Interview with Dr. Vamsi Krishna Ithapu (Meta): Designing for Cognitive Load in Patient Communication

Dr. Vamsi Ithapu has spent his career studying how people process information and building technology that reduces cognitive overload. His work is grounded in a deceptively simple question: how much information can people actually process in critical moments? During his PhD at the University of Wisconsin-Madison, he built predictive models for Alzheimer's disease. Later, at Meta Reality Labs, he led teams building systems designed to reduce cognitive overload for millions of users. In this episode, he brings that perspective into healthcare and makes a compelling case for why patient communication should be designed with cognitive load in mind. This conversation explores why discharge instructions so often fail, what healthcare gets wrong about information delivery, and how systems can be built around what patients are actually able to absorb in vulnerable moments. Vamsi also breaks down the difference between prediction, reasoning, and planning in AI, where large language models are useful in clinical settings, and where leaders should be far more skeptical. We also discuss what it takes to move from research to real-world product, what healthcare can learn from consumer-scale technology, and why defining an ideal recovery state may be the most important starting point in designing better surgical journeys. The Surgical Journey is sponsored by NovaNav, the surgical patient journey platform designed to reduce readmissions, coordinate post-surgical care, and support patients from the OR through full recovery. Learn more at NovaNav.ai. In this conversation, we discuss: Dr. Ithapu shares four lessons from Meta's product experience that translate directly to health system AI strategy The three core things AI systems actually do: prediction, reasoning, and planning, plus where healthcare expectations often go wrong The reality of large language models in clinical environments: where they are useful, where they hallucinate with dangerous confidence, and what hospital leaders should be asking vendors right now A different way to think about discharge instructions. Cognitive overload is a design problem as much as it is a technology problem. We talk about what "minimum viable information" might look like for a surgical patient going home The idea of a "North Star" recovery state: defining what ideal recovery actually looks like for a patient, then designing the entire surgical journey backward from that point Throughout the episode, Dr. Ithapu disvusses where these systems help, where they fail, and what healthcare leaders need to understand before adopting them in clinical workflows. The discussion is especially relevant for anyone thinking seriously about discharge, recovery, and the gap between technical capability and patient reality. The Surgical Journey is sponsored by NovaNav, the surgical patient journey platform designed to reduce readmissions, coordinate post-surgical care, and support patients from the OR through full recovery. Learn more at NovaNav.ai. Episode Timestamps 0:00 Introduction to NovaNav 0:58 Introduction to Dr. Ithapu 4:38 From Alzheimer's research to Meta Reality Labs 5:52 Why "AI" is an overloaded term 6:03 The three functions of AI: prediction, reasoning, and planning 7:40 What AI is actually good at today, and where it still struggles 10:16 What hospital executives should ask AI vendors 11:42 Why personalization in healthcare is different from consumer tech 18:49 Where LLMs are genuinely useful in clinical settings 19:45 Hallucinations, opacity, and why failure is hard to detect 25:57 Discharge instructions and cognitive overload 29:40 "Minimum viable information" for patients going home 32:17 What it takes to move from research to real-world product 33:10 Four product lessons healthcare can borrow from Meta 41:23 Why not every healthcare problem needs an AI solution 47:26 The "North Star" framework for recovery and care design 48:11 Closing