Webcast: De-Risk Clinical Trials using Machine Learning
Download this webcast to learn how to de-risk your trials with machine learningand avoid data inconsistencies or submission errors that cause agency requests for further analysis or worse — non-approval.
Although traditional data quality processes catch many problems, subtle-but-critical issues can escape detection and surprise study teams late in the process or during agency review. Real-time insights from advanced analytics de-risk clinical trials and accelerate time to market by increasing the likelihood of regulatory approval. In this webcast, you’ll uncover:
- How one pharma company beat their competitor to market by avoiding an extra FDA data review cycle
- Five key data quality issues that can derail drug approvals
- The brains and technology behind Medidata Edge Trial Assurance
VP, Data Science at Medidata Solutions & Former FDA Statistical Reviewer
Michael Elashoff is VP of Data Science at Medidata. Prior to Medidata, he co-founded a company, Patient Profiles, that developed machine learning software for clinical trial analysis; the company was acquired by Medidata in 2014. He was previously a statistical reviewer and team leader at the FDA, and worked for several biotech companies developing genomic diagnostics for clinical use. Michael received his PhD in Biostatistics from Harvard University.