(Originally published May 29th on Slice of Healthcare)
________________________________________________________________________________________________________
Read More on Clinical Trial Feasibility
In this episode of the BioBreakthroughs podcast, host Jared Taylor engages with two esteemed guests, Rohit Nambisan, CEO and Co-Founder of Lokavant, and Christine Senn, PhD, Senior Vice President of Site Sponsor Innovation at Advarra. They delve into the intricacies of clinical trial feasibility, the impact of rare disease trials, and the potential of AI and technology in transforming clinical trials.
The Challenges of Clinical Trial Feasibility
Rohit Nambisan begins by explaining Lokavant’s role in enhancing clinical trial feasibility through computational tools and AI models. He underscores the difficulty of identifying patient populations in rare disease trials, describing it as finding “needles in a haystack.” These challenges necessitate accurate patient density identification and low participant burden to maintain adherence throughout the trial.
Nambisan notes a trend towards more specific patient populations, such as those with multiple comorbidities, which adds layers of complexity to feasibility. Traditional data sources and site relationships, while reliable, often lack the diversity and specificity needed for these niche trials. Nambisan advocates for a broader, more inclusive approach to data collection, incorporating real-world data and diverse investigator networks to better predict trial outcomes.
The Site Perspective on Feasibility
Christine Senn provides insight from the site side, emphasizing the pitfalls of rushing the feasibility process. She argues that inadequate time and incomplete information during feasibility assessments lead to flawed patient enrollment projections and trial delays. Senn stresses the importance of comprehensive protocol sharing and pre-emptive problem-solving to ensure accurate feasibility assessments.
She highlights the need for better site relationships and the inclusion of diverse sites to avoid biases and enhance patient representation in trials. Senn also discusses the potential of AI in identifying patient populations for specific conditions but cautions against over-reliance on technology without considering the nuances of clinical data.
The Role of AI and Technology
The conversation pivots to the potential of AI and automation in addressing feasibility challenges. Rohit Nambisan sees AI as a powerful tool for predictive modeling, provided the input data is comprehensive and unbiased. He suggests that leveraging AI to process eligibility criteria and historical study data can enhance accuracy in patient identification and trial planning.
Christine Senn echoes the benefits of AI, especially in fields like oncology, where data is highly quantifiable. However, she cautions against excluding new patient populations by relying solely on existing site databases. Senn advocates for technology that facilitates broader site participation and data sharing to ensure inclusivity in large-scale trials.