PCMA Lab is supported by internal and external funding from University of Calgary, Calgary Center for Clinical Research, Alberta Innovates, MSI Foundation, National Science and Engineering Research Council of Canada, & Canadian Institutes for Health Research. Some ongoing externally funded projects are described below

Doctor and Patient

IMPROVE Cardiovascular Care Study

Person-centered care is fundamental to high-quality health systems because it improves experiences people have with care, better aligns health services delivery with individual needs. This is achieved by integrating clinical data with both objectively collected patient reported outcomes (PROMs) and patient reported experiences (PREMs), which quantify the subjective aspects of a person’s health status and their experience with processes of care.


Unfortunately, PROMs and PREMs in individuals living the cardiovascular disease are still generally collected through telephone and paper-based surveys in Alberta as outcomes in research studies. Although there are well developed and validated PROMs and PREMs for cardiovascular disease, there is a lack of electronic platform for collecting and reporting these measures back to care providers and patients so that they can use them to improve quality and outcomes of care in Alberta. This CIHR-funded study will develop an electronic platform needed to facilitate deployment of an electronic PROMs and PREMS system for cardiovascular disease into routine clinical settingsDetails


Precision Cardiovascular Medicine using Patient-Centered Risk Prediction Tools

In recent years, there is a growing call for personalized approaches to cardiovascular disease management which aims to tailor treatments to an individual’s needs. Clinical prediction models are essential to particularly essential for aiding such tailored clinical decision in the management of individuals with cardiovascular diseases.  This CIHR-funded project develops aims to develop patient-centered prognostic risk scores that incorporates patients’ assessment of their own health and well-being of their own into the estimation of patients’ risk of adverse outcomes associated with each treatment options. These tools will be deployed in clinical settings to facilitate the use of these outcomes in disease monitoring and improvement of patient outcomes

This research is in  collaboration with the Alberta Provincial Project on Outcomes for Coronary Artery Disease (APPROACH)

machine learning.jpeg

Machine Learning Algorithms for Multivariate Repeated Measures Designs

Machine learning and other classification algorithms have been developed for discriminating between population groups. But their extension to more than one measurement occasion is limited. This project develops robust repeated measures discriminant analysis models for discriminating between two population groups in multivariate repeated measures designs.  The overarching purpose of my research program is the development of more accurate classification

models based on the longitudinal profiles of individual subjects for predicting group membership of new

subjects in MRM designs. The objectives of my proposed program are to:

  1. develop robust repeated measures classifiers based on RMDA and quadratic inference function (QIF) derived from generalized estimating equations for discriminating between population groups characterized by non-Gaussian continuous distributions

  2. develop robust likelihood ratio tests for repeated measures discriminant analysis models in multivariate non-normal distributions, 

  3. investigate and incorporate variable selection approaches for selecting important variables with the optimal discriminatory power for improving the accuracy of MRM classifiers.

This research is funded by NSERC Discovery Grant