A Large Language Model Screening Tool to Target Patients for Best Practice Alerts: Development and Validation.
Thomas SavageJohn WangLisa ShiehPublished in: JMIR medical informatics (2023)
These results show a proof of concept on how language models can be used as a screening tool for BPAs. We provide an example AI screening tool that uses a HIPAA (Health Insurance Portability and Accountability Act)-compliant BioMed-RoBERTa model deployed with minimal computing power. Larger models (eg, Generative Pre-trained Transformers-3, Generative Pre-trained Transformers-4, and Pathways Language Model) will exhibit superior performance but require data use agreements to be HIPAA compliant. We anticipate LLMs to revolutionize quality improvement in hospital medicine.
Keyphrases
- health insurance
- quality improvement
- autism spectrum disorder
- end stage renal disease
- healthcare
- ejection fraction
- newly diagnosed
- chronic kidney disease
- primary care
- resistance training
- prognostic factors
- artificial intelligence
- peritoneal dialysis
- electronic health record
- patient safety
- big data
- machine learning
- patient reported outcomes
- body composition
- drug induced