Class weight modifiers applied to 'no mention' cases in the loss function improve rule-out performance for negated disease findings in deep classifiers trained on chest X-ray data derived from clinical notes.
We achieved this by automatic text analysis of the reports accompanied by the MIMIC-CXR dataset [3]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Boosting the rule-out accuracy of deep disease detection using class weight modifiers
Class weight modifiers applied to 'no mention' cases in the loss function improve rule-out performance for negated disease findings in deep classifiers trained on chest X-ray data derived from clinical notes.