The Lifelong Study: Insights From Rotterdam

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

Could a new treatment be on the way for prostate cancer? We explore early research into [177Lu]Lu-NeoB, a substance targeting prostate cancer cells. This treatment has shown promise in slowing cancer growth and extending life in early studies. Surprisingly, giving more of this treatment didn't always work better and could potentially affect the kidneys. We'll explain these important findings and discuss how this new approach might fit with current prostate cancer therapies.https://link.springer.com/article/10.1007/s11307-023-01851-4

Missed ECR 2024 or want a refresher? We're diving back into the key discussions and breakthroughs from the European Congress of Radiology 2024. From AI implementation and integrated diagnostics to new techniques in musculoskeletal imaging and debates around the future of chest X-rays, we'll explore how these advancements are shaping radiology today. Tune in to get up to speed before the next wave of innovation hits!

his podcast episode explores a major study analysing over 5.5 million dementia cases, revealing critical insights into life expectancy and nursing home admissions. Discover how prognosis is significantly affected by factors like age, sex, and the type of dementia. We discuss the wide range of survival times, from 2.2 years to 8.9 years, and how a large proportion of remaining life is spent in nursing homes, with a median time to admission of 3.3 years. Learn how these findings can help families and healthcare professionals better plan for and navigate the challenges of dementia. Brück, C.C., Mooldijk, S.S., Kuiper, L.M., Sambou, M.L., Licher, S., Mattace-Raso, F. and Wolters, F.J., 2025. Time to nursing home admission and death in people with dementia: systematic review and meta-analysis. bmj, 388.

Delve into the groundbreaking world of multi-omics, where scientists combine data from genes, proteins, metabolites, and more to unlock the secrets of health and disease. Join experts as they explore cutting-edge technologies, innovative applications in drug discovery, and the future of precision medicine. Get ready to be inspired by the power of multi-omics! https://frontlinegenomics.com/multi-omics-playbook-2024/

This podcast offers listeners a front-row seat to the latest breakthroughs discussed at the Cohorts for Heart and Aging Research in Genomic Epidemiology (CHARGE) Investigator Meeting in Rotterdam. Instead of focusing solely on genomics, we will broaden the scope to encompass the exciting advancements in precision medicine. https://www.chargeconsortium.com/

Join us as we explore the controversial world of biological aging clocks. Do they hold the key to understanding and treating age-related diseases, or are they misleading measures based on a flawed understanding of aging? We examine the scientific evidence and discuss the implications for health research. https://www.nature.com/articles/s41591-024-03297-9

Join us as we explore the fascinating world of 3D stereophotogrammetry and its impact on the diagnosis and treatment of craniosynostosis, a condition affecting the skull's development in infants.

What makes us who we are? Is it our genes, our upbringing, or a complex mix of both? The Generation R Study seeks to answer these questions by following a diverse group of children in Rotterdam from the womb to young adulthood.

Welcome to 'MicroMiracle,' the episode where we dive into the world of microRNA – the cellular superstars so small, yet so mighty, they've just been celebrated with a Nobel Prize for their discovery! Join us as we unravel how these minuscule molecules act like master switches, controlling everything from eye color to disease resistance, right within our cells. We'll break down the science into bite-sized, easy-to-understand pieces, exploring how microRNA impacts our health, influences aging, and even shapes the future of medicine. Whether you're fascinated by biology or just curious about what makes you, tune in to discover why these 'micro' wonders are a 'macro' deal in the grand scheme of life!

Have you ever wondered how tiny variations in our DNA can lead to complex diseases? This podcast takes you on a journey into the world of human genetics, exploring the challenges of interpreting non-coding variants and the development of new tools like BRAIN-MAGNET that are helping to unlock the secrets of our genome. We'll discuss the implications for understanding common diseases, rare disorders, and the future of personalized medicine. https://www.medrxiv.org/content/10.1101/2024.04.13.24305761v2

This podcast explores the exciting and rapidly evolving world of artificial intelligence in medicine. Join us as we go beyond the hype and examine the real-world applications of AI in diagnosing diseases, predicting patient outcomes, and developing new treatments. We'll break down complex concepts like machine learning and deep learning, making them accessible to everyone. But it's not just about the tech – we'll also delve into the ethical considerations, the importance of explainable AI, and the challenges of integrating these powerful tools into clinical practice. Tune in to "Beyond the Average" to discover how AI is transforming healthcare, one byte at a time. https://doi.org/10.18174/662462

This week, we're talking about a surprising new tool in the fight against skin cancer: your selfie! Tune in as we discuss a fascinating study that uses AI to identify subtle facial features linked to skin cancer risk. We'll break down the science in an easy-to-understand way and explore the potential of this technology to revolutionize how we approach skin cancer screening and prevention. https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(24)00129-9/fulltext

Join us as we explore the perspectives of a large elderly patient population on telemedicine during the COVID-19 pandemic. We'll unpack the pros and cons, examine what factors influence patient preference for virtual or in-person consultations, and consider the implications for the future of healthcare. Is telemedicine here to stay, or is it just a passing fad? Tune in to find out! https://bmchealthservres.biomedcentral.com/articles/10.1186/s12913-023-09794-w

In this episode we are talking about the report from The Lancet which summarizes a recent commission on dementia prevention, intervention, and care. The authors reviewed existing research and conducted new meta-analyses to identify 14 potentially modifiable risk factors for dementia. These risk factors are categorised by the stage of life in which they are most impactful, and the commission has calculated the population attributable fraction (PAF) for each factor, finding that nearly half of dementia cases could be prevented by eliminating these risks. The report provides a comprehensive overview of current research on dementia, including a discussion of modifiable risk factors, interventions for cognitive and neuropsychiatric symptoms, and the use of biomarkers for diagnosis and clinical trials. https://doi.org/10.1016/ S0140-6736(24)01296-0

This podcast explores a new study published in the European Radiology journal examining the progression of arterial calcification over a 14 year period. We'll uncover what causes these 'hidden harbingers' of disease, learn where they occur in our bodies, and discover how cardiovascular risk factors and sex impact their development. Join us as we translate the science and explain why understanding arterial calcification matters for your health https://doi.org/10.1007/s00330-023-10566-7

In this series, we dive into the fascinating world of genetics and how our DNA can help us understand the causes of diseases. This episode focuses on a groundbreaking technique called Mendelian Randomization, which uses genetic differences to figure out how certain risk factors—like high blood pressure or diabetes—affect our health. The catch? Many of these factors are either "yes" or "no" (you either have the condition, or you don’t), but the science behind them is much more complex. We explore how researchers deal with these challenges, using our genes to make sense of the messy reality behind conditions like hypertension. Learn how scientists use genetics to uncover potential ways to prevent diseases and improve health outcomes, all while facing the tricky task of dealing with binary choices in data. Whether you're into science or just curious about how your genes influence your health, this episode will give you a clearer picture of how researchers use Mendelian Randomization to unlock the secrets of our genetic code. Based on the paper: https://pubmed.ncbi.nlm.nih.gov/30039250/

Have you ever wondered how scientists are using cutting-edge technology to understand our DNA? Join us as we explore the fascinating world of deep learning in genomics and discuss a new paper that examines how to make these powerful tools more interpretable. Deep learning, a type of artificial intelligence, is revolutionizing many fields, including genomics. By analyzing vast amounts of genetic data, these complex algorithms can uncover hidden patterns and make predictions about our health, traits, and even our ancestry. But there's a catch: deep learning models are often described as "black boxes" because it's difficult to understand how they reach their conclusions. This lack of transparency can make it challenging for scientists to trust and fully utilize these powerful tools. This is where interpretable deep learning comes in. The paper we'll be discussing, "Designing Interpretable Deep Learning Applications in Genomics: a Quantitative Analysis", explores different approaches to open up the black box and shed light on the decision-making processes of these complex models

Summary The Rotterdam Study is a long-term, population-based cohort study in the Netherlands focused on identifying risk factors and understanding the progression of multifactorial diseases, particularly in mid-life and older individuals. The research encompasses a broad range of disease areas including cardiovascular disease, diabetes, internal medicine, pulmonary disease, dermatology, neurological diseases, mental health, musculoskeletal diseases, otolaryngology, liver disease, population imaging, and population genomics. Researchers at the Rotterdam Study utilise various data collection methods including questionnaires, physical examinations, biological samples, and automated linkage to health records. They are actively investigating the roles of genetics, lifestyle, and environmental factors on disease development and progression.