Faculty members of the CDU Center for Biomedical Informatics are recognized nationally and internationally for their research in a number of areas in this broad discipline.
Machine learning involves the use of statistical theory and mathematics to create models that capture existing patterns in data and to utilize these patterns to solve new problems. Since it offers the ability to provide diagnostic and prognostic predictions that can help health workers as they make clinical decisions, machine learning plays an increasingly important role in Biomedical Informatics. Work at CDU in this area includes machine learning methods applied to primary and secondary datasets for assessing predictors and outcomes of chronic diseases/conditions that disproportionately affect patients in the university's service area (e.g., chronic kidney disease, diabetic retinopathy).
Sociotechnical factors in biomedical informatics involve a focus on both the technical processes and the social systems operating within the health care environment to improve organizational performance. Because health care involves the tight interrelation of several elements in a system - such as people, tools, organizational routines, documents, etc. - the introduction of a new element such as health information technology (HIT) can have reverberating consequences throughout the system. To better understand the impact of HIT implementation in such systems, evaluation needs to incorporate multimethod, longitudinal and systematic sociotechnical approaches that are able to capture the contingent and negotiated nature of the ongoing workflow despite the existence of predetermined task descriptions and formal procedures. Attention to sociotechnical factors is particularly important for the successful diffusion and acceptance of HIT in the Charles Drew University service area, given the "digital divide" that prevails among the multicultural and vulnerable patient populations served and the consequent challenges in the health care delivery context for patients, providers and organizations. Multiple methods are utilized in sociotechnical analyses, including quantitative techniques such as surveys, experiments and cost-benefit analyses as well as qualitative techniques such as participant observation, in-depth and focus group interviews and content analyses.
Health Information Technology Standards
The Center provides leadership in standards development organizations such as Health Level Seven International as well as foundational research that helps support the development of standards for data representation and clinical decision support.
Computer-Based Clinical Decision Support
Members of the Center have engaged in extensive research activities in the domain of Clinical Decision Support (CDS) and provide leadership at the national and international level in this field. For example, the CDU Electronic Disease Registry to Improve Chronic Care (CEDRIC) project brought together community clinicians and members of the Center to create a registry to support clinical practice and provide CDS in the care of patients who suffer from diabetes mellitus. In addition, members of the Center lead efforts to develop health information technology standards to facilitate implementation of CDS and support knowledge sharing that can help reduce health disparities.