Real‐Time Arrhythmia Detection Using Hybrid Convolutional Neural Networks

Abstract

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.

Neural Network-Enabled Identification of Weak Inspiratory Efforts during Pressure Support Ventilation Using Ventilator Waveforms

“…The benefits of neural network-based approaches rely on the inherent ability of a NN to recognize patterns and extract features from raw data without extensive pre-processing and hardcoded feature engineering, which makes them particularly appealing for implementation in monitoring devices. Convolutional deep neural networks have been used to extract features from ECG to identify arrhythmias [ 33 ], predict atrial fibrillation [ 34 ] and hyperkalemia [ 35 ] with promising results. Algorithms to detect asynchronies or weak inspiratory efforts, such as the one developed in this study, could be introduced in ventilators’ software or in monitoring devices connected to the ventilators.…”

Experiences and mediating factors in nurses' responses to electronic device alarms: A phenomenological study

“…This need to reduce clinically irrelevant alarms should be addressed in collaboration with key stakeholders (e.g., patients and engineers) and health services, taking advantage of the development of technology with better algorithms that reduce false alarms (Bollepalli et al, 2021; Hyland et al, 2020; Ruppel, De Vaux, et al, 2018; Wilken et al, 2019). In addition, the devices must be useful, adjusting the sensitivity and specificity of the alarms, and their operation must be easy to learn (Fernandes et al, 2020; Muroi et al, 2020).…”

Machine learning techniques for arrhythmic risk stratification: a review of the literature

“…A deep learning architecture based on one-dimensional CNN layers and an LSTM network was found to be timely and accurate for the detection of VF in automated external defibrillators [ 60 ]. Furthermore, ML-based intensive care unit alarm systems have been found to achieve higher positive predictive values for the identification of asystole, extreme bradycardia, VT and VF compared to the bedside monitors used in the PhysioNet 2015 competition [ 9 , 10 , 61 ].…”

“…Machine learning (ML) can integrate and interpret data from different domains in settings where conventional statistical methods may not be able to perform [ 8 ]. Recently, the role of ML techniques has been studied in different aspects of medicine, including electronic health records, diagnosis, risk stratification, timely identification of abnormal heart rhythms in the intensive care unit [ 9 , 10 ], on prognosis and guidance of personalized management [ 11 , 12 ]. However, application of ML study findings has been limited due to the lack of a regulatory framework for its implementation and the clinicians’ unfamiliarity in using as well as trusting ML techniques [ 13 ].…”