Can reproducibility be improved in clinical natural language processing? A study of 7 clinical NLP suites.

Abstract

The increasing complexity of data streams and computational processes in modern clinical health information systems makes reproducibility challenging. Clinical natural language processing (NLP) pipelines are routinely leveraged for the secondary use of data. Workflow management systems (WMS) have been widely used in bioinformatics to handle the reproducibility bottleneck. To evaluate if WMS and other bioinformatics practices could impact the reproducibility of clinical NLP frameworks. Based on the literature across multiple researcho fields (NLP, bioinformatics and clinical informatics) we selected articles which (1) review reproducibility practices and (2) highlight a set of rules or guidelines to ensure tool or pipeline reproducibility. We aggregate insight from the literature to define reproducibility recommendations. Finally, we assess the compliance of 7 NLP frameworks to the recommendations. We identified 40 reproducibility features from 8 selected articles. Frameworks based on WMS match more than 50% of features (26 features for LAPPS Grid, 22 features for OpenMinted) compared to 18 features for current clinical NLP framework (cTakes, CLAMP) and 17 features for GATE, ScispaCy, and Textflows. 34 recommendations are endorsed by at least 2 articles from our selection. Overall, 15 features were adopted by every NLP Framework. Nevertheless, frameworks based on WMS had a better compliance with the features. NLP frameworks could benefit from lessons learned from the bioinformatics field (eg, public repositories of curated tools and workflows or use of containers for shareability) to enhance the reproducibility in a clinical setting.