Locations of visitors to this page

The EMBS Chapter of the IEEE Ottawa Section was recognized as the Best Ottawa Chapter in 2008, 2010, 2014, 2019, and 2022 and received the Outstanding Chapter Award from IEEE EMBS in 2011!

Extracting Medical Concepts from Biomedical Articles Using Deep Learning

Photo of Dr. Isar Nejadgholi

Dr. Isar Nejadgholi

Machine Learning Research Officer, National Research Council Canada

November 20, 2019 18:00 - 19:30

Mackenzie Building Room 4463, Carleton University

Paid parking available on campus



Extracting medical concepts from clinical notes or biomedical articles is an important task in the field of medical text Processing. There has been a lot of work on medical Named Entity Recognition (NER) in recent years, but most of these works focus on extracting only a small subset of the medical concepts. In real applications, we need to extract a much broader range of entities and ideally, we want to be able to extract all the concepts mentioned in the Unified Medical Language System (UMLS). This talk will review the efficiency of the state-of-the-art deep learning models developed for extracting medical entities and highlights the impact of various elements of such models including general vs domain-specific and contextual vs non-contextual pre-trained representations. The talk will cover some of the risks and opportunities in developing such systems and will shed some light on the gap between the most recent research results and the desired solutions for real-world problems.


Isar Nejadgholi is a research officer at National Research Council Canada. She received her PhD in biomedical engineering in 2012. In her MSc and PhD research, she designed neural network models and used them to solve speech-to-text and computer vision problems. In her postdoctoral studies, she applied machine learning methods to process biomedical signals in a variety of applications.

Last updated November 17, 2019

Printable version