We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
cover of episode Helping Doctors Make Better Decisions With Data: UC Berkeley's Ziad Obermeyer

Helping Doctors Make Better Decisions With Data: UC Berkeley's Ziad Obermeyer

2023/2/14
logo of podcast Me, Myself, and AI

Me, Myself, and AI
AI Deep Dive AI Chapters Transcript
People
S
Sam Ransbotham
S
Shervin Khodabandeh
Z
Ziad Obermeyer
Topics
Ziad Obermeyer: 我的研究主要集中于将机器学习和人工智能应用于医疗数据。然而，我花费大量时间寻求获取所需数据，这非常困难。因此，我和同事创建了Nightingale Open Science非营利组织，利用慈善资金与医疗系统合作构建有趣的数据集，包括医学影像和电子健康记录数据，并将其免费提供给全球研究人员。这些数据集旨在解决一些重要的医疗问题，例如癌症扩散、COVID-19并发症等。我们希望通过提供开放、精选的数据集，推动机器学习在医疗领域的进步，就像ImageNet等数据集推动其他领域进步一样。我的研究背景是医学和数据科学的结合，在急诊室的工作经历让我意识到机器学习可以帮助医生改进诊断等方面的工作。机器学习可以帮助医生进行更准确的诊断，并推动医学科学发展。医学中机器学习的挑战在于“ground truth”的复杂性，人类专家的意见不能被完全视为真理。算法可以揭示医学知识中的偏见，例如放射科医生在X光片上系统性地忽略了导致黑人患者疼痛的细节。算法既可以放大医疗保健系统和社会中的偏见，也可以成为促进公平的工具。创建用于训练算法的医疗数据集是一个很大的挑战，需要整合来自不同来源的数据。将机器学习应用于医疗领域需要具备医学和数据科学的双重技能。行为经济学是需要双重技能的领域的例子，这需要经济学家和心理学家的合作。建立公共资源（如Nightingale Open Science）有助于培养能够将机器学习应用于医疗领域的社区。纵向数据和数据链接的价值随着规模和范围的扩大呈指数级增长，为学习提供了新的可能性。我参与创建的Dandelion Health公司利用医疗数据开发医疗产品，这存在风险，但也有不使用数据的风险。机器学习可以用于预测阿尔茨海默病，这有助于开发预防性药物。我最引以为豪的AI成就是开发算法预测心源性猝死。我对AI的担忧是算法偏差可能造成伤害。我对AI的未来愿望是将AI应用于医疗保健等领域，创造更大的社会价值。 Sam Ransbotham: 机器学习研究人员难以获取医疗数据，限制了研究进展。探讨了是否必须具备医学和数据科学的双重技能才能将机器学习应用于医疗领域，数据量的增加可能会改变我们对疾病诊断的理解和标准。 Shervin Khodabandeh: 在医疗领域训练算法的挑战在于缺乏ground truth，需要同时纠正算法和医生的偏见或不准确之处。

Deep Dive

Chapters
Ziad Obermeyer discusses the creation of Nightingale Open Science, a nonprofit aimed at building interesting healthcare data sets in partnership with health systems, and how these data sets can drive significant advancements in medical research and practice.

Shownotes Transcript

When Ziad Obermeyer was a resident in an emergency medicine program, he found himself lying awake at night worrying about the complex elements of patient diagnoses that physicians could miss. He subsequently found his way to data science and research and has since coauthored numerous papers on algorithmic bias and the use of AI and machine learning in predictive analytics in health care.

 Ziad joins Sam and Shervin to talk about his career trajectory and highlight some of the potentially breakthrough research he has conducted that’s aimed at preventing death from cardiac events, preventing Alzheimer’s disease, and treating other acute and chronic conditions. Read the episode transcript here).

For more about Ziad: http://ziadobermeyer.com/research)

Nightingale Open Science: https://www.nightingalescience.org/)

Dandelion Health: https://dandelionhealth.ai/)

*Me, Myself, and AI *is a collaborative podcast from MIT Sloan Management Review and Boston Consulting Group and is hosted by Sam Ransbotham and Shervin Khodabandeh. Our engineer is David Lishansky, and the coordinating producers are Allison Ryder and Sophie Rüdinger.

Stay in touch with us by joining our LinkedIn group, AI for Leaders at mitsmr.com/AIforLeaders) or by following Me, Myself, and AI on LinkedIn).

Guest bio:

Dr. Ziad Obermeyer works at the intersection of machine learning and health. He is an associate professor and the Blue Cross of California Distinguished Professor at the University of California, Berkeley; a Chan Zuckerberg Biohub Investigator; and a faculty research fellow at the National Bureau of Economic Research. His papers have appeared in a wide range of journals, including Science, Nature Medicine, and The New England Journal of Medicine; his work on algorithmic bias is frequently cited in the public debate about artificial intelligence. He is a cofounder of Nightingale Open Science, a nonprofit that makes massive new medical imaging data sets available for research, and Dandelion, a platform for AI innovation in health. Obermeyer continues to practice emergency medicine in underserved communities.

We encourage you to rate and review our show. Your comments may be used in Me, Myself, and AI materials.

We want to know how you feel about Me, Myself, and AI. Please take a short, two-question survey).