(Machine) Learning About Sudden Cardiac Death

Co-sponsored by Peking University's Institute for Global Health and Development and the Asia Health Policy Program

Every year, hundreds of thousands of people suffer sudden cardiac death. What makes these deaths so tragic is that many of them are preventable, with an implanted cardioverter defibrillator (ICD) — if only we could know who was at high risk before they died. Using a massive new dataset of electrocardiograms (ECGs) linked to death certificates, we predict sudden cardiac death far better than current methods, both in a hold-out set of Swedish patients and in a completely independent dataset from Taiwan. We also show that high-risk patients — and only high-risk patients — who receive ICDs have significantly lower mortality. Finally, we create a generative model of the ECG waveform to tie what the model is ‘seeing’ back to underlying cardiac electrophysiology.

Image

Ziad Obermeyer's research uses machine learning to help doctors make better decisions and help researchers make new discoveries — by ‘seeing’ the world the way algorithms do. His work on algorithmic racial bias has impacted how many organizations build and use algorithms, and how lawmakers and regulators hold AI accountable. He is a co-founder of Nightingale Open Science and Dandelion Health, a Chan Zuckerberg Biohub Investigator, and a faculty research fellow at the National Bureau of Economic Research. He was named one of the 100 most influential people in AI by TIME magazine. Previously, he was an assistant professor at Harvard Medical School and continues to practice emergency medicine in underserved communities.