AI-based Approach for Safety Signals Detection from Social Networks: Application to the Levothyrox Scandal in 2017 on Doctissimo Forum

TL;DR

This paper presents an AI-based method combining NLP indicators and a novel deep learning model, WC-CNN, to detect pharmaceutical safety signals from social media reviews, demonstrated on the Levothyrox scandal with promising results.

Contribution

It introduces a new deep learning architecture, WC-CNN, and a comprehensive set of NLP indicators for temporal safety signal detection from social media data.

Findings

WC-CNN trained on monthly word clouds achieves 75% accuracy.

NLP indicators like sentiment and ADR mentions effectively signal safety issues.

Temporal analysis improves detection performance.

Abstract

Social media can be an important source of information facilitating the detection of new safety signals in pharmacovigilance. Various approaches have investigated the analysis of social media data using AI such as NLP techniques for detecting adverse drug events. Existing approaches have focused on the extraction and identification of Adverse Drug Reactions, Drug-Drug Interactions and drug misuse. However, non of the works tackled the detection of potential safety signals by taking into account the evolution in time of relevant indicators. Moreover, despite the success of deep learning in various healthcare applications, it was not explored for this task. We propose an AI-based approach for the detection of potential pharmaceutical safety signals from patients' reviews that can be used as part of the pharmacovigilance surveillance process to flag the necessity of an in-depth pharmacovigilance investigation. We focus on the Levothyrox case in France which triggered huge attention from the media following the change of the medication formula, leading to an increase in the frequency of adverse drug reactions normally reported by patients. Our approach is two-fold. (1) We investigate various NLP-based indicators extracted from patients' reviews including words and n-grams frequency, semantic similarity, Adverse Drug Reactions mentions, and sentiment analysis. (2) We propose a deep learning architecture, named Word Cloud Convolutional Neural Network (WC-CNN) which trains a CNN on word clouds extracted from the patients comments. We study the effect of different time resolutions and different NLP pre-processing techniques on the model performance. Our results show that the proposed indicators could be used in the future to effectively detect new safety signals. The WC-CNN model trained on word clouds extracted at monthly resolution outperforms the others with an accuracy of 75%.