PROJECT SUMMARY/ABSTRACT While lung transplantation is the only treatment option for end-stage lung disease, early post-operative complications are common and limit long-term patient survival while concomitantly increasing the economic burden of an already expensive therapy. Successful surgical outcomes can be defined by an ideal or “textbook outcome” (TO) where the patient does not have significant early post-operative complications, which for lung transplant can include primary graft dysfunction, acute lung allograft dysfunction, renal failure or infection. Our group recently published the first lung transplant TO definition based on single-center data and found failure to achieve TO was strongly associated with worse patient survival and significantly higher cost to the health system. A subsequent registry analysis of 62 US lung transplant centers found the rate of achieving TO ranged from 27% to 72%, emphasizing wide variability in outcomes and potential for intervention and improvement. The Lung Transplant Clinical Center in this proposal include Duke University, University of Louisville, University of Minnesota and University of Pennsylvania. These centers are four of the oldest and most respected lung transplant centers in the country with geographic and size diversity, including small, medium, and large volumes. Our proposal aims to understand the critical pretransplant clinical characteristics, as well as novel underlying biologic aging differences, that contribute to worse early outcomes, or failure to achieve a TO. We hypothesize that specific clinical variables and biological aging measures can predict early complications. Biological age in the pretransplant patient may be driven by organ specific advanced lung disease and therefore ameliorated with lung transplant. Alternatively, biological age may be a systemic process across organs systems and does not resolve with transplant. To determine the significance of organ specific versus systemic aging, we will evaluate pretransplant biological aging in the recipient's pretransplant immune system and explanted lung. Using iterative machine learning we will develop and validate a TO prediction model based on the identified clinical variables and biological measurements to determine a personalized perioperative risk of lung transplantation for individual candidates. More than just a predictive tool, this proposal will allow for identification of potentially modifiable clinical and biologic variables that can be leveraged to improve outcomes. As part of the larger Lung Transplant Consortium, we will enroll participants and contribute data and biospecimens through a common research protocol under the auspices of the Lung Transplant Consortium Data Coordinating Center and Steering Committee.