Key result
IoT-based deep learning ECG prototype classifies real-time arrhythmia and CHF but lacks clinical data.
Why the study?
The study was conducted to develop a simple, cost-efficient, and easy-to-access ECG analyzer for real-time acquisition and classification using IoT devices.
A prototype using deep learning on IoT devices was developed to acquire and classify ECG signals in real-time for basic medical insight.
Answers are grounded in this paper and cite their sources.
Hypothesis-generating for real-time IoT arrhythmia detection; prospective clinical validation required before adoption.
This paper develops a simple, cost-efficient, and easy-to-access ECG analyzer. The proposed prototype can perform the acquisition of ECG Signals lively from the subject, and display ECG Signals in real-time through IoT devices such as mobiles. The work diagnoses such as classifying the subject to having Arrhythmia, Congestive Heart Failure and Normal Sinus Rhythm. The prototype is to be equipped with a pre-trained Deep Learning model, which helps in the classification of ECG signals obtained from the subject, thus helping in providing a quick and basic insight into the would-be medical care needed by the subject. The prototype is to be equipped with a pre-trained Deep Learning model, which helps in the classification of ECG signals obtained from the subject, thus helping in providing a quick and basic insight into the would-be medical care needed by the subject.
No takes yet. Share an insight, caveat, or question.
A et al. (2023) studied Arrhythmia and Congestive Heart Failure. IoT-based ECG analyzer with Deep Learning was evaluated on Classification of ECG signals. A prototype IoT-based ECG analyzer equipped with a deep learning model was developed to classify real-time signals for arrhythmia and congestive heart failure, though no clinical data is reported.
Synapse has enriched 10 related papers. Consider them for comparative context: