Interests:

Machine learning, natural language processing, and clinical informatics.

Background:

Dr. Kevin Lybarger is a tenure-track Assistant Professor in the Department of Information Sciences and Technology at George Mason University, specializing in machine learning and natural language processing (NLP). He has an established track record in clinical informatics, focusing on information extraction from clinical text to facilitate secondary use applications. His methodological contributions include the design of annotation schemas and taxonomies, the creation of high-quality annotated datasets, and the development of novel task-specific NLP architectures.

Representative publications:

• N. A. Sathe, S. Xian, F. L. Mabrey, D. R. Crosslin, S. D. Mooney, E. D. Morrell, K. Lybarger, M. Yetisgen, G. P. Jarvik, P. K. Bhatraju, et al. Evaluating construct validity of computable acute respiratory distress syndrome denitions in adults hospitalized with COVID-19: an electronic health records based approach. BMC Pulmonary Medicine, 23(1), 2023. doi:10.1186/s12890-023-02560-y.
• M. G. Prado, L. G. Kessler, M. A. Au, H. A. Burkhardt, M. Z. Suchsland, et al. Symptoms and signs of lung cancer prior to diagnosis: case-control study using electronic health records from ambulatory care within a large US-based tertiary care centre. BMJ Open, 13(4), 2023. doi: 10.1136/bmjopen-2022-068832.
• K. Lybarger†, N. J. Dobbins†, R. Long, A. Singh, P. Wedgeworth, Ö. Uzuner, and M. Yetisgen. Leveraging natural language processing to augment structured social determinants of health data in the electronic health record. Journal American Medical Informatics Association, 2023. doi: 10.1093/jamia/ocad073. [free-access link] (†authors contributed equally).
• A. L. Hartzler, S. J. Xie, P. Wedgeworth, C. Spice, K. Lybarger, et al. Integrating patient voices into the automatic extraction of social determinants of health from clinical records: Ethical considerations and recommendations. Journal American Medical Informatics Association, 2023. doi: 10.1093/jamia/ocad043. [free-access link]
• G. K. Ramachandran, K. Lybarger, Y. Liu, D. Mahajan, J. J. Liang, et al. Extracting medication changes in clinical narratives using pre-trained language models. Journal Biomedical Informatics, page 104302, 2023. doi: 10.1016/j.jbi.2023.104302.
• K. Lybarger, M. Yetisgen, and Ö. Uzuner. The 2022 n2c2/UW shared task on extracting social determinants of health. Journal American Medical Informatics Association, 2023. doi: 10.1093/jamia/ocad012. [free-access link]
• M. Zigman Suchsland, L. Kowalski, H. A. Burkhardt, M. G. Prado, L. G. Kessler, et al. How timely is diagnosis of lung cancer? Cohort study of individuals with lung cancer presenting in ambulatory care in the United States. Cancers, 14(23), 2022. doi: 10.3390/cancers14235756.
• W. Lau, K. Lybarger, M. Gunn, and M. Yetisgen. Event-based clinical findings extraction from radiology reports with pre-trained language model. Journal Digital Imaging, 2022. doi: 10.1007/s10278-022-00717-5.
• J. S. Tauscher, K. Lybarger, X. Ding, A. Chander, W. J. Hudenko, et al. Automated detection of cognitive distortions in text exchanges between clinicians and people with serious mental illness. Psychiatric Services, 2022. doi: 10.1176/appi.ps.202100692.
• K. Lybarger, M. Ostendorf, M. Thompson, and M. Yetisgen. Extracting COVID-19 diagnoses and symptoms from clinical text: A new annotated corpus and neural event extraction framework. Journal Biomedical Informatics, 2021. doi: 10.1016/j.jbi.2021.103761.
• K. Lybarger, M. Ostendorf, and M. Yetisgen. Annotating social determinants of health using active learning, and characterizing determinants using neural event extraction. Journal Biomedical Informatics, 113:103631, 2021. doi: 10.1016/j.jbi.2020.103631. (slides)
• T. Payne, W. Alonso, J. Markiel, K. Lybarger, R. Lordon, et al. Using voice to create inpatient progress notes: effects on note timeliness, quality, and physician satisfaction. Journal American Medical Informatics Association Open, 1(2):218-226, 2018. doi: 10.1093/jamiaopen/ooy036.
• K. Lybarger, M. Ostendorf, E. Riskin, T. Payne, A. White, et al. Asynchronous speech recognition affects physician editing of notes. Applied Clinical Informatics, 9(4):782-790, 2018. doi: 10.1055/s-0038-1673417.
• T. Payne, W. Alonso, A. Markiel, K. Lybarger, and A. White. Using voice to create hospital progress notes: description of a mobile application and supporting system integrated with a commercial electronic health record. Journal Biomedical Informatics, 77:91-96, 2017. doi: 10.1016/j.jbi.2017.12.004.