Project summary/abstract Fundamental gaps in prevention of chronic lung disease in premature infants include the lack of understanding of mechanisms by which maturation of ventilatory control allows maintenance of adequate oxygenation, and how immature breathing phenotypes contribute to outcomes. Achieving the long-term goal of trials of effective preventive measures and treatments includes detection and analysis of immature breathing patterns in a large database of clinical information and cardiorespiratory monitoring data from multiple Neonatal ICUs, including vital signs and waveforms. The objectives of this proposal are (1) automated, validated detection of immature breathing patterns by teams of clinicians and mathematicians, and (2) a Leadership and Data Coordination Center (LDCC) for this NIH cooperative agreement to study a prospective observational cohort. The central hypothesis is that quantification of immature breathing will identify physiological biomarkers that can serve as targets for prevention and treatment that improve outcomes. A proposed multicenter protocol has Aims 1 and 2 to develop predictive models for immature breathing, and to relate them to clinically significant respiratory outcomes. The proposed LDCC builds on the experience of this university in successful completion of the heart rate characteristics monitoring trial, the largest RCT in premature infants, NIH-funded and completed on time and on budget. The computing requirements will be met by a new University of Virginia Center and in concert with our partners Lawrence Livermore National Laboratory and Intel Corporation. We will isolate and store DNA in our Biorepository and Tissue Research Facility, and manage sites with our Clinical Trials Office. Large-scale computing clusters dedicated for this work are in daily use. The contributions are expected to be (1) computational tools for prediction of respiratory outcomes, and (2) effective LDCC performance in data management, computational modeling, biorepository, and clinical studies management. The proposed research will be significant because it is the first step in programs for better therapies and preventive measures for chronic lung disease in premature infants. The proposed advanced analysis of monitoring data is innovative because of the cutting edge solutions to advanced computing and data security that may also inform other NIH multicenter studies of Big Data.