
The AI Health Podcast
By Pranav Rajpurkar, Adriel Saporta, Oishi Banerjee, Marc Robbins

The AI Health PodcastJul 26, 2022

Harvard's Dr. George Church on Aging Reversal, Woolly Mammoths, and the Future of Genomics

How Academia Can Make an Impact: University of Michigan's Dr. Karandeep Singh on Deployment and Evaluation

Immunai's Luis Voloch on Industrial-Scale Immunology

Changemakers and Truth-Seekers: Johns Hopkins's Dr. Suchi Saria on Bayesian Health

Medical (Incentives) Engineering: Harvard's Dr. Trishan Panch on Wellframe, Research and Entrepreneurship

The Medical AI 2x2: GV’s Dr. Krishna Yeshwant on Market Positioning and Investing

Like the Internet in 1999: Andreessen Horowitz‘s Julie Yoo on Investing and Modernizing Healthcare

Building a Bicycle: Obvious Ventures’ Nan Li on Investing and Platform Biology

Illuminating Mental Illness: The National Institute of Mental Health's Dr. Joshua Gordon on AI and Psychology

The Economics of AI: Stanford's Dr. Susan Athey on How AI Shapes Markets

Correlation vs. Causation: Stanford's Dr. Sherri Rose on Informing Health Policy
Sherri Rose, Ph.D. is an Associate Professor at Stanford University in the Center for Health Policy and Center for Primary Care and Outcomes Research. She speaks with us about detangling causation from correlation, measuring the effectiveness of different interventions, and influencing real-world health policy.
Pranav and Adriel first give an overview on risk adjustment, where medicine, health policy, and financial incentives interact in complex ways, before the interview, which starts at 12:04. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Painful Paperwork: AKASA's Varun Ganapathi on Improving Medical Billing
Varun Ganapathi, Ph.D. is co-founder and CTO at AKASA. He speaks with us about surprise bills and other medical paperwork problems and explores how AI can make healthcare billing less painful for all of us.
If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

A 5-Minute Explanation: Wired's Tom Simonite on AI Journalism
Tom Simonite is a senior writer for WIRED covering AI. Previously, he was San Francisco bureau chief at MIT Technology Review, and he wrote and edited technology coverage at New Scientist magazine in London. He speaks with us about his writing process and the challenges of keeping the general public informed about AI and health.
If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Citizen Endo and Enigmatic Illness: Columbia's Dr. Noémie Elhadad on Tech, Equity, and Citizen Science
Dr. Noémie Elhadad is an Associate Professor of Biomedical Informatics, affiliated with Computer Science and the Data Science Institute at Columbia University. She speaks with us about her work on using AI and crowdsourced data to study menstrual health. More broadly, she discusses opportunities and challenges around crowdsourced health information, which can help researchers learn about otherwise understudied conditions and efficiently collect otherwise hard-to-access medical data.
Pranav and Adriel first give an overview of endometriosis and Professor Elhadad's work with self-tracked data. The interview with Professor Elhadad starts at 8:25. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Thou Shalt Share: Harvard’s Professor Zak Kohane on Making Our Data Work for Us
Zak Kohane, M.D., Ph.D., is the Chair of the Department of Biomedical Informatics at Harvard Medical School. He speaks with us about sharing medical data and using AI to gain actionable insights from it.
Pranav and Adriel first give an overview on the rules and standards that shape medical data sharing today. The interview with Professor Kohane starts at 12:21. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Verily's Dr. Vivian Lee on The Annual Trillion Dollar Tug-of-War
Vivian S. Lee, M.D., Ph.D., M.B.A. is the President of Health Platforms at Verily Life Sciences and a senior lecturer at Harvard Medical School. She speaks with us about her recent book, The Long Fix: Solving America's Health Care Crisis with Strategies that Work for Everyone, and explores how AI can make the US healthcare system more efficient and effective.
Pranav and Adriel first give an overview on how financial incentives shape healthcare. The interview with Dr. Lee starts at 12:05. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Dr. Daphne Koller of insitro on Digital Biology and Drug Discovery
This is the last episode of Season 1. Join us in the Fall for Season 2, and in the meantime, please take our brief survey! http://bit.ly/theaihealthpodcast
Dr. Daphne Koller is CEO and Founder of insitro, a machine-learning enabled drug discovery company. She has been a Stanford CS Professor, co-founder of Coursera and Engageli, one of TIME Magazine’s 100 influential people, and a MacArthur Fellow. She speaks with us about how insitro uses AI and induced pluripotent stem cells to make drug discovery more efficient and successful.
Pranav and Adriel first give an overview on pluripotent stem cells. The interview with Dr. Koller starts at 5:41. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

The FDA's Bakul Patel on Regulating AI Medical Devices
Bakul Patel is the director of the FDA's Digital Health Center of Excellence. In this interview, he shares his perspective on approving AI systems. He discusses how the FDA is evolving to keep up with the medical AI market, and he addresses key ethical concerns such as equity and access.
Pranav and Adriel first give an overview on the FDA's premarket pathways for medical devices. The interview with Bakul starts at 8:56. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Medical AI and Outcomes Research with Yale's Dr. Harlan Krumholz
Harlan Krumholz is a cardiologist and scientist at Yale University and Yale New Haven Hospital. He is the Harold H. Hines, Jr. Professor of Medicine and is the founder and Director of the Yale Center for Outcomes Research and Evaluation (CORE), one of the nation’s most prominent groups working to improve health and health care. In this interview, he discusses how AI can improve medical outcomes and how engineers can better harness its power by interpreting both inputs and outputs with more nuance.
Pranav and Adriel first give an overview on big data and how ready medicine is to handle big data. The interview with Dr. Krumholz starts at 6:33. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

AI-Powered Cardiac Monitoring with iRhythm's Michael Coyle and Dr. Mark Day
Mike Coyle is the CEO of iRhythm, and Mark Day is the Executive Vice President of Research & Development of iRhythm, a digital healthcare company redefining the way cardiac arrhythmias are clinically diagnosed by combining wearable biosensing technology with cloud-based data analytics and machine learning capabilities. Together, they speak with us about how AI can help diagnose heart problems and enable longer-term cardiac monitoring. They discuss iRhythm's technology, its business strategy, and the power of AI-human collaboration.
Pranav and Adriel first give an overview on heart arrhythmias and ambulatory ECGs. The interview with Mike and Mark starts at 6:42. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Dr. Eric Topol on the Transformative Power of Medical AI
Dr. Eric Topol is a cardiologist, a professor, a best-selling author and the founder and director of the Scripps Research Translational Institute. In this wide-ranging conversation, he explains how medical AI can harness new data sources, draw novel connections and restore the human connection between doctor and patient. He also discusses key challenges facing the field, especially around reproducibility and regulation.
Pranav and Adriel first give an overview of precision medicine and provide context for the interview. The interview with Dr. Topol starts at 4:22. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

AI for Stethoscopes with Eko's Connor Landgraf
Connor Landgraf is the CEO and co-founder of Eko, a cardiopulmonary digital health company. He speaks with us about AI for auscultation, the unique challenges of developing hardware as well as software, and the roller-coaster ride of running a start-up.
Pranav and Adriel first give an overview on the history of the stethoscope. The interview with Connor starts at 6:35. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

COVID-19 and Racial Inequality with Microsoft Research's Dr. Emma Pierson
Dr. Emma Pierson is a senior researcher at Microsoft Research and an incoming assistant professor of computer science at Cornell Tech. Her work has been recognized by a Rhodes Scholarship and Forbes 30 Under 30 in Science, and she has written for publications like The New York Times, FiveThirtyEight, The Atlantic, The Washington Post, and Wired. She speaks with us about her research on racial inequities in COVID-19 testing and pain disparities, and she gives advice to aspiring AI researchers.
Pranav and Adriel first give an overview on some of Emma's papers that will be discussed in the interview, which starts at 4:12. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Facebook AI Research's Dr. Joelle Pineau on COVID-19 Projects
Joelle Pineau is co-Managing Director of Facebook AI Research (FAIR), supporting labs across North America and Europe. She is also a faculty member at Mila and an Associate Professor and William Dawson Scholar at the School of Computer Science at McGill University, where she co-directs the Reasoning and Learning Lab. She speaks with us about FAIR's research into AI and medicine, with special attention to Facebook's COVID-19 projects.
Pranav and Adriel first give an overview on computer vision and the history of pretraining and finetuning models in the context of medical imaging. The interview with Dr. Pineau starts at 8:12. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

DCVC's Dr. Kiersten Stead on Venture for Deep Tech in Life Sciences
Dr. Kiersten Stead is a Managing Partner at DCVC Bio, a venture capital fund supporting companies using deep tech within life science industries. She talks with us about opportunities within biomedical AI, especially around making clinical trials more efficient.
Pranav and Adriel first give an overview on digital twin technology for the interview, which starts at 7:02. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

AI for Accessible Ultrasounds with Caption Health's Dr. Charles Cadieu
Dr. Charles Cadieu is the co-founder and CEO of Caption Health. Previously, he was an expert in deep learning at MIT and Berkeley and was a founding member of IQ Engines, acquired by Yahoo!. In this interview, he explains how Caption Health is using AI to make it easier for clinicians to capture high-quality ultrasound images. He also discusses broader questions of how AI can make medicine more accessible and equitable, and he gives insight into the process of developing a medical AI startup.
Pranav and Adriel first give an overview on ultrasounds and provide context for the interview, which starts at 5:44. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Promise and Pitfalls of AI for Dermatology with UT Austin's Dr. Adewole Adamson
Dr. Adewole "Ade" Adamson is a board-certified dermatologist and assistant professor in the Department of Internal Medicine at Dell Medical School at the University of Texas at Austin. He speaks with us about AI applications in dermatology and addresses challenges around racial bias and overdiagnosis.
Pranav and Adriel first talk about the potential for racial disparities in ML systems for dermatology and provide context for the interview, which starts at 5:06. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

a16z's Dr. Vijay Pande on Innovation in Medical AI
Dr. Vijay Pande is a general partner at Andreessen Horowitz and an Adjunct Professor of Bioengineering at Stanford University. As the founding investor of a16z’s Bio Fund, he leads the firm’s investments at the cross section of biology and computer science. He speaks with us about drug discovery and other major opportunities for entrepreneurs in the medical AI space.
Pranav and Adriel first talk about the protein folding problem and the Folding@Home Distributed Computing Project, and then provide context for the interview, which starts at 6:44. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Dr. Andrew Ng on the State of AI
Andrew Ng is Founder of DeepLearning.AI, General Partner at AI Fund, Chairman and Co-Founder of Coursera, and an Adjunct Professor at Stanford University. A pioneer in both machine learning and online education, Dr. Ng now focuses primarily on his entrepreneurial ventures, looking for the best ways to accelerate responsible AI practices in the larger global economy. In this wide-ranging interview, he discusses both the specific challenges of developing AI for healthcare and the broader state of AI.
Pranav and Adriel first talk about the cost and compute of AI breakthroughs, and then provide context for the interview, which starts at 7:53. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Clinical Trial Reporting for AI Interventions with Dr. Alastair Denniston and Dr. Xiao Liu
Our guests today are Dr. Alastair Denniston and Dr. Xiao Liu. Together they discuss their work on SPIRIT-AI and CONSORT-AI, two pioneering sets of guidelines that help researchers conduct and report AI clinical trials in a safe, transparent manner.
Dr. Alastair Denniston is a consultant ophthalmologist, an honorary professor at University Hospitals Birmingham and the Centre for Regulatory Science and Innovation at the University of Birmingham. Dr. Xiao Liu is an ophthalmology resident and clinical researcher at the University of Birmingham and University Hospitals Birmingham.
Pranav and Adriel first discuss why clinical trial guidelines are necessary and then provide context for the interview, which starts at 7:20. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Lux Capital's Zavain Dar on Investing and Drug Discovery
Our guest today is Zavain Dar, a partner at Lux Capital and a founding investor in Anagenex. He speaks about his investments in cutting-edge medical tech companies, especially in the drug discovery space. He also describes common pitfalls faced by medical start-ups and gives advice to aspiring entrepreneurs.
Pranav and Adriel first discuss Pfizer-BioNTech's and Moderna's COVID mRNA vaccines and then provide context for the interview, which starts at 7:02. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Google Health's Dr. Lily Peng on AI for Disease Screening
Our guest today is Dr. Lily Peng, a product manager at Google Health. Named to Fortune's 2020 "40 Under 40 - Healthcare" list, she describes her work on automatic disease screening, exploring the challenges of design and deployment. She also discusses her own career path and the role of Big Tech in healthcare.
Pranav and Adriel first discuss the challenges in deploying AI technologies, and then provide context for the interview, which starts at 6:02. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

AI-Enabled Scribes and Entrepreneurship with Ian Shakil (Augmedix)
Our guest today is Ian Shakil, Founder, Director, and Chief Strategy Officer of Augmedix. He explains how Augmedix is changing how electronic health records are generated, saving doctors time and improving patient experience. He also tells the story of how he founded Augmedix, and he discusses how his company differentiates itself in a competitive market.
Pranav and Adriel first give a history of EHRs and provide context for the interview. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Race, Medical Data and AI with University of Toronto's LLana James
Our guest today is LLana James, Faculty of Medicine and PhD candidate at the University of Toronto and the AI, Medicine & Data Justice Post Doctoral Fellow at Queen’s University. She explains how racism has shaped Western medical practice, and she discusses the insidious ways in which old biases resurface in modern medical AI.
Pranav and Adriel first give some background on how racial biases surface in modern AI before the interview. If you'd like to skip right to the interview with LLana, start listening at 7:37. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Interpretability and Data Challenges with Duke University's Dr. Cynthia Rudin
Our guest today is Dr. Cynthia Rudin, a professor of computer science, electrical and computer engineering, and statistical science at Duke University. She describes her work on data-driven risk prediction models, which have been validated in real Intensive Care Units and provide a simpler, effective alternative to neural nets. She also discusses the benefits of model interpretability and the challenges that researchers face when accessing medical data.
Pranav and Adriel first provide context for the interview, giving an overview of prognostic models, interpretability and black box models, and GDPR and CCPA, which starts at 13:05. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Deployment and FDA Approvals with Digital Diagnostics' Dr. Michael Abramoff
Our guest today is Dr. Michael Abramoff, founder and executive Chairman of Digital Diagnostics and a professor at the University of Iowa. He describes how Digital Diagnostics won the first FDA's approval for an autonomous medical AI system. He also gives advice on how to deploy medical AI systems and ensure they are useful, reliable and ethically sound.
Pranav and Adriel first give an overview of the FDA and IDx-DR, and provide context for the interview, which starts at 12:18. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Pathology AI and Entrepreneurship with PathAI's Dr. Aditya Khosla
Our guest today is Dr. Aditya Khosla, co-founder and CTO of PathAI. He discusses PathAI's cutting-edge work on using deep learning for pathology, explaining how AI can more accurately diagnose cancer and personalize medical treatment. He also gives advice from in the trenches on creating and funding successful AI health start-ups.
Pranav and Adriel first give an overview of pathology AI and sources of funding for AI health start-ups, and provide context for the interview, which starts at 12:26. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

NEA's Blake Wu on Healthcare Investing and Data
Our guest today is Blake Wu, a partner at New Enterprise Associates specializing in healthcare services, healthcare IT, and biopharmaceuticals. He discusses NEA's investments in AI for radiology and medical analytics, plus the challenges of investing in healthcare internationally and the near-term future of medical AI.
Before the interview, Pranav and Adriel give overviews on healthcare roll-ups, value-based care vs. fee-for-service care, and real-world data and evidence. If you'd like to skip right to the interview with Blake, start listening at 11:29. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

The Frontier of Radiology AI with Stanford AIMI's Dr. Matthew Lungren
Our guest today is Dr. Matthew Lungren, Co-Director of the Stanford Center for Artificial Intelligence in Medicine and Imaging and Associate Professor in the Department of Radiology at Stanford University Medical Center. Dr. Lungren discusses the need for AI in radiology, the technical and legal challenges of clinical deployment, and the exciting future of deep learning for medicine.
Pranav and Adriel first give a history of computer aided diagnosis (CAD) and introduce convolutional neural networks (CNNs) before the interview. If you'd like to skip right to the interview with Matt, start listening at 8:17. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Annie Lamont (Oak HC/FT) on Innovation in Healthcare
Our guest today is Annie Lamont, a Co-Founder and Managing Partner of Oak HC/FT, where she focuses on growth equity and early-stage venture opportunities in healthcare. Described by The New York Times as "one of the most successful women ever in the lofty realm of venture capital," Annie talks to us about the evolution of the healthcare market and some notable medical AI companies in her portfolio. She also makes predictions about post-COVID healthcare and shares advice for aspiring health tech entrepreneurs.
Pranav and Adriel first give an overview of Medicare and the Affordable Care Act, and then provide context for the interview, which starts at 9:38. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.

Drug Discovery's AI Paradigm Shift with Dr. Abraham Heifets (Atomwise)
Our guest today is Dr. Abraham Heifets, CEO and Co-Founder of Atomwise, whose research on AI-enhanced drug discovery was featured in the July 2019 Moonshot issue of Newsweek. He discusses Atomwise's pioneering work on the use of deep convolutional neural networks for faster drug discovery, allowing researchers to screen billions of molecules in a matter of days.
Pranav and Adriel first give an overview of drug discovery and provide context for the interview, which starts at 7:10. If you like what you hear, let a friend know, subscribe wherever you get your podcasts, and connect with us on Twitter @AIHealthPodcast.