Research Repository
LU|ZONE|UL distributes and preserves the scholarly work of LU faculty. It is a space for faculty to support the dissemination of knowledge created at Laurentian.
Electronic Theses and Dissertations (ETD) Repository This section preserves Master's theses and doctoral dissertations accepted at Laurentian University and is a mechanism for making this form of scholarly work widely accessible.
Communities in LU|ZONE|UL
Select a community to browse its collections.
Recent Submissions
Early risk prediction in acute aortic syndrome on clinical data using machine learning
(Laurentian University Library & Archives, 2024-04) Tavafi, Mehdi; Dr. Kalpdrum Passi
Dr. Robert Ohle
Advancements in machine learning present novel opportunities for early prediction of Acute
Aortic Syndrome (AAS) as a critical and life-threatening clinical condition and the identification
of critical features influencing this prediction. This study concentrates on integrating, cleaning,
and handling missing data from extensive clinical datasets sourced from 150 emergency
departments across Canada and the USA. Covering medical histories of nearly 150,000 patients
from 2021 to 2022, the dataset comprises categorical clinical variables. Additionally, the research
focuses on constructing predictive machine learning models utilizing various data-splitting
strategies and classifiers to optimize AAS prediction. Methodologically, the study encompasses
data identification, acquisition, exploration, processing, and feature extraction, followed by
dimensionality reduction using Principal Component Analysis (PCA) and other feature selection
methods such as Correlation-based (CFS) and Relief. The multiple imputations method and the
SMOTE method are utilized for handling missing and imbalanced data, respectively. The findings
demonstrate that employing the Relief-feature method with an 80-10-10 split ratio alongside the
Random Forest classifier yields an exceptional accuracy of 99.3%, surpassing alternative models..
Furthermore, this research addresses a prevalent challenge encountered by many researchers
regarding dataset size limitations, thereby facilitating the utilization of the integrated and prepared
dataset for research on AAS and other cardiovascular diseases.
Les effets de l’enseignement virtuel pendant la COVID-19 sur le sentiment d’auto- efficacité des enseignants du Grand Sudbury : une étude de cas
(Laurentian University Library & Archives, 2025-01-17) Grenier, Catherine; Georges Kpazaï
Le but de cette étude de maîtrise est de mieux comprendre l’impact de l’enseignement
virtuel, lors de la pandémie de la COVID-19, sur le sentiment d’auto-efficacité des
enseignant.e.s de l’élémentaire dans la ville du Grand Sudbury. Les études antérieures
démontraient que l’enseignement virtuel pendant la pandémie avait touché la santé
mentale, mais ne démontraient pas comment il avait influencé le sentiment d’auto-
efficacité, spécifiquement celui des enseignant.e.s de niveau primaire. Une approche
qualitative utilisant des entrevues semi-structurées auprès de huit enseignant.e.s de
différentes écoles élémentaires du Grand Sudbury, ville du nord de l’Ontario, a été
utilisée. En s’appuyant sur les quatre facteurs du sentiment d’auto-efficacité de Bandura,
l’analyse de contenu du corpus recueilli a révélé que les enseignant.e.s vivaient des
vagues d’émotions en lien avec la relation pédagogique, et ce, entre eux et leurs élèves,
lors de l’enseignement virtuel. En conséquence, ces enseignant.e.s avaient de la difficulté
à bâtir de solides rapports en lien avec leur mission d’enseignement auprès de leurs
élèves. Bien que la majorité des enseignant.e.s se sentaient bien appuyés, ils indiquent
avoir vécu des répercussions négatives par rapport à leurs émotions. Par ailleurs, ils
mentionnent qu’ils ont plus de temps pour le repos et l’exercice physique, contribuant au
sentiment d’auto-efficacité. En somme, l’enseignement virtuel, lors de la pandémie, a fait
en sorte que les enseignant.e.s vivaient plus d’émotions négatives, mais cet enseignement
a aussi amené des éléments positifs comme le temps de repos de la vie autrement
chaotique vécue par ceux-ci. En général, le sentiment d’auto-efficacité a été légèrement
touché.
Examining the role of carotenoids and retinoids in modulating cellular response to oxidative stress: an evidence-based approach
(Laurentian University Library & Archives, 2025-04-22) Akter, Sharmin; Radu Alexandru (Alex) Moise
Oxidative stress, resulting from an imbalance between reactive oxygen species (ROS) production
and antioxidant defense systems, plays a critical role in cellular damage and the progression of
diseases such as neurodegeneration, cardiovascular disorders and cancer. Carotenoids and
retinoids, naturally occurring compounds with potent antioxidant properties, modulate oxidative
stress by scavenging free radicals, preventing lipid peroxidation and regulating gene expression.
This review explores the bioavailability, metabolism and molecular mechanisms of carotenoids,
including β-carotene, lutein, and lycopene. Additionally, it investigates the influence of retinoic
acid on gene regulation through retinoic acid receptors (RARs) and retinoid X receptors (RXRs),
emphasizing their impact on cellular differentiation, apoptosis and oxidative defense. The
therapeutic potential of carotenoids in neurodegenerative disorders, cardiovascular health and
cancer treatment is discussed. The review concludes that while carotenoids and retinoids offer
significant protective benefits against oxidative stress, their clinical application requires careful
consideration of bioavailability, dosage and individual genetic variations to maximize therapeutic
outcomes.
A hybrid Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for detecting Keratoconus in patients using genetic algorithm
(Laurentian University Library & Archives, 2024-09-16) Ghasedi Katak Lahijani, Somayeh ; Dr. Amr Abdel-Dayem
Nowadays, there are still significant challenges encountered in the accurate diagnosis of various
eye diseases, such as Keratoconus (KCN) and cataracts. Early detection of Keratoconus is crucial
in preventing its progression and ensuring the best treatment outcomes. Artificial intelligence (AI)
is being widely applied in ophthalmology through the training of deep learning networks for the
early detection of eye diseases. This research presents a novel, integrated machine learning
approach for diagnosing Keratoconus disease by combining feature extraction through
Convolutional Neural Networks (CNN) with a Support Vector Machine (SVM) and Artificial
Neural Network (ANN) for classification. Employing a multi-objective genetic algorithm, the
method optimizes feature selection, aiming to minimize both diagnostic error and the number of
features. The study utilizes a dataset of 5,152 ophthalmic images (1288 samples) categorized into
Normal (476), Suspect (453), and Keratoconus (359) cases, sourced from an eye clinic in Egypt.
Combining a Convolutional Neural Network (CNN) for feature selection with a Genetic Algorithm
(GA) significantly improved diagnostic accuracy. Consequently, by focusing on the most relevant
features of Keratoconus (KC), the model achieved an impressive 98.63% accuracy for ANN
classification with a genetic algorithm, and 98.13% for SVM classification with a genetic
algorithm. The accuracy of the algorithm exceeded that of when SVM and ANN were used without
the genetic algorithm alone, which were 97.53% and 96.9% respectively, underscoring the benefit
of combining Artificial Neural Networks (ANNs) with Genetic Algorithms (GAs) in KC diagnosis.
Implementing this model can assist physicians in more accurate Keratoconus detection, providing
better predictions regarding patients' eye conditions, and offering timely treatment
recommendations.
The expression and function of nAChRs in human T cells
(Laurentian University Library & Archives, 2024-03-06) Laforest, Bailey; Dr. Alain Simard
Nicotinic acetylcholine receptors (nAChRs) are known to modulate immune responses, but their
specific role in human T cells remains poorly understood. This thesis project aimed to investigate
the expression, regulation, and functional roles of nAChRs in human T cells to shed light on the
underlying mechanisms of nAChR-mediated immune regulation. Our study utilized two T cell
lines, CCRF-CEM and Jurkat, which express various nAChR subunits, including ⍺7, ⍺9, ⍺10,
and dup⍺7. The expression of these subunits was characterized using quantitative PCR. Notably,
48-hr mitogen-induced activation of Jurkat cells induced dynamic changes in nAChR subunit
gene expression, including the upregulation of dup⍺7 and downregulation of ⍺7, ⍺9, and α10.
Pharmacological studies using several nAChR ligands revealed differential effects on cytokine
production in Jurkat cells. The ⍺7-selective antagonist, ArIB, hindered the mitogen-induced
release of IL-2 and TNF-⍺, suggesting that ⍺7 nAChR inhibition may suppress T cell-mediated
immune responses. Overall, this thesis advances the current understanding of nAChR expression
and function in human T cells and underscores the complex and cell type-dependent nature of
nAChR signaling. These findings provide a foundation for further research into the role of
nAChRs in the immune system and potential therapeutic interventions for immune-related
disorders.