Assistant Professor, Georgia State University
https://cas.gsu.edu/profile/juan-banda/
Dr. Juan M. Banda, PhD is a computer scientist and a SAGE Center awardee at Georgia State University. Previously, Dr. Banda was a research scientist and a postdoctoral data science research fellow at Stanford University in the Stanford Center for Biomedical Informatics Research. His research combines machine learning, computer vision, and Natural Language Processing methods to generate insights from multi-modal large-scale data sources, such as structured and unstructured text from electronic health records and social media platforms, and develop novel research tools. His laboratory collaborates across several medical disciplines, including aging, ethnogeriatrics, Alzheimer’s disease, and related dementias, infectious diseases, drug safety, clinical decision-making, and health communication. Dr. Banda’s research has demonstrated the feasibility of using large amounts of unstructured data from multiple sources for drug safety surveillance, learning practice patterns, building predictive models, and elucidating the quality of care.
He is also well-versed in extracting terms and clinical concepts from millions of unstructured electronic health records and using them to build predictive models (electronic phenotyping) and mine for potential multi-drug interactions (drug safety). His work in electronic phenotyping includes leading the development of APHRODITE, a tool that allows researchers to build phenotypes using noisy labels. Dr. Banda has published over 90 peer-reviewed conference and journal papers. He is an active collaborator of the Observational Health Data Sciences and Informatics, and his work has been funded by Google, the National Institutes of Health, the Department of Veteran Affairs, as well as NASA and NSF.
Dr. Juan M. Banda, PhD is a computer scientist and a SAGE Center awardee. His research focuses on machine learning, computer vision, and Natural Language Processing methods that help to generate insights from multi-modal large-scale data sources. With applications to precision medicine, medical informatics, astroinformatics as well as other domains, working with large volumes of image data, extracting and transforming computer vision image features into large content-based image retrieval systems for NASA’s Solar Dynamics Observatory mission. He is also well-versed in extracting terms and clinical concepts from millions of unstructured electronic health records and using them to build predictive models (electronic phenotyping) and mine for potential multi-drug interactions (drug safety). His work in electronic phenotyping includes leading the development of APHRODITE, a tool that allows researchers to build phenotypes using noisy labels. Dr. Banda has published over 45 peer-reviewed conference and journal papers. He is an active collaborator of the Observational Health Data Sciences and Informatics and his work has been funded by the Department of Veteran Affairs, National Institute of Aging as well as NASA, NSF, and NIH.
SAGE Project: Are phenotyping algorithms fair for underrepresented minorities within older adults?
Dr. Banda’s SAGE project focused on examining bias of probabilistic phenotyping algorithms for older adults from underrepresented minority groups. Using local and national datasets, he showed that the accuracy and sensitivity of these algorithms for diagnosing dementia, frailty, mild cognitive impairment, Alzheimer’s disease, and Parkinson’s disease varied by disease phenotype and across the Asian, White, Black, Native American, and Pacific Islander populations. These results strongly illustrate the importance of conducting a rigorous investigation of algorithm performance before they are introduced into clinical practice. This work has been presented at several national and regional meetings, including the RCMAR Annual Meeting and the 2021 OHDSI Symposium. The APRODITE phenotype tool is also freely available to the research community: https://github.com/OHDSI/Aphrodite
