Following on from Part II in our healthcare series, which explored the application of machine-learning models to generate phase transition and approval predictions, we provide our view on the alternative datasets that pharma and biotech investors can use to augment their R&D pipeline analysis.

WHAT INFORMATION IS COLLECTED ON CLINICAL TRIALS?

First, for those who are unfamiliar with this topic – clinical trial registration refers to the publication of a formal record of a clinical trial. A trial should be registered by its sponsor (or principal investigator) at or before the time of first patient enrolment. To do so, the sponsor must submit information to a clinical trial registry (e.g. ClinicalTrials.gov or The EU Clinical Trials Register) about the design, conduct, and administration of the trial. Each registry then stores this information in a publicly accessible database.

Trial registration is a regulatory requirement in some countries (including the US and EU member states) and ‘strongly encouraged’ in others. An additional incentive to register trials comes from the growing number of medical journals refusing to publish the results of trials that were not registered on time (a result of