is therefore subject to a current status observation scheme, or Case I interval censoring, and subjects tested before seroconversion are misclassified as nonseroconverters. We develop a likelihood-based approach for fitting regression models that accounts for misclassification of the seroconversion status due to early testing using parametric and nonparametric estimates of the seroconversion time distribution. The method is shown to reduce the bias resulting from naive analyses in simulation studies and an application to the data from the orthopedic studies provides further illustration.

Design of cancer trials based on progression-free survival with intermittent assessment: Design of cancer trials based on progression-free survival with intermittent assessment

Therapeutic advances in cancer mean that it is now impractical to performed phase III randomized trials evaluating experimental treatments on the basis of overall survival. As a result, the composite endpoint of progression-free survival has been routinely adopted in recent years as it is viewed as enabling a more timely and cost-effective approach to assessing the clinical benefit of novel interventions. This article considers design of cancer trials directed at the evaluation of treatment effects on progression-free survival. In particular, we derive sample size criteria based on an illness-death model that considers cancer progression and death jointly while accounting for the fact that progression is assessed only intermittently. An alternative approach to design is also considered in which the sample size is derived based on a misspecified Cox model, which uses the documented time of progression as the progression time rather than dealing with the interval censoring. Simulation studies show the validity of the proposed methods.

Tracing studies in cohorts with attrition: Selection models for efficient sampling

Cohort studies of chronic diseases involve recruitment and longitudinal follow-up of affected individuals with a view to studying the effect of risk factors on disease progression and death. When the time to withdrawal from the cohort is conditionally independent of the disease process the primary consequence is a loss of information on the parameters of interest. This loss can sometimes be mitigated through the conduct of tracing studies in which a subsample of those lost to follow up are contacted and some information is obtained on their disease and survival status. We describe the use of selection models to sample individuals for tracing who will yield more efficient estimators than those obtained by simple random sampling. Efficient sampling schemes featuring cost constraints are also developed and shown to perform well. An application to data from the University of Toronto Psoriatic Arthritis Cohort illustrates how to apply the method in a real setting.