A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology

Shashikumar, Supreeth P.; Shah, Amit; Qiao, Li; Clifford, Gari D.; Nemati, Shamim

doi:10.1109/bhi.2017.7897225

Cited by 121 publications

(102 citation statements)

References 18 publications

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…Previously, Shashikumar et al 26 reported a convolutional neural network (CNN) with a lower AUC of 0.92 and accuracy of 85.8% for detecting AF using spectrogram images derived from PPG signals instead of using the PPG waveforms directly as input to the CNN. The discriminative power of the prior CNN may have been limited by the potential loss of information when converting a PPG waveform into a spectrogram image, the small training set (98 patients) and a comparatively shallow network architecture (six layers).…”

Section: Discussionmentioning

confidence: 99%

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Poh

Chan

et al. 2018

Heart

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Poh

Chan

et al. 2018

Heart

View full text Add to dashboard Cite

show abstract

“…Regularization approaches were successfully applied to improve the performance of AF detection. 51,52 Table 1 summarizes a selection of PPG-based AF detection studies which used statistical models. Different study aspects are shown to depict the patient population and datasets used, the features and methods, the context (inpatient vs outpatient), and the performance results.…”

Section: Ppg Representationsmentioning

confidence: 99%

Photoplethysmography based atrial fibrillation detection: a review

et al. 2020

View full text Add to dashboard Cite

Atrial fibrillation (AF) is a cardiac rhythm disorder associated with increased morbidity and mortality. It is the leading risk factor for cardioembolic stroke and its early detection is crucial in both primary and secondary stroke prevention. Continuous monitoring of cardiac rhythm is today possible thanks to consumer-grade wearable devices, enabling transformative diagnostic and patient management tools. Such monitoring is possible using low-cost easy-to-implement optical sensors that today equip the majority of wearables. These sensors record blood volume variations-a technology known as photoplethysmography (PPG)-from which the heart rate and other physiological parameters can be extracted to inform about user activity, fitness, sleep, and health. Recently, new wearable devices were introduced as being capable of AF detection, evidenced by large prospective trials in some cases. Such devices would allow for early screening of AF and initiation of therapy to prevent stroke. This review is a summary of a body of work on AF detection using PPG. A thorough account of the signal processing, machine learning, and deep learning approaches used in these studies is presented, followed by a discussion of their limitations and challenges towards clinical applications.npj Digital Medicine (2020) 3:3 ; https://doi.org/10.1038/s41746-019-0207-9 PHOTOPLETHYSMOGRAPHY PPG signal PPG waveform is generated during a cardiac cycle and typically measured at a peripheral site. Therefore, it is essentially a pulse pressure waveform that originates from the heart contraction and propagates through the vascular tree. As blood flow is controlled

show abstract

“…Because of the lack of clinical data at the beginning of the project an alternative for the implementation of the prototype has to be found. According to many comparable studies (Limam & Precioso, 2017;PhysioNet, 2016;Shashikumar, Shah, Li, Clifford & Nemati, 2017;Sujadevi, Soman, & Vinayakumar, 2018;Yuan, Yan, Zhou, Bai, & Wang, 2016) PhysioNet provides an open source collection of physiologic signals including atrial fibrillation samples. Therefore, the MIT-BIH AF database as well as the MIT-BIH normal sinus rhythm database from PhysioNet are used to replace the currently missing clinical data (see thesis chapter 5.1.2).…”

Section: Data Preprocessingmentioning

confidence: 99%

“…The web application is deployed in the IBM Cloud using a Node.js runtime and Cloud Foundry (see thesis chapter 5.2.5). Even though these databases are also used in further studies (Limam & Precioso, 2017;Shashikumar, Shah, Li, Clifford & Nemati, 2017;Sujadevi, Soman, & Vinayakumar, 2018;Yuan, Yan, Zhou, Bai, & Wang, 2016), there are reluctance to believe in the quality of the data. First of all, the AF and normal sinus rhythm database differ in their frequency with AF having 250 Hz and Normal Sinus Rhythm having 125 Hz which was solved with interpolation for the healthy database.…”

Section: Web Applicationmentioning

confidence: 99%

Transformation of Medical Diagnostics with Machine Learning by Considering the Example of Atrial Fibrillation Identification

Schneider¹,

Gau²,

Grosse³

et al. 2019

Humanizing Technology for a Sustainable Society

View full text Add to dashboard Cite

The paper addresses the problem of detecting one of the most common cardiac arrhythmias atrial fibrillation with artificial intelligence. The arrhythmia increases the risk of suffering from a stroke massively. Because of this, it is essential to detect atrial fibrillation early. As the arrhythmia occurs in short sequences, it is only possible to detect the disease in long-term measurements for example with electrocardiography. All common current detection techniques are calculating the R-R intervals with variations of the root mean square of successive differences. Because this approach is inflexible and expensive, a major hospital in Germany suggests the implementation of an artificial intelligence solution for atrial fibrillation detection. The aim of the paper is to study the feasibility of atrial fibrillation detection with artificial intelligence in the clinical setting of the hospital.

show abstract

A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology

Cited by 121 publications

References 18 publications

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Photoplethysmography based atrial fibrillation detection: a review

Transformation of Medical Diagnostics with Machine Learning by Considering the Example of Atrial Fibrillation Identification

Contact Info

Product

Resources

About