Josh Cardosi (@ladothlak) profile picture

ML in Healthcare Researcher

Columbus, Ohio
Joined June 2020
Photo by Josh Cardosi (@ladothlak)
Replying to @ProfSiston
@ProfSiston good timing with 6700!
Calcium hyperproficiency is a rare complication of vitamin D deficiency, where excess calcium from bone resorption forms complex structures resembling primary teeth. Neoformed teeth grow on different bones, such as this patient's hand, causing fractures and joint dysfunction.
1
Thankfully apparently not real 😅
If you aren't following @stratosinit already, this may be a good time to start
Reporting and handling missing values in observational research. This paper introduces the TARMOS framework Open access: jclinepi.com/article/S0895-4…
12
41
Authors designed a #ML model not requiring restrictive criteria/medical expertise in order to generalise #trauma outcome predictions in US #EDs. "Machine learning for outcome predictions of patients with trauma during emergency department care" ow.ly/SKEy50GoZKf #bmjhci
3
1
Josh Cardosi retweeted
After 14 years and 24 'minor' version increments, I am really excited for scikit-learn to go v1.0 🥳🎉 Release notes here: scikit-learn.org/dev/whats_n…
We just put out a release candidate for the next release (version 1.0), with many new features, and you can test it by `pip install --pre scikit-learn`
2
68
5
579
Today, I finally started getting positive responses to my job applications. An interview and a code screening! I am beyond excited. It's been tough applying for so many positions, but I think things are looking up :) #jobsearch #celebrate
1
Taking up this year's Advent of Code challenge! I'm excited to tackle some of the more difficult problems as the month goes on. Join up here: adventofcode.com/2020 #adventofcode2020 #AdventOfCode
1
1
Josh Cardosi retweeted
#hacktoberfest2020 was great for me thanks to @zerotomasteryio 's discord community for helping me to figure things out. I made some really great PRs that I am proud of and one of them is this artwork for @deno_land .#designer #CodeNewbie #100DaysOfCode
4
19
2
99
Josh Cardosi retweeted
These two figures basically list all of the methods people have tried so far to make stochastic gradient descent work “Descending through a Crowded Valley — Benchmarking Deep Learning Optimizers” arxiv.org/abs/2007.01547
10
221
14
932
In our work "Machine Intelligence for Outcome Predictions of Trauma Patients During Emergency Department Care," we present a novel architecture for detecting patients at high risk for mortality based on commonly available patient data. arxiv.org/abs/2009.03873 #AI #ML #healthcare
1
3
2
Just finished the excellent joke telling project from @AndreiNeagoie 's js projects course and added some of my own ideas as well. Thank you for the consistently excellent quality classes! #ZeroToMastery ladothlak.github.io/Joke-Tel…
2
1
8
Barriers to Autonomous AI in Healthcare: A discussion on the challenges of integrating decision-making AI into healthcare. Passive AI is changing how we think about patient health, but autonomous AI has yet to take center stage. Why? #AI #MachineLearning shorturl.at/vACIU
Josh Cardosi retweeted
Michela Paganini, Postdoctoral Researcher, shares her personal experience creating a core PyTorch feature: Pruning (torch.nn.utils.prune). In this talk, you will learn about pruning, why it's important and how to get started: youtu.be/TaOwEa3m5dw
2
55
1
248
Josh Cardosi retweeted
The full version of the Deep Learning with PyTorch book from Luca Antiga, Eli Stevens, and Thomas Viehmann is now available! New chapters include in-depth real-world examples and production deployment. Grab a free digital copy on: pytorch.org/deep-learning-wi…
26
678
77
2,332