Just read a hot off the presses paper. Uses #MachineLearning to predict adverse outcome from medical scans.
Total N=32, cases=12
AUC=0.82
Sr author is full prof of BME at world renowed place
Journal IF=5
How would you describe this?
-
Show this thread
-
Replying to @venkmurthy
In situations like this, I always like to remember that I can get an AUC of ~0.8 using logistic regression in a 100,000+ sample predicting risk of diabetes using only age
1 reply 0 retweets 4 likes -
Replying to @GidMK
Venk Murthy Retweeted Venk Murthy
Agree, but then this:https://twitter.com/venkmurthy/status/1273037703873990661?s=19 …
Venk Murthy added,
1 reply 0 retweets 3 likes
Replying to @venkmurthy
Surely that's just more of a reason to give me millions of dollars in funding so that I can occasionally type "lroc diabetes age" in Stata
4:43 PM - 16 Jun 2020
0 replies
0 retweets
2 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.