scholarly journals A Deep Learning Approach for Featureless Robust Quality Assessment of Intermittent Atrial Fibrillation Recordings from Portable and Wearable Devices

Entropy ◽  
2020 ◽  
Vol 22 (7) ◽  
pp. 733
Author(s):  
Álvaro Huerta Herraiz ◽  
Arturo Martínez-Rodrigo ◽  
Vicente Bertomeu-González ◽  
Aurelio Quesada ◽  
José J. Rieta ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Quality Assessment ◽  
Heart Rhythm ◽  
Wearable Devices ◽  
Automatic Identification ◽  
High Quality ◽  
Learning Capability ◽  
Ecg Signals ◽  
Challenging Environment

Atrial fibrillation (AF) is the most common heart rhythm disturbance in clinical practice. It often starts with asymptomatic and very short episodes, which are extremely difficult to detect without long-term monitoring of the patient’s electrocardiogram (ECG). Although recent portable and wearable devices may become very useful in this context, they often record ECG signals strongly corrupted with noise and artifacts. This impairs automatized ulterior analyses that could only be conducted reliably through a previous stage of automatic identification of high-quality ECG intervals. So far, a variety of techniques for ECG quality assessment have been proposed, but poor performances have been reported on recordings from patients with AF. This work introduces a novel deep learning-based algorithm to robustly identify high-quality ECG segments within the challenging environment of single-lead recordings alternating sinus rhythm, AF episodes and other rhythms. The method is based on the high learning capability of a convolutional neural network, which has been trained with 2-D images obtained when turning ECG signals into wavelet scalograms. For its validation, almost 100,000 ECG segments from three different databases have been analyzed during 500 learning-testing iterations, thus involving more than 320,000 ECGs analyzed in total. The obtained results have revealed a discriminant ability to detect high-quality and discard low-quality ECG excerpts of about 93%, only misclassifying around 5% of clean AF segments as noisy ones. In addition, the method has also been able to deal with raw ECG recordings, without requiring signal preprocessing or feature extraction as previous stages. Consequently, it is particularly suitable for portable and wearable devices embedding, facilitating early detection of AF as well as other automatized diagnostic facilities by reliably providing high-quality ECG excerpts to further processing stages.

scholarly journals Automated P-Wave Quality Assessment for Wearable Sensors

Proceedings ◽  
2018 ◽  
Vol 4 (1) ◽  
pp. 13
Author(s):  
Diogo Tecelão ◽  
Peter Charlton
Keyword(s):  
At Risk ◽  
Quality Assessment ◽  
Wearable Sensors ◽  
P Wave ◽  
Sensor Data ◽  
Wearable Sensor ◽  
High Quality ◽  
P Waves ◽  
Ecg Signals ◽  
Wave Morphology

Hospital patients recovering from major cardiac surgery are at risk of paroxysmal atrial fibrillation (AF), an arrhythmia which can be life-threatening. Wearable sensors are routinely used for electrocardiogram (ECG) monitoring in patients at risk of AF, providing real-time AF detection. However, wearable sensors could have greater impact if used to identify the subtle changes in P-wave morphology which precede AF. This would allow prophylactic treatment to be administered, potentially preventing AF. However, ECG signals acquired by wearable sensors are susceptible to artefact, making it difficult to distinguish between physiological changes in P-wave morphology, and changes due to noise. The aim of this study was to design and assess the performance of a novel automated P-wave quality assessment tool to identify high-quality P-waves, for AF prediction. We designed a two-stage algorithm which uses P-wave template-matching to assess quality. Its performance was assessed using the AFPDB, a database of wearable sensor ECG signals acquired from both healthy subjects and patients susceptible to AF. The algorithm’s quality assessments of 97,989 P-waves were compared to manual annotations. The algorithm identified high-quality P-waves with high sensitivity (93%) and good specificity (82%), indicating that it may have utility for identifying high-quality P-waves in wearable sensor data. Measurements of P-wave morphology derived from high-quality P-waves could be used to predict AF, improving patient outcomes, and reducing healthcare costs. Further studies assessing the clinical utility of the presented tool are warranted for validation.

scholarly journals Deep learning approaches for plethysmography signal quality assessment in the presence of atrial fibrillation

2019 ◽  
Vol 40 (12) ◽  
pp. 125002 ◽  
Author(s):  
Tania Pereira ◽  
Cheng Ding ◽  
Kais Gadhoumi ◽  
Nate Tran ◽  
Rene A Colorado ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Quality Assessment ◽  
Signal Quality ◽  
Learning Approaches

scholarly journals P.058 Software algorithms for atrial fibrillation screening with wearable devices: a systematic review

2017 ◽  
Vol 44 (S2) ◽  
pp. S27-S28
Author(s):  
GA Jewett ◽  
S Crooks ◽  
JL Sapp
Keyword(s):  
Atrial Fibrillation ◽  
Systematic Review ◽  
Continuous Monitoring ◽  
Screening Method ◽  
Heart Rhythm ◽  
Wearable Devices ◽  
Current State ◽  
Software Algorithms ◽  
Similar Accuracy ◽  
English Articles

Background: Atrial fibrillation (AF) is an important risk factor for ischemic stroke but has no recognized screening method. Wearable devices have the potential to provide near continuous monitoring to detect AF. This systematic review evaluates the current state of software capable of detecting AF using wearable devices. Methods: We conducted a systematic search using PRISMA method of Medline, CENTRAL, PubMed and trial registries up to January 15, 2017. Abstracts and titles were screened, and relevant articles reviewed fully. English articles were selected if reporting on (1) software for AF detection (2) using heart rhythm signal, (3) theoretically applicable to wearable technology. Quality was evaluated with Cochrane GRADE. Results: Of 269 unique abstracts, 54 were identified for full review. 20 studies met inclusion criteria for algorithm accuracy analysis. Sensitivity and specificity ranged from 87.0 - 97.6% and 89.0 - 99.6%, respectively. 4 studies analyzed signal acquired using mobile devices with similar accuracy. Algorithms were potentially portable to wearable devices. Qualitative observations on the state and applicability of technology were made. Conclusions: Software analysing heart rhythm may be accurate for AF screening, but has not been tested on wearable devices. Such technology is promising but may be limited by hardware accuracy and high false positive rates.

scholarly journals Application of Deep Learning for Quality Assessment of Atrial Fibrillation ECG Recordings

2020 ◽  
Author(s):  
Alvaro Huerta Herraiz ◽  
Arturo Martinez-Rodrigo ◽  
Miguel Angel Arias ◽  
Philip Langley ◽  
José J Rieta ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Quality Assessment

scholarly journals Multi-task deep learning for cardiac rhythm detection in wearable devices

2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Jessica Torres-Soto ◽  
Euan A. Ashley
Keyword(s):  
Atrial Fibrillation ◽  
Heart Rate ◽  
Deep Learning ◽  
Biomedical Applications ◽  
Large Scale ◽  
High Sensitivity ◽  
Wearable Devices ◽  
Replication Cohort ◽  
Data Problem

Abstract Wearable devices enable theoretically continuous, longitudinal monitoring of physiological measurements such as step count, energy expenditure, and heart rate. Although the classification of abnormal cardiac rhythms such as atrial fibrillation from wearable devices has great potential, commercial algorithms remain proprietary and tend to focus on heart rate variability derived from green spectrum LED sensors placed on the wrist, where noise remains an unsolved problem. Here we develop DeepBeat, a multitask deep learning method to jointly assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation. The model is trained on approximately one million simulated unlabeled physiological signals and fine-tuned on a curated dataset of over 500 K labeled signals from over 100 individuals from 3 different wearable devices. We demonstrate that, in comparison with a single-task model, our architecture using unsupervised transfer learning through convolutional denoising autoencoders dramatically improves the performance of atrial fibrillation detection from a F1 score of 0.54 to 0.96. We also include in our evaluation a prospectively derived replication cohort of ambulatory participants where the algorithm performed with high sensitivity (0.98), specificity (0.99), and F1 score (0.93). We show that two-stage training can help address the unbalanced data problem common to biomedical applications, where large-scale well-annotated datasets are hard to generate due to the expense of manual annotation, data acquisition, and participant privacy.

scholarly journals Comparison of Machine Learning Algorithms for the Quality Assessment of Wearable ECG Signals Via Lenovo H3 Devices

2021 ◽  
Author(s):  
Fan Fu ◽  
Wentao Xiang ◽  
Yukun An ◽  
Bin Liu ◽  
Xianqing Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Quality Assessment ◽  
Learning Algorithms ◽  
Wearable Devices ◽  
Machine Learning Algorithms ◽  
Assessment System ◽  
Support Vector ◽  
Signal Quality ◽  
Ecg Signals

Abstract Purpose Electrocardiogram (ECG) signals collected from wearable devices are easily corrupted with surrounding noise and artefacts, where the signal-to-noise ratio (SNR) of wearable ECG signals is significantly lower than that from hospital ECG machines. To meet the requirements for monitoring heart disease via wearable devices, eliminating useless or poor-quality ECG signals (e.g., lead-falls and low SNRs) can be solved by signal quality assessment algorithms. Methods To compensate for the deficiency of the existing ECG quality assessment system, a wearable ECG signal dataset from heart disease patients collected by Lenovo H3 devices was constructed. Then, this paper compares the performance of three machine learning algorithms, i.e., the traditional support vector machine (SVM), least-squares SVM (LS-SVM) and long short-term memory (LSTM) algorithms. Different non-morphological signal quality indices (i.e., the approximate entropy (ApEn), sample entropy (SaEn), fuzzy measure entropy (FMEn), Hurst exponent (HE), kurtosis (K) and power spectral density (PSD) features) extracted from the original ECG signals are fed into the three algorithms as input. Results The true positive rate, true negative rate, sensitivity and accuracy are used to evaluate the performance of each method, and the LSTM algorithm achieves the best results on these metrics (97.14%, 86.8%, 97.46% and 95.47%, respectively). Conclusions Among the three algorithms, the LSTM-based quality assessment method is the most suitable for the signals collected by the Lenovo H3 devices. The results also show that the combination of statistical features can effectively evaluate the quality of ECG signals.

scholarly journals Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study (Preprint)

2018 ◽  
Author(s):  
Soonil Kwon ◽  
Joonki Hong ◽  
Eue-Keun Choi ◽  
Euijae Lee ◽  
David Earl Hostallero ◽  
...  
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Deep Learning ◽  
Diagnostic Accuracy ◽  
Diagnostic Performance ◽  
Wearable Devices ◽  
Screening Tools ◽  
Support Vector ◽  
Direct Current Cardioversion ◽  
Number Of Patients

BACKGROUND Wearable devices have evolved as screening tools for atrial fibrillation (AF). A photoplethysmographic (PPG) AF detection algorithm was developed and applied to a convenient smartphone-based device with good accuracy. However, patients with paroxysmal AF frequently exhibit premature atrial complexes (PACs), which result in poor unmanned AF detection, mainly because of rule-based or handcrafted machine learning techniques that are limited in terms of diagnostic accuracy and reliability. OBJECTIVE This study aimed to develop deep learning (DL) classifiers using PPG data to detect AF from the sinus rhythm (SR) in the presence of PACs after successful cardioversion. METHODS We examined 75 patients with AF who underwent successful elective direct-current cardioversion (DCC). Electrocardiogram and pulse oximetry data over a 15-min period were obtained before and after DCC and labeled as AF or SR. A 1-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) were chosen as the 2 DL architectures. The PAC indicator estimated the burden of PACs on the PPG dataset. We defined a metric called the confidence level (CL) of AF or SR diagnosis and compared the CLs of true and false diagnoses. We also compared the diagnostic performance of 1D-CNN and RNN with previously developed AF detectors (support vector machine with root-mean-square of successive difference of RR intervals and Shannon entropy, autocorrelation, and ensemble by combining 2 previous methods) using 10 5-fold cross-validation processes. RESULTS Among the 14,298 training samples containing PPG data, 7157 samples were obtained during the post-DCC period. The PAC indicator estimated 29.79% (2132/7157) of post-DCC samples had PACs. The diagnostic accuracy of AF versus SR was 99.32% (70,925/71,410) versus 95.85% (68,602/71,570) in 1D-CNN and 98.27% (70,176/71,410) versus 96.04% (68,736/71,570) in RNN methods. The area under receiver operating characteristic curves of the 2 DL classifiers was 0.998 (95% CI 0.995-1.000) for 1D-CNN and 0.996 (95% CI 0.993-0.998) for RNN, which were significantly higher than other AF detectors (P<.001). If we assumed that the dataset could emulate a sufficient number of patients in training, both DL classifiers improved their diagnostic performances even further especially for the samples with a high burden of PACs. The average CLs for true versus false classification were 98.56% versus 78.75% for 1D-CNN and 98.37% versus 82.57% for RNN (P<.001 for all cases). CONCLUSIONS New DL classifiers could detect AF using PPG monitoring signals with high diagnostic accuracy even with frequent PACs and could outperform previously developed AF detectors. Although diagnostic performance decreased as the burden of PACs increased, performance improved when samples from more patients were trained. Moreover, the reliability of the diagnosis could be indicated by the CL. Wearable devices sensing PPG signals with DL classifiers should be validated as tools to screen for AF.

Atrial fibrillation frequency tracking in ambulatory ECG signals: The significance of signal quality assessment

2018 ◽  
Vol 102 ◽  
pp. 227-233 ◽  
Author(s):  
Birutė Paliakaitė ◽  
Andrius Petrėnas ◽  
Mikael Henriksson ◽  
Jurgita Skibarkienė ◽  
Raimondas Kubilius ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Quality Assessment ◽  
Signal Quality ◽  
Frequency Tracking ◽  
Ecg Signals ◽  
Ambulatory Ecg

scholarly journals Analyzing artificial intelligence systems for the prediction of atrial fibrillation from sinus-rhythm ECGs including demographics and feature visualization

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Pietro Melzi ◽  
Ruben Tolosana ◽  
Alberto Cecconi ◽  
Ancor Sanz-Garcia ◽  
Guillermo J. Ortega ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Normal Sinus Rhythm ◽  
Area Under The Curve ◽  
Heart Rhythm ◽  
Demographic Groups ◽  
Ecg Signals ◽  
Normal Sinus ◽  
Visualization Techniques ◽  
Feature Visualization

AbstractAtrial fibrillation (AF) is an abnormal heart rhythm, asymptomatic in many cases, that causes several health problems and mortality in population. This retrospective study evaluates the ability of different AI-based models to predict future episodes of AF from electrocardiograms (ECGs) recorded during normal sinus rhythm. Patients are divided into two classes according to AF occurrence or sinus rhythm permanence along their several ECGs registry. In the constrained scenario of balancing the age distributions between classes, our best AI model predicts future episodes of AF with area under the curve (AUC) 0.79 (0.72–0.86). Multiple scenarios and age-sex-specific groups of patients are considered, achieving best performance of prediction for males older than 70 years. These results point out the importance of considering different demographic groups in the analysis of AF prediction, showing considerable performance gaps among them. In addition to the demographic analysis, we apply feature visualization techniques to identify the most important portions of the ECG signals in the task of AF prediction, improving this way the interpretability and understanding of the AI models. These results and the simplicity of recording ECGs during check-ups add feasibility to clinical applications of AI-based models.

P1880Entropy-based algorithm for atrial fibrillation detection using photoplethysomgraphic signal recorded by a smart watch

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
J Y Chiang ◽  
C M Fu ◽  
Y C Lin ◽  
B W Ku ◽  
S U Hsu ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Characteristic Curve ◽  
Green Light ◽  
Heart Rhythm ◽  
High Sensitivity ◽  
Signal Acquisition ◽  
Light Spectrum ◽  
Ecg Signals ◽  
Smart Watch

Abstract Background Atrial fibrillation (AF) is the most common arrhythmia, and its paroxysmal and short duration nature makes its detection challenging. The most important limitation of current smartwatches is that patients need to touch to the sensor of the watch to record signals when patients feel discomfort. We developed a wearable smart watch and evaluated its accuracy to differentiate AF from sinus rhythm, which can continuously detecting heart rhythm without hand touching the device. Methods and results A wearable smart watch with PPG sensor and electrocardiogram (ECG) recording function was used for signal acquisition. A total 399 patients with a mean age of 67 years old were enrolled in the study, of whom 237 (81.5%) were male, and 101 have been diagnosed with AF. Pulse wave extracted from the green light spectrum of the signal and ECG were recorded for about 10 minutes for each patient. Pulse-to-pulse intervals (PPI) were automatically identified. All ECG signals were verified by two cardiologists. The correlation between R-to-R interval on ECG and PPI were excellent, with a correlation coefficient R >0.99 (p<0.05). An entropy-based algorithm which combined Shannon entropy of successive difference of PPI and sample entropy of PPI was used to discriminate between AF and sinus rhythm. This method had high sensitivity and specificity (96% and 98%, respectively), the area under receiver operating characteristic curve reached 0.98. Conclusions We developed an entropy-based algorithm for AF detection with PPG signal recorded by a wearable smart watch. This algorithm discriminates AF from sinus rhythm accurately. This advance in technology overcomes an important clinical obstacle and can increase the AF detection rate tremendously.

Sign in / Sign up

Export Citation Format

Share Document