Key result
An optimized machine learning approach using Random Forest and signal quality indices achieved a score of 83.08 in the real-time category on the hidden test set for reducing false ICU arrhythmia alarms.
Why the study?
A majority of current bedside monitor alarms in the intensive care unit are false, motivating approaches to reduce false alarms.
An optimized machine learning approach incorporating signal quality indices can effectively reduce false arrhythmia alarms in the ICU, potentially alleviating alarm fatigue.
ML-based false-alarm reduction in ICU monitors is feasible; leaves open whether it improves outcomes or generalizes prospectively.
This work attempts to reduce the number of false alarms generated by bedside monitors in the intensive care unit (ICU), as a majority of current alarms are false. In this study, we applied methods that can be categorized into three stages: signal processing, feature extraction, and optimized machine learning. At the stage of signal processing, we ensured that the heartbeats were properly annotated. During feature extraction, besides extracting features that are relevant to the arrhythmic alarms, we also extracted a set of signal quality indices (SQIs), which we used to distinguish noise/artifact from normal physiological signals. When applying a machine learning algorithm (Random Forest), we performed feature selection in order to reduce the complexity of the models and improve the efficiency of the algorithm. The dataset used is from Reducing False Arrhythmia Alarms in the ICU: the PhysioNet/Computing in Cardiology Challenge 2015. Using the performance metric "score" from the Challenge, we achieved a score of 83.08 in the real-time category on the hidden test set, which is the highest in all published work.
No takes yet. Share an insight, caveat, or question.
Au‐Yeung et al. (2019) studied ICU arrhythmia alarms (n=1,250). Optimized machine learning based approach (Random Forest) was evaluated on Performance score on the hidden test set (real-time category). An optimized machine learning approach using Random Forest and signal quality indices achieved a score of 83.08 in the real-time category on the hidden test set for reducing false ICU arrhythmia alarms.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: