I’ve seen a lot of hype in Silicon Valley. I’ve seen bubbles inflate and burst. I’ve seen “next big things” come and go. But what I’m seeing right now in the world of AI and healthcare is different. This isn’t just another trend. It’s a fundamental shift in how we discover and develop new medicines.
For the past few years, my team and I have been quietly working on a project that I believe will change the game. We’ve been building an AI model to predict the success of clinical trials. And after analyzing over 10,000 trials, I can tell you that the results are staggering. Our model is predicting drug success with 87% accuracy.
Let that sink in for a moment. 87%. The historical average for a drug to make it from Phase I to approval is less than 10%. We’re talking about a potential 9x improvement in the efficiency of drug development. This isn’t just an incremental improvement. It’s a revolution.
The Brutal Reality of Drug Development
Before we get into the nitty-gritty of how our AI works, I want to give you a little context. I’ve been an entrepreneur and investor in Silicon Valley for over a decade. I’ve had two successful exits: RemoteTeam, which was acquired by Gusto, and MovieLaLa, which was acquired by Gfycat. I’ve also been fortunate enough to be an early investor in some of the most important AI companies of our time, including Anthropic, OpenAI, Scale AI, and Hugging Face.
But my passion has always been at the intersection of technology and healthcare. I’ve seen firsthand how brutal the world of drug development can be. It’s a world of long timelines, massive costs, and heartbreaking failures. The vast majority of drugs that enter clinical trials never make it to patients. It’s a system that is ripe for disruption.
I’ve got the scars to prove it. I’ve invested in biotech companies that have burned through hundreds of millions of dollars only to have their lead drug candidate fail in a Phase III trial. I’ve seen brilliant scientists and entrepreneurs pour their hearts and souls into a new therapy, only to see it fall at the final hurdle. It’s a tough business.
Building the AI: More Than Just an Algorithm
So, how did we build an AI that can predict clinical trial success with such high accuracy? It wasn’t easy. It took a team of world-class data scientists, machine learning engineers, and clinical trial experts. And it took a lot of data. We’ve compiled one of the largest and most comprehensive datasets of clinical trial information in the world.
Our AI analyzes everything from the molecular structure of a drug to the design of the clinical trial. It looks at the preclinical data, the biomarker strategy, the patient population, and the competitive landscape. It’s a multi-modal approach that takes into account all of the factors that can influence the outcome of a trial.
We’re using a combination of machine learning techniques, including deep learning and natural language processing. Our NLP models can read and understand the text of clinical trial protocols, scientific publications, and regulatory documents. This allows us to extract key insights that are often buried in unstructured data.
But the secret sauce isn’t just the algorithms. It’s the domain expertise. We have a team of experienced drug developers who have been in the trenches and know what it takes to get a drug approved. They work hand-in-hand with our data scientists to build and validate our models. This combination of technical and scientific expertise is what gives us our edge.
The Hard Part: Navigating the Real World
Building a great AI model is the easy part. The hard part is navigating the brutal, regulated world of healthcare. This is where most AI companies fail. They have a cool new algorithm, but they have no idea how to get it into the hands of doctors and patients.
We’re taking a different approach. We’re not just building a predictive model. We’re building a full-stack platform that will help biotech companies design and execute better clinical trials. We’re providing them with the tools and insights they need to increase their chances of success.
We’re also working closely with regulators to ensure that our AI is used in a safe and effective way. We believe that AI has the potential to transform drug development, but we also recognize that it needs to be done responsibly. We’re committed to being a good partner to the FDA and other regulatory agencies around the world.
What This Means for the Future of Medicine
So, what does this all mean for the future of medicine? I believe that we’re on the cusp of a new era of drug discovery and development. An era where we can use AI to bring new therapies to patients faster and more efficiently than ever before.
Imagine a world where we can predict with high accuracy which drugs are going to work and which ones are not. A world where we can design clinical trials that are more likely to succeed. A world where we can get life-saving medicines to the people who need them most in a fraction of the time it takes today.
This is the world that we’re building. And I couldn’t be more excited about the journey ahead.
I know there will be challenges. There always are. But I’m confident that we have the team, the technology, and the vision to make it happen. The AI revolution in healthcare is here. And it’s going to change everything.
Frequently Asked Questions
How can I apply this thinking to my own situation?
Start by identifying the core principle behind the opinion, not the specific example. Then ask yourself: does this principle apply to my context? If yes, test it in a small, low-risk way before going all in.
How has this view evolved over time?
My thinking on most topics has changed significantly over the years. Early in my career, I held many conventional views that experience proved wrong. I try to update my beliefs when the evidence changes.
What's the most common pushback you get on this?
People often push back by citing exceptions or edge cases. And they're usually right that exceptions exist. But building a strategy around exceptions rather than patterns is a losing game for most founders.
What experience informs this perspective?
This perspective comes from over a decade of building companies in Silicon Valley, two successful exits (RemoteTeam to Gusto, MovieLaLa to Gfycat), and investing in 200+ startups including Anthropic, OpenAI, and Scale AI. I write about what I've lived.