Zachary D.W. Dezman, MD, MS, in collaboration with Cheng Gao, PhD, Hsiao-Chi Li, PhD, Shiming Yang, PhD, Peter Hu, PhD, and Colin F. Mackenzie, MBChB, in the Shock Trauma Anesthesiology Research Center, Department of Anesthesiology, and with Yao Li, MS, and Chein-I Chang, PhD, from the Remote Sensing Signal and Image Processing Laboratory, Department of Computer Science and Electrical Engineering at UMBCpublished the article titled “Anomaly Detection Outperforms Logistic Regression in Predicting Trauma Patient Outcomes” in the March/April issue of Prehospital Emergency Care (21[2]:174?179). Their study was based on the records of 5464 patients seen at Shock Trauma in 2009 and 2010. Anomaly detection and logistic regression were equally capable of predicting the need for massive transfusion, but anomaly decision significantly outperformed logistic regression in identifying patients who would receive uncrossmatched blood, who would receive a transfusion within 6 hours after admission, who would need intensive care, and who were most likely to die during hospitalization.