AI in health and medicine | Eric Topol, Scripps Research Translational Institute | Discovery |
|
Discover how Artificial Intelligence (AI) is poised to broadly reshape medicine, improving the experiences of both clinicians and patients. Dr. Topol will discuss the key findings from a 2-year weekly effort to track and share key developments in medical AI, and cover prospective studies and advances in medical image analysis, which have reduced the gap between research and deployment. Several promising avenues for novel medical AI research including non-image data sources, unconventional problem formulations and human–AI collaboration will be presented. Lastly, he will discuss the consideration of serious technical and ethical challenges in issues spanning from data scarcity to racial bias. As these challenges are addressed, AI’s potential may be realized, making healthcare more accurate, efficient and accessible for patients worldwide.
Speakers: Eric Topol, Professor, Molecular Medicine, and Executive Vice-President of Scripps Research, and Founder and Director of its Scripps Research Translational Institute Shownotes: 00:00 Panelist intro 1:31 Zak Kohane 5:58 Eric Topol, Scripps Research Translational Institute 7:20 ai and medicine 8:26 retina 8:55 what the machine sees in the retina 9:45 myocardial infarction from scans and personal information 10:29 seen in the ECG 10:55 ECG-based Atrial Fibrillation 11:22 elevated pulmonary capillary from ECG 12:00 Ejection fraction detection 12:46 Arrhythmic sudden death survival prediction 13:50 beta-blocker response - cluster analysis 14:42 pathology 15:45 EGFR genotype and targeted therapy 16:34 mammography and breast cancer risk 17:51 data being missed 18:28 delayed and missed care 19:21 prospective trials in clinical environments 19:56 randomized trials 21:15 speech recognition for the hearing impaired 21:29 opportunities for augmentation 22:20 new guidelines for AI clinical research 23:28 disappointments == 23:56 COVID via Chest X-rays 25:26 Breast screening programmes 26:45 colonoscopy 27:48 AI in the ER 28:14 subtle shift in patient data 28:48 sepsis 29:12 clinical implementation 30:13 Ziad Obermeyer 30:33 Trust in AI 30:49 doctorless diagnosis 30:51 opportunities 33:55 the virtual medical assistant 33:34 ethical challenge 35:21 explainability and trust 35:53 principled AI 36:11 federated learning 36:59 swarm learning 37:51 inequities 38:24 smartphone ultrasound 38:58 AI wihh smartphone ultrasound 40:02 Topol medical selfie 40:27 telephone connections - target COVID aid 41:34 the robot will see you now 42:00 Topol Review of the NHS 43:34 natural language processing 43:51 thinking, fast and slow 44:27 the gift of time 44:52 there is no algorithm for empathy 44:56 Francis Peabody 45:53 == Q&A == 45:55 use of stethoscope in medicine schools 46:59 entrenchment in medicine 47:37 smartphone ultrasound 48:00 inertia 48:30 Topol clinic 49:22 the need for change 50:10 disbelief among medical students 51:12 combining western and traditional medicine 51:53 the book deep medicine – progress since 52:18 going beyond accuracy 53:18 interpretation of genomes – human limitations 53:43 data donations 54:08 “All of us” 55:43 should medical practices create their own AI? 56:13 context dependent – don’t want to reinvent the wheel 57:26 is the FDA well equipped for AI? 57:30 retrospective, proprietary algorithms, frozen algorithms 58:22 thanks from the moderator 58:37 thanks from ITU Explore more #AIforGood content: AI for Good Top Hits https://www.youtube.com/playlist?list=PLQqkkIwS_4kXXQWhP4vSr0Rtl13t2Ud2w AI for Good Webinars https://www.youtube.com/playlist?list=PLQqkkIwS_4kUwDVioxixBf8OYlGAS_9_z AI for Good Keynotes https://www.youtube.com/playlist?list=PLQqkkIwS_4kUmK6zjiuWWE4fImrbGBWRF Stay updated and join our weekly AI for Good newsletter: http://eepurl.com/gI2kJ5 Discover what's next on our programme! https://aiforgood.itu.int/programme/ Check out the latest AI for Good news: https://aiforgood.itu.int/newsroom/ Explore the AI for Good blog: https://aiforgood.itu.int/ai-for-good-blog/ Connect on our social media: Website: https://aiforgood.itu.int/ Twitter: https://twitter.com/ITU_AIForGood LinkedIn Page: https://www.linkedin.com/company/26511907 LinkedIn Group: https://www.linkedin.com/groups/8567748 Instagram: https://www.instagram.com/aiforgood Facebook: https://www.facebook.com/AIforGood What is AI for Good? The AI for Good series is the leading action-oriented, global & inclusive United Nations platform on AI. The Summit is organized all year, always online, in Geneva by the ITU with XPRIZE Foundation in partnership with over 35 sister United Nations agencies, Switzerland and ACM. The goal is to identify practical applications of AI and scale those solutions for global impact. Disclaimer: The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU. #AIforGoodDiscovery #AIforHealth #AIforMedicine |