Machine learning for the extraction and classification of medical data from unstructured medical documents

This project addresses challenging needs of medicolegal report writers. Subject matter experts who provide expert witness testimony in the form of a medicolegal report, are asked to review thousands of pages of documents from a variety of sources to formulate their opinions. Report Mate’s goal is to develop an online platform aimed at medical report writing experts to manage large amounts of document data and help synthesize it into a chronological, searchable database to facilitate the creation of expert witness reports. One of the major challenges in synthesizing a cohesive report from this vast quantity of information is to be able to identify key pieces of information in large unstructured medicolegal documents. This project aims to use recent advances in deep learning and Natural Language Processing, to identify and classify individual medical reports and provide a classification of the type of the report.

Faculty Supervisor:

Moulay Akhloufi

Student:

Partner:

SIftmed Inc.

Discipline:

Computer science

Sector:

Information and Communications Technology; Health and Related Sciences & Technology; New and Digital Media

University:

Université de Moncton

Program: