Webinar: Modernizing Clinical Trial Feasibility—Machine Learning for Patient Forecasting and Site Selection

The clinical development marketplace continues to become more complex and competitive, with stricter regulatory standards and trial oversight—all the while demanding patient-centric drug development.  These, and other factors, contribute to increased costs and longer timelines before much-needed therapies reach the market. As the industry looks to technology to drive efficiencies and reduce costs—machine learning continually rises as one of the most promising solutions. In this webinar, we will demonstrate specifically how machine learning can augment clinical trial design and execution. Inteliquet's rich data, machine learning capabilities and patient contact can ultimately support more effective trials: from retrospective real-world analysis for trial design, to synthetic cohorts as alternatives for control arms, to improved patient and site forecasting for enrollment needs. 

Key Takeaways:

  • Identify various areas of clinical data and analytics where machine learning can influence clinical trials
  • Patient data can be enhanced beyond the discrete fields in an EMR system to digitally screen patients for clinical trials
  • Synthetic cohorts are an emerging way to utilize real-world data to reduce patient burden and the costs associated with running a clinical trial
  • Forecasting when patient groups will become available offers better prediction at the time of trial design as to the duration, and therefore cost, of the clinical trial
  • Finding the right patient at the right time is key to trial recruitment, and longitudinal analysis highlights the need to have ongoing monitoring of potentially eligible patients


David Hadley, PhDDebra Kientop