Home > Clinical Research > Population-Based Research > Artificial Intelligence and Machine Learning
Artificial Intelligence and Machine Learning

The electrocardiogram (ECG) is a common medical test that artificial intelligence (AI) technology now aids in analyzing more effectively. The primary goal of the ECG-SAFE study is to improve AI algorithms that use ECGs to diagnose heart issues and predict future problems. The study team will determine if the algorithms they developed in acute care environments work well within community settings. They will also create new algorithms to identify individuals at a higher risk of future adverse events.
CVC Faculty Involvement:
Padma Kaul, PhD
Roopinder Sandhu, MD, MPH

Electrocardiograms (ECG) are collected routinely as part of clinical practice, but their utility to provide information on the risk of future adverse events has not been fully explored. The EXPLORE-AI study utilizes ECG-based machine learning models to predict short- and long-term mortality among patients presenting to an emergency department (ED) or hospitals in the Northern Zone in Alberta. The study team is using 12-lead ECG traces and measurements from 1,605,268 ECGs from 748,773 healthcare episodes of 244,077 patients (February 2007 – April 2020) to demonstrate the validity of ECG-based deep-learning mortality prediction models at the population scale.
CVC Faculty Involvement:
Padma Kaul, PhD
Justin Ezekowitz, MBBCh, MSc
Kevin Bainey, MD, MSc
Roopinder Sandhu, MD, MPH
Finlay McAlister, MD, MSc
Publications:
- Development and validation of machine learning algorithms based on electrocardiograms for cardiovascular diagnoses at the population level.
Kalmady SV, Salimi A, Sun W, Sepehrvand N, Nademi Y, Bainey K, Ezekowitz J, Hindle A, McAlister F, Greiner R, Sandhu R, Kaul P. NPJ Digit Med. 2024. doi: 10.1038/s41746-024-01130-8.
- Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms.
Sun W, Kalmady SV, Sepehrvand N, Salimi A, Nademi Y, Bainey K, Ezekowitz JA, Greiner R, Hindle A, McAlister FA, Sandhu RK, Kaul P.
NPJ Digit Med. 2023. doi: 10.1038/s41746-023-00765-3.