Click the menu icon in the upper right of the video to select 1-7 in the playlist.
As we have witnessed in recent years, there has been a lot of confusion around the use of race and ethnicity in medicine and medical algorithms. Precision Medicine 2021: Race & Ethnicity focused on how they inform and bias precision medicine* diagnostics and therapeutics. We also addressed how machine learning has the potential to both accentuate and reduce existing bias in these precision medicine tasks. We provided expert-led discussions of how identity is used in care and how to best advance precision medicine for all populations. As we have done in previous years, we centered on elevating the patient voice and building patient engagement.
Tuesday, September 14, 2021
9:30 am – 4:00 pm ET
|Time||Topic & Speaker(s)|
|9:30–9:40 AM||Welcome — Isaac Kohane, Harvard Medical School|
|9:40–9:50 AM||Opening Remarks — George Daley, Dean, Harvard Medical School|
|9:50–10:35 AM||Opening Keynote — Tabia Akintobi, Morehouse School of Medicine|
|10:35–11:35 AM||PANEL 1 — The environmental determinants of health equity
Genetics has had a disproportionately large profile in the public and professional understanding of disease risk. To date there has been insufficient measurement of the environmental and cultural contributions to disease diagnosis and treatment. In this panel, we explore how to assess this contribution and how it can and should inform our implementations of precision medicine.
|11:35 AM – 1:00 PM||Lunch|
|1:00–2:00 PM||PANEL 2 — Achieving performance and equity in clinical practice
Estimating kidney function has served as a canary-in-the-coal-mine of an urgent and overdue reconsideration of how to personalize treatments and avoid using coarse group memberships such as “self-reported race” in providing this personalization. We discuss the challenges and the path forward to achieve precision medicine while moving beyond problematic and imprecise labels that have traditionally been used in medical equations.
|2:10–3:10 PM||PANEL 3 — Fairness, bias and race in an algorithmic world
As medicine becomes more data-driven and more computationally-enabled, how does computation inform bias—good and bad—in the practice of medicine and what is there specifically around the data that we acquire and the algorithms that we write? In this panel we will address emerging approaches to promote the equitable deployment of clinical artificial intelligence.
|3:10–3:55 PM||Closing Keynote — Gary Gibbons, NHLBI|
|3:55–4:00 PM||Closing Remarks — Isaac Kohane, HMS|
Location and Registration
The 2021 conference was held virtually, with an in-person option at the Joseph B. Martin Conference Center in Boston for the Harvard University community. This on-site attendance limitation was due to ongoing COVID-19 restrictions.
Contact us at firstname.lastname@example.org.
Conference sponsored by Takeda, Genentech, Medidata, Merck, and Pfizer.
*What do we mean by “precision medicine”? From the perspective of one of the members of the National Academy of Sciences committee that wrote the report, we mean taking an explicit multidimensional view of patients: not just one data modality such as genomics or environmental exposure. We argue that this perspective allows for more precise matching of humans to disease states (diagnosis), future disease states (prognosis) and appropriate therapies.