To succeed at an AI startup, you have to be able to show your work and its value. During this episode, I am joined by Brigham Hyde, Co-Founder and CEO of Atropos Health, to talk about his app that gathers real-world evidence for healthcare. He is an entrepreneur, operator, and investor who is deeply immersed in the potential of data and AI. Join us as he shares his journey to creating Atropos Health, why he believes AI is important for healthcare, and the potential it holds to bridge the evidence gap. We discuss how the lack of diversity in healthcare data has impacted patient outcomes leading up to this point and explore some of the methods Atropos uses to get the most out of machine learning. We discuss the AI data-gathering process, how each setup is validated and adapted, and how he measures the impact of his technology. In closing, he shares advice for other leaders of AI-powered startups and offers his vision for the future impact of Atropos.

Key Points:

• Welcoming Brigham Hyde, co-founder and CEO of Atropos Health.
• His journey to creating Atropos Health after working in other medical AI arenas.
• Why AI is important for healthcare: the evidence gap.
• Atropos’s perspective on the role of real-world evidence.
• How the lack of diversity in healthcare data sets impacts patient outcomes.
• Methods Atropos uses to leverage machine learning to ensure that patient populations are supported.
• The data-gathering process.
• How the setup is validated and adapted according to need.
• Measuring the impact of the technology.
• Advice for other leaders of AI-powered startups.
• Where Brigham foresees the impact of Atropos in three to five years.

Quotes:

“At Atropos, we focus on the automation and generation of high-quality real-world evidence to support clinical decision-making with the dream of creating personalized evidence for everyone.” — Brigham Hyde

“We see the role of real-world evidence and observational research as a great way to supplement that gap.” — Brigham Hyde

“It's our ability to create that evidence, transparently show you the populations that are being used and the bias that is involved, and the techniques to remove that bias that are the key.” — Brigham Hyde

“You've got to be able to show how what you're doing works, that it's not biased, and that it's applicable to the health system you're working with, and it's got to be done in extremely high quality.” — Brigham Hyde

Links:

Brigham Hyde on LinkedIn

Brigham Hyde on X
Atropos Health
Atropos Health on LinkedIn

Atropos Health on X

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

As machine learning becomes increasingly widespread, AI holds the potential to revolutionize drug development, making it faster, safer, and more affordable than ever. In this episode, I'm joined by Jo Varshney, Founder and CEO of VeriSIM Life, to explore how her company is transforming drug translation through hybrid AI.

With her unique blend of expertise as a veterinarian and computer scientist, Jo leverages biology, chemistry, and machine learning knowledge to tackle the translational gap between animal models and human patients. You’ll learn about VeriSIM Life’s innovative approach to overcoming data limitations, synthesizing new data, and applying ML models tailored to various diseases, from rare conditions to neurological disorders. Jo also reveals VeriSIM’s unique translational index score, a tool that predicts clinical trial success rates and helps pharma companies identify promising drugs early and avoid costly failures.

For anyone curious about the future of AI in healthcare, this episode offers a fascinating glimpse into the world of biotech innovation. To discover how VeriSIM Life’s technology is poised to bring life-saving treatments to patients faster and more safely than ever before, be sure to tune in today!

Key Points:

• How Jo's background and interest in translational challenges led her to found VeriSIM Life.
• Addressing translational gaps between animal models and human trials with hybrid AI.
• Combining biology-based models with ML to enhance drug testing accuracy.
• Small molecules, peptides, large molecules, clinical trial outcomes, and other data inputs.
• Ways that VeriSIM’s models are tailored per data type, ensuring maximum accuracy.
• Insight into the challenge of overcoming data gaps and how VeriSIM solves it.
• How hybrid AI reduces overfitting, boosting model accuracy in data-limited scenarios.
• What goes into validating VeriSIM’s models through partnerships and external testing.
• Measuring the impact of this technology with VeriSIM’s translational index score.
• Jo’s advice for AI-powered startups: be specific, validate technology, and be adaptable.
• Her predictions for the impact VeriSIM will have in the next few years.

Quotes:

“[Hybrid AI] helps us not only unravel newer methods and mechanisms of actions or novel targets but also helps us identify better drug candidates that could eventually be safer and more effective in human patients.” — Jo Varshney

“Biology is complex. We need to understand it enough to create a codified version of that biology.” — Jo Varshney

“If you're just using machine learning-based methods, you may not get the right features to see the accuracy that you would see with the hybrid AI approach that we take.” — Jo Varshney

“Focus on validation and showing some real-world outcomes [rather than] just building the marketing outcome because, ultimately, we want it to get to the patients. We want to know if the technology really works. If it doesn't work, you can still pivot.” — Jo Varshney

Links:

VeriSIM Life

Jo Varshney on LinkedIn

Jo Varshney on X

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

Today’s guest believes that decoding the immune system is at the heart of improving drug efficacy. He is currently focused on this effort as the CEO and Co-founder of Immunai – a company that is building an AI model of the immune system to facilitate the development of next-generation immunomodulatory therapeutics. Noam Solomon begins our conversation by detailing his professional history and how it led to Immunai before explaining what Immunai does and why this work is vital for healthcare. Then, we discover how understanding the immune system will help to improve how drugs work in our bodies, how the team at Immunai accomplishes its goals, the major challenges of working with complex ML models, and some helpful recommendations for processing the high-dimensional nature of biological data. Noam also explains the collaborative landscape of Immunai, how the evolution of technology made his work possible, Immunai’s plans for the future, and his advice to others on a similar career path.

Key Points:

• Unpacking Noam Solomon’s professional journey that led to his founding of Immunai.
• What Immunai does and why this work is vital for the healthcare industry.
• How understanding the immune system will help to improve drug efficacy.
• Exploring how Noam and his team use AI to accomplish their goals.
• The standardization of data and other challenges of working with complex ML models.
• Techniques for handling the high-dimensional nature of biological data.
• How ML experts collaborate with other domains to inform and build Immunai’s models.
• The technical advancements that have made Noam’s work possible.
• His advice to other leaders of AI-powered startups, and imagining the future of Immunai.
• How to connect with Noam and his work.

Quotes:

“First, let’s talk about the problem, which is today, getting a drug from IND approval to FDA approval—which is the process of doing clinical trials—has less than a 10% chance of success, usually about a 5% chance, takes more than 10 years, and more than $2 billion of open immune therapy.” — Noam Solomon

“Different people respond differently to the same drug, and the reason they respond differently is because their immune system is different.” — Noam Solomon

“You first need to fall in love with the problems. Many ML people—physicists, mathematicians, computer scientists—we love building models; we love solving puzzles. In biology, you need to really fall in love with the question you are trying to answer.” — Noam Solomon

“It’s a great decade for biology.” — Noam Solomon

Links:

Noam Solomon on LinkedIn

Noam Solomon on X

Immunai

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.