Classification of Patients' Judgments of Their Physicians in Web-Based Written Reviews Using Natural Language Processing: Algorithm Development and Validation.
Farrah MadanayKarissa TuAda CampagnaJ Kelly DavisSteven S DoerstlingFelicia ChenPeter A UbelPublished in: Journal of medical Internet research (2024)
Our 2 classification models coded interpersonal manner and technical competence judgments with high precision, recall, and accuracy. These models were validated using review star ratings and results from previous research. RoBERTa can accurately classify unstructured, web-based review text at scale. Future work could explore the use of this algorithm with other textual data, such as social media posts and electronic health records.
Keyphrases
- electronic health record
- social media
- machine learning
- deep learning
- end stage renal disease
- newly diagnosed
- health information
- ejection fraction
- clinical decision support
- primary care
- big data
- artificial intelligence
- autism spectrum disorder
- prognostic factors
- randomized controlled trial
- systematic review
- current status
- meta analyses