Video-on-Demand Library


Collection
Keyword or phrase

Topic

14 September 2022

Health related quality of life as measured by the EQ-5D is dependent on a lot of different factors. How can the predictive value of certain patient characteristics be depicted? This Wonderful Wednesday is presented by Irene de la Torre Arenas. And the visualisations are available on the Wonderful Wednesday blog.

Read more...

Health related quality of life as measured by the EQ-5D is dependent on a lot of different factors. How can the predictive value of certain patient characteristics be depicted? This Wonderful Wednesday is presented by Irene de la Torre Arenas. And the visualisations are available on the Wonderful Wednesday blog

It helps to better understand the data, if the modelled dependency is plotted on top of the underlying data as done in the first proposal. The use of color helps to distinguish different dependencies. This can be further supported by plotting facets and choosing symbols, that can easily be identified. Another proposal showed the effects including interactions in a network plot and the relative importance side-by-side. The next challenge is about the different scales of a quality of life assessment in cancer patients. See the Wonderful Wednesday homepage for more detail.

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Alexander Schacht, Mark Baillie, Zachary Skrivanek, Lorenz Uhlmann, Rachel Phillips, David Carr, Steve Mallett, Julia Igel, Rhys Warham, Irene de la Torre Arenas

13 September 2022

If you've ever thought about making a career change or taking a career break then this Lunch & Learn can provide you with an insight from those who have been there and done it.

Read more...

Claire Brittain, Chetan Mistry, Lucy Rowell, Graeme Archer, Lucy Keeling.

The idea of changing careers or taking a career break can lead to feelings of being both frightened and excited at the same time. Our next PSI Lunch & Learn discussion will include a panel who have taken the leap and relaunched their careers. Find out about the benefits, the challenges and how it impacted their lives and careers in the long term.

07 September 2022

This journal club features two papers on the topic of “Estimating Treatment Effects”. Please join us to hear Yongming Qu (Eli Lilly) and Solomon Harrar (University of Kentucky) present their recent work. The webinar will be chaired by Ilya Lipkovich (Eli Lilly)

Read more...

Chaired by Ilya Lipkovich (Eli Lilly), our presenters are:  
Yongming Qu (Eli Lilly) - Estimating the treatment effect for adherers using multiple imputation  
Zi Ye (Lehigh University) - Estimation of multivariate treatment effects in contaminated clinical trials  

10 August 2022

Ranking based on network meta-analysis is an intuitive approach to compare several treatment arms. Rhys Warham presents examples showing how to visualize the results. All visualizations are available on the Wonderful Wednesday blog.

Read more...

Ranking based on network meta-analysis is an intuitive approach to compare several treatment arms. Rhys Warham presents examples showing how to visualise the results. All visualisations are available on the Wonderful Wednesday blog.

Network meta-analysis is an extension of "classical" meta-analysis and allows to include more than two arms into one model. Based on this model, rankings of treatment arms can be performed. Line plots, Lolly plots, a innovative way of using colors, a dashboard, and an app were presented in this webinar as a way to communicate the results of the ranking procedure. The next challenge is about visualising the results of a regression model to predict EQ-5D (Health related quality of life) based on several subject characteristics. See the Wonderful Wednesday homepage for more details.

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

13 July 2022

How do we combine detailed patient level data into an informed representation of the patient? Solutions to this problem are presented by Bodo Kirsch. All visualisations are available on the Wonderful Wednesday blog.

Read more...

How do we combine detailed patient level data into an informed representation of the patient? Solutions to this problem are presented by Bodo Kirsch. All visualisations are available on the Wonderful Wednesday blog

Patient level data contains demographic information as well as exposure, concomitant medications, adverse events and laboratory data. These can be presented in one plot or multiple aligned plots. Interactive visualisations are shown allowing to expand and collapse selected details. The use of color and pre-attentive attributes is supporting easy interpretation of the data. The next challenge is to visualise ranking data. See the Wonderful Wednesday homepage for more detail.

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

21 June 2022

Dr Francq discusses the need for analytical methods to deliver unbiased and precise results. Her talks in detail about confidence, prediction and tolerance intervals in linear mixed models and the interpretation of statistical results.

Read more...

Dr Francq discusses the need for analytical methods to deliver unbiased and precise results. Her talks in detail about confidence, prediction and tolerance intervals in linear mixed models and the interpretation of statistical results.

15 June 2022

This session is a collection of presentations considering approaches to dose finding in early phase trials.

Read more...

Pavel Mozgunov; Andrew Hall; Lizzi Pitt

This session is a collection of presentations considering approaches to dose finding in early phase trials.

Practical Implementation of the Partial Ordering Continual Reassessment Method in a Phase I Combination-Schedule Dose-Finding Trial  - Pavel Mozgunov 
There is a growing medical interest in combining several agents and optimising their dosing schedules in a single trial. Evaluating doses of several drugs and their scheduling in a single Phase I trial simultaneously posses a number challenges, and specialised methods to tackle these are required. While several suitable designs were developed and proposed in the literature, the uptake of these methods is slow and implementation examples of such advanced methods are still sparse.  
 
In this presentation, we will share our recent experience of developing and implementing a modified model-based Partial Ordering Continual Reassessment Method (POCRM) Design for 3-dimensional dose-finding in a Phase I oncology clinical trial in patients with advanced solid tumours. In the trial, doses of two agents and the dosing schedule of one of them can be escalated. We will provide a step-by-step overview on how the POCRM design was implemented and communicated to the trial team. We will demonstrate a novel approach to specify the design parameters that is more intuitive for communication and will demonstrate a number of developed visualisation tools to demonstrate the statistical properties of the design. This included both performance in a comprehensive simulation study and in individual scenarios. The proposed design went through evaluations of health authorities and was successfully used to aid the decision-making in the ongoing trial.  
 
Decision making under uncertainty in PI-II dose finding trials in Oncology - Andrew Hall 
There is increased interest in dose finding methods in oncology using both toxicity and efficacy endpoints with targeted therapies. A phase I trial design proceeds in stages with a decision as which dose to give the next group of patients made after every stage. Bayesian decision theoretical approaches have previously been found to be in theory ethically and scientifically sound. In practice however, it is challenging to specify a utility function capturing clinical preferences while maintaining good operating characteristics sensitive to specification.  
 
Outcomes from treatments are not deterministic; utilities are a measure of preference when facing an uncertain outcome. We consider situations where preferences/utilities are defined with respect to outcome probabilities. In doing so clinicians can account for individual patient risk while meeting wider trial objectives, i.e. identifying a recommended phase II dose. We argue attitudes to risk in this setting follow heuristics from prospect theory. Namely they are framed from the perspective of a reference point, with a risk averse attitude for perceived gains, and risk seeking for losses. Additionally, with loss aversion it is ethical to avoid losses more so than to pursue gains. The bivariate utility is formed by inspecting utility independence axioms to describe the payoff between two separate utility functions for efficacy and toxicity.  
 
I will explain why heuristics from prospect theory to structure utilities around outcome probabilities are justified in dose finding trials, and show this leads to consistent and in some scenarios improved operating characteristics over designs specifying value rather than utility functions.  
 
Building the bridge from PhD to practice: optimising phase I trials using estimand-style formulation - Lizzi Pitt 
We have developed a framework to obtain optimal dose escalation schemes for phase I trials. The emphasis is on fully specifying the aims of the trial up front: if you tell us what you want the trial to do, we can find the optimal dose escalation scheme for your specific trial. We achieve this using dynamic programming. We have considered trials with one binary safety endpoint with a variety of aims, as well as trials that also include a binary efficacy endpoint.  
 
This research was conducted as a PhD project and focussed on a first in human trial with a particular generic structure. How do we translate this theory into practice and apply the methodology to a real trial, with a different structure?  
 
We shall present reflections on some case studies of real phase I trials with different structures and covering different therapeutic areas. Spoiler alert! The key is in the problem formulation. This framework encourages early discussion on what makes the trial a success, what quantity the trial seeks to estimate and how the information will be used in phase II. This brings the flavour of estimands to phase I trials and creates trial designs that are fit for purpose, facilitate decision making and enable us to learn more about the treatment earlier.

14 June 2022

This session, brought to you by the Data Sharing ESIG, is based on their recent paper “Synthetic data use: exploring use cases to optimise data utility” and will cover the following topics: • Overview of synthetic data - what it is and where it could be used • How synthetic data can be produced • Examples where synthetic data has been used.

Read more...

Lisa Winstanley (AstraZeneca), Finn Janson (Roche), Mimmi Sundler (AstraZeneca)

This session, brought to you by the Data Sharing ESIG, is based on their recent paper “Synthetic data use: exploring use cases to optimise data utility” and will cover the following topics:
• Overview of synthetic data - what it is and where it could be used
• How synthetic data can be produced
• Examples where synthetic data has been used.

14 June 2022

COVID 19 presented a variety of challenges in the conduct and analysis of ongoing clinical trials, including additional protocol deviations that lead to increased missing data and the occurrence of unforeseen intercurrent events. This session includes 3 talks covering the following aspects: 1) How regulators approached the acceptability of changes in conduct and handling of missing data or intercurrent event; 2) A case study of a Phase 3 trial where the collection of the primary endpoint was impacted, as well reconsideration being needed of dosing, analyses, data collection and site monitoring; 3) A case study of the development of a treatment for COVID-19, navigating emerging scientific information and evolving regulatory pathways.

Read more...

Khadija Rantell (MHRA), Asa Hellqvist (AstraZeneca), Nicola Scott (GSK)

COVID 19 presented a variety of challenges in the conduct and analysis of ongoing clinical trials, including additional protocol deviations that lead to increased missing data and the occurrence of unforeseen intercurrent events. This session includes 3 talks covering the following aspects: 1) How regulators approached the acceptability of changes in conduct and handling of missing data or intercurrent event; 2) A case study of a Phase 3 trial where the collection of the primary endpoint was impacted, as well reconsideration being needed of dosing, analyses, data collection and site monitoring; 3) A case study of the development of a treatment for COVID-19, navigating emerging scientific information and evolving regulatory pathways.

Interpretation and translation of clinical trial outcome impacted by COVID-19 pandemic:
COVID 19 presents a variety of challenges in the conduct and analysis of ongoing clinical trials, including additional protocol deviations that lead to increased missing data and the occurrence of unforeseen intercurrent events. In response to these difficulties, regulatory agencies issued guidance on how to assess potential impacts on ongoing clinical trials. This stressed the importance of collecting additional pandemic related data in order to distinguish between pandemic and non-pandemic related intercurrent events and to select an appropriate strategy for handling them. Selecting appropriate statistical analyses, with justifiable and plausible assumptions, is also critical to the delivery of reliable interpretable results targeting an agreed estimand that can be reliably translated into a clinically meaningful and interpretable treatment effect for decision making. In this talk, I will provide examples of trial results impacted by COVID-19 pandemic, describe their approaches to handling intercurrent events and missing data, and provide regulatory feedback on their acceptability.

Delivering a clinical study during a global pandemic: Experiences from the OSTRO nasal polyps study:
The phase III OSTRO trial of Benralizumab in Nasal Polyps was ongoing at the beginning of the COVID pandemic in early 2020. The pandemic restricted the ability of subjects to travel and attend scheduled visits, and it prevented the collection of data. The nasal endoscopy procedures required to collect the co-primary endpoint Nasal Polyp Score (NPS) were put on hold by the sponsor because of the high risk, to both subjects and site staff, of exposure to COVID-19. More than 25% of subjects would miss their primary endpoint due to inability to collect the Week 56 endoscopy. The effort to overcome the difficulties introduced by the pandemic involved reconsidering dosing procedures, statistical analyses, and planned approaches to data collection and site monitoring. We introduced flexibility in dosing and data collection to allow subjects to remain at home. We allowed flexibility for data monitoring without sacrificing study integrity. The statistical testing hierarchy was updated to consider an earlier timepoint for primary testing, which allowed for nearly 100% pre-pandemic contribution from subjects. We also considered other sensitivity analyses to assess the impact of COVID by determining on a subject level when the pandemic first had an impact on their data. While a global pandemic cannot be anticipated, we can still learn lessons from these challenges and solutions. In other trials we have introduced flexibility in operations and planned for statistical sensitivity analyses. In this presentation we will discuss the OSTRO experience and how we learn from it.

Statistical and operational challenges of developing a treatment for COVID-19:
A case study of the development of treatment for COVID-19. A story of navigating the ever changing nature of the COVID-19 pandemic while focusing on the target of delivering a drug to patients as soon as possible; fluctuating background rates of infection, evolving disease knowledge, emerging variants, changing competitive landscape and new regulatory procedures.

13 June 2022

In this session we will introduce this new PSI Data Science SIG, its goals and current activities. Three talks will cover the following: An example of recent blog posts developed within the group to elicit engagement and discussions within the community and to help data science partitioners to expand their tool kits and data modalities. A presentation introducing current methods for feature selection and feature construction with their application to clinical data. A published project on predicting immunochemotherapy tolerability is used as the guiding example. A talk focused on an application of a work flow that combines traditional survival analysis techniques like KM curves and Cox models with state-of-the-art machine learning methods and explainers. As with all the activities of our SIG, our goal is to generate interest and discussion, not to advocate for particular methods, and to be introductory and practical.

Read more...

Domingo Salazar (AstraZeneca), Carsten Henneges (Syneos Health)

In this session we will introduce this new PSI Data Science SIG, its goals and current activities. Three talks will cover the following: An example of recent blog posts developed within the group to elicit engagement and discussions within the community and to help data science partitioners to expand their tool kits and data modalities. A presentation introducing current methods for feature selection and feature construction with their application to clinical data. A published project on predicting immunochemotherapy tolerability is used as the guiding example. A talk focused on an application of a work flow that combines traditional survival analysis techniques like KM curves and Cox models with state-of-the-art machine learning methods and explainers. As with all the activities of our SIG, our goal is to generate interest and discussion, not to advocate for particular methods, and to be introductory and practical.

Introduction to the PSI Data Science SIG: In this talk we will introduce this new PSI Data Science SIG, its goals and current activities. As an example, we will cover to recent blog posts developed within the group: one of the creation of effective dashboards and the other on the application of the particularities of the analysis of omics datasets. In general, the goal of our blogs is to elicit engagement and discussions within the community and to help data science partitioners to expand their tool kits and data modalities.

Feature Selection:
The presentation will introduce current methods for feature selection and feature construction with their application to clinical data. A published project on predicting immunochemotherapy tolerability is used as the guiding example to share learnings, and critically review and discuss approaches. Since feature selection is a wide-spread task, the aim is to work out and highlight the specialties and needs related to its application to clinical data.

Machine Learning in Survival Analysis: This talk will focus on an application of a particular tried-and-tested work flow that combines traditional survival analysis techniques like KM curves and Cox models with state-of-the-art machine learning methods and explainers. As with all the other activities of our SIG, our goal is to generate interest and discussion, not to advocate for particular methods. Also, in line with our philosophy, the talk would be introductory and practical.

13 June 2022

The COVID-19 pandemic is the greatest health challenge for a generation and has highlighted the critical importance of generating rapid and rigorous evidence for decision-making. The International COVID-19 Data Alliance (ICODA) was formed, a global coordinated, health data-led research initiative bringing together for- and non-profit companies and organisations, to enable researchers to access RCT and RWD health data to accelerate knowledge of the prevention and treatment of COVID-19. This talk will be in two parts; the first will be less technical and focus on the ICODA journey – how to successfully bringing different companies and non-profit organisations to collaborate towards a common goal, and how statistician played an essential role in this. The second part will present results from one of the ICODA projects evaluating existing medical interventions to support drug repurposing efforts.

Read more...

Jonas Haggstrom (Cytel)

The COVID-19 pandemic is the greatest health challenge for a generation and has highlighted the critical importance of generating rapid and rigorous evidence for decision-making for the treatment of COVID-19. As a response to this challenge the International COVID-19 Data Alliance (ICODA) was formed, an open and inclusive global coordinated, health data-led research initiative bringing together for- and non-profit companies and organisations working collaboratively to enable and empower researchers to access RCT and RWD health data in a responsible way, making use of innovative data science, contemporary tools and technology to accelerate knowledge of the prevention and treatment of COVID-19. This talk will be in two parts; the first will be less technical in its nature and focus on the ICODA journey from its inauguration in July 2020 to the current state with 12 driver projects, including more than 130 researchers, working on data from over 40 different countries – the ins and outs of how to successfully bringing different companies and non-profit organisations to collaborate towards a common goal, and specifically how statistician played an essential role to make it happen. The second part will present results from one of the ICODA projects evaluating the efficacy and safety of COVID-19 of existing medical interventions to support drug repurposing efforts.

13 June 2022

Recording of the 2022 PSI Conference Young Statistician Session from 1:30-3:00pm on Monday 13th June.

Read more...

Daniel Leibovitz, Jan Meis, Holly Jackson, Lauren Cowie & Alessandra Serra.

Recording of the 2022 PSI Conference Young Statistician Session from 1:30-3:00pm on Monday 13th June.
Talks in this session were as follows: Daniel Leibovitz “The Least Bad Option: A Simulation Approach to Minimizing Bias when Accounting for Treatment Switching in RCTs”, Jan Meis “Performance of different estimators in adaptive two-stage clinical trials with optimized design parameters”, Holly Jackson “An alternative to traditional sample size determination for small patient populations”, Lauren Cowie “Quantifying expert judgements using Bayesian elicitation techniques” and Alessandra Serra “A Bayesian multi-arm multi-stage clinical trial design incorporating information about treatment ordering”.
Page:

Upcoming Events

Latest Jobs