Computational Linguistics for Enhancing Scientific Reproducibility and Reducing Healthcare Inequities

Julia Parish-Morris


Abstract
Computational linguistics holds promise for improving scientific integrity in clinical psychology, and for reducing longstanding inequities in healthcare access and quality. This paper describes how computational linguistics approaches could address the “reproducibility crisis” facing social science, particularly with regards to reliable diagnosis of neurodevelopmental and psychiatric conditions including autism spectrum disorder (ASD). It is argued that these improvements in scientific integrity are poised to naturally reduce persistent healthcare inequities in neglected subpopulations, such as verbally fluent girls and women with ASD, but that concerted attention to this issue is necessary to avoid reproducing biases built into training data. Finally, it is suggested that computational linguistics is just one component of an emergent digital phenotyping toolkit that could ultimately be used for clinical decision support, to improve clinical care via precision medicine (i.e., personalized intervention planning), granular treatment response monitoring (including remotely), and for gene-brain-behavior studies aiming to pinpoint the underlying biological etiology of otherwise behaviorally-defined conditions like ASD.
Anthology ID:
W19-3011
Volume:
Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venues:
CLPsych | NAACL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
94–102
Language:
URL:
https://www.aclweb.org/anthology/W19-3011
DOI:
10.18653/v1/W19-3011
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-3011.pdf