- This event has passed.
Informatics Research Seminar: Predicting Inpatient Deterioration-From Quality Improvement to Research
April 10 @ 4:00 pm - 5:00 pm EDT
Speaker: Ben Goldstein, PhD
Presented from Duke
Broadcast Link: Seminar (Audio only)
Abstract: (A story in 5 Acts)
As Electronic Health Record (EHR) systems mature, the opportunity exists to implement real-time clinical decision support tools. One area of focus has been the prediction of who will deteriorate while in the hospital. In 2015, the National Early Warning Score (NEWS), with an associated best practice alert, was implemented into the Duke University Health Systems EHR system. After the score had been used for over year, we were asked to evaluate its effectiveness (Act 1). With effectiveness found lacking, we were asked to develop a better score (Act 2). After developing a better score, we implemented our model and evaluated its performance prospectively (Act 3). This raised additional questions about how much better we could do if our prediction model was not constrained by the limitations of the implementation environment of the EHR system. In response, we have developed a time-to-event deep learning recurrent neural network (RNN) model (Act 4). As we built out and tried to refine our models, new questions were raised regarding how changing clinical measurements relate to risk of deterioration (Act 5). Ultimately, what started as a question of quality improvement, turned into a research investigation. This story illustrates how partnerships with the health system can lead (hopefully) to better patient care and spur academic research. This work is joint with a variety of faculty, students and staff who are statisticians, clinicians and informaticists.
Ben Goldstein, MPH, PhD, is an Associate Professor of Biostatistics & Bioinformatics at Duke University, while also holding joint appointments with the Duke Clinical Research Institute and the Children’s Health & Discovery Initiative. His research interests are in the meaningful use of Electronic Health Records data. His work sits at the intersection of Biostatistics, Biomedical Informatics, Epidemiology and Machine Learning. Dr. Goldstein collaborates actively with both clinicians and fellow methodologists locally at Duke and nationally. He received his MPH and PhD in Biostatistics from the University of California at Berkeley.