What can a 2017 colonoscopy study teach us about using AI diagnostics safely in 2025?

An AI diagnostic tool boasts 99% accuracy. Should you trust it? In this episode, I explain why that number can be dangerously misleading and equip medical professionals with the practical strategies needed to see through the hype and protect their patients.As artificial intelligence becomes more integrated into healthcare, the ability to critically evaluate these tools is no longer optional; it's a core clinical skill. This session moves beyond the headlines to uncover the common, often hidden, flaws in AI training that can lead to inflated performance metrics and real-world risk. Learn how to become the essential human-in-the-loop who can distinguish a robust, reliable AI from a brittle and dangerous one.In this video, you will learn:The "Memorizing Student" Problem: A simple analogy to understand Overfitting, one of the most common ways AI models fail in the real world.How to Spot the Flaws: Practical techniques to diagnose unreliable AI, including how to interpret learning curves and why true external validation is the gold standard.The Danger of "Cherry-Picking": How selective reporting creates a false perception of reliability and why demanding transparency is crucial.The Colonoscopy Analogy: A powerful, real-world framework for how clinicians should approach AI results right now. Learn how to use a "positive" AI signal to your advantage and, more importantly, how to handle a "negative" signal to prevent catastrophic errors from automation bias.Your Ultimate Responsibility: Why the physician, not the algorithm, is always accountable and how to use AI as a tool for support, not an absolution of your clinical judgment.If you are a physician, medical student, resident, or healthcare administrator, this presentation provides the foundational knowledge you need to navigate the next wave of medical technology safely and effectively.

Are we caught in another tech hype cycle with AI? The promise of technology often clashes with financial and practical reality. This presentation cuts through the noise to offer a clear and balanced framework for thinking about the future of artificial intelligence in business and society.Join me for a thoughtful exploration of how to navigate the booms and busts of innovation. Using the "Could, Should, Might, and Don't" mindsets developed by futures designer Nick Foster, this talk dissects the different ways we approach the future—from the exciting, sci-fi visions of "Could Futurism" to the critical, ethical questions of "Don't Futurism."In this video, you will learn:How to recognize the phases of a technology hype cycle and avoid common pitfalls.The four key mindsets for engaging with the future of AI.Why user-centric design and adaptability are crucial for successful innovation, learning from past tech implementations.The importance of balancing optimism with a healthy dose of skepticism and ethical consideration.What are your thoughts on the future of AI? Which mindset—Could, Should, Might, or Don't—resonates most with you?

This episode provides an overview of Total Energy Expenditure (TEE) and Basal Energy Expenditure (BEE), emphasizing their definitions, measurement methods, and patterns across the human lifespan. It explains that TEE is the total of all calories burned, comprised mainly of BEE (the energy needed for basic functions at rest), the Thermic Effect of Food, and Physical Activity Energy Expenditure. Contrary to common beliefs, I explain that metabolism remains stable from ages 20 to 60, and midlife weight gain is primarily linked to lifestyle shifts rather than a sudden slowdown. The episode stresses the importance of objective measurement techniques, such as doubly labeled water for TEE, and highlights that body composition, particularly lean mass, is the main determinant of BEE. Finally, it corrects misconceptions regarding the impact of exercise and notes that metabolism declines gradually only after age 60, largely due to loss of lean tissue.

Sources:

Herman Pontzer, Yosuke Yamada, Hiroyuki Sagayama, Philip N. Ainslie, Lene F. Andersen, Liam J. Anderson, Lenore Arab, Issaad Baddou, Kweku Bedu-Addo, Ellen E. Blaak, Stephane Blanc, Alberto G. Bonomi, Carlijn V.C. Bouten, Pascal Bovet, Maciej S. Buchowski, Nancy F. Butte, Stefan G. Camps, Graeme L. Close, Jamie A. Cooper, Richard Cooper, et al. Daily energy expenditure through the human life course. Science, 373(6556):808–812, 2021. doi:10.1126/science. abe5017.

Kay Nguo, Helen Truby, and Judi Porter. Total energy expenditure in healthy ambulatory older adults aged ≥80 years: A doubly labelled water study. Annals of Nutrition and Metabolism, 79(2):263–273, 2023. doi:10.1159/000528872.

John R. Speakman, Jasper M. A. de Jong, Srishti Sinha, Klaas R. Westerterp, Yosuke Yamada, et al. Total daily energy expenditure has declined over the last 3 decades due to declining basal expenditure not reduced activity expenditure. Nature Metabolism, 5(4):579–588, 2023. doi:10.1038/s42255-023-00782-2.

Marie-Pierre St-Onge and Dympna Gallagher. Body composition changes with aging: The cause or the result of alterations in metabolic rate and macronutrient oxidation? Nutrition, 26(2):152–155, February 2010. doi:10.1016/j.nut.2009.07.004.