Know What's Happening in HealthTech

Integrating Patient-Reported Weight Gain Cause Narratives Into Personalized Obesity Management: A Data-Driven Approach with Natural Language Processing and Machine Learning

Researchers used a GPT‑4.1 large language model to automatically label 2,463 patient‑reported weight‑gain narratives into 12 thematic categories, achieving over 90% precision and recall. The study linked specific reported causes—such as disrupted schedules, mental health challenges, and external circumstances—to higher risks of unhealthy eating and physical inactivity, and identified seven distinct patient phenotypes with differing weight‑loss outcomes. Mean weight loss across participants was 9.2% over roughly 109 days, while the combined cause patterns proved more predictive of treatment response than individual factors. The findings demonstrate that AI‑driven narrative analysis can enhance personalized obesity management.