We are pleased to announce Dr Satrajit Roychoudhury of Pfizer as the winner of the 2023 Statistical Excellence in the Pharmaceutical Industry Award, which is presented jointly by Statisticians in the Pharmaceutical Industry (PSI) and the Royal Statistical Society (RSS).
Dr Satrajit Roychoudhury has had a significant impact in developing, implementing, and disseminating efficient statistical methodology in four distinct areas:
- Bayesian design for COVID-19 vaccine trial
- Use of external control data
- Implementation of model-based approach in Phase I oncology studies
- Statistical approaches for non-proportional hazard
For his work on COVID-19 vaccines, he has recognised the urgent need to evaluate and identify a vaccine, but also to enable communication of findings to end users. The end result was one of the first Bayesian Phase III trials that has led to regulatory approval. For many researchers, developing novel methodology ends with acceptance of a manuscript or when the methodology is used in practice. Dr Roychoudhury has gone well beyond that and made it his mission to also educate the wider community on these methods.
The award was presented at the PSI annual conference in June, by Mags Wiley (RSS) and Kate Tsirtsonis (PSI) where the award was collected on Satrajit’s behalf by his colleague at Pfizer, Amanda Darekar.
Chrissie Fletcher, chair of PSI, said: 'Many congratulations to Satrajit for this significant achievement and well deserved recognition for his statistical excellence in the Pharmaceutical Industry. It is truly outstanding to implement and disseminate efficient statistical methodology in not just one, but four, important and diverse areas. An amazing accomplishment, well done.'
Dr Andrew Garrett, president of the RSS, commenting on the news said: 'Congratulations to Satrajit who should be applauded for the breadth and depth of his contributions. His work on Covid-19 vaccines clearly illustrates impact - notably how Bayesian methods can be used in a confirmatory setting to support regulatory review and approval.'
In 2022, the PSI/RSS award was presented to a team of biostatisticians and statistical engineers from the healthcare company Roche, in collaboration with the University of Bath.
Their winning entry was focused on ‘Standard and reference-based conditional mean imputation (methodology and open-source software)’. The team comprising of Marcel Wolbers, Alessandro Noci, Paul Delmar, Craig Gower-Page, Sean Yiu (of Roche) and Jonathan W. Bartlett (of the University of Bath) were praised by the judges for their innovative approach.
The project addressed the need of trial statisticians in the pharmaceutical industry to fully align their analysis strategy with the targeted estimand and flexible missing data assumptions for clinical trials with continuous longitudinal outcomes. The team present a novel imputation procedure which is fully deterministic (i.e. free of Monte Carlo error) and provides treatment effect estimates consistent with the Bayesian approach as well as reliable frequentist and inference with accurate standard error estimation and type I error control. The companion open-source R package ‘rbmi’ is a flexible toolbox to implement these methods in practice.
Chrissie Fletcher, Chair of PSI, said: ‘The PSI/RSS Statistical Excellence in the Pharmaceutical Industry Award is a significant achievement and recognition of a new statistical innovation created to advance drug development. Well done to the team at Roche who have applied innovative statistical thinking to a common issue in clinical trials relating to missing data and also provided a new R package to implement the methodology.’
Stian Westlake, RSS CEO, added: ‘The team are to be congratulated for this outstanding piece of work which could potentially be a big game-changer for the industry.’
The photo shows Marcel Wolbers and Alessandro Noci presenting on their award winning research at the 2023 PSI conference.