English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This study proposes a deep learning model that effectively suppresses thefalse alarms in the intensive care units (ICUs) without ignoring the truealarms using single- and multimodal biosignals. Most of the current work in theliterature are either rule-based methods, requiring prior knowledge ofarrhythmia analysis to build rules, or classical machine learning approaches,depending on hand-engineered features. In this work, we apply convolutionalneural networks to automatically extract time-invariant features, an attentionmechanism to put more emphasis on the important regions of the input segmentedsignal(s) that are more likely to contribute to an alarm, and long short-termmemory units to capture the temporal information presented in the signalsegments. We trained our method efficiently using a two-step training algorithm(i.e., pre-training and fine-tuning the proposed network) on the datasetprovided by the PhysioNet computing in cardiology challenge 2015. Theevaluation results demonstrate that the proposed method obtains better resultscompared to other existing algorithms for the false alarm reduction task inICUs. The proposed method achieves a sensitivity of 93.88% and a specificity of92.05% for the alarm classification, considering three different signals. Inaddition, our experiments for 5 separate alarm types leads significant results,where we just consider a single-lead ECG (e.g., a sensitivity of 90.71%, aspecificity of 88.30%, an AUC of 89.51 for alarm type of VentricularTachycardia arrhythmia)

Single-modal and Multi-modal False Arrhythmia Alarm Reduction using Attention-based Convolutional and Recurrent Neural Networks