The Jonathan Weiner Lab researches the impact of electronic health records (EHRs), e-health and other health information technology (HIT) on populations, integrated delivery systems and public health agencies.

The Maura McGuire Lab focuses on the improvement of quality and safety in ambulatory medicine through care management, point-of-care laboratory testing, and electronic health records and care delivery optimization. We also study the use of assessment and technology to augment learning in health care professionals and primary care physicians.

Research in the Casey Overby Lab focuses on the intersection of public health genomics and biomedical informatics. We’re currently developing applications to support the translation of genomic research to clinical and population-based health care settings. We’re also working to develop knowledge-based ways to use big data — including electronic health records — to improve population health.

Research in the Hadi Kharrazi Lab focuses primarily on contextualizing clinical decision support (CDS) into population health informatics (PHI) to be used at different HIT levels of managed care, including electronic health records (EHRs) and consumer health informatics (CHI) solutions. Our team has modified and regenerated electronic quality measures (eQM) based on PHI-derived CDS to represent a population aspect of the health quality measurements. Through the Center for Population Health IT (CPHIT) at the Bloomberg School of Public Health, we are pursuing PHI research that provides direct population-based CDS to providers, patients and payers.

Work in the Christopher Chute Lab involves the management of clinical data to enable effective evidence-based clinical practice and translational research. Recently, we developed an EHR-based genetic testing knowledge base to be integrated into the genetic testing ontology (GTO) and identified potential barriers to pharmacogenomics clinical decision support (CDS) implementation.

Researchers in the Harold Lehmann Lab study evidence-based medicine. We are currently examining the informatics infrastructure of research and the secondary use of electronic health record data for research. The team is also evaluating the value of classic evidence reports versus social media versus links to community services for community health workers.

The Johns Hopkins Laboratory of Computational Intensive Care Medicine (LCICM) has been established to gain knowledge on the mechanisms of critical illness and injury, with the aim of identifying novel methods to treat patients admitted to the intensive care unit (ICU). Members of the lab apply mathematical and statistical models, artificial intelligence, and domain expertise to unravel patterns in data from sources such as electronic health records, high-frequency physiological recordings, and medical imaging. These patterns are resolved into health signatures that can be leveraged for classification and prediction. The overarching goal is to enhance the precision, efficacy, and outcomes of care delivered to critically ill patients.