Click here to watch a video of this episode.
In drug development, translational science can generate endless options, but decision-grade evidence starts with the patient decision. This episode looks at why AI and digital biomarkers often get adopted before we agree what “better” means for patients and for the teams who carry the risk. Here’s the uncomfortable question: are we improving outcomes, or just improving the story we tell ourselves about progress? We talk about how platform-first thinking quietly rewires priorities, shifts incentives, and turns “innovation” into a procurement cycle instead of a decision discipline. The goal is not fewer tools. The goal is a tighter link between what we measure and what we are trying to decide, in a world where biology and regulators do not accept vibes as evidence. Takeaway: before you build or buy anything, write the decision, the patient impact, and the owner in one paragraph.

• (00:00) - Videocast launch, origin, and purpose
• (03:00) - Background and roles across multiple hats
• (04:00) - Toxicologic pathology perspective on drug development
• (05:00) - Machine learning career and pharma transition
• (07:00) - Patients first, platforms second framing
• (08:00) - Defining the problem before chasing solutions
• (12:00) - Purpose-driven framing and leadership reward signals
• (19:00) - AI not a miracle button framing
• (21:00) - Data foundations, modalities, and emerging AI trends
• (26:00) - Decision support versus dashboard accumulation
• (28:00) - Breaking silos and improving probability of success
• (30:00) - Closing takeaway on direction, feedback, and humility