ABSTRACT
Signal quality assessment is essential for biomedical signal processing, analysis, and interpretation. Various methods exist, including averaged numerical values, thresholding, time- or frequency-domain analysis, and nonlinear approaches. This study evaluated the quality of gyrocardiographic signals (GCG) using symmetric projection attractor reconstruction (SPAR) analysis. Two classifiers, random forest and bagged trees, were used to assess the performance of the SPAR-based approach. Eleven features were extracted from the variables v and w, calculated on the basis of the signal delay. These features included minimum and maximum values, mean, standard deviation (SD), median, and Euclidean distance. The results showed that the SPAR-based approach achieved high accuracy, precision, and recall. The random forest classifier achieved 0.729 accuracy, 0.726 precision, and 0.729 recall, while the bagged trees classifier achieved 0.792 accuracy, 0.804 precision, and 0.792 recall. These findings suggest that the SPAR-based approach is a promising method to accurately assess the quality of GCG signals.
- Philip J Aston, Mark I Christie, Ying H Huang, and Manasi Nandi. 2018. Beyond HRV: attractor reconstruction using the entire cardiovascular waveform data for novel feature extraction. Physiological Measurement 39, 2 (Mar 2018), 024001. https://doi.org/10.1088/1361-6579/aaa93dGoogle ScholarCross Ref
- Philip J Aston, Manasi Nandi, Mark I Christie, and Ying H Huang. 2014. Comparison of attractor reconstruction and HRV methods for analysing blood pressure data. In Computing in Cardiology 2014. IEEE Press, Cambridge, MA, USA, 437–440.Google Scholar
- P.H. Charlton, L. Camporota, J. Smith, M. Nandi, M. Christie, P.J. Aston, and R. Beale. 2015. Measurement of cardiovascular state using attractor reconstruction analysis. In 2015 23rd European Signal Processing Conference (EUSIPCO). IEEE, Nice, France, 444–448. https://doi.org/10.1109/eusipco.2015.7362422Google ScholarCross Ref
- Nitesh V. Chawla, Kevin W. Bowyer, Lawrence O. Hall, and W. Philip Kegelmeyer. 2002. SMOTE: Synthetic Minority over-Sampling Technique. J. Artif. Int. Res. 16, 1 (jun 2002), 321–357.Google ScholarDigital Library
- Javier de Pedro-Carracedo, David Fuentes-Jimenez, Ana María Ugena, and Ana Pilar Gonzalez-Marcos. 2020. Phase Space Reconstruction from a Biological Time Series: A Photoplethysmographic Signal Case Study. Applied Sciences 10, 4 (Feb 2020), 1430. https://doi.org/10.3390/app10041430Google ScholarCross Ref
- Parastoo Dehkordi, Kouhyar Tavakolian, Mojtaba Jafari Tadi, Vahid Zakeri, and Farzad Khosrow-khavar. 2020. Investigating the estimation of cardiac time intervals using gyrocardiography. Physiological Measurement 41, 5 (Jun 2020), 055004. https://doi.org/10.1088/1361-6579/ab87b2Google ScholarCross Ref
- Charles R. Harris, K. Jarrod Millman, Stéfan J. van der Walt, Ralf Gommers, Pauli Virtanen, David Cournapeau, Eric Wieser, Julian Taylor, Sebastian Berg, Nathaniel J. Smith, Robert Kern, Matti Picus, Stephan Hoyer, Marten H. van Kerkwijk, Matthew Brett, Allan Haldane, Jaime Fernández del Río, Mark Wiebe, Pearu Peterson, Pierre Gérard-Marchant, Kevin Sheppard, Tyler Reddy, Warren Weckesser, Hameer Abbasi, Christoph Gohlke, and Travis E. Oliphant. 2020. Array programming with NumPy. Nature 585, 7825 (Sep 2020), 357–362. https://doi.org/10.1038/s41586-020-2649-2Google ScholarCross Ref
- Ying H. Huang, Jane V. Lyle, Anisa Shahira Ab Razak, Manasi Nandi, Celia M. Marr, Christopher L.-H. Huang, Philip J. Aston, and Kamalan Jeevaratnam. 2022. Detecting paroxysmal atrial fibrillation from normal sinus rhythm in equine athletes using Symmetric Projection Attractor Reconstruction and machine learning. Cardiovascular Digital Health Journal 3, 2 (Apr 2022), 96–106. https://doi.org/10.1016/j.cvdhj.2022.02.001Google ScholarCross Ref
- Jussi Jaakkola, Samuli Jaakkola, Olli Lahdenoja, Tero Hurnanen, Tero Koivisto, Mikko Pänkäälä, Timo Knuutila, Tuomas O. Kiviniemi, Tuija Vasankari, and K.E. Juhani Airaksinen. 2018. Mobile Phone Detection of Atrial Fibrillation With Mechanocardiography. Circulation 137, 14 (2018), 1524–1527. https://doi.org/10.1161/CIRCULATIONAHA.117.032804Google ScholarCross Ref
- Matti Kaisti, Mojtaba Jafari Tadi, Olli Lahdenoja, Tero Hurnanen, Mikko Pänkäälä, and Tero Koivisto. 2018. Mechanocardiograms with ECG reference. IEEE DataPort. https://doi.org/10.21227/vfcs-k196 DOI: 10.21227/vfcs-k196.Google ScholarCross Ref
- Matti Kaisti, Mojtaba Jafari Tadi, Olli Lahdenoja, Tero Hurnanen, Antti Saraste, Mikko Pankaala, and Tero Koivisto. 2019. Stand-Alone Heartbeat Detection in Multidimensional Mechanocardiograms. IEEE Sensors Journal 19, 1 (Jan 2019), 234–242. https://doi.org/10.1109/jsen.2018.2874706Google ScholarCross Ref
- Olli Lahdenoja, Tero Hurnanen, Mojtaba Jafari Tadi, Mikko Pänkäälä, and Tero Koivisto. 2016. Heart Rate Variability Estimation with Joint Accelerometer and Gyroscope Sensing. In Computing in Cardiology, Vol. 43. IEEE Press, Vancouver, BC, Canada, 717–720.Google Scholar
- Jane V Lyle, Manasi Nandi, and Philip J Aston. 2019. Investigating the Response to Dofetilide with Symmetric Projection Attractor Reconstruction of the Electrocardiogram. In 2019 Computing in Cardiology (CinC). IEEE Press, Singapore, Page 1–Page 4. https://doi.org/10.22489/CinC.2019.073Google ScholarCross Ref
- S. Mehrang, M. Jafari Tadi, M. Kaisti, O. Lahdenoja, T. Vasankari, T. Kiviniemi, J. Airaksinen, T. Koivisto, and M. Pänkäälä. 2018. Machine Learning Based Classification of Myocardial Infarction Conditions Using Smartphone-Derived Seismo- and Gyrocardiography. In 2018 Computing in Cardiology Conference (CinC), Vol. 45. IEEE Press, Maastricht, Netherlands, 1–4. https://doi.org/10.22489/CinC.2018.110Google ScholarCross Ref
- Manasi Nandi and Philip J. Aston. 2020. Extracting new information from old waveforms: Symmetric projection attractor reconstruction: Where maths meets medicine. Experimental Physiology 105, 9 (May 2020), 1444–1451. https://doi.org/10.1113/ep087873Google ScholarCross Ref
- Manasi Nandi, Jenny Venton, and Philip J Aston. 2018. A novel method to quantify arterial pulse waveform morphology: attractor reconstruction for physiologists and clinicians. Physiological Measurement 39, 10 (Oct 2018), 104008. https://doi.org/10.1088/1361-6579/aae46aGoogle ScholarCross Ref
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825–2830.Google ScholarDigital Library
- T. Penzel, B. Kemp, G. Klosch, A. Schlogl, J. Hasan, A. Varri, and I. Korhonen. 2001. Acquisition of biomedical signals databases. IEEE Engineering in Medicine and Biology Magazine 20, 3 (May 2001), 25–32. https://doi.org/10.1109/51.932721Google ScholarCross Ref
- Deepak Rai, Hiren Kumar Thakkar, Shyam Singh Rajput, Jose Santamaria, Chintan Bhatt, and Francisco Roca. 2021. A Comprehensive Review on Seismocardiogram: Current Advancements on Acquisition, Annotation, and Applications. Mathematics 9, 18 (Sep 2021), 2243. https://doi.org/10.3390/math9182243Google ScholarCross Ref
- Francesca Santucci, Daniela Lo Presti, Carlo Massaroni, Emiliano Schena, and Roberto Setola. 2022. Precordial Vibrations: A Review of Wearable Systems, Signal Processing Techniques, and Main Applications. Sensors 22, 15 (Aug 2022), 5805. https://doi.org/10.3390/s22155805Google ScholarCross Ref
- Udit Satija, Barathram Ramkumar, and M. Sabarimalai Manikandan. 2018. A Review of Signal Processing Techniques for Electrocardiogram Signal Quality Assessment. IEEE Reviews in Biomedical Engineering 11 (2018), 36–52. https://doi.org/10.1109/rbme.2018.2810957Google ScholarCross Ref
- Arash Shokouhmand, Chenxi Yang, Nicole D. Aranoff, Elissa Driggin, Philip Green, and Negar Tavassolian. 2021. Mean Pressure Gradient Prediction Based on Chest Angular Movements and Heart Rate Variability Parameters. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC). IEEE Press, Guadalajara, Mexico, 7170–7173. https://doi.org/10.1109/EMBC46164.2021.9630805Google ScholarCross Ref
- Szymon Sieciński, Paweł S. Kostka, and Ewaryst J. Tkacz. 2020. Heart Rate Variability Analysis on Electrocardiograms, Seismocardiograms and Gyrocardiograms on Healthy Volunteers. Sensors 20, 16 (Aug 2020), 4522. https://doi.org/10.3390/s20164522Google ScholarCross Ref
- Szymon Sieciński, Ewaryst Janusz Tkacz, and Paweł Stanisław Kostka. 2023. Heart Rate Variability Analysis on Electrocardiograms, Seismocardiograms and Gyrocardiograms of Healthy Volunteers and Patients with Valvular Heart Diseases. Sensors 23, 4 (Feb 2023), 2152. https://doi.org/10.3390/s23042152Google ScholarCross Ref
- Szymon Sieciński, Paweł S. Kostka, and Ewaryst J. Tkacz. 2020. Gyrocardiography: A Review of the Definition, History, Waveform Description, and Applications. Sensors 20, 22 (Nov 2020), 6675. https://doi.org/10.3390/s20226675Google ScholarCross Ref
- M. J. Tadi, E. Lehtonen, T. Koivisto, M. Pänkäälä, A. Paasio, and M. Teräs. 2015. Seismocardiography: Toward heart rate variability (HRV) estimation. In 2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings. IEEE Press, Turin, Italy, 261–266. https://doi.org/10.1109/MeMeA.2015.7145210Google ScholarCross Ref
- M. J. Tadi, E. Lehtonen, M. Pankäälä, A. Saraste, T. Vasankari, M. Terás, and T. Koivisto. 2016. Gyrocardiography: A new non-invasive approach in the study of mechanical motions of the heart. Concept, method and initial observations. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE Press, Orlando, FL, USA, 2034–2037. https://doi.org/10.1109/EMBC.2016.7591126Google ScholarCross Ref
- Mojtaba Jafari Tadi, Eero Lehtonen, Antti Saraste, Jarno Tuominen, Juho Koskinen, Mika Teräs, Juhani Airaksinen, Mikko Pänkäälä, and Tero Koivisto. 2017. Gyrocardiography: A New Non-invasive Monitoring Method for the Assessment of Cardiac Mechanics and the Estimation of Hemodynamic Variables. Scientific Reports 7, 1 (July 2017), 6823. https://doi.org/10.1038/s41598-017-07248-yGoogle ScholarCross Ref
- Floris Takens. 1981. Detecting strange attractors in turbulence. In Lecture Notes in Mathematics. Springer Berlin Heidelberg, Coventry, UK, 366–381. https://doi.org/10.1007/bfb0091924Google ScholarCross Ref
- Chenxi Yang, Banish Ojha, Nicole D. Aranoff, Philip Green, and Negar Tavassolian. 2020. Classification of Aortic Stenosis Before and After Transcatheter Aortic Valve Replacement Using Cardio-mechanical Modalities*. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC). IEEE Press, Montreal, QC, Canada, 2820–2823. https://doi.org/10.1109/EMBC44109.2020.9176321Google ScholarCross Ref
Index Terms
- Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction
Recommendations
A machine learning approach to multi-level ECG signal quality classification
A five-level ECG signal quality classification algorithm using a machine learning approach was proposed.13 signal quality metrics were derived from segments of ECG waveforms.The algorithm was trained and tested on a simulated dataset and was validated ...
Assessing the signal quality of electrocardiograms from varied acquisition sources: A generic machine learning pipeline for model generation
Abstract Background and objectiveLong-term electrocardiogram monitoring comes at the expense of signal quality. During unconstrained movements, the electrocardiogram is often corrupted by motion artefacts, which can lead to inaccurate physiological ...
Highlights- Long-term electrocardiogram monitoring comes at the expense of signal quality.
- Automated quality assessment methods are necessary to filter out the unreliable segments.
- A generic machine learning pipeline for generating ECG signal ...
Comments