Video-on-Demand Library


Collection
Keyword or phrase

Topic

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

12 March 2019

An interesting webinar with three speakers looking at how pharmaceutical statisticians can engage with their commercial and other business teams. Camilo Zapata will introduce the field of “business analytics” in the context of pharmaceuticals, Helena Baptista will talk about how we can measure the effectiveness of our communications and Lucy Frith will speak about communicating efficacy data in a manner appropriate for health care professionals.

Read more...

Business analytics is the “discipline” in charge of identifying and leveraging meaningful patterns in data to drive or inform business decisions. It is multidisciplinary in nature as it operates at the intersection between mathematics/statistics, computer science and management. In this talk we will discuss how these three areas converge to deliver impactful results and share some relevant examples. We will also talk about what characteristics an organization requires in order to leverage this discipline as in the business world the ability to impact decisions is not only determined by the quality of the analyses, but also the robustness of the processes, the skills of the decision makers and the approachability of the results. We have been measuring the efficacy and safety of our medicines for a long time. What are we doing to measure the efficacy of our promotional strategies? Developing great medicines is key, but if we fail to let the scientific community know when and why they should use our products, patients that would benefit the most will hardly get access to them. We need to provide directions to the marketing teams on how, when and how often to reach the interested health care providers. On top, in Europe, we need to do that with limited access to data. We will discuss what we can do and where do we have the biggest challenges. Working with a commercial organisation provides a varied array of tasks that often need complex analyses explained in a very concise but transparent way. This can lead to re-use of study data to present the results in a manner that meets the specific needs of different external groups such as health care professional (HCPs). Two such examples will be presented here. Firstly, overlaying the costs of treatments and patient care onto patient outcomes to support discussions with payer groups. Secondly, using Markov Chain modelling to utilise long-term data and provide Health care professionals a presentation of the data that aligns to the probability of a patient changing health status in a given period of time. To give further context to how these presentations of data could be used, such work is reviewed using data collected in a traditional efficacy study and in a pragmatic effectiveness situation.

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

19 February 2019

Prof. Malcolm Macleod - Across a range of scientific disciplines, concerns have been raised about the reproducibility of research findings. This has generally been a bad thing. Certainly, some of the failure to replicate key findings is due to poor experimental design, underpowered experiments and poor reporting of neutral or negative studies or inconvenient outcomes. To the extent that these problems might be addresses, they represent an opportunity for improvement, an opportunity to reduce research waste. However, in other situations it appears that the failure to replicate may have been due to the influence of some latent nuisance variable, present in one lab but not another, which had a biological effect on the phenomenon being tested. Understanding better the nature of these variables, and how their influence is made manifest, provides opportunities for deeper biological understanding. Professor Macleod discuss in this webinar issues of research waste; of replication; and of how these issues might be harnessed to improve research.

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Related Documents

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Chrissie Fletcher - The key themes and topics raised during the public consultation of the ICH E9 addendum will be presented. A summary of the E9 working group discussion of the key aspects raised during public consultation and an update of how the E9 working group are trying to address the comments in the final E9 addendum will be provided.

Read more...

The draft ICH E9(R1) and addendum to E9 incorporating a new framework on estimands and sensitivity analyses in clinical trials was released for public consultation in the first region at the end of August 2017 and the public consultation ended in the last region by the end of April 2018.  The ICH E9 working group met in June 2018 to review the 1200+ comments that were submitted.  The ICH E9 addendum and E9(R1) is scheduled to reach step 4 and sign-off by all the ICH regions in June 2019. 

The key themes and topics raised during the public consultation of the ICH E9 addendum will be presented.  A summary of the E9 working group discussion of the key aspects raised during public consultation and an update of how the E9 working group are trying to address the comments in the final E9 addendum will be provided.

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Anja Schiel - In August 2017 the ‘ICH E9 (R1) Addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials’ was released for consultation and has stirred discussion and excitement, mainly in the regulatory world.

Read more...

In August 2017 the ‘ICH E9 (R1) Addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials’ was released for consultation and has stirred discussion and excitement, mainly in the regulatory world. But, what does this new framework offer to other stakeholders? The uptake of new concepts into health technology assessment is notoriously difficult because there are fundamental differences in the evidence requirements for establishing risk-benefit and those for relative effectiveness. The Estimand framework offers new possibilities to allow studies to be designed with both perspectives in mind, wherever possible. To design studies based on the Estimand concept requires a wider communication between the different specialists involved in drug development, from pharmacologists to clinical experts and statisticians. However, this dialogue should in fact be expanded all the way to the health economists to fully harness the potential of this new framework.

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Evgeny Degtyarev - Marked by the recent approval of the first chimeric antigen receptor T cell (CAR-T) therapies, these autologous therapies provided patients with new options to fight cancer. Because the CAR-T treatment strategy involves personalized manufacturing before patients can receive the final product, the scientific objective and its associated estimand must be carefully thought through to allow appropriate interpretation of study results.

Read more...

Marked by the recent approval of the first chimeric antigen receptor T cell (CAR-T) therapies, these autologous therapies provided patients with new options to fight cancer. Unique challenges arises in the design and analysis of randomized studies involving autologous CAR-T therapies. Because the CAR-T treatment strategy involves personalized manufacturing before patients can receive the final product, the scientific objective and its associated estimand must be carefully thought through to allow appropriate interpretation of study results. Different testing procedures and estimation methods will be discussed in a case study of Phase 3 clinical trial.

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Michael O’Kelly - Randomisation can be thought of as providing “a ‘reasoned basis’ of testing the null hypothesis of no effect without resort to distributional assumptions such as normality” (Fisher); and indeed randomisation has been accepted as providing as close to causal inference as was needed for the approval of new treatments. However, clinical triallists are now seeing that, over the time of follow-up, intercurrent events (ICEs) result in changes to treatment.

Read more...

Randomisation can be thought of as providing “a ‘reasoned basis’ of testing the null hypothesis of no effect without resort to distributional assumptions such as normality” (Fisher); and indeed randomisation has been accepted as providing as close to causal inference as was needed for the approval of new treatments. However, clinical triallists are now seeing that, over the time of follow-up, intercurrent events (ICEs) result in changes to treatment. Because of this, the planned trial of a randomized treatment regimen can morph into no more than a survey whose only inference from randomisation is confined to the mere act of assigning a plan of treatment, a survey whose inference about the treatment regimen itself loses much of its credibility because those ICEs constitute non-randomized changes and distortions of the regimen to be tested. This presentation tries to convey in a non-technical manner the idea of causal inference and how it can work and be of use in clinical trials, making at least a gesture towards inference about outcomes as actually planned. Noting the overlap with missing data research, the presentation then shows a detailed example of the use of one approach to causal inference for an outcome censored by death. From the example it may be concluded that, while causal inference is probably invaluable for many clinical trial designs including the example presented, results from causal inference have their own limitations and will often need to be interpreted alongside other results, even if the other results are more open to bias than those from causal inference.  

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Ian White - This talk is about causal inference and estimands from the perspective of DAGs (directed acyclic graphs), which are widely used for causal inference in observational studies.

Read more...

This talk is about causal inference and estimands from the perspective of DAGs (directed acyclic graphs), which are widely used for causal inference in observational studies. DAGs allow complex statistical issues to be represented pictorially yet still rigorously. Ian briefly describes the ideas of DAGs, then draws suitable DAGs for randomised trials with non-randomised treatment changes and uses them to discuss some key estimands and how these may be estimated. The talk is conceptual rather than mathematical, and points to types of approach rather than specific approaches.

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Related Documents

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Stephen Burgess - Mendelian randomization is a technique for assessing the causal role of a modifiable risk factor on a disease outcome using genetic data.

Read more...

Mendelian randomization is a technique for assessing the causal role of a modifiable risk factor on a disease outcome using genetic data. If genetic variants associated with the risk factor are also associated with the outcome, this increases the plausibility that the risk factor is a causal determinant of the outcome. However, if the genetic variants in the analysis do not have a specific biological link to the risk factor, then causal claims can be spurious. Recent advances in genome-wide association studies and the increasing availability of publicly available summary data on associations of genetic variants with risk factors and disease outcomes in large sample sizes have enabled powerful Mendelian randomization analyses to be performed relatively quickly and simply.

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Oliver Keene - The talk will discuss the application of different strategies for intercurrent events in the non-inferiority setting and what additional comparisons of intercurrent events will be helpful.

Read more...

The estimand framework described in the draft addendum to the ICH E9 regulatory guideline has led to a reappraisal of non-inferiority trials. Currently, these trials often make use of a Per Protocol Population where subjects who violate the protocol are excluded. In the estimands framework, protocol violations after randomisation can be seen as intercurrent events and subjects who do not fulfil inclusion/exclusion criteria can potentially be excluded based on the population of interest. Therefore, the role of a Per Protocol Population is substantially diminished or eliminated entirely.
The strategy to be employed for intercurrent events such as discontinuation of randomised treatment in the non-inferiority setting has not been established yet.  For example, some statisticians favour use of a hypothetical strategy for key intercurrent events, while others believe a treatment policy strategy provides more robust estimation. This talk will use a case study of a trial in COPD to illustrate how to implement the estimands framework to a non-inferiority trial.  

The talk will discuss the application of different strategies for intercurrent events in the non-inferiority setting and what additional comparisons of intercurrent events will be helpful.  

Related Videos

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

Part of Collection(s)

Topic(s)


This content is restricted to members of PSI. If you are already a member please login. To join PSI or to see all the benefits of membership click here.

29 January 2019

Yolanda Barbachano, Chrissie Fletcher, Anja Schiel, Evgeny Degtyarev, Michael O’Kelly, Oliver Keene Panel Discussion from the one day meeting.

Part of Collection(s)

Topic(s)


Page: