Video-on-Demand Library


Collection
Keyword or phrase

Topic

02 June 2021

You will be guided through a case study (CheckMate 037) and interactively deepen the knowledge to gain hands-on experience in developing estimands. You will be introduced to the background and disease context of the case study, the concept of an estimand, and important clinical events (increased dropout rate and crossover therapy) that occurred in the trial and affected interpretation of the results. Using non-technical language and clear graphical presentation of the concepts, you will experience how the estimand framework provides a common language to describe the diversity of patient journeys and why it is important to address the right question in clinical trials.

Read more...

You will be guided through a case study (CheckMate 037) and interactively deepen the knowledge to gain hands-on experience in developing estimands. You will be introduced to the background and disease context of the case study, the concept of an estimand, and important clinical events (increased dropout rate and crossover therapy) that occurred in the trial and affected interpretation of the results. Using non-technical language and clear graphical presentation of the concepts, you will experience how the estimand framework provides a common language to describe the diversity of patient journeys and why it is important to address the right question in clinical trials. Target audience (no prior knowledge in oncology or of estimands required): Clinicians, Investigators, Regulatory Experts, Medical Writers, Ethics Committees, Statisticians.

The targeted learning outcomes are as follows: - Recognize the benefits of following the estimand framework (ICH E9 (R1) addendum) in the context of a clinical trial, in order to: - have a common language to describe the diversity of patient journeys - address the right question in clinical trials - Be able to construct an estimand, including identification of relevant intercurrent events and application of relevant strategies to address them - Gain insights from a cross-industry international working group on estimands in oncology Presented by members of the Estimands in Oncology special interest group www.oncoestimand.org 

25 May 2021

The objective of this PSI webinar is to enable practical interaction among clinical statisticians actively working in oncology and those interested to work in this area. The format of this meeting specifically facilitates these interactions, by balancing equally time dedicated to short talks covering a broad range of relevant topics and to Q&A.​

Read more...

Presented by Rachel Hodge (AstraZeneca), Thomas Jaki (MRC Biostatistics Unit), Archan Bhattacharya (Janssen), Nigel Stallard (University of Warwick) and Emma Clark (Roche).

Effective treatment, early detection and prevention of cancer remain fundamental challenges to current clinical research. Discovering and developing successful oncology treatments requires design and execution of an increasing variety of clinical studies, calling for a commensurate range of fit-for-purpose statistical methods. Clinical statisticians working in oncology are thus exposed to a flow of evolving objectives, endpoints, measurement technologies, methodological and operational challenges. The objective of this PSI webinar is to enable practical interaction among clinical statisticians actively working in oncology and those interested to work in this area. The format of this meeting specifically facilitates these interactions, by balancing equally time dedicated to short talks covering a broad range of relevant topics and to Q&A.
This webinar was sponsored by Janssen R&D.

19 May 2021

Presented by Mine Çetinkaya-Rundel, in this talk we'll introduce the Grammar of Graphics, which allows you to compose graphs by combining independent components, and the implementation of this theory in R -- the ggplot2 package. We will describe the basics of building plots with ggplot2 and touch on a few approaches for customizing the plots. We will also highlight a few packages that are built to supplement ggplot2.

Read more...

Presented by Mine Çetinkaya-Rundel, in this talk we'll introduce the Grammar of Graphics, which allows you to compose graphs by combining independent components, and the implementation of this theory in R -- the ggplot2 package. We will describe the basics of building plots with ggplot2 and touch on a few approaches for customizing the plots. We will also highlight a few packages that are built to supplement ggplot2.

Key learnings include: - Fundamentals of the theory of the Grammar of Graphics - Basics of building plots with ggplot2, layer by layer - Customising plots with functionality that comes with the ggplot2 package as well as supplemented by other packages. To access the slides from this presentation, please visit: http://bit.ly/ggplot2-vissig

12 May 2021

Lorenz Uhlmann presents the visualisation proposals for sustained response. The challenge was to display the timing of response and how this response was sustained over time. This was approached by showing individual as well as summary data. All visualisations are available on the Wonderful Wednesday blog.

Read more...

Lorenz Uhlmann presents the visualisation proposals for sustained response. The challenge was to display the timing of response and how this response was sustained over time. This was approached by showing individual as well as summary data. All visualisations are available on the Wonderful Wednesday blog.

On the individual data level a lasagna plot is suitable to clearly show how quick the response was obtained and if it was sustained. Intelligent sorting supports the visual impression. The interactive bar chart allows for treatment comparison on summarised data. A complete new approach combines trajectory clustering with a set of displays to describe the clusters. The next challenge is on vasculitis data. How can visualisation help to explore the effectiveness of the treatment across a range of different clinical outcomes?

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Alexander Schacht, Mark Baillie, Daniel Saure, Zachary Skrivanek, Lorenz Uhlmann, Rachel Phillips, Markus Vogler, David Carr, Steve Mallett, Abi Williams, Julia Igel, Gakava Lovemore, Katie Murphy, Rhys Warham, Sara Zari, Irene de la Torre Arenas.

05 May 2021

Incomplete datasets due to missing data is an issue that has been, and will be, around for a long time. At this meeting we will present the evolution of missing data approaches, looking at how they have been handled in the past, the current established missing data approaches and the impact of the new ICH E9 R1 addendum on the handling of missing data, focussing in particular on the treatment policy estimand.

Read more...

David Wright (AstraZeneca), James Bell (Elderbrook solutions GmbH), Michael O’Kelly (IQVIA), Daniel Bratton (GSK)

Incomplete datasets due to missing data is an issue that has been, and will be, around for a long time. At this meeting we will present the evolution of missing data approaches, looking at how they have been handled in the past, the current established missing data approaches and the impact of the new ICH E9 R1 addendum on the handling of missing data, focussing in particular on the treatment policy estimand.

David Wright (AstraZeneca) Aligning how subjects with missing data due to study discontinuation are handled in the primary analysis with the primary estimand. James Bell (Elderbrook solutions GmbH) The Practicalities of Treatment Policy Estimation Michael O’Kelly (IQVIA) Even a “treatment policy” estimand may have missing data: how can we take account of this? Daniel Bratton (GSK) Treatment policy estimands for recurrent event data using data collected after cessation of randomised treatment. Panel discussion (led by David Wright) and closing remarks.

Key Timings
03:38 
- Introduction & Welcome
05:20 - David Wright
45:08 - James Bell
1:27:05 - Michael O'Kelly
2:10:00 - Daniel Bratton
2:34:00 - Panel Q&A

04 May 2021

Incomplete datasets due to missing data is an issue that has been, and will be, around for a long time. At this meeting we will present the evolution of missing data approaches, looking at how they have been handled in the past, the current established missing data approaches and the impact of the new ICH E9 R1 addendum on the handling of missing data, focussing in particular on the treatment policy estimand.

Read more...

Khadija Rantell (MHRA), Jiawei Wei (Novartis), Bohdana Ratitch (Bayer)

Incomplete datasets due to missing data is an issue that has been, and will be, around for a long time. At this meeting we will present the evolution of missing data approaches, looking at how they have been handled in the past, the current established missing data approaches and the impact of the new ICH E9 R1 addendum on the handling of missing data, focussing in particular on the treatment policy estimand.

Khadija Rantell (MHRA) History of missing data in regulatory settings. Jiawei Wei (Novartis) On the role of hypothetical estimand in clinical trials and its estimation. Bohdana Ratitch (Bayer) Statistical Issues and Recommendations for Clinical Trials Conducted During the COVID-19 Pandemic. Panel discussion (led by Khadija Rantell) other panel members Daniel Bratton, David Wright, James Bell, Michael O’Kelly, Bohdana Ratitch.

Key Timings
04:30 
- Introduction & Welcome
06:18 - Khadija Rantell
44:30 - Jiawei Wei
1:38:00 - Bohdana Ratitch
2:23:50 - Panel Q&A

29 April 2021

Designs of clinical trials with time to event primary endpoints usually rely on hazards being constant over time. A major challenge in immuno-oncology is the delayed onset of benefit with such therapies and the presence of non-proportional hazards. The impact of this needs to be accounted for in sample size calculations, analysis methodology and reporting. This meeting we will examine possible strategies to handle such features, which may not be fully known when the trial is initiated.

Read more...

Jonathan Bartlett (Univ. Bath); Kaspar Rufibach (Roche; Jose Jimenez (Novartis); Satrajit Roychoudhury (Pfizer); John O’Quigley (Univ. College London); Carl-Fredrik Burman (AZ); Martin Posch (Medical Univ. Vienna).

Designs of clinical trials with time to event primary endpoints usually rely on hazards being constant over time. A major challenge in immuno-oncology is the delayed onset of benefit with such therapies and the presence of non-proportional hazards. The impact of this needs to be accounted for in sample size calculations, analysis methodology and reporting. This meeting we will examine possible strategies to handle such features, which may not be fully known when the trial is initiated.

Non-proportional hazards may also occur in situations where a proportion of patients is cured, where there are crossing survival curves, or diminishing hazards. This meeting we will examine possible strategies to handle such features, which may not be fully known when the trial is initiated. The talks cover methods including weighted log-rank tests, combination tests or KM-based tests such as restricted mean survival time as well as discussion of if testing and estimation should precisely correspond.

Key Timings:
00:00 
- Introduction & Welcome
08:00 - Jonathan Bartlett
41:50 - Kaspar Rufibach
1:23:55 - Jose Jimenez
2:00:30 - Introduction to second half
2:02:32 - Satrajit Roychoudhury
2:34:55 - John O-Quigley
3:19:26 - Carl-Fredrik Burman
4:07:40 - Martin Posch
4:47:37
 - Panel Q&A

28 April 2021

When combining visual cues, conjunctive visual cues, the pre-attentive qualities are generally lost. We will illustrate these concepts through an empirical experiment with the audience. The audience will be expected to participate and identify targets and borders within 250 milliseconds. We will cover what types of visual cues are conducive to pre-attentive processing and how to incorporate these concepts in your data visualizations.

Read more...

The visual cortex can recognize certain “targets” and “borders”, based on variations in visual cues such as shape and color, within 250 milliseconds; this is called pre-attentive processing. This is faster than it takes to become conscious of the image. When combining visual cues, conjunctive visual cues, the pre-attentive qualities are generally lost. We will illustrate these concepts through an empirical experiment with the audience. The audience will be expected to participate and identify targets and borders within 250 milliseconds. We will cover what types of visual cues are conducive to pre-attentive processing and how to incorporate these concepts in your data visualizations. Similarly, the study of gestalt principles from psychology, seeing meaning in a purposeful arrangement of design elements, can be leveraged for effective data visualizations. We will also discuss the hierarchies of perception and how this applies to data visualization.

14 April 2021

Irene de la Torre Arenas presents the results of last month mobile app data challenge. The change of individual app usage over time has been visualised in very different ways as well as its impact on individual symptoms of COPD. The discussion center around the usability of the respective display type for the given purpose . All visualisations are available on the Wonderful Wednesday blog.

Read more...

Irene de la Torre Arenas presents the results of last month mobile app data challenge. The change of individual app usage over time has been visualised in very different ways as well as its impact on individual symptoms of COPD. The discussion center around the usability of the respective display type for the given purpose . All visualisations are available on the Wonderful Wednesday blog. 

The weekly app usage was shown in a video of scatter plots for all individuals. A deep dive into all aspects of the data was made possible by an interactive dashboard that connects two different rankings via line-up linking. For an overview on the whole observation period a multiplot mirrored bar chart over time is very useful, especially because of the different sorting orders that can be applied interactively. For the display of the timing of app usage a daily overlayed dot plot is presented.

The next challenge is about sustained response data. Find out more on the Wonderful Wednesday homepage

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Alexander Schacht, Mark Baillie, Daniel Saure, Zachary Skrivanek, Lorenz Uhlmann, Rachel Phillips, Markus Vogler, David Carr, Steve Mallett, Abi Williams, Julia Igel, Gakava Lovemore, Katie Murphy, Rhys Warham, Sara Zari, Irene de la Torre Arenas.

24 March 2021

Watch this Journal Club webinar to hear Dominic Magirr (Novartis) and Chang Yu (Vanderbilt University) present their recent work. With the webinar chaired by Jennifer Rogers (PHASTAR).

Read more...

Dominic Magirr (Novartis):- Non‐proportional hazards in immuno‐oncology: Is an old perspective needed?
Authors: Dominic Magirr; Pharmaceutical Statistics. 20 20;1-16.
Click here to view the slides

Chang Yu (Vanderbilt University):- A weighted log‐rank test and associated effect estimator for cancer trials with delayed treatment effect
Authors: Chang Yu, Xiang Huang, Hui Nian and Philip He; Pharmaceutical Statistics. 20 21;1– 23.
Click here to view the slides

16 March 2021

This webinar will give an overview of the system and the data collected, along with the benefits gained from continuous cage monitoring using the DVC®. We will use a case study to highlight some of the key discussion points in this presentation.

Read more...

Typically, animal welfare and behaviour are monitored and assessed visually at periodic times throughout the day. However, in order to go beyond this level of assessment we have been using the Digital Ventilated Cage (DVC®) to capture this information quantitively. The DVC® is a non-invasive Home Cage Monitoring system that uses electromagnetic sensors to track and monitor the cage activity. Research Statistics advised on study designs, protocols and carried out extensive exploratory and further statistical analyses on the data. This webinar will give an overview of the system and the data collected, along with the benefits gained from continuous cage monitoring using the DVC®. We will use a case study to highlight some of the key discussion points in this presentation.

10 March 2021

Steve Mallet leads the discussion on ways to display data that is actually missing. The example data was based on a study with multiple measurements of pain that were partially incomplete. The presented visualisations can help to describe the amount, the nature and the impact of missing data on the study outcome. The mirrored histogram highlighted the difference in missing data in specific subgroups. In the Sankey diagram it is possible to see the missing data linked to the actual outcome pain. The course of pain over time is nicely shown in an animated scatter plot. For exploration of the complete data a complex lasagna plot surrounded with additional graphs gives insight. And a powerful tool to actually guide the reader though the data is scrolly-telling. All visualisation are available on the Wonderful Wednesday blog.

Read more...

Steve Mallet leads the discussion on ways to display data that is actually missing. The example data was based on a study with multiple measurements of pain that were partially incomplete. The presented visualisations can help to describe the amount, the nature and the impact of missing data on the study outcome. The mirrored histogram highlighted the difference in missing data in specific subgroups. In the Sankey diagram it is possible to see the missing data linked to the actual outcome pain. The course of pain over time is nicely shown in an animated scatter plot. For exploration of the complete data a complex lasagna plot surrounded with additional graphs gives insight. And a powerful tool to actually guide the reader though the data is scrolly-telling. All visualisation are available on the Wonderful Wednesday blog.

There was a wide range of visualisations presented serving very different purposes. A simple heat map focusses on the amount of missing data in the different treatment arms. The next challenge is about mobile app data. How does individual app usage change over time? And how does app usage impact individual outcomes?

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Alexander Schacht, Mark Baillie, Daniel Saure, Zachary Skrivanek, Lorenz Uhlmann, Rachel Phillips, Markus Vogler, David Carr, Steve Mallett, Abi Williams, Julia Igel, Gakava Lovemore, Katie Murphy, Rhys Warham, Sara Zari, Irene de la Torre Arenas 
Page:

Upcoming Events

Latest Jobs