What if a chatbot designed to support recovery instead encouraged the very behaviors it was meant to prevent? In this episode, we unravel the cautionary saga of Tessa, a digital companion built by the National Eating Disorder Association to scale mental health support during the COVID-19 surge—only to take a troubling turn when powered by generative AI.

At first, Tessa was a straightforward rules-based helper, offering pre-vetted encouragement and resources. But after an AI upgrade, users began receiving rigid diet tips: restrict calories, aim for weekly weight loss goals, and obsessively track measurements—precisely the advice no one battling an eating disorder should hear. What should have been a lifeline revealed the danger of unguarded algorithmic “help.”

We trace this journey from the earliest chatbots—think ELIZA’s therapeutic mimicry in the 1960s—to today’s sophisticated large language models. Along the way, we highlight why shifting from scripted responses to free-form generation opens doors for innovation in healthcare and, simultaneously, for unintended harm. Crafting effective guardrails isn’t just a technical challenge; it’s a moral imperative when lives hang in the balance.

As providers eye AI to extend care, Tessa’s story offers vital lessons on rigorous testing, transparency around updates, and the irreplaceable role of human oversight. Despite the pitfalls, we close on a hopeful note: with the right safeguards, AI can amplify human expertise—transforming support for vulnerable patients without losing the empathy and nuance only people can provide.

Reference:

National Eating Disorders Association phases out human helpline, pivots to chatbot
Kate Wells
NPR, May 2023

An eating disorders chatbot offered dieting advice, raising fears about AI in health
Kate Wells
NPR, June 2023

The Unexpected Harms of Artificial Intelligence in Healthcare
Kerstin Denecke Guillermo Lopez-Compos, Octavio Rivera-Romero, and Elia Gabarron
Studies in Health Technology and Informatics, May 2025

Credits:

Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 4.0
https://creativecommons.org/licenses/by/4.0/

What if an AI could write your medical chart—and what happens when it gets it wrong? Doctors have long lamented the paperwork that comes with every patient encounter. “Charting was the bane of my existence,” admits Dr. Laura Hagopian, an emergency physician who’s spent countless hours piecing together fragmented notes and outdated records. Could artificial intelligence finally lift this administrative weight?

Recent advances in large language models promise to generate discharge summaries as accurately as seasoned clinicians, potentially returning precious time to the bedside. By training on thousands of patient encounters and lab reports, these systems can stitch together coherent narratives of care—micro-diagnoses, treatment plans, and follow-up recommendations—at a speed no human chart-writer can match.

Yet with speed comes risk. When an AI hallucination slips into a diagnosis and becomes enshrined in a patient’s record, who is accountable? Dr. Hagopian highlights the stark difference between human and machine error: “I feel very different about a human making a mistake compared to an AI making a mistake.” As trust in automated documentation grows, so too do questions about responsibility, oversight, and patient safety.

In this episode, AI researcher Vasanth Sarathy and Dr. Hagopian peel back the layers of these complex issues. They explore the nuts and bolts of AI summarization algorithms, discuss promising clinical trials, and weigh the ethical dilemmas of delegating clinical judgment to code. How do we ensure that efficiency doesn’t override accuracy when every data point can mean life or death?

Whether you’re a clinician craving relief from chart fatigue, an AI developer pushing the boundaries of what’s possible, or a patient curious about who’s really recording your health story, this conversation offers a vital look at the future of medical documentation. Join us as we navigate the promise—and the pitfalls—of letting machines tell our most critical health narratives.

References:

Physician- and Large Language Model–Generated Hospital Discharge Summaries
Christopher Y. K. Williams, et al.
JAMA, Internal Medicine, 2025

Credits:

Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 4.0
https://creativecommons.org/licenses/by/4.0/

What if a 19th-century nurse laid the foundation for 21st-century disease surveillance?

Florence Nightingale, widely known for her compassion, was also a pioneering statistician who used data to reveal a hidden crisis: more soldiers in the Crimean War were dying from infections than from battle wounds. Her insights led to life-saving reforms—and sparked a revolution in how we understand public health.

Today, that same spirit of data-driven action lives on through artificial intelligence. In this episode, we explore how modern AI systems are transforming outbreak detection by scanning signals across the digital world—social media, search trends, news in multiple languages, even environmental data—to identify early signs of emerging health threats.

From tools like HealthMap to natural language processing engines that monitor disease mentions across continents, AI has already proven its value by detecting outbreaks like H1N1 and COVID-19 before official systems sounded the alarm. But history reminds us that data can be misleading: Google Flu Trends famously overestimated flu cases by mistaking media buzz for actual spread.

That’s why the most powerful systems today pair AI with human epidemiologists, combining rapid pattern recognition with expert judgment. It’s a modern-day continuation of Nightingale’s legacy—a partnership where algorithms spot weak signals, and people decide how to act.

This episode uncovers how statistical thinking has evolved into intelligent surveillance, offering public health leaders a critical advantage: time. Time to act, time to intervene, and time to prevent the next outbreak before it becomes a crisis.

References:

Artificial intelligence in public health: the potential of epidemic early warning systems
Chandini Raina MacIntyre, Xin Chen, Mohana Kunasekaran, Ashley Quigley, Samsung Lim, Haley Stone, Hye-young Paik, Lina Yao, David Heslop, Wenzhao Wei, Ines Sarmiento, Deepti Gurdasani
Journal of International Medical Research, March 2023

Digital Disease Detection — Harnessing the Web for Public Health Surveillance
John S. Brownstein, Clark C. Freifeld, Lawrence C. Madoff
The New England Journal of Medicine, May 2009

HealthMap: Global Infectious Disease Monitoring through Automated Classification and Visualization of Internet Media Reports
Clark C. Freifeld, Kenneth D. Mandl, Ben Y. Reis, John S. Brownstein
Journal of the American Medical Informatics Association (JAMIA), 2008

Surveillance Sans Frontières: Internet-Based Emerging Infectious Disease Intelligence and the HealthMap Project
John S. Brownstein, Clark C. Freifeld, Ben Y. Reis, Kenneth D. Mandl
PLoS Medicine, July 2008

AI systems aim to sniff out coronavirus outbreaks
Adrian Cho
Science, May 2020

Real-time alerting system for COVID-19 and other stress events using wearable data
Arash Alavi, Gireesh K. Bogu, Meng Wang, Ekanath S. Rangan, Andrew W. Brooks, Qiwen Wang, Emily Higgs, Alessandra Celli, Tejaswini Mishra, Ahmed A. Metwally, and many others
Nature Medicine, January 2022

Real-Time Digital Surveillance of Vaping-Induced Pulmonary Disease
Yulin Hswen, John S. Brownstein
The New England Journal of Medicine, October 2019

Advances in Artificial Intelligence for Infectious-Disease Surveillance
John S. Bro

What if the next breakthrough treatment for a rare disease was already sitting on the pharmacy shelf?

Drug repurposing, the science of finding new uses for existing medications, is transforming how we discover treatments, blending serendipity with strategy. It began with surprises like Viagra, a heart drug turned blockbuster, but today it's driven by advanced data tools that accelerate discovery and reduce risk.

We explore how knowledge graphs (vast maps of biomedical relationships between drugs, genes, and diseases) are now at the core of this revolution. When paired with artificial intelligence, these networks can surface overlooked connections buried in decades of medical literature. Unlike opaque algorithms, these AI systems can explain why a drug might work for a new condition, providing testable hypotheses and building trust with clinicians.

This approach doesn’t just save time—it can save lives. Traditional drug development takes over a decade and billions of dollars. Repurposed drugs, having already passed safety checks, can reach patients faster and cheaper. That’s a game-changer for rare and neglected diseases where time and resources are limited.

This episode is a journey through beautiful mistakes and brilliant methods, showing how multidisciplinary teams, from data scientists to clinicians, are reshaping the future of medicine. Join us to learn how technology is turning chance into choice, and uncovering new hope in old drugs.

References

Drug repurposing: approaches, methods and considerations | Elsevier
Elsevier Industry Overview
(No individual author listed)

Trends and Applications in Computationally Driven Drug Repurposing
Luca Pinzi & Giulio Rastelli
International Journal of Molecular Sciences, 2023

Biomedical Knowledge Graph Refinement with Embedding and Logic Rules
Sendong Zhao, Bing Qin, Ting Liu, Fei Wang
arXiv preprint, 2020

COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation
Qingyun Wang et al.
NAACL Demonstrations, 2021

Explainable Drug Repurposing via Path Based Knowledge Graph Completion
Ana Jiménez, María José Merino, Juan Parras, Santiago Zazo
Scientific Reports, 2024

Knowledge Graphs for Drug Repurposing: A Review of Databases and Methods
Pablo Perdomo-Quinteiro & Alberto Belmonte-Hernández
Briefings in Bioinformatics, 2024

Credits:

Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 4.0
https://creativecommons.org/licenses/by/4.0/

What if a convincing medical article you read online—citing peer-reviewed journals and quoting real-sounding experts—was entirely fabricated by AI?

In this episode, we dive into the unsettling world of AI-generated health disinformation. Researchers recently built custom GPT-based chatbots trained to spread myths. The result? Persuasive narratives full of fabricated studies, misleading statistics, and plausible-sounding jargon—powerful enough to sway even savvy readers.

We break down how these AI systems were created, why today’s safeguards failed to stop them, and what this means for public health. With disinformation spreading faster than truth on social media, even a single viral post can lead to real-world consequences: lower vaccination rates, delayed treatments, or widespread mistrust in medical authorities.

But there’s hope. Using a four-pronged approach—fact-checking, digital literacy, communication design, and policy—we explore how society can fight back. This episode is a call to action: to become vigilant readers, ethical technologists, and thoughtful citizens in a world where even falsehoods can be generated on demand.

References:

How to Combat Health Misinformation: A Psychological Approach
Jon Roozenbeek & Sander van der Linden
American Journal of Health Promotion, 2022

Health Disinformation Use Case Highlighting the Urgent Need for Artificial Intelligence Vigilance: Weapons of Mass Disinformation
Bradley D. Menz, Natansh D. Modi, Michael J. Sorich, Ashley M. Hopkins
JAMA Internal Medicine, 2024

Current Safeguards, Risk Mitigation, and Transparency Measures of Large Language Models Against the Generation of Health Disinformation
Bradley D. Menz et al.
BMJ, 2024

Urgent Need for Standards and Safeguards for Health-Related Generative Artificial Intelligence
Reed V. Tuckson & Brinleigh Murphy-Reuter
Annals of Internal Medicine, 2025

Assessing the System-Instruction Vulnerabilities of Large Language Models to Malicious Conversion Into Health Disinformation Chatbots
Natansh D. Modi, Bradley D. Menz, and colleagues
Annals of Internal Medicine, 2025

Credits:

Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 4.0
https://creativecommons.org/licenses/by/4.0/

What if a simple photograph of your eye could prevent blindness? Diabetic retinopathy silently steals vision from millions worldwide, yet it's treatable when caught early. The challenge? Too few specialists, limited access to care, and not enough awareness about this serious complication of diabetes.

We dive deep into how artificial intelligence is transforming this landscape by analyzing retinal photos with remarkable accuracy. Through neural networks trained on thousands of eye images, these systems can detect subtle signs of disease—microaneurysms, hemorrhages, and abnormal blood vessels—that signal potential vision loss. With accuracy rates exceeding 98% for severe cases, AI technology serves not as a replacement for ophthalmologists but as a powerful triage tool that extends their reach.

The implications are profound, especially for underserved areas where specialists are scarce. By implementing AI screening at primary care visits, more people with diabetes can receive timely evaluation without the barriers of specialist referrals, travel costs, or time off work. The technology represents a perfect example of human-AI collaboration: machines handle initial screening at scale, while medical professionals focus their expertise on treatment and complex cases. This partnership model could revolutionize preventive care for one of the leading causes of preventable blindness worldwide.

References mentioned:

• Performance of a Deep Learning Diabetic Retinopathy Algorithm in India - PubMed
• Diabetic Retinopathy Is Massively Underscreened-An AI System Could Help - PubMed
• A deep learning based model for diabetic retinopathy grading | Scientific Reports
• A Survey on Deep-Learning-Based Diabetic Retinopathy Classification - PMC

Credits:

Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 4.0
https://creativecommons.org/licenses/by/4.0/