Protecting Health Information. Ensuring Data Integrity.
Protecting Health Information. Ensuring Data Integrity.

EHIL Blog and Announcements

Upcoming Webinar: On the evaluation of synthetic data utility

On September 24, Dr. Fida Dankar will present her research work on synthetic data utility.

Upcoming Webinar: What not to do when publishing a machine learning modeling study

On November 13, Dr. Khaled El Emam will distill key learnings about publishing studies utilizing machine learning models.

Webinar: Ethics of research involving humans in epidemiology and public health research

Do you conduct research involving human participants? Are you subject to the Tri-Council Policy Statement: Ethical Conduct for Research Involving Humans (TCPS)? In this webinar, Hanan Abdel-Akher, Senior Policy Analyst with the Secretariat on Responsible Conduct of Research, answers these questions and more.

Webinar: Generating and Applying Synthetic Health Data

Synthetic data generation is an emerging approach for responsibly sharing data. Dr. Khaled El Emam reviews the use of generative models to produce synthetic real-world data and clinical trial data, along with studies evaluating the replicability of analyses using synthetic data and the privacy risks of synthetic data will. He also discusses further applications for enabling federated analysis and (selection) bias mitigation.

Webinar: The Utility Costs of Anonymization

On April 17, Lisa Pilgram presented an example application of anonymization in the field of nephrology.  The focus was on utility and attention drawn to potential pitfalls. Video and slides available.

Webinar: Mitigating Bias in Real World Health Data

In February 2024, Lamin Juwara joined us to discuss the results of his recently published study “An evaluation of synthetic data augmentation for mitigating covariate bias in health data” on bias mitigation techniques to correct biased datasets. Webinar video available at: https://vimeo.com/918399218

Release of machine learning R package (experimental)

This is the release announcement for the sdgm R package. This is the package we use on our intro to machine learning class.

Code and data files for RWD bias mitigation paper by Juwara et al.

This post includes links to the data and code files for the Juwara et al. paper code and data files.

R files for article on VMS in breast cancer patients by Cole et al.

R files for paper by Cole et al. on change scores for VMS in breast cancer patients.

Minor correction to recently published Scientific Reports paper

This blog makes a minor correction to one of the tables in the paper recently published in Scientific Reports:

https://www.nature.com/articles/s41598-023-38457-3

Synthetic Data Use: Exploring use cases to optimize data utility

On March 9, Stef James, Senior Director, Capability and Operations at AstraZeneca UK, joined EHIL to present her study of use cases for synthetic data within the pharmaceutical industry.