Bayesian designs for phase I-II clinical trials by Ying Yuan, Hoang Q. Nguyen, Peter F. Thall

By Ying Yuan, Hoang Q. Nguyen, Peter F. Thall

Reliably optimizing a brand new therapy in people is a serious first step in scientific assessment because selecting a suboptimal dose or agenda could lead to failure in later trials. even as, if promising preclinical effects don't translate right into a genuine remedy strengthen, you will need to be sure this speedy and terminate the medical review technique to save some assets.

Bayesian Designs for part I–II medical Trials describes how section I–II designs can function a bridge or protecting barrier among preclinical reviews and massive confirmatory medical trials. It illustrates a number of the serious drawbacks with traditional equipment used for early-phase scientific trials and provides quite a few Bayesian designs for human medical trials of latest experimental therapy regimes.

The first chapters reduce the technical language to cause them to obtainable to non-statisticians. those chapters talk about the serious drawbacks of the traditional paradigm used for early-phase scientific trials and clarify the section I–II paradigm for optimizing dose, or extra basic therapy regimes, in line with either efficacy and toxicity. the rest of the ebook covers a wide selection of medical trial methodologies, together with designs to optimize the dose pair of a two-drug mix, together optimize dose and agenda, establish optimum customized doses, optimize novel molecularly specific brokers, and select doses in therapy cycles.

Written by way of learn leaders from the college of Texas MD Anderson melanoma middle, this publication indicates how Bayesian designs for early-phase scientific trials can discover, refine, and optimize new experimental remedies. It emphasizes the significance of basing judgements on either efficacy and toxicity.

Show description

Read or Download Bayesian designs for phase I-II clinical trials PDF

Similar biostatistics books

Basic Pharmacokinetics and Pharmacodynamics: An Integrated Textbook and Computer Simulations

Up-to-date with new chapters and subject matters, this ebook offers a accomplished description of all crucial issues in modern pharmacokinetics and pharmacodynamics. It additionally positive aspects interactive laptop simulations for college kids to scan and detect PK/PD versions in motion. •    Presents the necessities of pharmacokinetics and pharmacodynamics in a transparent and innovative manner•    Helps scholars greater take pleasure in very important innovations and achieve a better realizing of the mechanism of motion of gear by means of reinforcing sensible purposes in either the booklet and the pc modules•    Features interactive machine simulations, on hand on-line via a significant other site at: http://www.

Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating

This booklet presents perception and sensible illustrations on how smooth statistical recommendations and regression equipment will be utilized in scientific prediction difficulties, together with diagnostic and prognostic results. Many advances were made in statistical methods in the direction of final result prediction, yet those thoughts are insufficiently utilized in clinical examine.

A Concise Guide to Statistics

The textual content provides a concise advent into primary options in statistics. bankruptcy 1: brief exposition of chance thought, utilizing normal examples. bankruptcy 2: Estimation in idea and perform, utilizing biologically inspired examples. Maximum-likelihood estimation in lined, together with Fisher details and gear computations.

Permutation Tests in Shape Analysis

Statistical form research is a geometric research from a collection of shapes during which data are measured to explain geometrical houses from comparable shapes or assorted teams, for example, the adaptation among female and male Gorilla cranium shapes, general and pathological bone shapes, and so on. a number of the very important elements of form research are to acquire a degree of distance among shapes, to estimate standard shapes from a (possibly random) pattern and to estimate form variability in a sample[1].

Additional resources for Bayesian designs for phase I-II clinical trials

Example text

Any greedy algorithm carries the risk of getting stuck at a suboptimal action. This is because, due to the play of chance, if a greedy algorithm happens to choose a suboptimal action, it may continue to take that suboptimal action and thus fail to explore other possibilities, including a different action that is truly optimal. By repeatedly taking a suboptimal action, a greedy algorithm may fail to take an optimal action often enough, or at all, and thus fail to obtain the necessary data to learn, statistically, which action is truly optimal.

54, which says that one knows very little about the dose-Toxicity distribution. If, as an alternative data analysis, a logistic regression model πT,j (α, β) = eα+βlog(dj ) 1 + eα+βlog(dj ) is fit to these data to borrow strength between doses, final inferences are improved, but still are not very informative. 1, which gives the posterior mean curve and 95% ci bands from the fitted model. These ci’s are more narrow due to the assumed model, but they still provide little information. 25, there is almost no evidence to distinguish reliably between doses 20 and 30, and almost nothing is known about the risk of Toxicity at dose 40.

Elements of Phase I–II Designs . . . . . . . . . . . . . . . . . Treatment Regimes and Clinical Outcomes . . . . . . . . . . . Sequentially Adaptive Decision Making . . . . . . . . . . . . . Risk–Benefit Trade-Offs . . . . . . . . . . . . . . . . . . . . . Stickiness and Adaptive Randomization . . . . . . . . . . . . . Simulation as a Design Tool . . . . . . . . . .

Download PDF sample

Rated 4.23 of 5 – based on 32 votes