Using Natural Language Processing to Predict Fatal Drug Overdose From Autopsy Narrative Text: Algorithm Development and Validation Study.

Leigh Anne Tang Jessica Korona-Bailey Dimitrios Zaras Allison Roberts Sutapa Mukhopadhyay Stephen Espy Colin G Walsh

Published in: JMIR public health and surveillance (2023)

The random forest classifier may be suitable for identifying potential accidental and undetermined fatal overdose autopsies. Further validation studies should be conducted to ensure early detection of accidental and undetermined fatal drug overdoses across all subgroups.

Keyphrases

climate change
machine learning
autism spectrum disorder
emergency department
adverse drug
risk assessment
deep learning
drug induced
human health
electronic health record