SEMINAR: Discovering Type 1 Diabetes Patient Subgroups through Integrative Analysis of Heterogeneou
Sayed Sadra Mirhendi
Co-Supervisors: Drs. Lourdes Pena-Castillo and Ting Hu
Discovering Type 1 Diabetes Patient Subgroups through Integrative Analysis of Heterogeneous Data
Department of Computer Science
Monday, March 05, 2018, 1:30 p.m., Room EN 2022
Type 1 diabetes (T1D)is a disease in which the pancreas does not produce insulin to control the level of glucose in the human blood. Our research investigates whether groups of patients at higher risk for developingT1D complications can be identified by integrating demographic, clinical and genetic data. Regarding this purpose, we analyzed a T1D dataset from a cohort of children aged 0-14 years who were diagnosed with T1D in the Avalon Peninsula of Newfoundland, Canada. We explore two methods including Generalized Low Rank Models (GLRM) and Similarity Network Fusion (SNF)
to investigate our dataset and to determine groups of patients at higher risk of developing complications or secondary disease related to T1D.
By applying the proposed methods, we have identified groups of patients suffering from nerve damage, high blood pressure, dyslipidemia, and thyroid diseases. This result can be used to stratify patients at a higher risk of developing T1D complications to allow them to take preemptive steps for reducing their risks of complications. The outcome could be used as the basis to achieve a predictive model that could allow patients and health-care providers to take preemptive stepsto reduce the risk of developing T1D related complications based on each patient characteristics.