Burden of Myasthenia Gravis Based on Sentiment Analysis of Patients’ Digital Conversations
Caroline Brethenoux1, Jacqueline Pesa2, Zia Chaudhry2, Patrick Furey1, Lili Gil Valleta1, Laura Gonzales Quijano1, Alex Lorenzo1
1CulturIntel, 2Janssen Scientific Affairs, LLC
Objective:

To describe overall sentiments towards Myasthenia Gravis (MG) and compare males and females on the most frequent themes.

Background:

MG is a rare, chronic autoantibody neuromuscular disease with profound patient burden. Data from digital conversations can provide an unprovoked view of MG disease burden and highlight areas of greatest concern to patients.

Design/Methods:

One year (8/2021 - 8/2022) of conversations focused on MG in the public domain originating from US internet protocol addresses were tagged based on self-identification in the conversations or on public profiles. Advanced search techniques together with artificial intelligence powered algorithms were used to extract and organize data by topics into a large, unstructured dataset. Sentiment analysis via natural language processing was conducted to categorize conversations as positive, negative or neutral and analyzed to derive the most frequent drivers of sentiment.

Results:
13,234 conversations were extracted from topical sites, message boards, social networks and blogs. The most frequent categories of conversation topics were diagnosis (29%), living with MG (28%), symptoms, (24%) and treatment (19%). Within 3176 conversations about symptoms, the most frequent discussion involved eye problems (21%), facial muscle problems (18%%), and fatigue (18%). Sentiment analysis categorized conversations into positive, negative and neutral of which most (59%) were “negative “in tone and meaning, 39% were “neutral” and only 2% were “positive”. Negative conversations were dominated by themes of “impact on life” (29%), “misdiagnosis problems” (27%), “treatment issues” (24%), and “symptoms severity” (20%).  Males had more conversations with negative sentiment vs females while females seemed more pragmatic in their outlook on MG.
Conclusions:

Digital conversations reveal a high degree of concern among patients with MG most specifically related to symptoms, life impact, misdiagnosis and treatments (for MG). Therapies that provide better symptom control could positively affect many aspects of patient’s lives.

10.1212/WNL.0000000000203146