Estimation of disease prevalence, true positive rate, and false positive rate of two screening tests when disease verification is applied on only screen-positives: a hierarchical model using multi-center data.

OBJECTIVES: A model is proposed to estimate and compare cervical cancer screening test properties for third world populations when only subjects with a positive screen receive the gold standard test. Two fallible screening tests are compared, VIA and VILI. METHODS: We extend the model of Berry et al. [1] to the multi-site case in order to pool information across sites and form better estimates for prevalences of cervical cancer, the true positive rates (TPRs), and false positive rates (FPRs). For 10 centers in five African countries and India involving more than 52,000 women, Bayesian methods were applied when gold standard results for subjects who screened negative on both tests were treated as missing. The Bayesian methods employed suitably correct for the missing screen negative subjects. The study included gold standard verification for all cases, making it possible to validate model-based estimation of accuracy using only outcomes of women with positive VIA or VILI result (ignoring verification of double negative screening test results) with the observed full data outcomes. RESULTS: Across the sites, estimates for the sensitivity of VIA ranged from 0.792 to 0.917 while for VILI sensitivities ranged from 0.929 to 0.977. False positive estimates ranged from 0.056 to 0.256 for VIA and 0.085 to 0.269 for VILI. The pooled estimates for the TPR of VIA and VILI are 0.871 and 0.968, respectively, compared to the full data values of 0.816 and 0.918. Similarly, the pooled estimates for the FPR of VIA and VILI are 0.134 and 0.146, respectively, compared to the full data values of 0.144 and 0.146. Globally, we found VILI had a statistically significant higher sensitivity but no statistical difference for the false positive rates could be determined. CONCLUSION: Hierarchical Bayesian methods provide a straight forward approach to estimate screening test properties, prevalences, and to perform comparisons for screening studies where screen negative subjects do not receive the gold standard test. The hierarchical model with random effects used to analyze the sites simultaneously resulted in improved estimates compared to the single-site analyses with improved TPR estimates and nearly identical FPR estimates to the full data outcomes. Furthermore, higher TPRs but similar FPRs were observed for VILI compared to VIA.

Bayesian inference of risk ratio of two proportions using a double sampling scheme.

We consider Bayesian point and interval estimation for a risk ratio of two proportion parameters using two independent samples of binary data subject to misclassification. In order to obtain model identifiability, we apply a double sampling scheme. For the identifiable model, we propose a Bayesian method for statistical inference for a two proportion risk ratio. Specifically, we derive an easy-to-implement closed-form sampling algorithm to draw from the posterior distribution of interest. We demonstrate the efficiency of our algorithm for Bayesian inference via Monte Carlo simulation studies and using a real data example.

Bayesian sample-size determination for two independent Poisson rates.

Because of the high cost and time constraints for clinical trials, researchers often need to determine the smallest sample size that provides accurate inferences for a parameter of interest. Although most experimenters have employed frequentist sample-size determination methods, the Bayesian paradigm offers a wide variety of sample-size determination methodologies. Bayesian sample-size determination methods are becoming increasingly more popular in clinical trials because of their flexibility and easy interpretation inferences. Recently, Bayesian approaches have been used to determine the sample size of a single Poisson rate parameter in a clinical trial setting. In this paper, we extend these results to the comparison of two Poisson rates and develop methods for sample-size determination for hypothesis testing in a Bayesian context. We have created functions in R to determine the parameters for the conjugate gamma prior and calculate the sample size for the average length criterion and average power methods. We also provide two examples that implement our sample-size determination methods using clinical data.

Performance and sample size requirements of Bayesian methods for binary outcomes in fixed-dose combination drug studies.

We develop a Bayesian analysis for the study of fixed-dose combinations of two or more drugs. The approach described here does not require knowledge of the dose-response relationships of the components or large sample approximations. We provide a procedure to estimate sample size in this context. In addition, we explore the performance of the Bayesian procedure in situations where existing methods are known to perform poorly.

A Bayesian approach to adjust for diagnostic misclassification between two mortality causes in Poisson regression.

Response misclassification of counted data biases and understates the uncertainty of parameter estimators in Poisson regression models. To correct these problems, researchers have devised classical procedures that rely on asymptotic distribution results and supplemental validation data in order to estimate unknown misclassification parameters. We derive a new Bayesian Poisson regression procedure that accounts and corrects for misclassification for a count variable with two categories. Under the Bayesian paradigm, one can use validation data, expert opinion, or a combination of these two approaches to correct for the consequences of misclassification. The Bayesian procedure proposed here yields an operationally effective way to correct and account for misclassification effects in Poisson count regression models. We demonstrate the performance of the model in a simulation study. Additionally, we analyze two real-data examples and compare our new Bayesian inference method that adjusts for misclassification with a similar analysis that ignores misclassification.

Bayesian estimation of intervention effect with pre- and post-misclassified binomial data.

We consider studies in which an enrolled subject tests positive on a fallible test. After an intervention, disease status is re-diagnosed with the same fallible instrument. Potential misclassification in the diagnostic test causes regression to the mean that biases inferences about the true intervention effect. The existing likelihood approach suffers in situations where either sensitivity or specificity is near 1. In such cases, common in many diagnostic tests, confidence interval coverage can often be below nominal for the likelihood approach. Another potential drawback of the maximum likelihood estimator (MLE) method is that it requires validation data to eliminate identification problems. We propose a Bayesian approach that offers improved performance in general, but substantially better performance than the MLE method in the realistic case of a highly accurate diagnostic test. We obtain this superior performance using no more information than that employed in the likelihood method. Our approach is also more flexible, doing without validation data if necessary, but accommodating multiple sources of information, if available, thereby systematically eliminating identification problems. We show via a simulation study that our Bayesian approach outperforms the MLE method, especially when the diagnostic test has high sensitivity, specificity, or both. We also consider a real data example for which the diagnostic test specificity is close to 1 (false positive probability close to 0).

Bayesian inference for a correlated 2 x 2 table with a structural zero.

We develop a new Bayesian approach to interval estimation for both the risk difference and the risk ratio for a 2 x 2 table with a structural zero using Markov chain Monte Carlo (MCMC) methods. We also derive a normal approximation for the risk difference and a gamma approximation for the risk ratio. We then compare the coverage and interval width of our new intervals to the score-based intervals over various parameter and sample-size configurations. Finally, we consider a Bayesian method for sample-size determination.

Bayesian sample-size determination for inference on two binomial populations with no gold standard classifier.

We consider the impact of test properties on the required sample size for the Bayesian design problem for comparing two proportions with error-prone data. Specifically, we examine four cases: a single diagnostic test and two independent diagnostic tests, both when the test properties are identical across populations and when they differ. Interval-based and moment-based sample-size determination criteria are contrasted using Monte Carlo simulation methods. We consider an application in which Strongyloides infections are compared in two populations.