Key result
Hybrid-CNN algorithm detects ICU arrhythmias with ~88% accuracy, suppressing ~77% of false alarms.
Why the study?
Traditional ICU monitors generate a high rate of false alarms causing alarm fatigue, creating a need for improved algorithms to detect life-threatening arrhythmias.
Does a hybrid convolutional neural network algorithm combining handcrafted and learned features from multimodal physiological signals improve arrhythmia detection accuracy and reduce false alarms compared to standard CNNs, feature-only models, and bedside monitors in ICU patients?
Observational (n=410)
No
Does a hybrid convolutional neural network algorithm combining handcrafted and learned features from multimodal physiological signals improve arrhythmia detection accuracy and reduce false alarms compared to standard CNNs, feature-only models, and bedside monitors in ICU patients?
Answers are grounded in this paper and cite their sources.
A multimodal hybrid-CNN algorithm accurately detects life-threatening ICU arrhythmias without prior knowledge of the monitor alarm type and suppresses 77.05% of false alarms, potentially reducing caregiver alarm fatigue.
Background Accurate detection of arrhythmic events in the intensive care units (ICU) is of paramount significance in providing timely care. However, traditional ICU monitors generate a high rate of false alarms causing alarm fatigue. In this work, we develop an algorithm to improve life threatening arrhythmia detection in the ICUs using a deep learning approach. Methods and Results This study involves a total of 953 independent life-threatening arrhythmia alarms generated from the ICU bedside monitors of 410 patients. Specifically, we used the ECG (4 channels), arterial blood pressure, and photoplethysmograph signals to accurately detect the onset and offset of various arrhythmias, without prior knowledge of the alarm type. We used a hybrid convolutional neural network based classifier that fuses traditional handcrafted features with features automatically learned using convolutional neural networks. Further, the proposed architecture remains flexible to be adapted to various arrhythmic conditions as well as multiple physiological signals. Our hybrid- convolutional neural network approach achieved superior performance compared with methods which only used convolutional neural network. We evaluated our algorithm using 5-fold cross-validation for 5 times and obtained an accuracy of 87.5%±0.5%, and a score of 81%±0.9%. Independent evaluation of our algorithm on the publicly available PhysioNet 2015 Challenge database resulted in overall classification accuracy and score of 93.9% and 84.3%, respectively, indicating its efficacy and generalizability. Conclusions Our method accurately detects multiple arrhythmic conditions. Suitable translation of our algorithm may significantly improve the quality of care in ICUs by reducing the burden of false alarms.
No takes yet. Share an insight, caveat, or question.
A 2021 study conducted an observational in Life-threatening arrhythmias in intensive care unit patients (n=410). Hybrid convolutional neural network (CNN) arrhythmia detection algorithm vs. Only-CNN classifier, only feature-based classifier, and existing bedside ICU monitors was evaluated on Overall arrhythmia classification accuracy (5-times 5-fold cross-validation) (p=<0.001). The hybrid-CNN algorithm detected ICU arrhythmias with 87.5% accuracy in cross-validation and 93.9% in external validation, suppressing 77.05% of false alarms.
Synapse has enriched 10 related papers. Consider them for comparative context: