ByteSight

Rare Diseases, Missing Data, and the Limits of Modern Medicine

In this episode of ByteSight, Dr. Manasi A-Ratnaparkhe [https://www.linkedin.com/in/dr-manasi-a-6286a347/] speaks with Faizan S. Mohammad [https://www.linkedin.com/in/faizansh/], founder and CEO of Leg&airy [https://legandairy.com/], about the overlooked reality of rare diseases and what it will take to change it. Drawing on personal experience navigating the healthcare system for his son, Faizan challenges the very label "rare" when an estimated 300 million people globally live with these conditions, is the problem really scarcity, or is it a failure of translation, data, and economic incentive? Together, they explore why the technology exists but the pathway to treatment doesn't, why AI alone won't solve what incomplete data created, and what a future built on individual biochemical fingerprints could look like.

AI as Data, Expertise as Insight in Life Sciences

In this episode of ByteSight, Dr. Manasi A-Ratnaparkhe [https://www.linkedin.com/in/dr-manasi-a-6286a347/] speaks with Dr. Grant Coren [https://www.linkedin.com/in/grantcoren/], Managing Director of PharmaSearch Limited, about the evolving role of AI in life sciences. Together, they explore how artificial intelligence is reshaping drug discovery, clinical trials, and leadership in pharma, while confronting critical questions around data diversity, inclusion, and human expertise. From the promise of personalized medicine to the risks of unequal representation, this conversation highlights why the future of AI in healthcare depends not only on technology, but on the data and values behind it. Learn more about Dr. Grant Coren [https://pharma-search.co.uk/management-profile/]

From Data Chaos to Clinical Clarity: How Pharma Turns Messy Clinical & Omics Data into Decisions

In this ByteSight episode, Dr. Manasi A-Ratnaparkhe speaks with Dr. Paul Agapow about why AI in biomedicine often gets the „right answer for the wrong reason.” Using the famous „wolf-husky problem,” they explore hidden correlations in medical data, why context matters as much as performance, and what it takes to move AI from pilot to real clinical impact. The conversation also dives into clinical trials as the „eye of the needle” for drug development, the cultural barriers to adoption, and why trust and explainability are essential for AI that truly helps patients.

When Policy Meets DNA: The Politics of Genomic Data

In this episode of ByteSight, Dr. Manasi A-Ratnaparkhe [https://www.linkedin.com/in/dr-manasi-a-6286a347/] speaks with Simeón Baker [https://www.linkedin.com/in/simeon-s-baker/], Executive Director of External Affairs at Genomics England, to explore what really happens when policy meets DNA. From newborn genome sequencing to national pharmacogenomics initiatives, the conversation goes far beyond science into ethics, governance, public trust, and the realities of building genomic programs at scale.   A compelling discussion on the future of genomics, the responsibilities that come with national-scale data, and how countries can move from ambition to meaningful, trusted impact. Learn more about Simeón Baker⁠ [https://www.linkedin.com/in/simeon-s-baker/]

The Last Mile of AI: Making Digital Pathology Work in Practice

Most AI models perform beautifully in the lab but fail when faced with real-world complexity. In this episode of ByteSight, host Dr. Manasi A-Ratnaparkhe [https://www.linkedin.com/in/dr-manasi-a-6286a347/] speaks with Dr. Heather Couture [https://www.linkedin.com/in/hdcouture/], Founder of Pixel Scientia Labs and host of the Impact AI podcast. Together, we explore why AI in digital pathology often fails to generalizeacross scanners, stains, and patient populations and what it really takes to build systems that are robust, explainable, and clinically meaningful. With over two decades of experience bridging AI research and healthcare practice, Heather shares practical insights on dataset diversity, model validation, and the human factors that shape trustworthy AI. Learn more about Dr.  Heather Couture [https://pixelscientia.com/].