JMIR Publications

ABSTRACT

Background:

Immune checkpoint inhibitors are associated with unique immune-related adverse events (irAEs). Because most of the immune checkpoint inhibitors are new to the market, it is important to conduct studies using real-world data sources to investigate their safety profiles.

Objective:

To develop a framework for signal detection and filtration of novel immune-related adverse events (irAEs) for 6 FDA approved immune checkpoint inhibitors.

Methods:

In our framework, we first used the FDA Adverse Event Reporting System (FAERS) standardized in an OHDSI common data model (CDM) to collect immune checkpoint inhibitors-related event data and conducted the irAE signal detection. We then filtered those already known irAEs from drug labels and literatures by using a customized text-mining pipeline based on cTAKES with MedDRA as a dictionary. Finally, we classified the irAE detection results into three different categories to discover potentially new irAE signals.

Results:

By our text-mining pipeline, 490 irAE terms were identified from drug labels and and 918 terms were identified from literature. In addition, of the 94 positive signals detected using CDM-based FAERS, 53 signals (56.38%) were labeled signals, 10 (10.64%) were unlabeled published signals, and 31 (32.98%) were potentially new signals.

Conclusions:

We demonstrated that our approach is effective in irAE signal detection and filtration. Moreover, our framework could facilitate ADE detection and filtration toward the goal of next generation pharmacovigilance.