This project aim is to develop a solution that could help reduce the clerical burden on physicians, introduce efficiencies into their interactions with the Electronic Health Record (EHR), and allow them to focus more on patients, through the application of existing speech to text solutions to the complex task of medical language and development of innovative natural language processing tools for named-entity recognition and classification in medical text.
An app to fully automate the referred process, by embedding artificially intelligent software into exam rooms and, without need for mouse and keyboard, can transcribe a conversation between a doctor and patient and upload key portions of it into a medical record.
Author: Diogo Duarte
Type: MSc thesis
Partner: FEUP – Faculdade de Engenharia da Universidade do Porto