Browsing by Author "White, James"

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    Cardiovascular Magnetic Resonance Imaging in Cardiometabolic Disease
    (2016-01-26) Schmidt, Anna; Anderson, Todd; Friedrich, Matthias; White, James; Pacaud, Danièle; Lau, David
    The unrelenting incidence of obesity and type 2 diabetes has become a global public health concern. Cardiovascular disease (CVD) remains the leading cause of morbidity and mortality in these cohorts. Cardiovascular Magnetic Resonance (CMR) imaging is a robust imaging modality with techniques to provide sensitive detection of early cardiovascular changes in obesity and diabetes. In a prospective study of obese adolescents (n=11, 10 to 20 years old) and a healthy weight control group (n=14), we found obesity was associated with increases in Left ventricular (LV) mass, LV wall thickness and mass:volume ratio. In this “early stage” of remodeling, these structural changes were not associated with elevations in Native T1, a surrogate marker of tissue fibrosis. Strain analysis, by novel CMR tissue tracking analysis, revealed a hyper-contractile state, likely representing a combined contribution of elevated systolic blood pressure with compensatory myocyte hypertrophy. Obese subjects were additionally enrolled in a comprehensive 6-month lifestyle intervention; subjects did not experience weight loss or any change in cardiac parameters after 6 months. Further along the natural history of CVD as related to metabolic disease, the second study looked to examine possible sub-clinical changes in the hearts of otherwise healthy diabetic patients. This study examined twenty-eight healthy type 2 diabetic patients without any observable vascular complications. The complementary use of CMR-based T1 mapping and 3-dimensional strain analysis demonstrated expansion of the extracellular matrix and a reduction in global longitudinal strain. In the endpoint of the cardiometabolic disease spectrum, we analyzed individuals with known or suspected Coronary Artery Disease. This study explored the relationship between intra-thoracic fat volume (ITFV) and 4D myocardial strain-based markers of adverse remodeling. In non-infarcted myocardium, ITFV is associated with reductions in myocardial strain. These findings suggest ITFV to be a potentially important marker of adverse ventricular remodeling. The findings of these three studies suggest a capacity of contemporary CMR to identify early changes in cardiometabolic disease and also lend insight into the progression of diabetic heart disease. CMR provides a non-invasive, accurate and reproducible imaging modality with the potential to be useful in screening and CVD risk-stratification.
  • Thumbnail Image
    ItemOpen Access
    Four-Dimensional Blood Flow Analysis in Patients with Repaired Tetralogy of Fallot: Development of Novel Tools to Analyze Turbulence
    (2023-01-26) Hudani, Ashifa; Garcia, Julio; Greenway, Steven; White, James; Fine, Nowell
    Medical imaging modalities are used every day and everywhere to obtain valuable information on diagnosis and treatment to help improve patient management along with the future outcome for patients. They enable us to see and understand what is happening within our body without invasive procedures or the need for surgery. Furthermore, these imaging modalities can be used for many diseases and abnormalities that occur within the entire human body due to each modality acquiring a unique attribute in the way it interacts with our tissues resulting in a better understanding of the abnormality or the diseases. Some common imaging modalities that are frequently used today include Magnetic Resonance Imaging (MRI), X-Ray, Computed Tomography, and Ultrasound, just to name a few. Due to the unique ability of these imaging modalities to obtain information, much research and technological improvements have been discovered to obtain as much information as we can for the desired questions at hand. However, MRI is one of the imaging modalities that is known to be non-invasive, does not use ionizing radiation, is very versatile, and can produce high-quality images for many diseases and abnormalities. MRI is commonly used to evaluate the function and morphology of the entire heart along with the surrounding vessels. Furthermore, due to the powerful ability of this imaging modality, it can quantify and visualize blood flow enabling us to better understand the underlying pathophysiology of many cardiac diseases. With further research and development, a newly emerging technique within MRI known as 4D Flow MRI can quantify and visualize blood flow in all three directions (X, Y, Z) throughout the cardiac cycle. Hence, 4D Flow MRI provides us with information on the spatial and temporal progression of 3D blood flow within an entire volumetric coverage of any vascular or cardiac region of interest. Moreover, this imaging modality can retrospectively analyze the patterns of blood flow at any location within the volume of interest along with assessing abnormal hemodynamic fluctuations, especially in patients with Congenital Heart Diseases (CHD). However, currently, 2D MRI is the current imaging method that is used for flow analysis within these patient cohorts. This may be due to 2D MRI having a quicker acquisition time, larger signal-to-noise ratio, and a quicker/simpler post-processing time compared to 4D Flow MRI. Although, 4D Flow MRI provides us with additional information that cannot be obtained from 2D MRI which can help with patient management and clinical decision-making among patients with CHD. Hence, this thesis aims to evaluate how 4D Flow MRI can be used to evaluate turbulent kinetic energy (TKE) in the entire heart within patients with rTOF and healthy controls. Currently, there is very little literature evaluating TKE within this patient cohort, however, is seen to be elevated within the heart of this patient cohort. This thesis also aims to compare accelerated imaging techniques including k-t GRAPPA and compressed sensing on TKE measurements within the pulmonary artery and aorta of healthy controls. Currently, there is no research comparing the two techniques. Hence, this aim will provide further insight into if different accelerating techniques impact various hemodynamic measurements. Lastly, this thesis also aims to develop simple visualization techniques for the aorta, pulmonary artery, left atrium, left ventricle, right atrium, and right ventricle to facilitate reporting of hemodynamic parameters obtained from 4D Flow MRI within the entire heart.
  • Thumbnail Image
    ItemOpen Access
    Integrating Multi-Domain Electronic Health Data, Machine Learning, and Automated Cardiac Phenomics for Personalized Cardiovascular Care
    (2024-04-19) Dykstra, Steven; White, James; Gavrilova, Marina; Wilton, Stephen; Alim, Usman
    This thesis aims to address core challenges surrounding the integration of multi-domain cardiovascular data, inclusive of patient reported health, electronic health information, and diagnostic imaging, to support artificial intelligence (AI) based risk prediction modelling. Despite inaugural success surrounding the use of AI-driven approaches to leverage granular features from each respective data source, the lack of integration continues to limit a comprehensive representation of patient health critical to the implementation of AI-augmented clinical decision support (AI-CDS). Central to this thesis was the primary hypothesis that patient-consented migration, integration, and curation of disparate data sources can be achieved in real-world clinical environments, permitting longitudinal accumulation of standardized resources for machine learning-based risk modelling. To test this hypothesis, my first aim was to develop a software infrastructure to establish and maintain a precision health data model for cardiovascular care. This data model forms the foundation of the Cardiovascular Imaging Registry of Calgary (CIROC), a platform which to date has generated structured data resources for over 20,000 unique patients with cardiovascular disease. The success of this robust data model has led to the expansion of this infrastructure to support all clinics of the Libin Cardiovascular Institute. The design of this initiative, called the PULSE program, was established as an objective of Aim 1, delivering a structured manuscript describing methods and recommendations for implementing a scalable institutional personalized medicine program for the ethical, fair, and equitable introduction of AI-CDS. Subsequently, the second aim demonstrates the value of the established data model, highlighting how it can be used for the development and validation of machine-learning based prediction models for cardiovascular outcomes. Utilizing multi-domain features of the CIROC data model, I demonstrated superiority of machine learning-based approaches over traditional risk prediction methods to predict new-onset atrial fibrillation, a leading cause of stroke. This study highlighted the value of integrating patient-reported health, electronic health record, and cardiac diagnostic data to forecast future cardiovascular events with improved accuracy. Further, my third aim targeted an expansion of disease features from source diagnostic testing data to improve risk modelling. To achieve this, I developed deep learning-based models for the automated analysis (segmentation and fiducial labelling) of the left ventricle from cine cardiac MRI imaging, enabling the delivery of 3D shape phenomics. This work showcases the capacity for deep learning techniques to further enhance the developed data models for patient-specific risk modelling by supporting advanced analyses of unique disease characteristics including shape and deformation. This novel solution is now planned for external validation by a large, international clinical study assessing the incremental value of 3D shape phenomics to improve prediction accuracy across a broad range of diseases. Overall, this thesis presents a comprehensive exploration of technical development required for, and value generated by multi-domain data integration for AI-CDS in cardiovascular care. Incremental to demonstrating feasibility, the deliverables of this thesis serve as a foundation for growth of an emerging institutional precision medicine initiative and for the development of future advanced multi-domain machine learning models relevant to cardiovascular care.
  • Thumbnail Image
    ItemOpen Access
    Machine learning using multimodal clinical, electroencephalographic, and magnetic resonance imaging data can predict incident depression in adults with epilepsy: A pilot study
    (Wiley, 2023-07-08) Delgado-García, Guillermo; Engbers, Jordan D. T.; Wiebe, Samuel; Mouches, Pauline; Amador, Kimberly; Forkert, Nils D.; White, James; Sajobi, Tolulope; Klein, Karl Martin; Josephson, Colin B.; Calgary Comprehensive Epilepsy Program Collaborators
    Objective: To develop a multi-modal machine learning (ML) approach for predicting incident depression in adults with epilepsy. Methods: We randomly selected 200 patients from the Calgary Comprehensive Epilepsy Program registry and linked their registry-based clinical data to their first-available clinical electroencephalogram (EEG) and magnetic resonance imaging (MRI) study. We excluded patients with a clinical or Neurological Disorders Depression Inventory for Epilepsy (NDDI-E)-based diagnosis of major depression at baseline. The NDDI-E was used to detect incident depression over a median of 2.4 years follow-up (IQR 1.5-3.3 years). A ReliefF algorithm was applied to clinical as well as quantitative EEG and MRI parameters for feature selection. Six ML algorithms were trained and tested using stratified three-fold cross-validation. Multiple metrics were used to assess model performances. Results: Of 200 patients, 150 had EEG and MRI data of sufficient quality for ML, of which 59 were excluded due to prevalent depression. Therefore, 91 patients (41 women) were included with a median age of 29 (IQR 22-44) years. A total of 42 features were selected by ReliefF, none of which were quantitative MRI or EEG variables. All models had a sensitivity >80% and 5 of 6 had an F1 score ≥0.72. Multilayer perceptron model had the highest F1 score (median 0.74; interquartile range [IQR] 0.71-0.78) and sensitivity (84.3%). Median area under the receiver operating characteristic curve and normalized Matthews correlation coefficient were 0.70 (IQR 0.64-0.78) and 0.57 (IQR 0.50-0.65), respectively. Significance: Multimodal machine learning using baseline features can predict incident depression in this population. Our pilot models demonstrated high accuracy for depression prediction. However, overall performance and calibration can be improved. This model has promise for identifying those at risk for incident depression during follow-up, though efforts to refine it in larger populations along with external validation are required.