AutoScribe: Extracting Clinically Pertinent Information from Patient-Clinician Dialogues
Khattak Faiza Khan, Serena Jeblee, Noah H. Crampton, Muhammad Mamdani, Frank Rudzicz · Studies in health technology and informatics · 2019
We present AutoScribe, a system for automatically extracting pertinent medical information from dialogues between clinicians and patients. AutoScribe parses the dialogue and extracts entities such as medications and symptoms, using context to predict which entities are relevant, and automatically generates a patient note and primary diagnosis.