Simplifying EHR Overview of Critically Ill Patients Through Vital Signs Monitoring

This paper presents a novel data-driven approach to graphical presentation of text-based electronic health records (EHR) while maintaining all textual information. We have developed the Patient Condition Timeline (PCT) tool, which creates a timeline representation of a patients’ physiological condition during admission. PCT is based on electronical monitoring of vital signs and then combining these into Early Warning Scores (EWS). Hereafter, techniques from Natural Language Processing (NLP) are applied on existing EHR to extract all entries. Finally, the two methods are combined into an interactive timeline featuring the ability to see drastic changes in the patients’ health, and thereby enabling staff to see where in the EHR critical events have taken place.