Skip to navigation Skip to content
Careers | Phone Book | A - Z Index
Applied Computing for Scientific Discovery

Rafael Zamora-Resendiz

Rafael Zamore Resendiz
Rafael Zamora-Resendiz

Rafael Zamora-Resendiz is a computer systems engineer (CSE-) in the Applied Mathematics and Computational Research Division (AMCR) at Lawrence Berkeley National Laboratory (LBNL). He currently is working on applied natural language processing (NLP) for healthcare in collaboration with the Department of Veterans Affairs  (VA). As part of the Million Veterans Program (MVP), he leads the development of NLP methods for scalable information retrieval using high-performance computing.

Rafael graduated with a B.S. in Computer Science from Hood College (Frederick, Maryland) in 2017. Through the Visiting Faculty Program (VFP), he interned under the mentorship of Dr. Xinlian Liu (Hood College) and  Dr. Silvia Crivelli (LBNL) where he researched applications of deep learning to structural proteomics. After the culmination of his initial appointment, he worked with Dr.Crivelli to bring computational science for healthcare research to LBNL. Rafael received his staff position at LBNL as a domain expert in machine learning in 2019. His focus is on providing methodological support to VA clinicians in the development and implementation of deep learning-enabled electronic health record analysis.

His current research includes the development of large language models for clinical text and scalable search algorithms for indexing U.S. Veteran mortality factors. His work helps inform the alignment of clinical vocabularies to VA data and investigate variation in clinical prose across facilities and providers.


Journal Articles

Destinee Morrow, Rafael Zamora-Resendiz, Jean C Beckham, Nathan A Kimbrel, David W Oslin, Suzanne Tamang, Million Veteran Program Suicide Exemplar Work, Silvia Crivelli, "A case for developing domain-specific vocabularies for extracting suicide factors from healthcare notes", Journal of psychiatric research, July 1, 2022, 151:328-338, doi: 10.1016/j.jpsychires.2022.04.009