Feature learning and personalized screening techniques in healthcare

Abstract

Data science is playing an increasingly important role in improving public health. Data used for public health studies are in various types, including electronic health records, image data, administrative data, claims data, and patient disease registries. The data variety provides opportunities and challenges for statisticians to impact public health in many ways. The value of statisticians lies in finding patterns in collected data, summarizing and presenting these in an effort to best describe the target population, and developing the necessary mathematical tools to ascertain associations of risk factors with the disease. This dissertation aims to develop data-driven, efficient statistical and machine learning techniques in some modern real-world applications. We consider four different contexts: (i) Visual impairment classification based on noisy high-frequency pupillary response behavior data collected from human-computer interaction, (ii) breast cancer diagnosis using image data from plain Xray, (iii) personalized screening for sepsis disease based on regularly measured longitudinal biomarkers, (iv) prediction on the overall burden of postoperative complications using laboratory measurements.