Menu Close

About

Towards scalable and accurate analysis of human clinical EEG data.

The goal of the CrowdEEG project is to combine human and machine intelligence—the joint effort of algorithms, experts, and non-expert crowds—for the accurate and scalable analysis of human clinical EEG data. 

The scope of our research encompasses several aims:

  1. The design of a computational framework which will selectively elicit feedback from clinical experts, as well as non-expert crowds, to train machine learning algorithms for highly accurate classifications of human clinical EEG data.
  2. The application of such algorithms to the interpretation of clinical EEGs in both resource-rich and resource-poor health settings—read more about our team’s involvement with The Bhutan Epilepsy Project.
  3. The preparation of a high quality data set of human clinical polysomnograms, to be made publicly available to support research endeavours of other groups in this field.

Our Application

https://app.crowdeeg.ca/

Our “crowdEEG” application is a collaborative annotation tool that allows experts or non-expert crowds to perform feature detection and high-level classification tasks on EEG recordings. Click here to view our annotator.

Our Research

Currently, our research team is conducting two ongoing studies:

The Nature of Expert Disagreement — an investigation of the effect of implicit contextual information in multi-channel biosignal time series data on agreement rates between multiple experts in the context of sleep stage classification. The objective of this study is to improve our understanding of the causes, effects, properties, and perception of expert disagreement and adjudication processes in the context of complex labelling tasks.

Active Learninghow can we automate the process of accurately classifying a given EEG recording into sleep stages while minimizing the number of times the machine classifier has to query a human expert for information about the correct sleep stage?

Read more about our ongoing studies here.

Our Team

The CrowdEEG team is headed by Edith Law out of the University of Waterloo with PhD Student Mike Schaekermann, in joint collaboration with Andrew Lim at Sunnybrook Hospital (University of Toronto), Joelle Pineau at McGill University, and Farrah Mateen at Harvard Medical School.

Visit our People page to view all of our past and present research team members.