Key result
Deep-learning model accurately distinguishes true from false VT alarms with ~0.90 AUC.
Why the study?
Nearly 9 out of 10 ICU arrhythmia alarms are false positives, causing alarm fatigue that leads to desensitization, delayed responses, and increased cognitive burden.
Does a deep-learning based 1D-CNN model improve the accurate classification of true vs false VT alarms using raw physiological waveform inputs?
Does a deep-learning based 1D-CNN model improve the accurate classification of true vs false VT alarms using raw physiological waveform inputs?
Effect estimate: AUC-ROC 0.901
A deep-learning 1D-CNN model leveraging multi-waveform inputs can accurately differentiate true from false VT alarms, offering a potential tool to mitigate alarm fatigue in the ICU.
May reduce ICU alarm fatigue if implemented; leaves open prospective validation before clinical use.
BACKGROUND: Ventricular tachycardia (VT) is a life-threatening arrhythmia that requires both relatively rapid and accurate detection in intensive care units (ICUs). Continuous monitoring systems play a crucial role in detecting them. However, previous studies have reported that nearly 9 out of 10 arrhythmia alarms in ICUs tend to be false positives, which usually transpire to a well-documented phenomenon called "alarm fatigue" that leads to desensitization, delayed responses, and increased cognitive burden on healthcare providers. METHODS: We developed a deep learning based, one-dimensional convolutional neural network (1D-CNN) to classify VT alarms using multiple raw waveform inputs, including two electrocardiogram (ECG) leads, photoplethysmogram (PPG) and arterial blood pressure (ABP) signals. The model was trained using the publicly available VTaC Arrhythmia Benchmark Dataset. We used the 10-second waveform segments that preceded each VT alarm, pre-processed and then used them to train the machine learning model to correctly classify the VT alarm. RESULTS: On the test set, the model achieved an area under the receiver operating characteristic curve of 0.901, overall accuracy of 83.22%, F1-score of 73.3%, sensitivity of 77.53%, specificity of 85.63%, and positive predictive value of 69.57%. The model successfully detected over three-quarters of them while significantly reducing false positive rates for the detection of VT. CONCLUSIONS: This study demonstrates that a deep learning based 1D-CNN model using short segments of raw waveform data can achieve robust performance in distinguishing true and false VT alarms.
No takes yet. Share an insight, caveat, or question.
Khanolkar et al. (2026) studied Ventricular tachycardia (VT) alarms in the ICU (n=2,376). Deep-learning based one-dimensional convolutional neural network (1D-CNN) was evaluated on Classification performance (Area Under the Receiver Operating Characteristic Curve) (AUC-ROC 0.901). A deep learning based 1D-CNN model using short segments of raw waveform data successfully distinguished true and false VT alarms, achieving an AUC-ROC of 0.901.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: