Leveraging Online Patient Forums to Understand Breast Reduction Concerns: A Machine-Learning Analysis of 3078 Patient...

Area of Science:

• Plastic Surgery
• Online Patient Communities
• Health Informatics

Background:

• Patients increasingly use social media and online forums for plastic surgery information, influencing expectations.
• Understanding online patient concerns is crucial for accurate, evidence-based information and productive clinical discussions.

Purpose of the Study:

• To analyze patient questions regarding breast reduction surgery on the online platform RealSelf.
• To identify common themes, regional trends, and temporal patterns in patient inquiries.

Main Methods:

• Data from RealSelf breast reduction questions (August 2008-May 2023) were analyzed.
• Questions were categorized by timing (preoperative/postoperative) and topic.
• Machine learning identified representative preoperative and postoperative questions.

Main Results:

• 3,078 questions were analyzed, with most originating from the Southern US and asked preoperatively.
• Top topics included Postoperative Care, Appearance/Sensation, and Surgical Logistics.
• Topic distribution varied significantly by region, with Insurance questions more common in the South.

Conclusions:

• This study uniquely uses machine learning to analyze a large dataset of breast reduction patient questions from an online forum.
• Analyzing online patient discussions with ML provides valuable insights into plastic surgery concerns and knowledge gaps.
• Surgeons can use these findings to enhance patient conversations, address misinformation, and improve care delivery.