Computational Methods for Identifying Hypertrophic Cardiomyopathy using 12-lead ECG

Hypertrophic cardiomyopathy (HCM) is a cardiovascular disease where the heart muscle is partially thickened and blood flow is - potentially fatally - obstructed. It is one of the leading causes of sudden cardiac death in young people. Electrocardiography (ECG) and Echocardiography (Echo) are the standard tests for identifying HCM and other cardiac abnormalities. The American Heart Association has recommended using a pre-participation questionnaire for young athletes instead of ECG or Echo tests due to considerations of cost and time involved in interpreting the results of these tests by an expert cardiologist. Initially we set out to develop a classifier for automated prediction of young athletes’ heart conditions based on the answers to the questionnaire. Classification results and further in-depth analysis using computational and statistical methods indicated significant shortcomings of the questionnaire in predicting cardiac abnormalities. Automated methods for analyzing ECG signals can help reduce cost and save time in the pre-participation screening process by detecting HCM and other cardiac abnormalities. Therefore, the main goal of this dissertation work is to identify HCM through computational analysis of 12-lead ECG. ECG signals recorded on one or two leads have been analyzed in the past for classifying individual heartbeats into different types of arrhythmia as annotated primarily in the MIT-BIH database. In contrast, we classify complete sequences of 12-lead ECGs to assign patients into two groups: HCM vs. non-HCM. The challenges and issues we address include missing ECG waves in one or more leads and the dimensionality of a large feature-set. We address these by proposing imputation and feature-selection methods. We develop heartbeat-classifiers by employing Random Forests and Support Vector Machines, and propose a method to classify full 12-lead ECGs based on the proportion of heartbeats classified as HCM. The results from our experiments show that the classifiers developed using our methods perform well in identifying HCM. Thus the two contributions of this thesis are the utilization of computational and statistical methods for discovering shortcomings in a current screening procedure and the development of methods to identify HCM through computational analysis of 12-lead ECG signals.

A HARD PUSH FOR SOFT SKILLS: AN EXAMINATION OF POLICY AND RESEARCH ON NON-COGNITIVE SKILLS IN CANADIAN K-12 SCHOOLING

Non-cognitive skills have caught the attention of current education policy writers in Canada. Within the last 10 years, almost every province has produced a document including the importance of supporting non-cognitive skills in K-12 students in the classroom. Although often called different names (such as learning skills, cross curricular competencies, and 20th Century Skills) and occasionally viewed through different lenses (such as emotional intelligence skills, character skills, and work habits), what unifies non-cognitive skills within the policy documents is the claim that students that are strong in these skills are more successful in academic achievement and are more successful in post-secondary endeavors. Though the interest from policy-makers and educators is clear, there are still many questions about non-cognitive skills that have yet to be answered. These include: What skills are the most important for teacher’s to support in the classroom? What are these skills’ exact contributions to student success? How can teachers best support these skills? Are there currently reliable and valid measures of these skills? These are very important questions worth answering if Canadian teachers are expected to support non-cognitive skills in their classrooms with an already burdened workload. As well, it can begin to untangle the plethora of research that exists within the non-cognitive realm. Without a critical look at the current literature, it is impossible to ensure that these policies are effective in Canadian classrooms, and to see an alignment between research and policy. Upon analysis of Canadian curriculum, five non-cognitive skills were found to be the most prevalent among many of the provinces: Self-Regulation, Collaboration, Initiative, Responsibility and Creativity. The available research literature was then examined to determine the utility of teaching these skills in the classroom (can students improve on these skills, do these skills impact other aspects of students’ lives, and are there methods to validly and reliably assess these skills). It was found that Self-Regulation and Initiative had the strongest basis for being implemented in the classroom. On the other hand, Creativity still requires a lot more justification in terms of its impact on students’ lives and ability to assess in the classroom.