TCTracey Jacqueline Fitchett Colella

Tracey Jacqueline Fitchett Colella

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Tracey Jacqueline Fitchett Colella has a total of 139 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    OPEN: A Benchmark Dataset and Baseline for Older Adult Patient Engagement Recognition in Virtual Rehabilitation Learning Environments

    by Ali Abedi, Sadaf Safa, Tracey J.F. Colella, Shehroz S. Khan

    Engagement in virtual rehabilitation programs is crucial for participant satisfaction, adherence, and successful program delivery. Measuring engagement in virtual group settings remains a significant challenge. There is growing interest in applying artificial intelligence (AI) for large-scale, automated engagement recognition. While engagement has been extensively studied among young learners in academic contexts, research methods and datasets focusing on older adults in virtual and telehealth environments are limited. Many existing approaches overlook the contextual relevance of learning materials and the longitudinal nature of engagement. This paper introduces OPEN (Older adult Patient ENgagement), a novel dataset created to support the development of AI models for engagement recognition. Data were collected from eleven older adults over six weeks of virtual cardiac rehabilitation sessions, totaling nearly 35 hours, making it one of the largest datasets of its kind. To protect privacy, raw video is withheld, but released data include facial, hand, and body joint landmarks, along with behavioral and affective features. Annotations provide second-level binary engagement states, emotional and behavioral labels, and contextual details. Machine-learning and deep-learning models trained on the dataset achieved up to 81% accuracy. OPEN provides a scalable foundation for advancing AI-driven engagement recognition in aging populations and broader research contexts.

  • Open Access

    Frailty Screening and Management in Cardiac Rehabilitation Programs Across Canada

    by Danielle Tsirulnikov, Courtney Pollock, Mikaela Hummel, Liam Munshi, Zhdania Wawruch, Sabrina Szkolmowski, Susan Marzolini, Tracey J.F. Colella


  • Open Access

    Rethinking Student Engagement Datasets for AI in Virtual Learning: A Narrative Review

    by Shehroz S. Khan, Ali Abedi, Tracey J. F. Colella

    Student engagement (SE) is central to learning success in virtual environments, and artificial intelligence (AI) models increasingly rely on annotated datasets to estimate it automatically. However, existing datasets vary substantially in how engagement is defined and operationalized. This narrative review examined 31 SE datasets collected in computer-based virtual learning settings, analyzing them across seven dimensions of engagement annotation: sources, modality, timing, temporal resolution, level of abstraction, combination, and quantification. Substantial heterogeneity was observed, with only 3 of the 31 datasets explicitly grounding their annotations in psychometrically validated or theoretically established engagement constructs. These inconsistencies have important implications for AI model development. For example, mismatches between the modality used for annotation and that used for model training may reduce robustness, and divergent quantification schemes (binary, ordinal, or continuous) restrict cross-dataset comparability and transferability. By explicitly linking dataset design decisions to risks affecting model validity, generalization, and interpretability, this review highlights the need for stronger construct grounding, clearer reporting of annotation protocols, and greater standardization to support more reliable and transferable engagement-aware AI systems.

  • Development and preliminary validation of the Coronary Artery Disease Education Questionnaire for Postpartum Women with pregnancy-related cardiometabolic complications (CADE-Q-PP): a modified Delphi approach

    by Gabriela Lima de Melo Ghisi, Lisa Cotie, Kara Nerenberg, Serena Gundy, Graeme Smith, Courtney Pollock, Karen Fleming, Tracey J F Colella

    Aims: Pregnancy-related cardiometabolic complications such as gestational diabetes mellitus, hypertensive disorders, and preterm birth significantly increase the risk of future cardiovascular diseases (CVD). Many postpartum women remain unaware of this risk, highlighting the need for targeted educational interventions. Validated tools to assess knowledge gaps in this population are lacking. Therefore, this study aimed to develop and preliminarily validate the Coronary Artery Disease Education Questionnaire for Postpartum Women (CADE-Q-PP) to ensure content validity and relevance. Methods and results: The CADE-Q was systematically revised to identify items specific to postpartum women's knowledge concerning pregnancy-related cardiometabolic complications and CVD risk. A modified Delphi process was conducted with a panel of 28 international experts to refine the items, using a five-point Likert scale for consensus (mean score ≥4). Items were further simplified into plain language and a clarity assessment was completed with 20 postpartum women. A total of 61 items were drafted across four key knowledge areas: cardiovascular risk, physical activity, mental health, and nutrition. Through iterative discussion, consensus was achieved on 22 questionnaire items. Clarity assessment revealed a high degree of understanding among postpartum women (total mean 4.3 ± 0.9), with 20/22 items scoring above 4.0. Items that scored lower concerned long-term risks and specific interventions. Suggestions included sentence structure and providing context for terms like ‘hidden sugar’ and ‘extra vitamins’. Conclusion: The CADE-Q-PP was developed as an accessible tool for clinicians to assess knowledge gaps regarding cardiovascular risk and health promotion in postpartum women. Future work will include testing of psychometric properties to confirm validity.


  • Open Access

    Women’s Cardiovascular Health and Cardiac Rehabilitation: a Priority-setting Partnership

    by Racquel K. Brown, Monica Parry, Paul Oh, Lisa Cotie, Jennifer Harris, Mireille Landry, Patrice Lindsay, Marilyn MacKay-Lyons, Karen Minden, Kerri-Anne Mullen, et al.

  • Open Access

    Characteristics of Existing Online Patient Navigation Interventions: Scoping Review

    by Meghan Marsh, Syeda Rafia Shah, Sarah E P Munce, Laure Perrier, Tin-Suet Joan Lee, Tracey J F Colella, Kristina Marie Kokorelias

    Background: Patient navigation interventions (PNIs) can provide personalized support and promote appropriate coordination or continuation of health and social care services. Online PNIs have demonstrated excellent potential for improving patient knowledge, transition readiness, self-efficacy, and use of services. However, the characteristics (ie, intervention type, mode of delivery, duration, frequency, outcomes and outcome measures, underlying theories or mechanisms of change of the intervention, and impact) of existing online PNIs to support the health and social needs of individuals with illness remain unclear. Objective: This scoping review of the existing literature aims to identify the characteristics of existing online PNIs reported in the literature. Methods: A scoping review based on the guidelines outlined in the Joanna Briggs Institute framework was conducted. A search for peer-reviewed literature published between 1989 and 2022 on online PNIs was conducted using MEDLINE, CINAHL, Embase, PsycInfo, and Cochrane Library databases. Two independent reviewers conducted 2 levels of screening. Data abstraction was conducted to outline key study characteristics (eg, study design, population, and intervention characteristics). The data were analyzed using descriptive statistics and qualitative content analysis. Results: A total of 100 studies met the inclusion criteria. Our findings indicate that a variety of study designs are used to describe and evaluate online PNIs, with literature being published between 2003 and 2022 in Western countries. Of these studies, 39 (39%) studies were randomized controlled trials. In addition, we noticed an increase in reported online PNIs since 2019. The majority of studies involved White females with a diagnosis of cancer and a lack of participants aged 70 years or older was observed. Most online PNIs provide support through navigation, self-management and lifestyle changes, counseling, coaching, education, or a combination of support. Variation was noted in terms of mode of delivery, duration, and frequency. Only a small number of studies described theoretical frameworks or change mechanisms to guide intervention. Conclusions: To our knowledge, this is the first review to comprehensively synthesize the existing literature on online PNIs, by focusing on the characteristics of interventions and studies in this area. Inconsistency in reporting the country of publication, population characteristics, duration and frequency of interventions, and a lack of the use of underlying theories and working mechanisms to inform intervention development, provide guidance for the reporting of future online PNIs.


  • Development of an Algorithm to Screen for Frailty Using the Clinical Frailty Scale with Postoperative Patients Entering Cardiac Rehabilitation

    by Coomal Rashid, Courtney Pollock, Madeleine Aldworth, Jennifer Chow, Michael Kent, Kristina Sapardanis, Sam Yentin, Susan Jaglal, Tracey Jf Colella

    Purpose: Frailty is not commonly assessed on intake to cardiac rehabilitation (CR), but screening could enable targeted interventions and potentially reduce secondary complications. This study aimed to develop and retrospectively examine the feasibility of utilizing a CR-specific algorithm based on the Clinical Frailty Scale (CFS). Our CFS-CR algorithm endeavoured to screen for frailty in older adults (> 65 y) entering CR following cardiac surgery/procedure. Method: The charts of 30 former patients (mean age: 74.0 ± 6.9 y) were examined by a clinician working in CR. Results: The clinician was unable to score any of the patients based on their medical charts using the CFS-CR due to insufficient data. Documentation was typically limited in the areas of instrumental and basic activities of daily living whereas exercise data were readily available. Conclusions: Current intake documentation in CR limited the ability to retrospectively screen for frailty. This finding suggests a need for a frailty-specific tool to support routine clinical screening. Prospective evaluation of the CFS-CR is warranted to further examine the clinical utility of the algorithm during CR intake assessments.


  • Open Access

    Women's Knowledge of Future Cardiovascular Risk Associated With Complications of Pregnancy: A Systematic Review

    by Gabriela Lima de Melo Ghisi, Laura Banks, Lisa M. Cotie, Maureen Pakosh, Courtney Pollock, Kara Nerenberg, Anna Gagliardi, Graeme Smith, Tracey J.F. Colella