Beyond the Posts: Analyzing Breast Implant Illness Discourse With Natural Language Processing and Deep Learning

Breast implant illness (BII) is a spectrum of symptoms some people attribute to breast implants. Although causality remains unproven, patient interest has grown significantly. Understanding patient perceptions of BII on social media is crucial because these platforms increasingly influence healthcare decisions.

The purpose of this study is to analyze patient perceptions and emotional responses to BII on social media using Robust optimizing Bidirectional Encoder Representations from Transformers, a natural processing model trained on 124 million X posts.

Posts mentioning BII from 2014 to 2023 were analyzed using 2 natural language processing models: 1 for sentiment (positive/negative) and another for emotions (fear, sadness, anger, disgust, neutral, surprise, and joy). Posts were then classified by their highest scoring emotion. The results were compared over across 2014-2018 and 2019-2023, with correlation analysis (Pearson correlation coefficient) between published implant explantation and augmentation data.

The analysis of 6099 posts over 10 years showed 75.4% were negative, with monthly averages of 50.85 peaking at 213 in March 2019. Fear and neutral emotions dominated, representing 35.9% and 35.6%, respectively. The strongest emotions were neutral and fear, with an average score of 0.293 and 0.286 per post, respectively. Fear scores increased from 0.219 (2014-2018) to 0.303 (2019-2023). Strong positive correlations (r > 0.70) existed between annual explantation rates/explantation-to-augmentation ratios and total, negative, neutral, and fear posts.

BII discourse on X peaked in 2019 characterized predominantly by negative sentiment and fear. The strong correlation between fear/negative-based posts and explantation rates suggests social media discourse significantly influences patient decisions regarding breast implant removal.