HeartQuake: Accurate Low-Cost Non-Invasive ECG Monitoring Using Bed-Mounted Geophones

被引:18
作者
Park, Jaeyeon [1 ]
Cho, Hyeon [2 ]
Balan, Rajesh Krishna [3 ]
Ko, JeongGil [1 ]
机构
[1] Yonsei Univ, Sch Integrated Technol, 85 Songdogwahak Ro, Incheon, South Korea
[2] Ajou Univ, Dept Comp Engn, 206 Worldcup Ro, Suwon, South Korea
[3] Singapore Management Univ, Sch Informat Syst, 80 Stamford Rd, Singapore, Singapore
来源
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT | 2020年 / 4卷 / 03期
基金
新加坡国家研究基金会;
关键词
ECG Waveform Prediction; Contactless Physiological Sensing; SYSTOLIC-TIME INTERVALS; ATRIAL-FIBRILLATION; RATE-VARIABILITY; SEISMOCARDIOGRAM; NONCONTACT; ELECTROCARDIOGRAM; ARRHYTHMIAS; FREQUENCY; PLATFORM; FAILURE;
D O I
10.1145/3411843
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This work presents HeartQuake, a low cost, accurate, non-intrusive, geophone-based sensing system for extracting accurate electrocardiogram (ECG) patterns using heartbeat vibrations that penetrate through a bed mattress. In HeartQuake, cardiac activity-originated vibration patterns are captured on a geophone and sent to a server, where the data is filtered to remove the sensor's internal noise and passed on to a bidirectional long short term memory (Bi-LSTM) deep learning model for ECG waveform estimation. To the best of our knowledge, this is the first solution that can non-intrusively provide accurate ECG waveform characteristics instead of more basic abstract features such as the heart rate using bed-mounted geophone sensors. Our extensive experimental results with a baseline dataset collected from 21 study participants and a longitudinal dataset from 15 study participants suggest that HeartQuake, even when using a general non-personalized model, can detect all five ECG peaks (e.g., P, Q, R, S, T) with an average error of 13 msec when participants are stationary on the bed. Furthermore, clinically used ECG metrics such as the RR interval and QRS segment width can be estimated with errors 3 msec and 10 msec, respectively. When additional noise factors are present (e.g., external vibration and various sleeping habits), the estimation error increases, but can be mitigated by using a personalized model. Finally, a qualitative study with 11 physicians on the clinically perceived quality of HeartQuake-generated ECG signals suggests that HeartQuake can effectively serve as a screening tool for detecting and diagnosing abnormal cardiovascular conditions. In addition, HeartQuake's low-cost and non-intrusive nature allow it to be deployed in larger scales compared to current ECG monitoring solutions.
引用
收藏
页数:28
相关论文
共 114 条
[61]   Identification of Location Specific Feature Points in a Cardiac Cycle Using a Novel Seismocardiogram Spectrum System [J].
Lin, Wen-Yen ;
Chou, Wen-Cheng ;
Chang, Po-Cheng ;
Chou, Chung-Chuan ;
Wen, Ming-Shien ;
Ho, Ming-Yun ;
Lee, Wen-Chen ;
Hsieh, Ming-Jer ;
Lin, Chung-Chih ;
Tsai, Tsai-Hsuan ;
Lee, Ming-Yih .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2018, 22 (02) :442-449
[62]   VALUE OF HOLTER MONITORING IN ASSESSING CARDIAC-ARRHYTHMIAS IN SYMPTOMATIC PATIENTS [J].
LIPSKI, J ;
COHEN, L ;
ESPINOZA, J ;
MOTRO, M ;
DACK, S ;
DONOSO, E .
AMERICAN JOURNAL OF CARDIOLOGY, 1976, 37 (01) :102-107
[63]  
Mahdiani S, 2015, IEEE ENG MED BIO, P5948, DOI 10.1109/EMBC.2015.7319746
[64]   Smart Homes for Elderly Healthcare-Recent Advances and Research Challenges [J].
Majumder, Sumit ;
Aghayi, Emad ;
Noferesti, Moein ;
Memarzadeh-Tehran, Hamidreza ;
Mondal, Tapas ;
Pang, Zhibo ;
Deen, M. Jamal .
SENSORS, 2017, 17 (11)
[65]   Recent Trends in the Incidence, Treatment, and Prognosis of Patients With Heart Failure and Atrial Fibrillation (the Worcester Heart Failure Study) [J].
McManus, David D. ;
Saczynski, Jane S. ;
Lessard, Darleen ;
Kinno, Menhel ;
Pidikiti, Rahul ;
Esa, Nada ;
Harrington, Josephine ;
Goldberg, Robert J. .
AMERICAN JOURNAL OF CARDIOLOGY, 2013, 111 (10) :1460-1465
[66]  
Medtronic, 2019, HEART MONITORS REVEA
[67]  
Michael S Hons, 2008, SEISMIC SENSING COMP
[68]   Occupant localization using footstep-induced structural vibration [J].
Mirshekari, Mostafa ;
Pan, Shijia ;
Fagert, Jonathon ;
Schooler, Eve M. ;
Zhang, Pei ;
Noh, Hae Young .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2018, 112 :77-97
[69]  
MP36, US
[70]  
Mullan P, 2015, IEEE ENG MED BIO, P6114, DOI 10.1109/EMBC.2015.7319787