@gretel_ai 2 years ago
A new study that used Gretel’s synthetic data API to augment a limited EEG dataset improved its ML model accuracy by an average of 14%. Exciting to see #syntheticdata supporting medical research. https://loom.ly/3p9wJx0 #datascience #developers https://t.co/95H1rezTis
@LauraBBalzer 5 years ago
Last ? from #DataScience 4 Public Health course- Who would you trust: a blackbox machine learning algorithm with 100% CV-prediction accuracy (AUROC=1) built with representative data OR a human medical provider (accuracy<100%; AUROC<1)? #epiTwitter #MachineLearning #SuperLearner