Steven Hirsch (@_stevenhirsch) profile picture

PhD, Biomechanics | Opinions are my own

Toronto, Ontario
Joined January 2019
Photo by Steven Hirsch (@_stevenhirsch)Photo by Steven Hirsch (@_stevenhirsch)Photo by Steven Hirsch (@_stevenhirsch)Photo by Steven Hirsch (@_stevenhirsch)
Steven Hirsch retweeted
As part of our partnership with @DrivelineBB , excited to share the initial report from @drivelinekyle , comparing Uplift Capture to gold standard markered and marker-less motion capture systems #transparencymatters #motioncapture #majorleaguebaseball #baseball #sportstechnology
This quoted post is unavailable.
2
4
1,506
Steven Hirsch retweeted
We are incredibly excited to partner with @DrivelineBB @drivelinekyle to provide portable, markerless motion capture for their biomechanics assessments. Stay tuned for the validation work we will collaboratively share in both the short & long term! #motioncapture #sportsscience
This quoted post is unavailable.
1
5
23
16,704
ACWR dividing the acute load by a random generated chronic load or fixed values gives same results. We warned there was something wrong. In the preprint the details. Thanks to all my co-authors @avigotsky, @AaronCoutts, @Maurizi13707619, @Alan_McCall_, osf.io/preprints/sportrxiv/e…
10
106
20
315
#ASB2023 week is here! We are thrilled to share this terrific line-up of sessions and events. Thanks to the organizing committee for putting it all together! asbweb.org/program/
9
3
22
6,194
ete-online.biomedcentral.com… This is a crucial concept to understand! It's common to falsely equate variables with predictive capacity of some outcomes as a causal factor, especially when assessing human movement to reduce injuries or improve athletic performance.
1
2
122
But it's entirely possible for factors that can predict injury/performance to have no causal link to that outcome, and factors that do not predict outcomes can still be causal factors! This has significant implications for designing training or rehabilitation programs.
1
29
Steven Hirsch retweeted
Labels matter for both researchers & clinicians So understanding the critical differences between 'Description, Prediction, & Causation in Sport and Exercise Medicine Research' will help us improve clinical care 🤝 Learn more 👉 ow.ly/xG3r50Pb1HV #yourJOSPT
10
1
29
11,725
Evaluating the assumptions on ratio scaling in biomechanics part 2! 🧵 sciencedirect.com/science/ar…
1
42
…(similar to how it is important to check other statistical assumptions when performing data analyses, such as ensuring the residuals of your regression models are normally distributed)…
1
32
…We have provided some sample R code in the supplementary materials of this paper, but I'll be putting together more comprehensive (and generalizable) R code in the future that will also include more thorough equivalence testing!
37
If you're at #ACSM23, I'm hiring for both a Master's and PhD level biomechanist! DM me to chat about it at the conference. Please spread the word and join me at @WVURNI! @AcsmBig @ACSMNews
1
9
11
4,148
JUST PUBLISHED!! CMCC's Director Human Performance Research, Dr. Howarth, questions conclusion re. spine flexion and its association with LBP from recent study in @ergonomics1957. 50 FREE DOWNLOADS tandfonline.com/eprint/SDPKN…
8
10
895
To lift without rounding your back, necessary motion must be reallocated to other joints. To find out where and how this motion is redistributed, check out our new pub! @_Tyson_Beach @JackieZehr @ChiroHPL authors.elsevier.com/c/1fy7B…
4
13
1
20
Steven Hirsch retweeted
“…even with an extensive data set, including anthropometric, clinical, neuromuscular, genetic, and sophisticated 3D biomechanical measurements, ACL injury prediction was poor…” Do we need to predict injuries to prevent them? Risk reduction heuristics? journals.sagepub.com/doi/ful…
3
6
Steven Hirsch retweeted
Too many studies that apply machine learning to science & medicine employ incorrect methodologies. Many make very basic mistakes, such as not having separate training & test sets, using the test set (not a separate validation set) for feature selection, hyperparameter tuning, etc
There’s a reproducibility crisis brewing in almost every scientific field that has adopted machine learning. On July 28, we’re hosting an online workshop featuring a slate of expert speakers to help you diagnose and fix these problems in your own research: sites.google.com/princeton.e…
24
173
20
899