Fig. 2.

A schematic representation of integrating data from patient monitors and electronic health record (EHR) system toward a precise patient monitoring solution. The integration takes three key steps. The first step involves representing raw data as time-stamped tokens, the second step then uses training data to identify predictive patterns of co-occurring tokens, and the last step monitors and detects the emerging patterns from the data streams in real-time and further processes the sequence of these pattern triggers to characterize the patient status