Bayesian Statistics

This episode of PharmaLex Talks features Bruno Boulanger, Senior Director, Global Head Statistics and Data Science at PharmaLex and an award-wining author on Global Statistics and Data Science (link https://www.pharmalex.com/bookauthority-announce-the-winner-of-the-best-new-bayesian-statistics-books-best-new-biostatistics-books-and-best-statistics-ebooks-of-all-time/). 

Bruno´s visionary approach to statistics and his efforts to streamline predictive models and facilitate decision making in pharma are of considerable value for the industry. Clement Laloux, Specialist Statistics & Data Sciences at Pharmalex supports the discussion and shares his thoughts on the influence of prior usage, helping to predict recruitment in Clinical Trials.

This episode focuses around the smooth running of patient enrolment as a key determinant of success for Clinical Trials. The reality is that many Clinical Trials fail to complete on time due to delays in patient recruitment (more than 80% of the Trials do not reach recruitment targets on schedule, Huang et al., 2018). And despite efforts over multiple decades to identify and address barriers, recruitment challenges persist.

In this episode, we shed light on patient enrolment as a key determinant of success in clinical trials, challenges with delays in drug submission and even shortages in hospitals. We touch upon factors that can impact the decision making and facilitate the choice of procedures to adapt models of prediction, particularly Bayesian models.

An important question is, how many additional centres should be opened in order to ensure completion within timelines? More practically, the proposed methodology is carried out under the Bayesian framework and aims at predicting the randomisation dates of future patients in the context of ongoing multicentre clinical trials.

If this topic is of interest to you, visit our webpage and check out our free webinar on the same topic:

https://go.pharmalex.com/pharmalex_webinar_bayesianapproachsupplychain_ondemand