Pharmaceutical Statistics最新文献

Preclinical studies are broad and can encompass cellular research, animal trials, and small human trials. Preclinical studies tend to be exploratory and have smaller datasets that often consist of biomarker data. Logistic regression is typically the model of choice for modeling a binary outcome with explanatory variables such as genetic, imaging, and clinical data. Small preclinical studies can have challenging data that may include a complete separation or quasi-complete separation issue that will result in logistic regression inflated coefficient estimates and standard errors. Penalized regression approaches such as Firth's logistic regression are a solution to reduce the bias in the estimates. In this tutorial, a number of examples with separation (complete or quasi-complete) are illustrated and the results from both logistic regression and Firth's logistic regression are compared to demonstrate the inflated estimates from the standard logistic regression model and bias-reduction of the estimates from the penalized Firth's approach. R code and datasets are provided in the supplement.

The duration of response (DoR) is defined as the time from the onset of response to treatment up to progression of disease or death due to any reason, whichever occurs earlier. The expected DoR could be a suitable estimand to measure the efficacy of a treatment but is in practice difficult to estimate, since patients' follow-up times are often right-censored. Instead, the restricted mean duration of response (RMDoR) is often used. The RMDoR in a time $\tau$ is equal to the expected DoR restricted to the interval $\left(0,\tau \right)$ . In this paper, we consider the behaviour of the RMDoR as a function of $\tau$ and its suitability as a measure to quantify the efficacy of a treatment. Besides, we focus on the estimation of the RMDoR. In oncology, the events response to treatment and progression of disease are typically detected through time-scheduled scans and are therefore interval-censored. We describe multiple estimators for the RMDoR that deal with the interval censoring in different ways and study the performance of these estimators in single arm trials and randomised controlled trials.

Clinical endpoints based on repeated measurements arise in many clinical research studies, and require specialized methods for sample size and power calculations. In clinical trials that measure counts over time, such as bleeding events in hemophilia, the dispersion of their distributions might change upon treatment and the measurements might be correlated. The generalized estimating equations (GEE) approach has been widely used for modeling correlated data and comparing rates. In this paper, we investigate the properties of GEE when applied to count outcomes with changes in dispersion. We derive general closed-form formulas to estimate sample size when the dispersion parameters and distributions of count data vary across two correlated measurements based on the GEE approach. These formulas allow for power and sample size estimation for intra-participant comparison of rates before and after an intervention, randomized controlled trials with equal allocation, or matched pairs designs. These formulas are derived for the following distributions: Poisson, negative binomial, zero-inflated Poisson, and zero-inflated negative binomial distributions, and do not assume that measurements before and after an intervention come from the same distribution. Furthermore, we propose modified methods for estimating sample size and confidence intervals for the negative binomial distributions to overcome Type I error inflation, which is especially useful for large changes in the negative binomial dispersion parameter. We perform simulations, and evaluate the performance of the empirical power and Type I error over a range of parameters. Applications and R functions implementing the methods are also provided.

In oncology, Phase II studies are crucial for clinical development plans as such studies identify potent agents with sufficient activity to continue development in the subsequent Phase III trials. Traditionally, Phase II studies are single-arm studies, with the primary endpoint being short-term treatment efficacy. However, drug safety is also an important consideration. In the context of such multiple-outcome designs, predictive probability-based Bayesian monitoring strategies have been developed to assess whether a clinical trial will provide enough evidence to continue with a Phase III study at the scheduled end of the trial. Therefore, we propose a new simple index vector to summarize the results that cannot be captured by existing strategies. Specifically, we define the worst and most promising situations for the potential effect of a treatment, then use the proposed index vector to measure the deviation between the two situations. Finally, simulation studies are performed to evaluate the operating characteristics of the design. The obtained results demonstrate that the proposed method makes appropriate interim go/no-go decisions.

Chemistry, manufacturing, and control (CMC) statisticians play a key role in the development and lifecycle management of pharmaceutical and biological products, working with their non-statistician partners to manage product quality. Information used to make quality decisions comes from studies, where success is facilitated through adherence to the scientific method. This is carried out in four steps: (1) an objective, (2) design, (3) conduct, and (4) analysis. Careful consideration of each step helps to ensure that a study conclusion and associated decision is correct. This can be a development decision related to the validity of an assay or a quality decision like conformance to specifications. Importantly, all decisions are made with risk. Conventional statistical risks such as Type 1 and Type 2 errors can be coupled with associated impacts to manage patient value as well as development and commercial costs. The CMC statistician brings focus on managing risk across the steps of the scientific method, leading to optimal product development and robust supply of life saving drugs and biologicals.

In compound hit screening, an important chemical property is target binding affinity, represented by a parameter ΔΔG. You can measure ΔΔG experimentally (ΔΔG_exp) or by calculations via simulations (ΔΔG_calc). Because it is expensive to measure ΔΔG experimentally, only a few experimental runs are performed. The relationship between the experimental data and the calculated results is a straight line with a slope that is not necessarily one. The goal is to estimate the linear relationship between ΔΔG_exp and ΔΔG_calc by fitting a Deming regression model that will be used to predict future values of ΔΔG_true based on the obtained ΔΔG_calc.

Stochastic curtailment tests for Phase II two-arm trials with time-to-event end points are traditionally performed using the log-rank test. Recent advances in designing time-to-event trials have utilized the Weibull distribution with a known shape parameter estimated from historical studies. As sample size calculations depend on the value of this shape parameter, these methods either cannot be used or likely underperform/overperform when the natural variation around the point estimate is ignored. We demonstrate that when the magnitude of the Weibull shape parameters changes, unblinded interim information on the shape of the survival curves can be useful to enrich the final analysis for reestimation of the sample size. For such scenarios, we propose two Bayesian solutions to estimate the natural variations of the Weibull shape parameter. We implement these approaches under the framework of the newly proposed relative time method that allows nonproportional hazards and nonproportional time. We also demonstrate the sample size reestimation for the relative time method using three different approaches (internal pilot study approach, conditional power, and predictive power approach) at the interim stage of the trial. We demonstrate our methods using a hypothetical example and provide insights regarding the practical constraints for the proposed methods.

Combination treatments have been of increasing importance in drug development across therapeutic areas to improve treatment response, minimize the development of resistance, and/or minimize adverse events. Pre-clinical in-vitro combination experiments aim to explore the potential of such drug combinations during drug discovery by comparing the observed effect of the combination with the expected treatment effect under the assumption of no interaction (i.e., null model). This tutorial will address important design aspects of such experiments to allow proper statistical evaluation. Additionally, it will highlight the Biochemically Intuitive Generalized Loewe methodology (BIGL R package available on CRAN) to statistically detect deviations from the expectation under different null models. A clear advantage of the methodology is the quantification of the effect sizes, together with confidence interval while controlling the directional false coverage rate. Finally, a case study will showcase the workflow in analyzing combination experiments.

Predictive models (a.k.a. machine learning models) are ubiquitous in all stages of drug research, safety, development, manufacturing, and marketing. The results of these models are used inside and outside of pharmaceutical companies for the purpose of understanding scientific processes and for predicting characteristics of new samples or patients. While there are many resources that describe such models, there are few that explain how to develop a robust model that extracts the highest possible performance from the available data, especially in support of pharmaceutical applications. This tutorial will describe pitfalls and best practices for developing and validating predictive models with a specific application to a monitoring a pharmaceutical manufacturing process. The pitfalls and best practices will be highlighted to call attention to specific points that are not generally discussed in other resources.

Animal models are used in cancer pre-clinical research to identify drug targets, select compound candidates for clinical trials, determine optimal drug dosages, identify biomarkers, and ensure compound safety. This tutorial aims to provide an overview of study design and data analysis from animal studies, focusing on tumor growth inhibition (TGI) studies used for prioritization of anticancer compounds. Some of the experimental design aspects discussed here include the selection of the appropriate biological models, the choice of endpoints to be used for the assessment of anticancer activity (tumor volumes, tumor growth rates, events, or categorical endpoints), considerations on measurement errors and potential biases related to this type of study, sample size estimation, and discussions on missing data handling. The tutorial also reviews the statistical analyses employed in TGI studies, considering both continuous endpoints collected at single time-point and continuous endpoints collected longitudinally over multiple time-points. Additionally, time-to-event analysis is discussed for studies focusing on event occurrences such as animal deaths or tumor size reaching a certain threshold. Furthermore, for TGI studies involving categorical endpoints, statistical methodology is outlined to compare outcomes among treatment groups effectively. Lastly, this tutorial also discusses analysis for assessing drug combination synergy in TGI studies, which involves combining treatments to enhance overall treatment efficacy. The tutorial also includes R sample scripts to help users to perform relevant data analysis of this topic.