iiinova — where your digital self keeps evolving

Madison Coots

@madisoncoots.com

Public Policy PhD Student @Harvard 📚 | @Stanford CS Alum 👩🏻‍💻 | Plant Hobbyist 🌱 | Interested in using data science to design policy and drive reform

Posts Replies Media

Madison Coots @madisoncoots.com · 13/12/2024

We conclude by arguing for an alternative framework for the design of equitable algorithms that moves beyond scrutinizing narrow statistical metrics and instead foregrounds health outcomes and utility and clarifies important trade-offs.

100

Madison Coots @madisoncoots.com · 13/12/2024

For each algorithm, we organize the fairness concerns into a taxonomy of four broad categories: 1️⃣ Inclusion/exclusion of race and ethnicity as inputs 2️⃣ Unequal decision rates across groups 3️⃣ Unequal error rates across groups 4️⃣ Label bias

100

Madison Coots @madisoncoots.com · 13/12/2024

🚨 Excited to share our new article in @annualreviews.bsky.social. Working with Kristin Linn, @5harad.com, Amol Navathe, and Ravi Parikh, we examine the fairness debates of seven prominent and controversial healthcare algorithms.🧵 madisoncoots.com/files/racial...

274

Madison Coots @madisoncoots.com · 05/12/2024

Yet, despite this miscalibration, clinical decisions (e.g., screening or treatment recommendations) differ between race-aware and race-unaware models for only a small fraction of individuals (~5%). The individuals whose decisions flip are those closest to the decision threshold.

100

Madison Coots @madisoncoots.com · 05/12/2024

Using cardiovascular disease, breast cancer, and lung cancer as case studies, we show that race-unaware models are often miscalibrated—underestimating risk for some groups and overestimating it for others. This finding is consistent with evidence cited in support of the use of race-aware models.

100

Madison Coots @madisoncoots.com · 05/12/2024

The use of race in clinical risk models is heavily debated. While race-aware models can be more accurate, some are concerned about reinforcing racialized views of medicine. In our paper, we offer a new perspective on this debate. 🧵👇https://annals.org/aim/article/doi/10.7326/M23-3166

123