No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

By taking advantage of the increasing amount of available electronic health data, applications of machine learning in the intensive care unit have the potential to improve medical diagnostics and risk stratification. This thesis proposes an approach for early onset prediction of pneumothorax with such technique, using time series data extracted from a clinical database. The prevalence of pneumothorax among patients is identified through ICD-9 codes, and labels for the onset are obtained by relying on proxies closely related to the condition. Both simple algorithms and deep learning networks are used in a sliding window-based prediction framework, and the importance of each feature is measured with weighted Shapley values. The results proved the feasibility of this approach using Long Short-Term Memory models, although the number of false positives is noticeably high. Mechanical ventilation was the most contributing feature for the outcome. In future work, the focus should be on addressing the large class imbalance that prevails, along with considering more well-founded methods of target labeling.

<p>Localization of speech onsets to determine onset latencies is a complicated problem with as many different methods for finding them as there are different areas which use such measurements. A majority of research performed in cognition uses a standard amplitude threshold voice key for estimating the speech onset latencies but a number of studies have shown that this method is incredibly inaccurate and can bias data or produce contradictory results. A number of alternative methods based on modifications to traditional voice-keys have been proposed to deal with the inconsistency although still show a number of deficiencies. Previous work has suggested that switching from the amplitude domain of a signal to the frequency domain a number of the issues present with voice keys can be overcome and when used in conjunction with a number of highly sensitive heuristics highly accurate onset latencies can be produced reliably under ideal conditions. This research is refined and paired with a new user interface to improve the ease of use and increase the adoption rate of this type of analysis. Recent work in the telecommunications industry also suggests that wavelet-based algorithms in conjunction with the Teager Energy Operator (TEO) can accurately detect speech even in the presence of noise. Four wavelet-based methods are investigated and tested; a simple wavelet transform test, and three methods using wavelet-packet transforms in conjunction with the TEO. Although these methods do not perform very well compared to traditional methods a number of potential issues with the implementation are discussed.</p> / Master of Science (MSc)

Background: Coronary Artery Disease (CAD) represents the leading cause of mortality and morbidity worldwide despite declines in the prevalence of environmental risk factors. This trend has drawn attention to the risk conferred by genetic variation. Twin and linkage studies demonstrate a profound hereditary risk for CAD, especially in young individuals. Rare genetic variants conferring high risk for extreme disease phenotypes can provide invaluable insight into novel mechanisms underlying CAD development. Methods: Whole exome sequencing was performed to characterize rare protein-altering variants in 52 early-onset CAD (EOCAD) patients encompassing the DECODE study. The enrichment of Mendelian dyslipidemias in EOCAD was assessed through interrogation of pathogenic mutations among known lipid genes. The identification of novel genetic CAD associations was conducted through case-only and case-control approaches across all protein-coding genes using rare variant burden and variance component tests. Lastly, beta coefficients for significant risk genes from the European population in the Early-onset Myocardial Infarction (EOMI) cohort (N=552) were used to construct calibrated, single-sample rare variant gene scores (RVGS) in DECODE Europeans (N=39) and a local European CAD-free cohort (N=77). Results: A 20-fold enrichment of Familial hypercholesterolemia mutation carriers was detected in EOCAD cases compared to CAD-free controls (P=0.005). Association analysis using EOMI Europeans revealed exome-wide and nominal significance for two known CAD/MI genes: CELSR2 (P=1.1x10-17) and APOA5 (P=0.001). DECODE association revealed exome-wide and nominal significance for genes involved in endothelial integrity and immune cell activity. RVGS based upon beta coefficients of significant CAD/MI risk genes were significantly increased in DECODE (z-score=1.84; p=0.03) and insignificantly decreased among CAD-free individuals (z-score=-1.61; p=0.053). Conclusion: Rare variants play a pivotal role in the development early CAD through Mendelian and polygenic mechanisms. Construction of RVGS that are calibrated against population and technical biases can facilitate discovery of single-sample and cohort-based associations beyond what is detectable using standard methods. / Thesis / Master of Science (MSc)

京都大学 / 新制・課程博士 / 博士(地球環境学) / 甲第24858号 / 地環博第241号 / 新制||地環||47(附属図書館) / 京都大学大学院地球環境学舎地球環境学専攻 / (主査)教授 星野, 敏, 准教授 鬼塚, 健一郎, 准教授 落合, 知帆 / 学位規則第4条第1項該当 / Doctor of Global Environmental Studies / Kyoto University / DGAM