Critical Transitions in Intensive Care Units: A Sepsis Case Study
share
Progression of complex human diseases is associated with transitions across dynamical regimes. These transitions are often phase transitions that generate early-warning signs and provide insights into the underlying disease-driving mechanism(s). In this paper, we propose a computational method to discover indicators of such transitions in a multivariate time series dataset of critical care patients (MIMIC-III database). Our main motivation is to model the dataset mathematically and to quantify the deterioration of the model's forecast performance relative to its past performance. Our data-sampling strategy around putative time-points of critical transitions offer early differentiation capability between septic shock and non-sepsis patients.
READ FULL TEXT