Developing a Framework to Enable Large-scale Analysis of Physiologic and Clinical Data Obtained through Electronic Health Records

Ali Afshar* 1, Aidan Crank 2, Digvijay Singh 2, Nauder Faraday 1, [1] Department of Anesthesiology and Critical Care Medicine, Johns Hopkins School of Medicine, [2] Department of Computer Science, Johns Hopkins Whiting School of Engineering

Poster

Our project aims to address some of the high-impact research problems in analyzing large-scale vital signs data available through Electronic Health Records. Specifically, our team plans to develop a framework to utilize time-dependent patterns in vital signs data to: i) Identify patients who experienced significant variations in their vital signs (blood pressure, heart rate, SpO2, Respiratory rate, among others) for short (few minutes) and/or longer periods of time (several days), and, ii) Predict clinical outcomes of interest. During the past several months, our team has performed the time-consuming task of data cleaning and identifying the patients that have meaningful physiologic and matched clinical data for at least a subset of physiologic signals, and quantified certain metrics that will inform feature extraction and development of predictive analytics in a systematic way.