Motion Artifact Reduction in Electrocardiogram Signals Through a Redundant Denoising Independent Component Analysis Method for Wearable Health Care Monitoring Systems: Algorithm Development and Validation

Overview

Journal JMIR Med Inform

Publisher JMIR Publications

Specialty Medical Informatics

Date 2022 Oct 24

PMID 36274196

Authors

Fabian Andres Castano Usuga

Christian Gissel

Alher Mauricio Hernandez

Affiliations

Soon will be listed here.

Abstract

Background: The quest for improved diagnosis and treatment in home health care models has led to the development of wearable medical devices for remote vital signs monitoring. An accurate signal and a high diagnostic yield are critical for the cost-effectiveness of wearable health care monitoring systems and their widespread application in resource-constrained environments. Despite technological advances, the information acquired by these devices can be contaminated by motion artifacts (MA) leading to misdiagnosis or repeated procedures with increases in associated costs. This makes it necessary to develop methods to improve the quality of the signal acquired by these devices.

Objective: We aimed to present a novel method for electrocardiogram (ECG) signal denoising to reduce MA. We aimed to analyze the method's performance and to compare its performance to that of existing approaches.

Methods: We present the novel Redundant denoising Independent Component Analysis method for ECG signal denoising based on the redundant and simultaneous acquisition of ECG signals and movement information, multichannel processing, and performance assessment considering the information contained in the signal waveform. The method is based on data including ECG signals from the patient's chest and back, the acquisition of triaxial movement signals from inertial measurement units, a reference signal synthesized from an autoregressive model, and the separation of interest and noise sources through multichannel independent component analysis.

Results: The proposed method significantly reduced MA, showing better performance and introducing a smaller distortion in the interest signal compared with other methods. Finally, the performance of the proposed method was compared to that of wavelet shrinkage and wavelet independent component analysis through the assessment of signal-to-noise ratio, dynamic time warping, and a proposed index based on the signal waveform evaluation with an ensemble average ECG.

Conclusions: Our novel ECG denoising method is a contribution to converting wearable devices into medical monitoring tools that can be used to support the remote diagnosis and monitoring of cardiovascular diseases. A more accurate signal substantially improves the diagnostic yield of wearable devices. A better yield improves the devices' cost-effectiveness and contributes to their widespread application.

References

Galarraga M, Serrano L, Martinez I, de Toledo P, Reynolds M . Telemonitoring systems interoperability challenge: an updated review of the applicability of ISO/IEEE 11073 standards for interoperability in telemonitoring. Annu Int Conf IEEE Eng Med Biol Soc. 2007; 2007:6162-6. DOI: 10.1109/IEMBS.2007.4353761. View

Vessella T, Zorzi A, Merlo L, Pegoraro C, Giorgiano F, Trevisanato M . The Italian preparticipation evaluation programme: diagnostic yield, rate of disqualification and cost analysis. Br J Sports Med. 2019; 54(4):231-237. PMC: 7029244. DOI: 10.1136/bjsports-2018-100293. View

Price J, Cole K, Bexley A, Kostiou V, Eyre D, Golubchik T . Transmission of Staphylococcus aureus between health-care workers, the environment, and patients in an intensive care unit: a longitudinal cohort study based on whole-genome sequencing. Lancet Infect Dis. 2016; 17(2):207-214. PMC: 5266793. DOI: 10.1016/S1473-3099(16)30413-3. View

Zhang D . Wavelet Approach for ECG Baseline Wander Correction and Noise Reduction. Conf Proc IEEE Eng Med Biol Soc. 2007; 2005:1212-5. DOI: 10.1109/IEMBS.2005.1616642. View

Shorten G, Burke M . Use of dynamic time warping for accurate ECG signal timing characterization. J Med Eng Technol. 2014; 38(4):188-201. DOI: 10.3109/03091902.2014.902514. View

Evans G, Shirk A, Muturi P, Soliman E . Feasibility of Using Mobile ECG Recording Technology to Detect Atrial Fibrillation in Low-Resource Settings. Glob Heart. 2017; 12(4):285-289. DOI: 10.1016/j.gheart.2016.12.003. View

Hyvarinen A, Oja E . Independent component analysis: algorithms and applications. Neural Netw. 2000; 13(4-5):411-30. DOI: 10.1016/s0893-6080(00)00026-5. View

Reed M, Grubb N, Lang C, Gray A, Simpson K, MacRaild A . Diagnostic yield of an ambulatory patch monitor in patients with unexplained syncope after initial evaluation in the emergency department: the PATCH-ED study. Emerg Med J. 2018; 35(8):477-485. DOI: 10.1136/emermed-2018-207570. View

Gernant S, Snyder M, Jaynes H, Sutherland J, Zillich A . The Effectiveness of Pharmacist-Provided Telephonic Medication Therapy Management on Emergency Department Utilization in Home Health Patients. J Pharm Technol. 2017; 32(5):179-184. PMC: 5600472. DOI: 10.1177/8755122516660376. View

10.

Baig M, GholamHosseini H, Connolly M . A comprehensive survey of wearable and wireless ECG monitoring systems for older adults. Med Biol Eng Comput. 2013; 51(5):485-95. DOI: 10.1007/s11517-012-1021-6. View

11.

Nathan V, Akkaya I, Jafari R . A particle filter framework for the estimation of heart rate from ECG signals corrupted by motion artifacts. Annu Int Conf IEEE Eng Med Biol Soc. 2016; 2015:6560-5. DOI: 10.1109/EMBC.2015.7319896. View

12.

Sonawane A, Manickam P, Bhansali S . Stability of Enzymatic Biosensors for Wearable Applications. IEEE Rev Biomed Eng. 2017; 10:174-186. DOI: 10.1109/RBME.2017.2706661. View

13.

Kania M, Rix H, Fereniec M, Zavala-Fernandez H, Janusek D, Mroczka T . The effect of precordial lead displacement on ECG morphology. Med Biol Eng Comput. 2013; 52(2):109-19. PMC: 3899452. DOI: 10.1007/s11517-013-1115-9. View

14.

Steinberg L, Knilans T . Syncope in children: diagnostic tests have a high cost and low yield. J Pediatr. 2005; 146(3):355-8. DOI: 10.1016/j.jpeds.2004.10.039. View

15.

Castano F, Hernandez A . Sensitivity and Adjustment Model of Electrocardiographic Signal Distortion Based on the Electrodes' Location and Motion Artifacts Reduction for Wearable Monitoring Applications. Sensors (Basel). 2021; 21(14). PMC: 8309909. DOI: 10.3390/s21144822. View

16.

Rush S, Driscoll D . EEG electrode sensitivity--an application of reciprocity. IEEE Trans Biomed Eng. 1969; 16(1):15-22. DOI: 10.1109/tbme.1969.4502598. View

17.

Liang Y, Chen Z, Ward R, Elgendi M . Hypertension Assessment via ECG and PPG Signals: An Evaluation Using MIMIC Database. Diagnostics (Basel). 2018; 8(3). PMC: 6163274. DOI: 10.3390/diagnostics8030065. View

18.

Francisco-Pascual J, Santos-Ortega A, Roca-Luque I, Rivas-Gandara N, Perez-Rodon J, Mila-Pascual L . Diagnostic Yield and Economic Assessment of a Diagnostic Protocol With Systematic Use of an External Loop Recorder for Patients With Palpitations. Rev Esp Cardiol (Engl Ed). 2018; 72(6):473-478. DOI: 10.1016/j.rec.2018.04.007. View

19.

Albinski M, Saubade M, Menafoglio A, Meyer P, Capelli B, Perrin T . Diagnostic yield and cost analysis of electrocardiographic screening in Swiss paediatric athletes. J Sci Med Sport. 2021; 25(4):281-286. DOI: 10.1016/j.jsams.2021.11.039. View

20.

Sourdet S, Lafont C, Rolland Y, Nourhashemi F, Andrieu S, Vellas B . Preventable Iatrogenic Disability in Elderly Patients During Hospitalization. J Am Med Dir Assoc. 2015; 16(8):674-81. DOI: 10.1016/j.jamda.2015.03.011. View