Beginning with my foundational training in medical physics and evolving through a specialized residency in Therapeutic Medical Physics, my trajectory has been one of merging clinical insights with innovative data-driven research. Early endeavors in harnessing machine learning for patient outcomes took a pivotal turn during my K08 award, where I was privileged to work closely with Dr. Jerome Friedman, one of the pioneering fathers of Statistical Learning, at Stanford. His teachings catalyzed my drive for innovations such as the Additive Tree. Further refining my craft, my collaboration with the esteemed Dr. Van der Laan, the co-creator of Targeted Learning, opened new avenues of exploration central to this proposal. My contributions, including MediBoost, Expert Augmented Machine Learning, The Conditional Super Learner, Representational Gradient Boosting and Lockout, are testament to my dedication to machine learning precision and interpretability. Serving as the director of the "Advanced Machine Learning" graduate course at UCSF and holding joint appointments in Radiation Oncology and Biostatistics, coupled with my appointments in the Center for Targeted Machine Learning and Causal Inference and the Precision Health Program at UCB, exemplify my commitment to bridging Machine Learning, Biostatistics and clinical acumen. The distinguished NIH BIBK08 award I've received further substantiated my passion for devising machine learning algorithms in myriad clinical landscapes and provided me with the training in fundamental statistics needed to carry on a project like the one is proposed here.
Machine Learning, Targeted Learning, Cancer Research
