The field of biomedical informatics encompasses the acquisition, management, and analysis of biomedical data, information, and knowledge to improve human health and well-being. Research within this diverse field can include clinical informatics, focusing on the individual patient, and public health informatics, focusing on the population as the patient. In addition, cross-cutting areas such as Natural Language Processing (NLP) can be utilized across these different disciplines to promote problem solving and decision making. This session will discuss various research efforts in biomedical informatics to promote decision making within clinical and public health environments.

Public health departments often utilize counts of reported disease cases for surveillance and monitoring . This is especially true for zoonotic diseases, infectious diseases transmittable between animals and humans. As an alternative to this traditional public health data, “translational public health” is a concept that is modeled after translational medicine and the need to translate data from the laboratory bench into knowledge that can be used at the bedside for personalized medicine and clinical decision-making. However, in translational public health, the “patient” is not an individual, but rather the population as a whole. This talk will focus on the potential of translational public health to support public health surveillance and decision making by developing an informatics system that brings sequence data of zoonotic viruses (generated from laboratories) to the forefront of public health decision-making at health departments, agriculture departments, and wildlife agencies. The system will enable these agencies to better understand the spread of disease and risk of transmission between animals and humans.

All medical research starts with the selection of a cohort of patients with the disease or finding of interest. Currently this is done through the selection of appropriate ICD9 and CPT codes, which are discrete data fields in the electronic medical record. However, sole reliance on diagnosis based and procedure related codes for cohort identification leads to missing cases of interest due to the inherent inadequacies and limited scope of these coding tools. Not only do codes not exist for every concept which might be investigated by a clinical researcher, but since these codes are applied within the clinical context for billing purposes, they may be incompletely applied. We present the framework of a natural language processing module (NLP) to extract relevant patient cohorts using the narrative text of pediatric emergency room encounters, and to test the accuracy and expressiveness of the approach to extract cohorts as compared to traditional ICD code-based queries. As a proof of concept, we chose to study concepts that could be coded, as well as those that do not have an existing code. Defining cohorts beyond the limitations of coding could have a profound impact on the development of prevention strategies and health policy initiatives. We will examine the extent to which reliance on ICD 9 and CPT codes for cohort selection under or over-estimates cohort size in clinical research.

The high variation in workflows and processes in biomedical research, most notably clinical trials, has been identified as a significant contributor to the inefficiency of the clinical trials process, and thus to the “pipeline problem” in the delivery of new therapies and the slowness of “knowledge turns” in biomedicine.  In order to speed the delivery of new therapies to patients, government agencies, clinical research sponsors and biomedical data standards bodies have made a concerted effort to formulate standardized, structured data representations of clinical trials.  This presentation describes these efforts and the fruits they have borne, and explores how the latter could form the basis of standardized, structured data representations of treatment guidelines and thus to an automated process for supplying content to clinical decision support systems.

Mayo Clinic is in the process of establishing an "Advanced Development Projects Lab", to serve as an interdisciplinary prototyping, usability testing, and evaluation environment for optimizing clinician performance, satisfaction, and patient safety with advanced electronic tools and workflows. This Mayo Clinic lab will be managed, staffed, and funded through the Mayo Clinic Center for the Science of Healthcare Delivery, with close collaboration with the Center for Innovation, the Clinical Practice Committee, and the Office of Information and Knowledge Management, and with Arizona State University’s Department of Biomedical Informatics. Mayo Clinic core EMR vendors will supply software instances as the base upon which to develop prototypes initially, with the intent to expand the system platforms subsequently. Closely coupled with this is a joint ASU-Mayo interoperable app "sandbox" initiative to encourage innovation and support for agile creation and testing of apps that can work with underlying EHR systems and middleware. Examples of the foci of this laboratory will be discussed. Authors: Keith A. Frey, MD, MBA, and Robert A. Greenes, MD, PhD. Dr. Frey is Professor of Family Medicine, Mayo Cliic, Scottsdale, AZ. Dr Greenes is Ira A. Fulton Chair and Professor, Department of Biomedical Informatics, Arizona State University, Scottsdale, AZ.