Target identification and validation
RWD can be used to identify potential disease targets and to validate existing targets through the analysis of large-scale patient data.
Label expansion is one of the most proliferate use case for real world data in drug development. With perhaps some of the most famous examples from Flatiron and Pfizer in use of Palbociclib in male breast cancer patients. Overall, real world data is essential when it comes to label expansion specifically in areas with rare diseases or small / patient populations and, hence, too costly economically to run a proper RCT.
Drug discovery is a very costly and time-consuming process and at best only 20% of clinical trials are successful, with this figure as low as 10% in Oncology and some other TAs.
With artificial intelligence and machine learning we have got the chance to increase these numbers and give molecules and substances a second chance. This is especially important since many of the failed drugs have proven to be safe and looking into applications beyond original label will save us significant resources.