Many research studies have been performed to examine various aspects of radiological workflow; however, few researchers, if any, have performed an in-depth analysis that considers only the radiologist and the work he or she does when reading a case using PACS workstation software, according to presenter Daniel Forsberg, PhD, of Sectra. As a result, the research team set out to apply statistical analysis and process-mining techniques to gain insight into PACS usage patterns.
"Process mining is a science in the intersection of data science/mining and business analytics/intelligence that allows us, based upon recorded event logs, to extract underlying process models and to analyze these to find areas of possible workflow improvements," Forsberg explained. "In our case, we're interested in using process mining as a way to model the interaction patterns of radiologists and to use these models to identify workflow aspects related to PACS usage where improvements can be made, either by improved system/user configuration or by training of the users."
The analysis included 567 cases of single-view chest radiographs that were read by 14 radiologists over a one-week period.
"Our research showed that process mining is relevant to use when performing an in-depth analysis of interaction patterns from PACS usage," Forsberg told AuntMinnie.com.
What else did they discover about how radiologists use PACS? Take in this Tuesday afternoon talk to get all the details.
