Nusrat J Epsi

Ph.D.

Adjunct Professor

School: Milken Institute School of Public Health

Department: Biostatistics and Bioinformatics

Contact:

Email: Nusrat J Epsi

Dr. Epsi is an Adjunct Professor in the Department of Biostatistics and Bioinformatics, where she teaches health data visualization to both undergraduate and graduate students in the School of Public Health. She is also a Research Scientist at the Henry M. Jackson Foundation for the Advancement of Military Medicine, where her work focuses on developing computational and machine learning approaches to improve acute respiratory infection prognosis, patient triage, and clinical decision-making. In addition, Dr. Epsi is an Assistant Professor in the Department of Preventive Medicine and Biostatistics at the Uniformed Services University of the Health Sciences (USUHS).

Education

PhD Rutgers, The State University of New Jersey (Summer 2020)
Majored in Biomedical Informatics, GPA: 4.00 (Received Academic excellence award)
Thesis: Pathway-centric generalizable computational framework uncovers pathway markers governing chemoresistance across cancers
MBA Ashland University (May 2015)
Majored in Business Analytics & Management Information System (Summa Cum Laude)

Expertise

Bioinformatics
Biostatistics
Data Science
Computational Biology

Teaching

Health Data Visualization PUBH 3242 and PUBH 6867 (Spring 2025)
Health Data Visualization PUBH 6867 (Fall 2025)

Research

Dr. Epsi applies advanced biostatistics, machine learning/AI, and multi-omics methods to infectious disease and operational medicine, integrating transcriptomic, proteomic, clinical, and biological data to study host-pathogen interactions and identify biomarkers of disease progression and outcomes. Her work includes rigorous evaluations of SARS-CoV-2 vaccine-induced immunity versus natural infection, development of calibrated performance and impact metrics for AI-driven combat casualty infection triage, and NLP models that extract COVID-19 symptomatology from clinical notes. When randomized studies are not feasible, she uses observational causal inference approaches (e.g., propensity scores, regression adjustment, difference-in-differences) to estimate intervention effects. She leads and collaborates across multidisciplinary teams, builds reproducible SQL and Python/R pipelines, publishes and supports grant development, and advises on responsible AI use in biomedical research.

Publications

Selected Journal Publications

Epsi, N.J., et al., Precision symptom phenotyping identifies early clinical and proteomic predictors of distinct COVID-19 sequelae. The Journal of infectious diseases (2024)
Editorial: Prospectively Defined Clusters of Coronavirus Disease 2019 Sequelae The Journal of infectious diseases (2024)
Epsi, N.J., Pollett, S., et al., A machine learning approach identifies distinct early-symptom cluster phenotypes which correlate with hospitalization, failure to return to activities, and prolonged COVID-19 symptoms. PLoS One (2023)
Epsi, N.J., Richard, S., Pollett, S., et al., Understanding ‘hybrid immunity’: comparison and predictors of humoral immune responses to SARS-CoV-2 infection and COVID-19 vaccines. The Clinical Infectious Diseases (2022)
Epsi, N.J., Richard, S., Pollett, S., et al., Clinical, immunological, and virological SARS-CoV-2 phenotypes in obese and non-obese military health system beneficiaries. The Journal of Infectious Diseases, Oxford Journals. (2021)
Epsi, N.J., Mitrofanova, A., et al., pathCHEMO: Uncovering (epi) genomic pathways of chemoresistance in lung adenocarcinoma. Nature Communications Biology (2019).

Book Publication

Epsi, N.J., * Panja, S., and Mitrofanova, A., Detection Methods in Precision Medicine. Chapter: Big Data and its emerging role in therapeutic response modeling, the Royal Society of Chemistry, 2020 (published). *co-first author

Complete List of Published Work: https://pubmed.ncbi.nlm.nih.gov/?term=Epsi%20N

Scopus author ID: 57200648798