Browsing by Author "MacDonald, Matthew Ethan"

Now showing 1 - 6 of 6
  • Thumbnail Image
    ItemOpen Access
    Deep learning methods for classifying disease subtypes in multiple sclerosis based on clinical imaging and non-imaging data
    (2024-09-23) Soleymani, Mahshid; Zhang, Yunyan; Bento, Mariana Pinheiro; Forkert, Nils Daniel; MacDonald, Matthew Ethan
    Multiple sclerosis (MS) is a common inflammatory demyelinating and neurodegenerating disease of the central nervous system impacting over 2.8 million people worldwide. Most people start MS with a relapsing-remitting form (RRMS), yet no two persons have the same disease course. Many of them will develop a secondary-progressive course (SPMS) despite treatment, causing dramatic health and socioeconomic consequences. Early accurate measurement of disease activity will permit early effective treatment for improved prognosis. But there is no established method to classify these two subtypes beforehand clinically. By leveraging the power of deep learning such as convolutional neural networks (CNNs), this project aims to optimize personalized disease characterization using standard clinical data especially brain magnetic resonance imaging (MRI). Specifically, based on 140 clinical participants with RRMS or SPMS, the research targets phenotype prediction through a series of development and validation processes. These included data optimization, model development and testing based on both 2D- and 3D- CNN models, and model interpretation using a recognized method called gradient-class activation mapping (Grad- CAM). Results showed that axial images normalized with a Z-score like approach were most feasible. Both the 2D and 3D models achieved >80% accuracy in predicting RRMS and SPMS, where combining both MRI and clinical variables appeared to perform better than either data type alone. The Grad-CAM analysis helped discern critical brain areas related to each MS subtype. These findings underscore the potential of deep learning based completely on clinical care data to detect disease activity, marking early diagnosis and personalized treatment possible.
  • Thumbnail Image
    ItemOpen Access
    Design and Implementation of a Recommender System for use at an Emergency Homeless Shelter in Calgary
    (2021-05-04) John, Caleb Thomas; Messier, Geoffrey; Yanushkevich, Svetlana; MacDonald, Matthew Ethan
    Modern homeless shelters are collecting data from key interactions with clients. This data can be utilized by machine learning algorithms to identify clients that are at risk for chronic homelessness. This would provide shelter operators with a powerful new tool to assist them in housing individuals. However, most machine learning algorithms are not suitable for the task due to the lack of interpretability. Classification rule learning is brought forward in this work as an exceedingly interpretable class of machine learning algorithms. A novel recommender system based on classification rule learning is proposed and evaluated on local homeless shelter data. The results from this work suggest that classification rule learning is robust and interpretable enough to be used to support modern homeless shelters.
  • Thumbnail Image
    ItemOpen Access
  • Thumbnail Image
    ItemOpen Access
    Quantitative Cerebrovascular Magnetic Resonance Imaging
    (2014-09-19) MacDonald, Matthew Ethan; Frayne, Richard
    This thesis explores quantitative cerebrovascular magnetic resonance (MR) imaging, a broad topic, with the aim of providing relevant numerical values associated with blood flow through the brain. Anatomy, pathology and basic angiography methods were reviewed. Several other MR imaging methods for obtaining cerebrovascular measurements are reviewed. Exploration of the lowest achievable variance with MR imaging was undertaken through simulation using a digital brain phantom. A phantom was constructed from a healthy human brain data set using advanced methodologies to yield volumes of MR parameters (i.e., coil sensitivity, B0, B1, M0, T1, T2, T2*, and magnetic susceptibility). The digital brain phantom was then used to simulate the MR acquisition process and generate images, in order to determine the minimal achievable variance as a function of coil profile distortion. It was found that the degree of coil correlation could affect the lowest achievable variance by up to 2× to 3× over practical ranges. The focus of the experimental chapters is on phase contrast velocity mapping and metrics that can be derived from velocity maps, such as: peak velocity, volume flow rate, and intravascular pressure. Prospective imaging was performed on healthy humans, and eight patients (five cerebral aneurysms and three arteriovenous malformations). A case study of a giant cerebral aneurysm was explored in greater detail, and stent treatment was shown to reduce flow asymmetry. Peak velocity and volume flow rate was determined for vessels in the normal brain. Bootstrapping is performed to assert that group-wise measurements are representative of the broader population and flow laterality is examined. Significant flow asymmetry was found between several paired vessel segments. Flow in the patients was imaged, and derived metrics were compared to the healthy cohort. Patients with aneurysm were found to have significantly lower flow in vessels distal to the aneurysm, while arteriovenious malformation patients were found to have significantly higher flow in vessels supplying the nidus.
  • Thumbnail Image
    ItemOpen Access
    The Bias of Using Cross-Validation in Genomic Predictions and Its Correction
    (2023-09-21) Qian, Yanzhao; Greenberg, Matthew; Long, Quan; Shen, Hua; MacDonald, Matthew Ethan
    Cross-validation (CV) is a widely used technique in statistical learning for model evaluation and selection. Meanwhile, various of statistical learning methods, such as Generalized Least Square (GLS), Linear Mixed-Effects Models (LMM), and regularization methods are commonly used in genomic predictions, a field that utilizes DNA polymorphisms to predict phenotypic traits. However, due to high dimensionality, relatively small sample sizes, and data sparsity in genomic data, CV in these scenarios may lead to an underestimation of the generalization error. In this work, we analyzed the bias of CV in eight methods: Ordinary Least Square (OLS), GLS, LMM, Lasso, Ridge, elastic-net (ENET), and two hybrid methods: one combining GLS with Ridge regularization (GLS+Ridge), and the other combining LMM with Ridge regularization (LMM+Ridge). Leveraging genomics data from the 1,000 Genomes Project and simulated phenotypes, our investigation revealed the presence of bias in all these methods. To address this bias, we adapted a variance-structure method known as Cross-Validation Correction (CVc). This approach aims to rectify the cross-validation error by providing a more accurate estimate of the generalization error. To quantify the performance of our adapted CVc towards all these methods, we applied the trained model to an independently generated dataset, which served as a gold standard for validating the models and calculating the generalization error. The outcomes show that, by leveraging CVc, we corrected the CV bias for most of the methods mentioned above, with two exceptions that are unrectifiable methods: ENET and Lasso. Our work revealed the substantial bias in the use of CV in genomics, a phenomenon under-appreciated by the field of statistical genomics and medicine. Additionally, we demonstrated that bias-corrected models may be formed by adapting CVc, although more work is needed to cover the full spectrum.
  • Thumbnail Image
    ItemEmbargo
    Using Domain Adaptation and Inductive Transfer Learning to Improve Patient Outcome Prediction in the Intensive Care Unit
    (2023-12-07) Mutnuri, Maruthi Kumar; Lee, Joon; Stelfox, Thomas; Forkert, Nils Daniel; MacDonald, Matthew Ethan; Parhar, Ken Kuljit
    Predicting patient outcomes in the intensive care unit (ICU) can allow appropriate allocation of resources, minimize costs, and provide better patient care. Machine learning and deep learning models can predict patient outcomes with a high degree of accuracy, but training those models is both data- and resource-intensive. Deep learning models trained on small datasets tend to overfit and generalize poorly, and transfer learning (TL) helps in such situations by leveraging the knowledge learned from pre-trained models. Transfer learning is a machine learning technique where a model pre-trained on source task is adapted for a different but related target task. Here, source task is trained with a large dataset whereas a small dataset is sufficient for training target task. Notably, TL is widely used in medical image analysis and natural language processing, but it is uncommon in electronic health record (EHR) analysis. Within the TL literature, domain adaptation (DA) is most common, whereas inductive transfer learning (ITL) is rare. This study explores both DA and ITL using EHR data. To investigate the effectiveness of these TL models, we compared them with baseline models of logistic regression (LR), lasso regression, and fully connected neural networks (FCNN) in the prediction of 30-day mortality, acute kidney injury (AKI), hospital length of stay (H_LOS), and ICU length of stay (ICU_LOS). We used two cohorts: (1) eCritical, a multicenter ICU data linked with administrative data from ICUs in Alberta, Canada between March 2013 and December 2019, which has 55,689 unique admission records from 48,672 unique patients admitted to 15 medical-surgical ICUs, and (2) MIMIC-III, a single-center publicly available ICU dataset from Boston, USA between 2001 and 2012. The first admission of adult patient records with more than 24-hour ICU stays were included in this retrospective study. We included common features from both the cohorts. Random data subsets of training data, ranging from 1% to 75%, and the full dataset were used to compare the performances of DA and ITL with FCNN, LR, and lasso. Overall, ITL outperformed baseline FCNN, LR, and lasso models in 55 of the 56 comparisons (7 data subsets, 4 outcomes, and 2 baseline models) using BA and MSE metrics. However, DA models outperformed the baseline models 45 out of the 56 times. ITL performance was comparatively better than DA considering the number of times it outperformed baseline models and the margin with which it outperformed baseline models. Also, in 11 out of the 16 cases (8 of 8 for ITL and 3 of 8 for DA) TL models outperformed baseline models at 1% data subset. This is significant because TL models are useful in data-scarce scenarios. When using EHR data, the similarity of data distributions in source and target domains was crucial, as evident from ITL performing much better than DA, mostly because of the domain mismatch in the two cohorts concerning AKI, H_LOS, and ICU_LOS outcomes. As the pre-trained models will be made available publicly, further research can be conducted with additional outcomes and different cohorts to make these pre-trained models more robust using incremental or cumulative transfer learning. These pre-trained models can be used for predicting patient outcomes at ICU.