What's New

Time Series Analysis of Nursing Notes for Mortality Prediction via a State Transition Topic Model

AUTHORS: Yohan Jo, Carnegie Mellon University | Natasha Loghmanpour, Carnegie Mellon University | Carolyn Penstein Rosé, Carnegie Mellon University


Accurate mortality prediction is an important task in intensive care units in order to channel prompt care to patients in the most critical condition and to reduce nurses’ alarm fatigue. Nursing notes carry valuable information in this regard, but nothing has been reported about the effectiveness of temporal analysis of nursing notes in mortality prediction tasks.

We propose a time series model that uncovers the temporal dynamics of patients’ underlying states from nursing notes. The effectiveness of this information in mortality prediction is examined for mortality prediction for ve different time spans ranging from one day to one year. Our experiments show that the model captures both patient states and their temporal dynamics that have a strong correlation with patient mortality. The results also show that incorporating temporal information improves performance in long-term mortality prediction, but has no significant effect in short-term prediction.

Download Publication