The Lifelong Study: Insights From Rotterdam

In biomedical AI, we constantly ask: Do we need more data, or do we need a smarter model?

In this episode, we break down The Zeta Law of Discoverability—a theoretical framework linking sample size complexity to the Riemann zeta function. We explore how signal-to-noise accumulates across spectral modes like a "Tower of Hanoi" puzzle, why certain diseases (like Alzheimer’s) can be detected with small datasets while others (like psychiatric conditions) need massive samples, and the counterintuitive "three-modality paradox"—how adding seemingly redundant data (like text) can dramatically boost sample efficiency by steepening spectral decay.

Welcome back to the podcast! Today we are diving into a thought-provoking new paper titled 'AI Must Embrace Specialization via Superhuman Adaptable Intelligence' by researchers including Judah Goldfeder and Yann LeCun.

If you follow the tech world, you hear the term AGI—Artificial General Intelligence—thrown around constantly by executives, doomsayers, and politicians. But this paper argues that our entire obsession with AGI is fundamentally flawed because it relies on the illusion that human intelligence is 'general'.

The authors argue that humans aren't actually general intelligence engines at all; we are highly specialized creatures who were honed by evolution to master a very narrow set of skills required for survival.Instead of chasing the myth of AGI, the authors propose a new North Star for the field: Superhuman Adaptable Intelligence, or SAI.

Rather than trying to build a single, monolithic AI that can do literally everything, SAI focuses on adaptability—specifically, the speed at which an AI can learn and master new, important tasks.

As the authors brilliantly put it: 'The AI that folds our proteins should not be the AI that folds our laundry!'.

This paper makes a compelling case that to push the boundaries of technology, we need to abandon our human-centric biases and lean into specialized models powered by self-supervised learning and world models. Let's get into it!"

Why are global Parkinson's disease cases projected to skyrocket to 25.2 million by 2050?

In this episode, we explore an ingenious "bathtub analogy" to explain this massive growth. We break down the "inflow" of new cases (driven by aging populations, environmental risks, and better diagnoses) and the "outflow" (where improved survival rates keep overall numbers high).

Tune in to find out why our healthcare systems are at risk of "overflowing" and the urgent need for new preventative and curative solutions!

Few scientific papers truly define a field. The Hallmarks of Cancer is one of them.

In this episode, I dive into the evolution of the Hallmarks framework—where it started, how it has shaped decades of cancer research, and how it continues to evolve today.

A must-listen for anyone curious about the foundations of modern cancer biology.

This episode dives into the history and persistent gaps in women’s health research — from decades of exclusion in clinical trials to today’s underfunding of critical conditions like menopause, autoimmune diseases, and cardiovascular health. We also explore the rise of FemTech, AI-powered precision medicine, and new policy initiatives reshaping the future of equitable healthcare for women.

Our latest podcast episode delves into the critical paper: "Bias recognition and mitigation strategies in artificial intelligence healthcare applications" . This essential review highlights how AI, despite its immense value and rapid growth in clinical practice, can inadvertently perpetuate healthcare disparities through various forms of bias.

De Rotterdam Studie is een langlopende, populatie-gebaseerde cohortstudie in Nederland die zich richt op het identificeren van risicofactoren en het begrijpen van het verloop van multifactoriële aandoeningen, met name bij mensen van middelbare en oudere leeftijd. Het onderzoek beslaat een breed scala aan ziektegebieden, waaronder hart- en vaatziekten, diabetes, interne geneeskunde, longziekten, dermatologie, neurologische aandoeningen, geestelijke gezondheid, aandoeningen van het bewegingsapparaat, keel-, neus- en oorheelkunde, leverziekten, populatiebeeldvorming en populatiegenomica. Onderzoekers van de Rotterdam Studie maken gebruik van diverse methoden voor gegevensverzameling, waaronder vragenlijsten, lichamelijke onderzoeken, biologische monsters en geautomatiseerde koppeling met medische dossiers. Zij onderzoeken actief de rol van genetica, leefstijl en omgevingsfactoren bij het ontstaan en verloop van ziekten.

We’re standing at a turning point in AI. Until now, machines have learned by studying us — reading our books, analyzing our conversations, mimicking our decisions.
But what happens when AI starts learning from its own experiences — exploring, experimenting, and evolving, just like humans?
In this episode, I break down the big ideas from "The Era of Experience" by David Silver and Richard Sutton, and explain (in plain English!) how this shift could unlock superhuman abilities — and what it means for our future.
Come along for a fascinating ride into the next generation of intelligent systems — no tech degree required!

AI is now helping to analyse your medical scans, but hidden factors could be leading to wrong answers. Join us as we uncover a clever new way AI can cut through this confusion, revealing the real links in your health images and making sense of what's truly there.https://www.sciencedirect.com/science/article/pii/S1361841525000775

Ever wondered how the tiny universe inside your gut impacts your health from childhood to old age?

Join us on "Gut Feelings" as we delve into the fascinating link between your gut microbiome and metabolic health across the entire lifespan.

We explore the groundbreaking findings of a major population-based study that identified distinct gut microbiome patterns associated with healthier and unhealthier metabolic statuses in pre-adolescents, adults, and older adults.

https://doi.org/10. 1016/j.lanepe.2024. 101195