Please read and agree to the terms and conditions of this site.
@ACKoongMDPhD 3 years ago
Combination of symptoms and sleep/activity data from wearables gives greatest AUC for predicting #COVID pos or neg in symptomatic population. Future of medicine arriving now. #DataScience https://go.nature.com/3oXtC1Q
@AriErcole 4 years ago
Comprehensive meta-analysis from @ESICM data science in Intensive Care Medicine: #MachineLearning can predict sepsis with AUC between 0.68–0.99 (ICU), 0.96–0.98 (hospital) and 0.87-0.97 (ED) But only 3 clinical implementations #TranslationGap https://doi.org/10.1007/s00134-019-05872-y https://t.co/HX9Gln3pAY
@raamana_ 4 years ago
tips to review #MachineLearning papers, esp. in #medicine & #neuroscience: -ask for a flowchart from raw data to final metrics! -don't assume CV (like repeated holdout) and advanced metrics (AUC) are implemented correctly. If you don't follow it drunk, they're likely wrong!