AI is the buzzword across every industry right now, and the pharma industry is not immune. Every conference I’ve been to in the last two years has been full of sessions covering the promise of AI in drug development (I’ve spoken in some of those sessions myself). Excitement is high, but is that enough?
Drug development is fundamentally grounded in science, evidence, reproducibility, and trust, not always what AI is known for currently. The future of AI in modeling and simulation cannot be built solely on black-box algorithms that cannot explain their outputs—transparent models are still needed. So how do we leverage the best of AI without losing the scientific rigor that is rightly required for the work we do?
At Simulations Plus, we see this from a very unique position because our foundation has been built on more than 30 years of scientific innovation, collaboration, and regulatory interaction. Over three decades, the industry has not only adopted sophisticated modeling and simulation approaches, but regulators have increasingly accepted and trusted them as part of the decision-making process. I have seen this first-hand with the adoption of modeling and simulation approaches informing label recommendations for marketed drugs in both drug-drug interactions and biopharmaceutics use cases.
Regulatory credibility is difficult to build and impossible to shortcut. Models influence critical decisions around safety, efficacy, dosing, and development strategy, and those decisions must stand up to scrutiny from scientists and regulators alike. Trust is not created through hype or speed, it is built through years of scientific validation, demonstrated reliability, and consistent outcomes.
That’s why in the age of AI, validated scientific models are more important than ever.
Organizations with deep scientific heritage have an important role to play in shaping the future AI ecosystem. The combination of mechanistic science and AI creates something far more powerful than either could deliver independently. As my colleagues Scott Q. Siler, James Beaudoin, and Christina Battista noted in more detail in a previous post, AI can accelerate discovery and uncover patterns at scale, but scientific engines built from decades of research provide the biological, chemical, and pharmacological rationale that ensures those insights are meaningful, explainable, and defensible.
AI cannot and should not replace established modeling and simulation approaches, but a scientific ecosystem where they are combined is the path for responsible drug development and regulatory trust.
If you are interested in learning more about how to implement an AI-powered ecosystem, I’m happy to chat.