🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Here's the slide that describes what Stanford hospital leadership have called "a very complex algorithm." Makes you wonder why they used the term "algorithm" in the first place. It's as if they thought the branding would help the human decision-makers shirk responsibility.

"This review indicates that [the 145 reviewed covid-19] models are poorly reported, at high risk of bias, and their reported performance is probably optimistic. Hence, we do not recommend any of these reported prediction models for use in current practice" bmj.com/content/369/bm…

Check out our new preprint on medRxiv!

The last paper from my PhD, "Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcare", has been accepted at FAccT! With Yizhe Xu, 忍, Nikos Ignatiadis, Julian Genkins, Nigam Shah. Preprint: arxiv.org/abs/2202.01906.

Very thoughtful analysis Stanford Department of Medicine by Agata Foryciarz, Stephen Pfohl, Birju Patel on the interaction between imposing fairness constraints and practice guideline adherence. Good example of our holistic view at Stanford Medicine as suggested by Stanford HAI

I stand in solidarity with Stanford & Packard Children's Hospital nurses fighting for a fair wage and sustainable working conditions. For two years, our nurses have been on the frontlines of the COVID pandemic – they deserve more than just our gratitude. sfchronicle.com/health/article…

This week at #FAccT2022, check out our paper “Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcare”. dl.acm.org/doi/10.1145/35…. With Yizhe Xu 忍 Nikos Ignatiadis Julian Genkins Nigam Shah

'Evaluating algorithmic fairness in the presence of clinical guidelines: the case of atherosclerotic cardiovascular disease risk estimation' bit.ly/3xNf2k2 Agata Foryciarz Stephen Pfohl Birju Patel Nigam Shah #specialcollection #specialissue

Our recent BMJ paper (with Stephen Pfohl Birju Patel Nigam Shah) on fairness evaluations of medical algorithms just got covered on the Stanford HAI blog! You can read the article here: hai.stanford.edu/news/ensuring-…

Thanks for the highlight on our 2021 JBI paper, "An Empirical Characterization of Fair Machine Learning for Clinical Risk Prediction". I encourage anyone interested to also check out our new paper published at FAccT this year that expands on the 2021 paper dl.acm.org/doi/abs/10.114…

During 4 days of card collecting, we have gathered over 3200 signed cards, including the majority of PhDs! Thank you to our awesome organizers for making this happen. Let’s finish the week strong with as many cards as we can! Sign here: sgwu.us