TY - GEN
T1 - Assessment of Artificial Intelligence Techniques for Automated Remote Classification of Cardiac Arrhythmia using Instantaneous Heart Rates
AU - Panindre, Prabodh
AU - Dama, Mahotsavy
AU - Gandhi, Vijay
AU - Kumar, Sunil
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/6/29
Y1 - 2021/6/29
N2 - Cardiac arrhythmia can cause serious health risks including sudden cardiac events, and a significant number of vulnerable individuals are undiagnosed or undertreated. Noting the widespread use of wireless health trackers and the efficacy of Artificial intelligence (AI) methods in processing a large amount of time-series sequential data, in this study we aim to find the best AI technique for diagnosing an arrhythmia. Various AI models have been trained and tested by utilizing publicly available medical data. From the confusion matrix, the accuracy, recall, F1-score, Area Under the Curve (AUC), and precision of each AI model have been evaluated and compared. This analysis and Friedman Tests indicate that Bi-LSTM-the deep learning method outperformed the classical machine learning methods. The process of remotely classifying arrhythmia provided in this study can be generalized for automatic diagnosis of many health risks.
AB - Cardiac arrhythmia can cause serious health risks including sudden cardiac events, and a significant number of vulnerable individuals are undiagnosed or undertreated. Noting the widespread use of wireless health trackers and the efficacy of Artificial intelligence (AI) methods in processing a large amount of time-series sequential data, in this study we aim to find the best AI technique for diagnosing an arrhythmia. Various AI models have been trained and tested by utilizing publicly available medical data. From the confusion matrix, the accuracy, recall, F1-score, Area Under the Curve (AUC), and precision of each AI model have been evaluated and compared. This analysis and Friedman Tests indicate that Bi-LSTM-the deep learning method outperformed the classical machine learning methods. The process of remotely classifying arrhythmia provided in this study can be generalized for automatic diagnosis of many health risks.
KW - Arrhythmia
KW - Deep Learning
KW - Machine Learning
KW - Tele-Health
KW - Wireless Health Trackers
UR - http://www.scopus.com/inward/record.url?scp=85112681031&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112681031&partnerID=8YFLogxK
U2 - 10.1109/ICAICST53116.2021.9497825
DO - 10.1109/ICAICST53116.2021.9497825
M3 - Conference contribution
AN - SCOPUS:85112681031
T3 - ICAICST 2021 - 2021 International Conference on Artificial Intelligence and Computer Science Technology
SP - 25
EP - 30
BT - ICAICST 2021 - 2021 International Conference on Artificial Intelligence and Computer Science Technology
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 International Conference on Artificial Intelligence and Computer Science Technology, ICAICST 2021
Y2 - 29 June 2021
ER -