Faced with unsustainable costs and enormous amounts of under-utilized data, health care needs more efficient practices, research, and tools to harness the benefits of data. These methods create a feedback loop where computational tools guide and facilitate research, leading to improved biological knowledge and clinical standards, which will in turn generate better data. In order to facilitate the necessary changes, better tools are needed for assessing risk and optimizing treatments, which further require better understanding of disease interdependencies, genetic influence, and translation into a patient's future. This dissertation explores network-centric data mining approaches for benefit in multiple stages of this feedback loop: from better understanding of disease mechanisms to development of novel clinical tools for personalized and prospective medicine. Applications include predicting personalized patient disease risk based on medical history, optimizing NICU nursing schedules to reduce negative effects, and predicting novel disease-gene interactions.