Selection of pseudo-annotated data for adverse drug reaction classification across drug groups

TL;DR

This paper evaluates the robustness of neural models for adverse drug reaction detection across various drug groups and explores the impact of pseudo-labeled data on improving classification performance.

Contribution

It introduces strategies for selecting pseudo-annotated data to enhance ADR classification across different drug groups and assesses model robustness with out-of-dataset experiments.

Findings

Pseudo-labeled data improves ADR classification performance.

Model robustness varies across drug groups.

Pseudo-data strategies mitigate supervised model breakdowns.

Abstract

Automatic monitoring of adverse drug events (ADEs) or reactions (ADRs) is currently receiving significant attention from the biomedical community. In recent years, user-generated data on social media has become a valuable resource for this task. Neural models have achieved impressive performance on automatic text classification for ADR detection. Yet, training and evaluation of these methods are carried out on user-generated texts about a targeted drug. In this paper, we assess the robustness of state-of-the-art neural architectures across different drug groups. We investigate several strategies to use pseudo-labeled data in addition to a manually annotated train set. Out-of-dataset experiments diagnose the bottleneck of supervised models in terms of breakdown performance, while additional pseudo-labeled data improves overall results regardless of the text selection strategy.