PROJECT SUMMARY/ABSTRACT Angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin receptor blockers (ARBs) are guideline- recommended therapies for preventing end-stage kidney disease (ESKD) and cardiovascular disease (CVD) events in patients with CKD. However, in real-world practice, ACEIs/ARBs are frequently discontinued by providers in the setting of acute kidney injury (AKI), rapid declines in kidney function, or advanced CKD. Premature discontinuation of ACEIs/ARBs can lead to adverse clinical outcomes among patients with CKD. However, discontinuation of these agents may be appropriate for certain CKD subgroups who are at higher risk of AKI and who may derive less benefit from these agents than trial populations. Although guidelines support the use of ACEIs/ARBs in patients with CKD, they also allow for individualization of decisions surrounding their use. However, it is unclear how to best individualize these decisions as CKD progresses to optimize kidney and cardiovascular outcomes. The overall objective of this proposal is to personalize ACEI/ARB therapy for patients with CKD based on each individual's risk factors for ESKD and CVD. To accomplish this, we will use data from the Chronic Renal Insufficiency Cohort (CRIC) Study. We will first identify factors that drive the discontinuation of ACEIs/ARBs (Aim 1). Next, we will build two clinical tools that model the relationship between ACEI/ARB discontinuation and risk of ESKD (Aim 2) or CVD events (Aim 3) in individuals with CKD. Our long-term goal is to reduce the burden of kidney disease and improve patient outcomes by individualizing medication use in CKD. We expect that completion of these aims will result in the development of two prediction tools that can be further refined and implemented in real-world clinical practice as part of a career development award application. The proposed aims are integrated into a comprehensive training plan that includes a Master's Degree in Clinical Research and practical mentored experiences. Through this training plan, Dr. Chen will have the opportunity to 1) learn and apply knowledge in advanced biostatistical and epidemiological methods, including marginal structural modeling; 2) gain familiarity with the CRIC Study database, 3) apply machine learning algorithms to the development of clinical prediction tools, 4) refine skills in scientific writing and presenting research, and 5) advance towards a career development award and independence as a clinical investigator.