Text Processing of Clinical Research Protocols and Informed Consents to Facilitate Tracking of Research Procedures

Authors

• Alok Panny
• Huser Vojtech

Abstract

Clinical Research Informatics (CRI) aims to improve the conduct of clinical research studies. Research decision support (RDS) alerts and reminders can monitor whether study protocol is being followed. This support is similar to clinical decision support (CDS) systems that monitor compliance with clinical guidelines. A necessary prerequisite for the provision of research decision support is a computable representation of a study protocol. Computable representation of research studies is an ongoing CRI challenge with only limited support from the existing CRI standards. Rather than requiring researchers to use additional protocol modelling software, our study pilots an approach where we use natural language processing (NLP) methods on study documents (protocol or IC) to detect study procedures. Extracted study milestone events (or procedures) can be subsequently used to track the progress of individual study participants through the protocol by observing the events recorded in the research data warehouse.

Scientific Focus Area: Research Support Services

This page was last updated on Friday, March 26, 2021