ShortCourses
 
Seven short courses will be given on June 28 and June 29, 2008.


SC1: An Overview of Clinical and Regulatory Statistics
(A 1-day short course, June 28, 2008 8:30 am - 5:10 pm)

Instructors: Drs. Ning Li (FDA), Daphne Lin (FDA), Natiee Ting (Pfizer) and William Wang (Merck)

The growing trend of global clinical drug development demands increasing numbers of biostatisticians across the globe. This course provides an overview of the role of the biostatistician in clinical development of drugs and biopharmaceutical products. It is designed for statisticians and clinical scientists new to the pharmaceutical industry and/or the drug development and regulatory review professionals new to the biostatistics operation. Specific topics include introduction to developing clinical plans, understanding FDA/ICH guidelines and the regulatory review process, developing protocols and statistical analysis plans (SAP), setting up clinical database and analysis-ready datasets, assessing safety and efficacy, conducting interim analyses, and the role of regulatory statistics reviewers and the industry/FDA interactions .

The faculty, which includes statisticians from industry and reviewers from regulatory agency, delivers information and shares their experiences using a combination of interactive sessions and a panel discussion. Throughout the course, case studies in oncology, anti-infective, anti-inflammatory and vaccine therapeutic areas will be used for illustration. Other clinical and statistical experts will also be invited to join the panel discussion at the end.


Back to Program

SC2: Adaptive Designs in Drug Development
(A half-day short course, June 28, 2008 8:30 am - 12:10 pm)

Instructors: Drs. Sue-Jane Wang and H.M. James Hung, Office of Biostatistics, OTS/CDER, U.S. Food and Drug Administration

As the costs increase dramatically, a typical clinical trial carries a high expectation that the trial is able to answer many study questions and subsequently the level of difficulty in conducting the trial rises significantly. Traditional non-adaptive fixed design methodology is therefore often deemed insufficient to achieve the many goals of the trial. The recent advances in adaptive design methodology have been made for evaluation of an experimental treatment, ranging widely from a new look of sample size re-estimation to a mid-term change of statistical decision tree, such as alpha allocation. This short course will give a brief overview of some interesting major advances and present the scenarios where some types of adaptation may be worthy of and needs further exploration. Topics to be covered include: role of adaptive design, learn versus confirm paradigm, sample size re-estimation, adaptive design versus adaptive strategy, adaptive selection of dose, statistical inference issues with adaptive design, logistics issues.


Back to Program

SC3: Non-inferiority Methodology in Clinical Trial
(A half-day short course: June 28, 2008, 1:30 pm - 5:10 pm)

Instructors: Drs. H.M. James Hung and Sue-Jane Wang, Office of Biostatistics, OTS/CDER, U.S. Food and Drug Administration

As a standard of care treatment is available, often ethical considerations do not permit use of a placebo in a randomized clinical trial for assessing the efficacy of an experimental agent. The selected agent is often known as an active control serving as the comparator for the experimental agent in an active controlled non-inferiority clinical trial. This short course is to provide a brief overview of essential design specifications and outline some fundamental issues in design and analysis of non-inferiority trials. Topics to be covered include: study objectives of non-inferiority trial and relevant parameters of primary interest, key assumptions and their implications to study design and statistical analysis, statistical hypotheses, non-inferiority margin, statistical methods for non-inferiority inference, challenges and barriers to the planning of non-inferiority trial.


Back to Program

SC4: Group Sequential Methods for Clinical Trials
(A half-day short course, June 29, 2008, 8:10 am - 12:10 pm)

Instructor: Professor Kyung Mann Kim, University of Wisconsin-Madison

The main objective of this short course is to introduce group sequential methods for clinical trials to practicing statisticians. After reviewing the classical sequential methods for statistical analysis such as sequential probability ratio tests and their modifications, the course will focus on the recent developments in group sequential methods, triangular tests, and stochastic curtailment tests. Emphasis will be on the application of group sequential methods for design and analysis of phase III randomized controlled trials in chronic diseases with failure time as primary endpoint. Applications of group sequential methods will be illustrated using examples from the clinical literature.


Back to Program

SC5: DRUG SAFETY EVALUATION AFTER CLINICAL TRIALS
(A half-day short course, June 29, 2008, 8:30 am - 12:10 pm)

Instructor: Dr. Lawrence Gould, INVESTIGATIONAL RESEARCH, Merck Research Laboratories

Surveillance of drug products in the marketplace continues after regulatory approval, to obtain information unavailable from the limited observations provided by the clinical trials carried out before approval. The surveillance is carried out to identify rare potential toxicities, and previously undetected adverse and beneficial effects that may be uncommon or delayed, i.e., emerging only after extended treatment. Information also is sought regarding patterns of drug use, the effect of drug overdoses, and clinical experience with study drugs in their "natural" environment.

The surveillance can take many forms, including literature review and evaluation of findings from information about drug safety collected after approval. A considerable amount of postmarketing safety information is provided by spontaneous reporting databases that accumulate large numbers of reports of adverse events over time. Postmarketing information also comes from insurance claims databases and databases maintained by consortia such as HMOs.These databases, especially the latter, provide fewer reports but allow the estimation of prevalence and incidence of adverse events because they also provide information about exposure.

Databases can be used to identify many tens of thousands of potential drug-event associations. Determining which of the drug-event associations, represent real reporting associations and which represent random noise can be operationally challenging because the resources available for medical and epidemiologic followup are limited. Data mining tools developed over the past decade are being used increasingly in pharmacovigilance activities.

This short course will provide an overview of pharmacovigilance with an emphasis on considerations that are important to the effective use of data mining technology. Examples of the use of the methods will be presented, along with a considerable emphasis on issues affecting interpretation of findings.


Back to Program

SC6: Introduction to the Economic Evaluation of Pharmaceutical Products
(A half-day short course, June 29, 2008, 1:30 pm - 5:10 pm)

Instructor: Dr. Wen Chen ( Professor, Health Economics Fudan University) and Dr. John Cook (Senior Director, Merck Research Laboratories)

The adoption of new medical treatments has traditionally focused on considerations of safety and efficacy. Today, due primarily to budgetary pressures, health care decision makers are expanding beyond these traditional measures to also evaluate new treatments on the basis of cost and cost-effectiveness. As a result, the collection of data on health care utilization and cost is becoming an important objective in clinical trials. When it is not possible to capture this information directly from a clinical trial, or when the time horizon of interest extends beyond the trial period, pharmacoeconomic models are needed to evaluate the cost-effectiveness of the new treatment.

This course will provide a brief introduction to (1) basic concepts in conducting pharmacoeconomic evaluations, (2) statistical considerations in the design and analysis of economic endpoints from clinical trials, and (3) modeling techniques used to evaluate cost-effectiveness.


Back to Program

SC7: Analysis of Microarray Data With Applications in Pharmacogenomics
(A half-day short course, June 29, 2008, 1:30 pm - 5:10 pm)

Instructor: Dr. Mei-Ling Ting Lee, Distinguished Professor in Biostatistics and Computational Biology, Ohio State University

Text book: Lee, Mei-Ling Ting, (2004). Analysis of Microarray Gene Expression Data, Kluwer Academic Publishers, Boston (now merged with Springer).

The talk will begin with a brief introduction to the usefulness of microarrays, the pros and cons of different types of microarray platforms and data types. We will discuss the inherent variability in microarray data and the need for normalization. Using case studies, I will illustrate statistical methods which can be used in analyzing microarray data, including experimental design, ANOVA, Bayesian methods, multiple testing procedures, permutation tests, nonparametric tests, and power and sample size considerations. Applications to pharmacogenomics will also be discussed.

Course Content
Session 1
  • Introduction to DNA, RNA, Proteins, and Gene Expression
  • Introduction to Microarray Technology
  • Inherent Variability in Array Data
  • Background Noise
  • Transformation and Normalization of Gene Expression Data
  • Case Studies
Session 2
  • Bayesian Models for Microarray Data
  • Experimental Design
  • Two-stage ANOVA Models
  • Multiple Comparisons in Microarray studies
  • Power and Sample Size Considerations
  • Case Studies
Session 3
  • Significant Analysis of Microarrays
  • Permutation Tests
  • Nonparametric Tests
  • Replicated Analysis of Microarray Studies
  • Case Studies
Session 4
  • Unsupervised Clustering Methods:
    Hierarchical clustering
    Self-Organizing Maps
  • Supervised Machine Learning Methods
    Support Vector Machines
    Neural Networks

Back to Program

 
 
   
For general information, contact info@IsBioStat.org