activity
20172020
most citedConfounding variables can degrade generalization performance of radiological deep learning models

1.7k citations · 1.7k across the 6 of their papers we have counts for

collaborators
Showing 2020Show all

2 papers · 1 filter

cs.LG2020

Controlling Level of Unconsciousness by Titrating Propofol with Deep Reinforcement Learning

Gabe Schamberg, Marcus Badgeley, Emery N. Brown

Reinforcement Learning (RL) can be used to fit a mapping from patient state to a medication regimen. Prior studies have used deterministic and value-based tabular learning to learn…

cs.CL2020★ 3 cited

Quantification of BERT Diagnosis Generalizability Across Medical Specialties Using Semantic Dataset Distance

Mihir P. Khambete, William Su, Juan Garcia +1

Deep learning models in healthcare may fail to generalize on data from unseen corpora. Additionally, no quantitative metric exists to tell how existing models will perform on new d…