The MaML Podcast - Medicine & Machine Learning

Beth Beadle, MD, PhD is the Director of Head & Neck Radiation Oncology at Stanford and co-creator of the Radiation Planning Assistant, a fully automated treatment planning assistant.  00:56 How did you come to the intersection of medicine and AI? 03:20  What is radiation oncology and why does it fit well with AI? 05:54 How has radiation changed in your lifetime? 09:19 What is the Radiation Planning Assistant? 13:10 Describe radiation oncology workflow before the use of the radiation planning assistant 20:45  How does the model compare humans? 23:45 Where was the data source for the radiation Planning Assistant Model? 26:45 What safeguards exist for RPA? 28:00 What has been the response from other physicians, physicists, and patients to this model? 33:30 Timeline for implementation of the radiation planning assistant? 34:45 Background of the Radiation Planning Assistant 38:25 Future of Radiation Planning Assistant implementation 40:55 Adaptive planning in radiation oncology 43:15 Future of the Radiation Planning Assistant in the next 10 years 44:50 Are there any other projects being planned currently? 47:00 How has mentorship shaped your path? 50:25 What is the future of AI in medicine in 10-20 years 51:48 What advice would you tell yourself when you were graduating from medical school 53:20 What brings your life joy and meaning? 54:50 What are your greatest fears? 55:15 Favorite places to travel?

Dr. Tignanelli is the scientific director for the Program for Clinical Artificial Intelligence at the UMN Center for Learning Health Systems Science, the director of UMN Center for Quality Outcomes, and the chair of the Health Information Technology (HIT) Committee for the American College of Surgeons. Dr. Tignanelli's work serving COVID-19 patients during the pandemic and advancing AI research earned him the title of “Health Care Hero” by the Minneapolis/St. Paul Business Journal in 2021. Follow us on Twitter @TheMaMLPodcast Guest: Christopher Tignanelli, @cjtign Host: Madeline Ahern, @maddie_ahern Producer: Kirsi Oldenburg Artwork: Saurin Kantesaria Music: Caligula - Windows96: Used with artist permission Notes: 01:00 tell us about yourself 04:00 critical care/acute care 06:30 COVID acute care 10:00 computer vision 14:00 rib fracture model 15:00 external vs internal validity 19:00 future of AI in medicine

Dr. Chenyang Xu is currently the President and Co-Chairman of PVmed Technologies, Co-Founding Partner of Silicon Valley Future Academy, Managing Partner of Brightway Future Capital, and an Advisory Board Member for the Johns Hopkins University BME department and formerly Advisory Board Member for the UC Berkeley EECS Department. He was formerly the Chief Business Officer of RSP Systems and the GM and CTO of Siemens Technology to Business (TTB) at Berkeley where he led the Siemens’s North America’s technology startup partnership and early-stage investment practice out of the Silicon Valley. As former head of Siemens Interventional Imaging Program, he led an R&D team that developed over 10 new computer vision-based medical imaging products (e.g. CartoMerge) and has achieved billion dollar scale new revenue stream. Follow us on Twitter! @TheMaMLPodcast Guest: Chenyang Xu Host: David Wu / Twitter: @davidjhwu Producer: Aaron Schumacher / Twitter: @a_schu95 Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96. Used with Artist Permission. 01:00 - tell us about your path 11:00 - the internet + grad school in the 90s 22:00 - “career thinking” advice 30:30 - Siemens VC - looking at 10,000 startups 37:00 - PVMed - AI cancer treatment company in China 43:30 - AI startup ecosystem in China vs. US vs. Europe 56:30 - Potential downsides of implementing AI too quickly? 1:02:10 - Future of AI in medicine in 10-20 yrs? 1:13:00 - “Minority Report”-like AI to predict falls? 1:16:30 - Closing Questions

Steven Lin, M.D. is the service chief of family medicine for Stanford Health Care and the Founder and Executive director for the Stanford Healthcare AI Applied Research Team.  Follow us on Twitter! @TheMaMLPodcast Host: Madeline Ahern / Twitter: @maddie_ahern Producer: Kirsi Oldenburg Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96. Used with Artist Permission.

Akilesh Bapu is co-founder and CEO of DeepScribe, an AI-powered medical scribe that passively records and understands a patient’s visit, generates a clinical note, and then seamlessly inputs it into the electronic medical record. Follow us on Twitter! @TheMaMLPodcast Guest: Akilesh Bapu / Twitter: @AkileshBapu Host: David Wu / Twitter: @davidjhwu Producer: Aaron Schumacher / Twitter: @a_schu95 Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96. Used with Artist Permission. 1:10 - Pathway towards the intersection of medicine and Machine Learning 9:45 - What specialties are best fitted for DeepScribe implementation 11:55 - How does DeepScribe find relevant information for the clinical encounter 14:45 - The creation process of the DeepScribe hardware. 18:10 - DeepScribe’s ability to discern fragments of the SOAP note 19:45 - DeepScribe and billing concerns 24:25 - Scaling the human scribe capacity behind DeepScribe 29:45 - Implementing predictive models with DeepScribe 32:00 - Voice diagnostics 33:40 - Patient privacy and DeepScribe 38:55 - Vision for deep scribe 40:20 - Google Care Studio EHR mention 42:00 - Physician Burnout 42:35 - Advice for future founders 44:15 - What brings you joy? 45:35 - What are your greatest fears? 47:00 - What gives your life meaning? 50:25 - How do medical students think about the future of healthcare

Dr. Nigam Shah is Professor of Medicine (Biomedical Informatics) at Stanford Medicine and Chief Data Scientist at Stanford Healthcare. Dr Shah’s research focuses on combining machine learning and prior knowledge in medical ontologies to enable use cases of the learning health system. Follow us on Twitter! @TheMaMLPodcast Guest: Nigam Shah / Twitter: @DrNigam Host: David Wu / Twitter: @davidjhwu Producer: Aaron Schumacher / Twitter: @a_schu95 Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96. Used with Artist Permission. TIMESTAMPS 0:45 tell us about your path and how you came to the intersection of MaML 4:15 what is the thesis of your work? 09:10 where is AI on the gartner hype curve 13:30 the equation of medicine - if risk > threshold, take action. Examples: GreenButton Consultation service + advanced care planning 27:00 how has mentorship shaped your path? 32:00 having fun in projects 34:00 “what makes a project fun?” 37:00 closing questions - what do you expect is the future of AI? 43:00 personal questions - what brings you joy?

Dr. Quynh Nguyen is an assistant professor of epidemiology and biostatistics at the University of Maryland School of Public Health. She received her PhD and MSPH in Epidemiology from University of North Carolina at Chapel Hill, Gillings School of Global Public Health. Dr. Nguyen is a social epidemiologist focusing on contextual and economic factors as they relate to health. She joined us to talk about her projects that leverage technology and big data sources to investigate and address health disparities. Host: Raeesa Kabir Producer: Kirsi Oldenburg Artwork: Saurin Kantesaria Follow us on Twitter: @TheMaMLPodcast Have a speaker you would like to see on our podcast? Contact us at contact@themamlpodcast.com

Dr. Vineeta Agarwala is a general partner at a16z, physician, adjunct clinical professor at Stanford, previously at Google Ventures, Flatiron Health, having received her MD/PhD at Harvard Medical School and the Broad Institute.  Many thanks to Ashlea Kosikowski from 1AB Media for making this episode happen! Follow us on twitter: @TheMaMLPodcast Host: David JH Wu @davidjhwu Producer: Aaron Schumacher @a_schu95 Design: Saurin Kantesaria

Dr. Harald Kittler is a Professor in the Department of Dermatology at the Medical University of Vienna, in Vienna, Austria. Dr. Kittler is the founder of Dermachallenge, a 2018 startup which uses the principles of gamification to teach and train health professionals. As a dermatologist and dermatopathologist, Dr. Kittler has a unique insight into how future physicians might be trained in his profession. Enjoy some gamification of dermatology by joining the over 5,000 players at Dermachallenge! Host: Madeline Ahern Producer: Kirsi Oldenburg Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96 (Used with artist permission) Have a speaker you would like to see on our podcast? Contact us at contact@themamlpodcast.com

Pat Walters is the Chief Data Officer and Patrick Riley is the senior VP of AI from Relay Therapeutics in Cambridge, MA. In this episode we discuss Relay's innovative approach to drug discovery, and how new developments in AI and computational modeling have accelerated this process.