Applying Bayesian Changepoint Model and Hierarchical Divisive Model for Detecting Anomalies in Clinical Decision Support Alert Firing Soumi Ray Brigham and Women’s Hospital and Harvard Medical School 75 Francis St Boston, MA 02115 443-765-5333 sr278@bwh.harvard.edu Adam Wright Brigham and Women’s Hospital and Harvard Medical School 75 Francis St Boston, MA 02115 617-732-7063 awright@bwh.harvard.edu ABSTRACT Clinical Decision Support (CDS) Systems are widely used to support efficient evidence-based care and have become an important aspect of healthcare. CDS systems are complex, and sometimes malfunction or exhibit anomalous behavior [4]. We have previously shown how anomaly detection models can be used to successfully identify malfunctions in CDS systems [3]. We have extended this work and applied two new anomaly detection models on CDS alert firing data from a large health system. 1. METHODS Hierarchical Divisive Changepoint Mode
