November 28, 2019IEEE Transactions on Biomedical Circuits and Systems

A 13.34 μW Event-Driven Patient-Specific ANN Cardiac Arrhythmia Classifier for Wearable ECG Sensors

View Full Paper

Ask AI

Bookmark

Why the study?

Implementation of ultralow power artificial neural network cardiac arrhythmia classifiers is challenged by intensive computations and performance limitations from imbalanced databases.

Population

MIT-BIH database

Authors

YZYang ZhaoShanghai Jiao Tong University ZSZhongxia ShangYork University YLYong LianGuangzhou University of Chinese Medicine

Discussion

Member takes

Implication

May enable ultralow-power wearable arrhythmia classifiers; leaves open prospective clinical validation.

Structured PICO

Population

MIT-BIH database (ECG records for arrhythmia classification)

Intervention

Continuous-in-time discrete-in-amplitude (CTDA) artificial neural network cardiac arrhythmia classifier (ANN-CAC) with conditional grouping scheme and biased training

Outcome

Classification accuracy, sensitivity, and positive predictivitysurrogate

A novel ultralow power ANN-based cardiac arrhythmia classifier demonstrates high accuracy and efficiency, showing promise for wearable ECG sensors.

Cite This Study

Zhao et al. (2019) studied this question.

synapsesocial.com/papers/6a73b14ddce227fde44ca1a0 https://doi.org/10.1109/tbcas.2019.2954479

View Full Paper

Ask AI

Bookmark

A 13.34 μW Event-Driven Patient-Specific ANN Cardiac Arrhythmia Classifier for Wearable ECG Sensors

Discussion

Member takes

Implication

Structured PICO

Cite This Study

A 13.34 μW Event-Driven Patient-Specific ANN Cardiac Arrhythmia Classifier for Wearable ECG Sensors

Discussion

Member takes

Implication

Structured PICO

Cite This Study

Also Consider

Also Consider