Michael A. Grasso

Michael A. Grasso, MD, PhD, is a Clinical Associate Professor in the Department of Medicine and Emergency Medicine at the University of Maryland School of Medicine. He practices Emergency Medicine and serves as Director of the Clinical Informatics Group and Program Director for Clinical Informatics graduate programs at the University of Maryland Baltimore.

His education includes:

• BS in Microbiology, University of Maryland (1983)
• MS in Computer Science, American University (1986)
• PhD in Computer Science, University of Maryland Baltimore County (1997)
• MD, George Washington University (2005)
• Internal Medicine Residency, University of Maryland (2008)
• Clinical Informatics Fellowship, University of Maryland (2013)

Dr. Grasso's research focuses on knowledge representation and reasoning for large-scale clinical data systems. Key areas include:

• Big data analytics for chronic disease prediction (diabetes, rheumatoid arthritis, opioid misuse)
• Patient safety and quality improvement in emergency medicine
• Impact of online consumer health information on clinical decision-making

His 13 recent publications (2011-2022) reveal strong trends in Veterans Health Administration data analysis, opioid prescribing patterns, and machine learning applications. Work emphasizes clinical decision support, predictive modeling for mortality/disease, and ICD-10 coding impacts in emergency settings.

Scientific honors include:

• Fellow of the American College of Physicians (FACP)
• Fellow of the American Medical Informatics Association (FAMIA)
• Three medical/computing honor societies

As Program Director for Clinical Informatics graduate programs, he mentors students in this emerging field. He has secured over $2,000,000 in grants from NIH, FDA, NIST, NASA, and DoD for:

• Knowledge representation with big clinical repositories
• Emergency department quality/safety initiatives
• Consumer health information impact studies

He leads the University of Maryland Clinical Informatics Group, leveraging Veterans Health Administration data (35M patients) and University of Maryland Medical System's EPIC repository (14 hospitals) to develop semantic-enhanced machine learning for disease prediction and treatment efficacy.