Early Diagnosis of Atrial Fibrillation Episodes: Comparative Analysis of Different Matrix Architectures
Abstract
1. Introduction
- (1)
- To present and analyze three different architectures of matrices for the early detection of atrial fibrillation episodes. The first two architectures are presented by and adapted from the work of Navickas et al. [32]. In this paper those matrices are labelled as Matrix Architecture One (MA1) and Matrix Architecture Two (MA2), respectively. It is important to mention that (MA1) and (MA2) are being used for the first time for the analysis of atrial fibrillation dataset. The third architecture is sourced from the work of the Qammar et al. [20], and is referred to as Perfect Matrices of Lagrange Differences (PMLDs).
- (2)
- It is noteworthy to mention and acknowledge that the groundwork for exploring the application of the PMLD for atrial fibrillation episodes has already been laid by Qammar et al. [20]. However, ref. [20] focuses on utilizing only three cardiac parameters of the recorded ECG—JT wave, QRS complex, and RR interval [20]. Building upon this foundation, the current paper aims to extend the application of the concept of PMLD matrices to employ a broader array of cardiac parameters. Thus, the multifold objectives of the study are summarized as follows:
- (i)
- To conduct a thorough analysis of the three matrix configurations to determine if the matrix norm or large discriminant yields favorable results for the analysis of ECG signals when utilizing only three cardiac parameters: JT wave, QRS complex, and RR interval.
- (ii)
- Once the most suitable matrix architecture is identified, it will be subjected to additional analysis to evaluate its expandability. The term “expandability” within the context of the matrix architecture denotes its capacity for transformation into higher orders by integrating additional cardiac parameters.
- (iii)
- The expandability analysis will aid in identifying the specific matrix architecture for further analysis.
- (iv)
- Both the matrix sensitivity and variability are then evaluated from the second to the fifth order for the identification and classification of the atrial fibrillation episodes.
- (v)
- Finally, the classification is performed, and the assessment of test applicants is then carried out, which will bring practical implications for furthering the clinical diagnosis.
2. Materials and Methods
2.1. Participants
2.2. Ethics Statement
2.3. Description of Matrix Architecture
2.4. The Architecture of PMLD Matrices
- Each element within the matrix is distinct.
- Zero-order differences are positioned along the main diagonal.
- First-order differences are positioned along the secondary diagonal.
- The indices and can assume one of three possible values as explained in [18].
- The ideal matrix of Lagrange differences maintains lexicographical balance, ensuring that the number of symbols and in the expressions of all matrix elements is equal.
- The ideal matrix of Lagrange differences maintains temporal balance, ensuring that the number of indices with subscripts minus delta and plus delta in the expressions of all matrix elements is equal.
2.5. The Architecture of MA1 and MA2 Matrices
2.6. The Significance of Matrix Expandability to Higher Orders
2.7. The Degree of Freedom in the Matrix Architecture
2.8. The Transformation of the Sequence of the Matrices into the Scalar Time Series
2.9. The Large Discriminant of the Matrix
2.10. The Norm of the Matrix
3. Results and Discussion
3.1. The Comparison between the Matrix Norm and the Matrix Discriminant
3.2. Matrix Expandability Analysis and the Selection of the Best Matrix Architecture
3.3. The Classification of the Matrix Architecture for the Different Orders
Testing Candidates
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
ECG | Electrocardiogram |
PMLD | Perfect Matrices of Lagrange Differences |
MA1 | Matrix Architecture 1 |
MA2 | Matrix Architecture 2 |
AF | Atrial Fibrillation |
CNN | Convolution Neural Networks |
RNN | Recurring Neural Networks |
References
- Cunha, S.; Antunes, E.; Antoniou, S.; Tiago, S.; Relvas, R.; Fernandez-Llimós, F.; da Costa, F.A. Raising awareness and early detection of atrial fibrillation, an experience resorting to mobile technology centred on informed individuals. Res. Soc. Adm. Pharm. 2020, 16, 787–792. [Google Scholar] [CrossRef]
- Odutayo, A.; Wong, C.X.; Hsiao, A.J.; Hopewell, S.; Altman, D.G.; Emdin, C.A. Atrial fibrillation and risks of cardiovascular disease, renal disease, and death: Systematic review and meta-analysis. BMJ 2016, 354, 4482. [Google Scholar] [CrossRef] [PubMed]
- Rho, R.W.; Page, R.L. Asymptomatic atrial fibrillation. Prog. Cardiovasc. Dis. 2005, 48, 79–87. [Google Scholar] [CrossRef]
- Savelieva, I.; Camm, A.J. Clinical relevance of silent atrial fibrillation: Prevalence, prognosis, quality of life, and management. J. Interv. Card. Electrophysiol. 2000, 4, 369–382. [Google Scholar] [CrossRef] [PubMed]
- Camm, A.J.; Corbucci, G.; Padeletti, L. Usefulness of continuous electrocardiographic monitoring for atrial fibrillation. Am. J. Cardiol. 2012, 110, 270–276. [Google Scholar] [CrossRef] [PubMed]
- Association, D.w.t.S.C.o.t.E.H.R.; Surgery, E.b.t.E.A.f.C.-T.; Members, A.T.F.; Camm, A.J.; Kirchhof, P.; Lip, G.Y.; Schotten, U.; Savelieva, I.; Ernst, S.; Van Gelder, I.C. Guidelines for the management of atrial fibrillation: The Task Force for the Management of Atrial Fibrillation of the European Society of Cardiology (ESC). Eur. Heart J. 2010, 31, 2369–2429. [Google Scholar]
- Members, W.G.; Wann, L.S.; Curtis, A.B.; January, C.T.; Ellenbogen, K.A.; Lowe, J.E.; Estes III, N.M.; Page, R.L.; Ezekowitz, M.D.; Slotwiner, D.J. 2011 ACCF/AHA/HRS focused update on the management of patients with atrial fibrillation (updating the 2006 guideline) a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines. Circulation 2011, 123, 104–123. [Google Scholar] [CrossRef] [PubMed]
- Kadri, N.; Abdulelah, A.; Abdulelah, Z.A.; Al-Hiari, M.; Salahat, Z.; Shaban, D.; Ismail, Y.; Al-Kasasbeh, A.; Obeidat, M.; Khasawneh, M. 101 Clinical profiles of hospitalized patients diagnosed with af compared to those diagonsed in an ambulatory setting: Analysis from the jordan atrial fibrilliation (jofib) study. Heart 2022, 108, A75–A76. [Google Scholar]
- Venero, J.E.V.; Benites-Zapata, V.A. Hyperuricemia as a Associated Factor to Atrial Fibrillation in Type 2 Diabetes Mellitus Patients an a Private Clinic in Peru 2020. Metab.-Clin. Exp. 2021, 116. [Google Scholar] [CrossRef]
- Heijman, J.; Luermans, J.G.; Linz, D.; van Gelder, I.C.; Crijns, H.J. Risk factors for atrial fibrillation progression. Card. Electrophysiol. Clin. 2021, 13, 201–209. [Google Scholar] [CrossRef]
- Lip, G.Y.; Khan, A.A.; Olshansky, B. Short-term outcomes of apixaban versus warfarin in patients with atrial fibrillation: Is body weight an important consideration? Am. Heart Assoc. 2019, 139, 2301–2303. [Google Scholar] [CrossRef] [PubMed]
- De Heredia, A.P.L.-F.; Ortiz, M.R.; Cabeza, A.I.P.; Expósito, A.D.; Valenzuela, M.I.F.; Bailén, M.C.; Cubiles, I.A.D.L.L.; Vega, A.M.; Aguilar, M.Z.; Munoz, M.C. Clinical outcomes and mortality in patients with atrial fibrillation and recently diagnosed lung cancer in oncology outpatient settings. Curr. Probl. Cardiol. 2023, 49, 102239. [Google Scholar] [CrossRef] [PubMed]
- Darwin, L.; Sembiring, Y.E.; Lefi, A. Diastolic dysfunction and atrial fibrillation in coronary heart disease surgery: A literature review. Int. J. Surg. Open 2023, 55, 100615. [Google Scholar] [CrossRef]
- Shah, N.A.; Shah, S.; Rijal, A.; Chaudhary, A.; Chand, S.; Pandey, S.; Rawal, L.; Parajuli, S.; Khanal, R.; Poudel, C.M. Anterior wall STEMI in a patient with paroxysmal atrial fibrillation due to coronary embolism: A case report. Ann. Med. Surg. 2022, 82. [Google Scholar] [CrossRef] [PubMed]
- Guidera, S.A.; Steinberg, J.S. The signal-averaged P wave duration: A rapid and noninvasive marker of risk of atrial fibrillation. J. Am. Coll. Cardiol. 1993, 21, 1645–1651. [Google Scholar] [CrossRef] [PubMed]
- Mehta, S.; Lingayat, N.; Sanghvi, S. Detection and delineation of P and T waves in 12-lead electrocardiograms. Expert Syst. 2009, 26, 125–143. [Google Scholar] [CrossRef]
- Qammar, N.W.; Orinaitė, U.; Šiaučiūnaitė, V.; Vainoras, A.; Šakalytė, G.; Ragulskis, M. The Complexity of the Arterial Blood Pressure Regulation during the Stress Test. Diagnostics 2022, 12, 1256. [Google Scholar] [CrossRef] [PubMed]
- Ziaukas, P.; Alabdulgader, A.; Vainoras, A.; Navickas, Z.; Ragulskis, M. New approach for visualization of relationships between RR and JT intervals. PLoS ONE 2017, 12, e0174279. [Google Scholar] [CrossRef] [PubMed]
- Erelund, S.; Karp, K.; Wiklund, U.; Hörnsten, R.; Arvidsson, S. Are ECG changes in heart-healthy individuals of various ages related to cardiac disease 20 years later? Upsala J. Med. Sci. 2021, 126. [Google Scholar] [CrossRef] [PubMed]
- Qammar, N.W.; Šiaučiūnaitė, V.; Zabiela, V.; Vainoras, A.; Ragulskis, M. Detection of atrial fibrillation episodes based on 3D algebraic relationships between cardiac intervals. Diagnostics 2022, 12, 2919. [Google Scholar] [CrossRef]
- Ebrahimzadeh, E.; Kalantari, M.; Joulani, M.; Shahraki, R.S.; Fayaz, F.; Ahmadi, F. Prediction of paroxysmal Atrial Fibrillation: A machine learning based approach using combined feature vector and mixture of expert classification on HRV signal. Comput. Methods Programs Biomed. 2018, 165, 53–67. [Google Scholar] [CrossRef] [PubMed]
- Hagiwara, Y.; Fujita, H.; Oh, S.L.; Tan, J.H.; San Tan, R.; Ciaccio, E.J.; Acharya, U.R. Computer-aided diagnosis of atrial fibrillation based on ECG Signals: A review. Inf. Sci. 2018, 467, 99–114. [Google Scholar] [CrossRef]
- Andersen, R.S.; Peimankar, A.; Puthusserypady, S. A deep learning approach for real-time detection of atrial fibrillation. Expert Syst. Appl. 2019, 115, 465–473. [Google Scholar] [CrossRef]
- Jafari, A. Sleep apnoea detection from ECG using features extracted from reconstructed phase space and frequency domain. Biomed. Signal Process. Control 2013, 8, 551–558. [Google Scholar] [CrossRef]
- Casaleggio, A.; Braiotta, S.; Corana, A. Study of the Lyapunov exponents of ECG signals from MIT-BIH database. In Proceedings of the Computers in Cardiology, Vienna, Austria, 10–13 September 1995; pp. 697–700. [Google Scholar]
- Übeyli, E.D. Detecting variabilities of ECG signals by Lyapunov exponents. Neural Comput. Appl. 2009, 18, 653–662. [Google Scholar] [CrossRef]
- Casaleggio, A.; Corana, A.; Ridella, S. Correlation dimension estimation from electrocardiograms. Chaos Solitons Fractals 1995, 5, 713–726. [Google Scholar] [CrossRef]
- Acharya, R.; Lim, C.; Joseph, P. Heart rate variability analysis using correlation dimension and detrended fluctuation analysis. Itbm-Rbm 2002, 23, 333–339. [Google Scholar] [CrossRef]
- Fojt, O.; Holcik, J. Applying nonlinear dynamics to ECG signal processing. IEEE Eng. Med. Biol. Mag. 1998, 17, 96–101. [Google Scholar] [CrossRef] [PubMed]
- Lee, J.-M.; Kim, D.-J.; Kim, I.-Y.; Park, K.-S.; Kim, S.I. Detrended fluctuation analysis of EEG in sleep apnea using MIT/BIH polysomnography data. Comput. Biol. Med. 2002, 32, 37–47. [Google Scholar] [CrossRef] [PubMed]
- Houshyarifar, V.; Amirani, M.C. Early detection of sudden cardiac death using Poincaré plots and recurrence plot-based features from HRV signals. Turk. J. Electr. Eng. Comput. Sci. 2017, 25, 1541–1553. [Google Scholar] [CrossRef]
- Petkus, V.; Vainoras, A.; Berskiene, K.; Navickas, Z.; Ruseckas, R.; Piper, I.; Deimantavicius, M.; Ragauskas, A. Method for prediction of acute hypotensive episodes. Elektron. Elektrotech. 2016, 22, 44–48. [Google Scholar] [CrossRef]
- Šiaučiūnaitė, V.; Ragulskis, M.; Vainoras, A.; Dabiri, B.; Kaniusas, E. Visualization of complex processes in cardiovascular system during electrical auricular vagus nerve stimulation. Diagnostics 2021, 11, 2190. [Google Scholar] [CrossRef] [PubMed]
- Berskiene, K.; Lukosevicius, A.; Jarusevicius, G.; Jurkonis, V.; Navickas, Z.; Vainoras, A.; Daunoraviciene, A. Analysis of dynamical interrelations of electrocardiogram parameters. Elektron. Elektrotech. 2009, 95, 95–98. [Google Scholar]
Matrix Architecture One (MA1) | Matrix Architecture Two (MA1) | The Architecture of PMLD Matrices | |||
---|---|---|---|---|---|
Variance of the Large Discriminant | Variance of the Norm | Variance of the Large Discriminant | Variance of the Norm | Variance of the Norm | |
0.0640 | 0.0016 | 0.042 | 0.0010 | 0.0012 | |
0.0633 | 0.0047 | 0.0313 | 0.0038 | 0.0030 | |
182.4470 | 0.0027 | 16.167 | 0.0020 | 0.0023 | |
44.6925 | 0.0014 | 1.6402 | 0.0014 | 0.0014 | |
608.0258 | 0.0076 | 94.7592 | 0.0052 | 0.0040 | |
12.4591 | 0.0026 | 2.9064 | 0.0008 | 0.0025 | |
1618.7723 | 0.0042 | 1490.7099 | 0.0216 | 0.0031 | |
62.0865 | 0.0042 | 65.921 | 0.0165 | 0.0018 |
Matrix Architecture One (MA1) | Matrix Architecture Two (MA1) | The Architecture of PMLD Matrices | |||
---|---|---|---|---|---|
Variance of the Large Discriminant | Variance of the Norm | Variance of the Large Discriminant | Variance of the Norm | Variance of the Norm | |
1144.7393 | 0.0012 | 21.2530 | 0.0008 | 0.0006 | |
1358.7248 | 0.0006 | 21.9133 | 0.0005 | 0.0004 | |
15.2796 | 0.0171 | 2.5576 | 0.0177 | 0.0082 | |
339.2649 | 0.0066 | 1566.6759 | 0.0111 | 0.0064 | |
4.8991 | 0.0023 | 0.9349 | 0.0030 | 0.0030 | |
84.2605 | 0.0013 | 3.0256 | 0.0022 | 0.0014 |
List of Healthy Candidates | 2nd-Order Matrix | 3rd-Order Matrix | 4th-Order Matrix | 5th-Order Matrix | |
---|---|---|---|---|---|
JT, QRS | JT, RR | JT, QRS, RR | JT, QRS, RR, DP | JT, QRS, RR, AP, DP | |
0.0018 | 0.0004 | 0.0012 | 0.0069 | 0.0096 | |
0.0015 | 0.0002 | 0.0029 | 0.0029 | 0.0074 | |
0.0013 | 0.0009 | 0.0023 | 0.0030 | 0.0150 | |
0.0007 | 0.0005 | 0.0014 | 0.0019 | 0.0022 | |
0.0030 | 0.0011 | 0.0040 | 0.0020 | 0.0056 | |
0.0018 | 0.0005 | 0.0025 | 0.0033 | 0.0033 | |
0.0013 | 0.0005 | 0.0031 | 0.0021 | 0.0109 | |
0.0007 | 0.0018 | 0.0018 | 0.0019 | 0.0038 |
List of Unhealthy Candidates | 2nd-Order Matrix | 3rd-Order Matrix | 4th-Order Matrix | 5th-Order Matrix | |
---|---|---|---|---|---|
JT, QRS | JT, RR | JT, QRS, RR | JT, QRS, RR, DP | JT, QRS, RR, AP, DP | |
0.0005 | 0.0001 | 0.0006 | 0.0031 | 0.0034 | |
0.0002 | 0.0001 | 0.0004 | 0.0004 | 0.0004 | |
0.0073 | 0.0023 | 0.0082 | 0.0229 | 0.0133 | |
0.0049 | 0.0012 | 0.0064 | 0.0039 | 0.0065 | |
0.0014 | 0.0003 | 0.0030 | 0.0100 | 0.0117 | |
0.0007 | 0.0004 | 0.0014 | 0.0036 | 0.0039 |
For the 3rd-Order PMLD | |||
---|---|---|---|
Condition 1 | Condition 2 | Condition 3 | |
If | Z | ||
Then, the probability indicator is: | |||
The candidate is classified as | Healthy | Unhealthy | In between the healthy and unhealthy group based upon the variance values |
For the 5th-Order PMLD | |||
If | Z | ||
Then, the probability indicator is: | |||
The candidate is classified as | Healthy | Unhealthy | In between the healthy and unhealthy group based upon the variance values |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Qammar, N.W.; Vainoras, A.; Navickas, Z.; Jaruševičius, G.; Ragulskis, M. Early Diagnosis of Atrial Fibrillation Episodes: Comparative Analysis of Different Matrix Architectures. Appl. Sci. 2024, 14, 6191. https://doi.org/10.3390/app14146191
Qammar NW, Vainoras A, Navickas Z, Jaruševičius G, Ragulskis M. Early Diagnosis of Atrial Fibrillation Episodes: Comparative Analysis of Different Matrix Architectures. Applied Sciences. 2024; 14(14):6191. https://doi.org/10.3390/app14146191
Chicago/Turabian StyleQammar, Naseha Wafa, Alfonsas Vainoras, Zenonas Navickas, Gediminas Jaruševičius, and Minvydas Ragulskis. 2024. "Early Diagnosis of Atrial Fibrillation Episodes: Comparative Analysis of Different Matrix Architectures" Applied Sciences 14, no. 14: 6191. https://doi.org/10.3390/app14146191
APA StyleQammar, N. W., Vainoras, A., Navickas, Z., Jaruševičius, G., & Ragulskis, M. (2024). Early Diagnosis of Atrial Fibrillation Episodes: Comparative Analysis of Different Matrix Architectures. Applied Sciences, 14(14), 6191. https://doi.org/10.3390/app14146191