Sinabro: A Smartphone-Integrated Opportunistic Electrocardiogram Monitoring System

Abstract

In our preliminary study, we proposed a smartphone-integrated, unobtrusive electrocardiogram (ECG) monitoring system, Sinabro, which monitors a user’s ECG opportunistically during daily smartphone use without explicit user intervention. The proposed system also monitors ECG-derived features, such as heart rate (HR) and heart rate variability (HRV), to support the pervasive healthcare apps for smartphones based on the user’s high-level contexts, such as stress and affective state levels. In this study, we have extended the Sinabro system by: (1) upgrading the sensor device; (2) improving the feature extraction process; and (3) evaluating extensions of the system. We evaluated these extensions with a good set of algorithm parameters that were suggested based on empirical analyses. The results showed that the system could capture ECG reliably and extract highly accurate ECG-derived features with a reasonable rate of data drop during the user’s daily smartphone use.

Ultra-short term HRV features as surrogates of short term HRV: a case study on mental stress detection in real life

“…To the best of the authors’ knowledge, none of the studies investigating ultra-short HRV features has proposed a robust methodology to assess if ultra-short HRV features are valid surrogates of short ones to detect stress [22]. There have been some attempts to investigate the reliability and accuracy of ultra-short term HRV analysis [15, 23, 24, 26–42], but only one study investigated the validity of ultra-short HRV features in a more rigorous way [39]. However, the authors in [39] only considered 2 time domain HRV features under one standard condition (i.e., rest phase).…”

Mobile Personal Health Monitoring for Automated Classification of Electrocardiogram Signals in Elderly

“…Our system has a number of advantages over previously developed mobile PHM systems for monitoring ECG signals, which do not report software design concept to address the user acceptability and acceptance issue in elderly [ 22 – 26 , 28 , 29 ], do not include automated classification [ 22 – 25 ], operate with commercial sensors [ 29 ], or do not provide internal methods for classifying arrhythmias [ 26 , 28 ]. The prototype detected normal and abnormal ECG patterns in a group of older adults residing in a LMIC with a high degree of accuracy (97%), sensitivity (100%), and specificity (96.6%).…”

“…However, although a number of PHM systems that collect ECG data have been developed, some of these do not include classification methods for automated detection of arrhythmias or other abnormalities. Among those validated, Kwon et al proposed a smartphone-integrated ECG monitoring system that works opportunistically during natural smartphone use [ 22 ]. The system captured ECG reliably in target situations with a reasonable rate of data drop.…”

“…The system was trained using the MIT-BIH arrhythmia database [ 30 ] and retrained based on real ECG recordings, ultimately demonstrating classification accuracy of 93.32%. None of the aforementioned studies [ 22 – 26 , 28 , 29 ] reported considerations in software design to address end-user usability and acceptance of mobile PHM systems in older adults.…”

ECG Monitoring Systems: Review, Architecture, Processes, and Key Challenges

“…Researches tried to apply multiple techniques to address the aforementioned issue, such as adopting Discrete Wavelet Transform and the Pan Tompkins Method to improve heartbeat abnormality classification from ECG signals in [93], or using time domain, frequency domain and distribution features for detection of atrial fibrillation (AF) in [46]. Keeping the good reliability of data and the quality of the signal are also challenges facing smartphone-integrated ECG monitoring systems; such a case was handled in [94] by enhancing the feature extraction process. The Wavelet Transform was also used in [7,60,67,95,96].…”