DBB faculty publish paper on analyzing time-to-event data
Guy Brock, PhD, and John Myers, PhD, Department of Bioinformatics and Biostatistics collaborated with Christopher Barnes, PhD, alumnus, and Julio Ramirez, MD, Division of Infectious Diseases, on the article, "How to handle mortality when investigating length of hospital stay and time to clinical stability," published online Oct. 16, 2011 in BMC Medical Research Methodology. This study examined the inherent challenge of how to handle mortality when analyzing time-to-event data (e.g., length of stay in the hospital, time to reach clinical stability) for hospitalized patients. For example, should an analyst censor the data, ignore the data, or input the "worst outcome"? Drs. Brock and Myers explored this issue using data on patients with community-acquired pneumonia and demonstrated the proper way to treat mortality, as a competing risk, when analyzing these and other time-to-event outcomes.
Download the article at http://www.biomedcentral.com/content/pdf/1471-2288-11-144.pdf.