Medicine is becoming an increasingly quantitative and precise field. With this in mind, I believe there is an emerging research area that has the potential to completely revolutionize the personalized-medicine landscape: artificial intelligence (AI). My long-term goal is a multifaceted approach to implement AI for personalized-medicine clinical decision support tools, with the intention of practicing as a clinician-scientist. As a mixed-race Hispanic-American raised on the US/Mexico border, I recognized early the importance and utility of viewing problems from different perspectives. My undergraduate education in physics served as an interdisciplinary foundation that allowed me to extract knowledge from varied fields of science, mathematics, and engineering, to apply in research. While in medical school, I gained an interest in the field of medical imaging. I applied machine learning methodology to solve quantitative imaging problems in central nervous system disease pathologies, such as brain tumors and multiple sclerosis, and presented my findings at prominent international conferences. These projects were structured with the intention of developing personalized-medicine frameworks based on AI. Moreover, by completing my clinical rotations before beginning my PhD I had the opportunity to organically approach hypothesis generation in translational science. Specifically, I learned how my patient interactions could drive my innovations in the lab. Therefore, I am innately cognizant of the lack of robust clinical decision support tools in current practice that I believe can be solved with quantitative approaches. Currently, I am utilizing my PhD graduate studies as an opportunity to further apply AI to medical imaging with the intention of improving diagnostic and prognostic capabilities of clinicians, particularly in the realm of head and neck radiotherapy. The overarching aim of my graduate work is to develop interpretable AI personalized-medicine solutions that can be readily translated as clinical decision support tools. I have helped develop tools for various facets of the radiotherapy workflow including: image processing, segmentation, and outcome prediction. I have been fortunate to receive generous support from the NIH through competitive training grants (TL1TR003169, 1 F31 DE031502-01). Ultimately, it is my ambition to give back to the underserved community I grew up in as a clinician-scientist, gaining inspiration from my patients to influence translational AI innovation that can be applied back to my patients in a cyclical fashion.