90% of clinical trials fail today at the same rate they did 30 years ago. Medicine has kept treating patients as populations while their biology has always been telling a more personal story.
Dr. Jenny Yang, co-founder and CEO of Outpost Bio, joins host Brian Chee to break down how combining lab-grown human microbiomes with AI could finally close the gap between what medicine predicts and what individual patients actually experience, and why our gut microbiome holds biological diversity that human DNA simply cannot explain.
----
🎙 ABOUT JENNY YANG:
Dr. Jenny Yang is a Chinese-Canadian scientist and entrepreneur who completed her DPhil at the University of Oxford in clinical machine learning, followed by a Marie Curie Fellowship focused on algorithmic fairness and bias mitigation. Her research sits at the intersection of machine learning and biology, with a focus on the human microbiome — an area she identified as a largely unmodelled layer that shapes drug metabolism, nutrient absorption, and individual health responses. In 2025, she co-founded Outpost Bio in London, where she serves as CEO. The company's Lab-in-the-Loop platform combines automated wet-lab experiments with machine learning to generate causal data on how microbial communities interact with chemical compounds, helping pharmaceutical, food, and consumer health companies predict product performance across diverse microbiome compositions before entering costly trials. Outpost Bio raised £2.6 million in pre-seed funding in March 2026, co-led by Merantix Capital and Seedcamp.
🎙 ABOUT HUMANIFAI HEALTHTECH:
HumanifAI HealthTech is a bi-weekly podcast exploring how AI is rewriting the rules of healthcare and putting people back at the center where they belong. Hosted by Francesca Vereb, SVP of Marketing at Net Health, the show features smart, candid conversations with leaders across the healthcare industry.
Podden och tillhörande omslagsbild på den här sidan tillhör
Net Health. Innehållet i podden är skapat av Net Health och inte av,
eller tillsammans med, Poddtoppen.