Ok … let’s unpack this nature.com/articles/d4158…

The punchline: Despite the claims -- and my desire as well -- nobody is predicting & preventing sports injuries with machine learning/AI. (1/6)
What are they actually doing? They're surveilling athletes 24/7, collecting truckloads of highly intimate and personal information, and calculating ‘workloads’ by way of questionable methods link.springer.com/article/10.100… @francoimpell (2/6)
Methods early proponents (cited by Rossi) are now walking back from ... "player workloads are merely a reference metric rather than a causal prognostic factor and they will never be able to predict injury with accuracy" ✌️@Billy_Hulin
researchgate.net/publication/35… (3/6)
Truest line in nature.com/articles/d4158…?

"There’s a gap between how much data we’ve been capturing and what’s actually been done with it... We’re trying to fill that gap using machine learning.” (4/6)
I’d love someone to show me a single article that uses machine learning/AI to PREDICT and PREVENT sports injuries. This is an aspiration -- but we're currently a long way from it (5/6)
This is why our projects led by @JuliaPowles @uwanews with @Science_Academy @theAIS & more are so crucial.

Let's call the game: boundless data capture is not it. We need evidence-based, mechanistic, scientifically rigorous approaches to the complexities of injury & health (6/6)

• • •

Missing some Tweet in this thread? You can try to force a refresh

Keep Current with JacquelineUWA

JacquelineUWA Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!


Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!