Use of Systematic Methods and Semantics, and AI to Facilitate AOP Development
On this page:
Automatic update of the information supporting an assessment is limited by manual finding, uploading, and migration of information between various systematic review tools. This is a particular challenge in the development of chemical assessments where a rapid compilation of new information and/or update to existing information is needed in a pre-decisional, regulatory context. Artificial intelligence was previously used to rapidly screen >40K studies for ~150 perfluoroalkyl substances and manually extracted data were summarized in systematic evidence maps (SEMs). Keeping these influential SEMs updated with the latest relevant research is time-consuming and labor-intensive. The use of text-mining, text analytics, natural language processing, and machine learning models to reduce this ongoing effort is a goal of the U.S. EPA Chemical Pollutant Assessment Division. However, creating such models first requires detailed, machine-readable annotation of datasets to label entities of interest. CPAD currently uses structured data extraction templates in various systematic review tools to make scientific information usable, accessible, and uniform (ensuring that the same task is not repeated multiple times internally or across agencies). Key areas needed to apply innovations in systematic review tools include mapping annotated terms that do not follow convention (e.g. linking to controlled vocabularies and ontologies), piloting annotation tool grouping and relating annotations according to predefined schema, and input/output formats that support interoperability between tools. The objective of this work is to demonstrate recent developments in systematic methods including in data annotation, semantics, and data migration that are applicable to informing exposures, pathways, and outcomes.