AutoScribe: Extracting Clinically Pertinent Information from Patient-Clinician Dialogues

Stud Health Technol Inform. 2019 Aug 21:264:1512-1513. doi: 10.3233/SHTI190510.

Abstract

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.

Keywords: Machine Learning; Medical Informatics; Medical Records.

MeSH terms

  • Databases, Factual*
  • Humans
  • Physician-Patient Relations