A multimodal approach to reduce false arrhythmia alarms in the intensive care unit

Fallet, Sibylle; Yazdani, Sasan; Vesin, Jean‐Marc

doi:10.1109/cic.2015.7408640

Cited by 32 publications

(43 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In diagnosing Ventricular Flutter or Fibrillation and Ventricular Tachycardia, the features were generated with spectral purity index (SPI) [44,51]. The reason why, these arrhythmias require a different method of detection of physiological QRS complexes as it is impossible due to the nature of ventricular originated arrhythmias (see Section 2).…”

Section: Feature Vectormentioning

confidence: 99%

Weighted Random Forests to Improve Arrhythmia Classification

et al. 2020

View full text Add to dashboard Cite

Construction of an ensemble model is a process of combining many diverse base predictive learners. It arises questions of how to weight each model and how to tune the parameters of the weighting process. The most straightforward approach is simply to average the base models. However, numerous studies have shown that a weighted ensemble can provide superior prediction results to a simple average of models. The main goals of this article are to propose a new weighting algorithm applicable for each tree in the Random Forest model and the comprehensive examination of the optimal parameter tuning. Importantly, the approach is motivated by its flexibility, good performance, stability, and resistance to overfitting. The proposed scheme is examined and evaluated on the Physionet/Computing in Cardiology Challenge 2015 data set. It consists of signals (electrocardiograms and pulsatory waveforms) from intensive care patients which triggered an alarm for five cardiac arrhythmia types (Asystole, Bradycardia, Tachycardia, Ventricular Tachycardia, and Ventricular Fultter/Fibrillation). The classification problem regards whether the alarm should or should not have been generated. It was proved that the proposed weighting approach improved classification accuracy for the three most challenging out of the five investigated arrhythmias comparing to the standard Random Forest model.

show abstract

Section: Feature Vectormentioning

confidence: 99%

Weighted Random Forests to Improve Arrhythmia Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Previously, good results for VFB and VTA classification have been reported with spectral purity index (Fallet et al 2015). The SPI was initially presented for electroencephalogram (EEG) analysis as a dimensionless parameter between 0 and 1 reflecting the signal bandwidth (Goncharova and Barlow 1990).…”

Section: Feature Computationmentioning

confidence: 99%

“…The spectral moments were implemented in the time domain according to Sörnmo and Laguna (2005). As done in the approach of Fallet et al (2015), before computing SPI, ECG signals were first downsampled to 35 Hz and smoothed using a 5-sample moving average filter. The window length for estimation of the spectral moments in the time domain was selected to be 4 s for VFB, since the length of the fibrillatory waveform should be at least 4 s. For VTA, the window length was 2 s. The SPI was then averaged in a window of 1 s, and the maximum and minimum of the averaged SPI in the window before the alarm were calculated as features.…”

Section: Feature Computationmentioning

confidence: 99%

See 1 more Smart Citation

False arrhythmia alarms reduction in the intensive care unit: a multimodal approach

2016

Self Cite

View full text Add to dashboard Cite

The purpose of this study was to develop algorithms to lower the incidence of false arrhythmia alarms in the ICU using information from independent sources, namely electrocardiogram (ECG), arterial blood pressure (ABP) and photoplethysmogram (PPG). Our approach relies on robust adaptive signal processing techniques in order to extract accurate heart rate (HR) values from the different waveforms. Based on the quality of available signals, heart rate was either estimated from pulsatile waveforms using an adaptive frequency tracking algorithm or computed from ECGs using an adaptive mathematical morphology approach. Furthermore, we developed a supplementary measure based on the spectral purity of the ECGs to determine whether a ventricular tachycardia or flutter/fibrillation arrhythmia has taken place. Finally, alarm veracity was determined based on a set of decision rules on HR and spectral purity values. The proposed method was evaluated on the PhysioNet/CinC Challenge 2015 database, which is composed of 1250 life-threatening alarm recordings, each categorized into either bradycardia, tachycardia, asystole, ventricular tachycardia or ventricular flutter/fibrillation arrhythmia. This resulted in overall true positive rates of 95%/99% and overall true negative rates of 76%/80% on the real-time and retrospective subsets of the test dataset, respectively.

show abstract

“…Ansari et al [4] adopted several peak detection algorithms to create a robust peak detection algorithm and exploited the information from all three ECG, ABP and PPG signals. Fallet et al [5] used an adaptive frequency tracking algorithm to estimate HR from PPG and ABP signals and an adaptive mathematical morphology approach to estimate HR from the ECG. Also, they exploited the Spectral Purity Index (SPI) to quantify the morphological changes of QRS complexes related to the Ventricular Arrhythmia.…”

Section: Introductionmentioning

confidence: 99%

Single-modal and multi-modal false arrhythmia alarm reduction using attention-based convolutional and recurrent neural networks

2020

View full text Add to dashboard Cite

This study proposes a deep learning model that effectively suppresses the false alarms in the intensive care units (ICUs) without ignoring the true alarms using single-and multimodal biosignals. Most of the current work in the literature are either rule-based methods, requiring prior knowledge of arrhythmia analysis to build rules, or classical machine learning approaches, depending on hand-engineered features. In this work, we apply convolutional neural networks to automatically extract time-invariant features, an attention mechanism to put more emphasis on the important regions of the input segmented signal(s) that are more likely to contribute to an alarm, and long short-term memory units to capture the temporal information presented in the signal segments. We trained our method efficiently using a two-step training algorithm (i.e., pre-training and fine-tuning the proposed network) on the dataset provided by the PhysioNet computing in cardiology challenge 2015. The evaluation results demonstrate that the proposed method obtains better results compared to other existing algorithms for the false alarm reduction task in ICUs. The proposed method achieves a sensitivity of 93.88% and a specificity of 92.05% for the alarm classification, considering three different signals. In addition, 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%, a specificity of 88.30%, an AUC of 89.51 for alarm type of Ventricular Tachycardia arrhythmia) 1 .

show abstract

A multimodal approach to reduce false arrhythmia alarms in the intensive care unit

Cited by 32 publications

References 10 publications

Weighted Random Forests to Improve Arrhythmia Classification

Weighted Random Forests to Improve Arrhythmia Classification

False arrhythmia alarms reduction in the intensive care unit: a multimodal approach

Single-modal and multi-modal false arrhythmia alarm reduction using attention-based convolutional and recurrent neural networks

Contact Info

Product

Resources

About