Authors:
Jonas Chromik
1
;
Bjarne Pfitzner
1
;
Nina Ihde
1
;
Marius Michaelis
1
;
Denise Schmidt
1
;
Sophie Anne Ines Klopfenstein
2
;
Akira-Sebastian Poncette
2
;
Felix Balzer
2
and
Bert Arnrich
1
Affiliations:
1
Hasso Plattner Institute, University of Potsdam, Germany
;
2
Charité – Universitätsmedizin Berlin, Berlin, Germany
Keyword(s):
Patient Monitor Alarm, Medical Alarm, Intensive Care Unit, Vital Parameter, Time Series Forecasting, Alarm Forecasting, Alarm Fatigue.
Abstract:
Too many alarms are a persistent problem in today’s intensive care medicine leading to alarm desensitisation and alarm fatigue. This puts patients and staff at risk. We propose a forecasting strategy for threshold alarms in patient monitors in order to replace alarms that are actionable right now with scheduled tasks in an attempt to remove the urgency from the situation. Therefore, we employ both statistical and machine learning models for time series forecasting and apply these models to vital parameter data such as blood pressure, heart rate, and oxygen saturation. The results are promising, although impaired by low and non-constant sampling frequencies of the time series data in use. The combination of a GRU model with medium-resampled data shows the best performance for most types of alarms. However, higher time resolution and constant sampling frequencies are needed in order to meaningfully evaluate our approach.