Abstract
Examining P-wave morphological changes in Electrocardiogram (ECG) is essential for characterizing atrial arrhythmias. However, standard 12-lead ECGsuffer from diagnostic redundancy due to low signal-to-noise ratio of P-waves. To address this issue, various optimal leads have been proposed for improved atrial activity recording, but the right selection among these leads is crucial for enhancing diagnostic efficacy. This study proposes an automated lead selection technique using the CatBoost machine learning (ML) model to improve the detection of P-wave changes among optimal bipolar leads under different heart rates. ECGs were obtained from healthy participants with a mean age of 25 ± 3.81 years (34% women), including 114 in sinus rhythm (SR) and 38 in sinus tachycardia (ST). The recordings were made using a newly designed atrial lead system (ALS), standard limb lead (SLL), modified limb lead (MLL), modified Lewis lead (LLM) and P-lead. P-wave features and Atrioventricular (AV) ratio were extracted for statistical analysis and ML classification. The optimum ML model was chosen to identify the best-performing optimal lead, which was selected based on the SLL metrics among different ML classifiers. CatBoost was found to outperform the other ML models in SLL-II with the highest accuracy and sensitivity of 0.82 and 0.90, respectively. The CatBoost model, amid other optimal leads, gave the best results for AL-I and AL-II (0.86 and 0.83 in accuracy and 0.91 and 0.93 in sensitivity). The developed CatBoost model selected AL-I and AL-II as the top two best-performing optimal leads for the enhanced acquisition of P-wave changes, which may be useful for diagnosing atrial arrhythmias.
Similar content being viewed by others
Data availability
The datasets that support the findings of this work are self-made datasets from real-time recorded ECG that are not publicly accessible. However, the datasets are provided to the scientific community for research purposes in supplementary information.
Abbreviations
- AF:
-
Atrial fibrillation
- ALS:
-
Atrial lead system
- AUC:
-
Area under the curve
- CART:
-
Classification and regression tree
- CVD:
-
Cardiovascular diseases
- DT:
-
Decision trees
- ECG:
-
Electrocardiogram
- GBDT:
-
Gradient boosting decision trees
- LLM:
-
Modified Lewis lead
- MAX_DI:
-
Maximum value of the discriminant index
- ML:
-
Machine learning
- MLL-II:
-
Modified limb lead-II
- RMS:
-
Root mean square
- ROC:
-
Receiver operating characteristic
- SHAP:
-
SHapley additive exPlanations
- SLL-II:
-
Standard limb lead-II
- SR:
-
Sinus rhythm
- ST:
-
Sinus tachycardia
References
Gerc V, Masic I, Salihefendic N, Zildzic M (2020) Cardiovascular diseases (CVDs) in COVID-19 pandemic era. Mater Socio Medica 32:158–164. https://doi.org/10.5455/msm.2020.32.158-164
Laslett LJ, Alagona P, Clark BA et al (2012) The worldwide environment of cardiovascular disease: prevalence, diagnosis, therapy, and policy issues: a report from the American College of Cardiology. J Am Coll Cardiol 60:S1–S49. https://doi.org/10.1016/j.jacc.2012.11.002
Lux RL, Greg R (2004) New leads for P wave detection and arrhythmia classification. J Electrocardiol 37:80
Lee G, Sanders P, Kalman JM (2012) Catheter ablation of atrial arrhythmias: state of the art. Lancet 380:1509–1519. https://doi.org/10.1016/S0140-6736(12)61463-9
Saposnik G, Gladstone D, Raptis R et al (2013) Atrial fibrillation in ischemic stroke: predicting response to thrombolysis and clinical outcomes. Stroke 44:99–104. https://doi.org/10.1161/STROKEAHA.112.676551
Saglietto A, Ballatore A, Xhakupi H et al (2022) Atrial fibrillation and dementia: epidemiological insights on an undervalued association. Medicina 58:361. https://doi.org/10.3390/medicina58030361
Hart RG, Lesly A, Pearce MIA (2007) Meta-analysis: antithrombotic therapy to prevent stroke in patients who have nonvalvular atrial fibrillation. Ann Intern Med 146:857–867. https://doi.org/10.7326/0003-4819-146-12-200706190-00007
Macfarlane PW, Van Oosterom A, Pahlm O et al (2010) Comprehensive electrocardiology. Springer Verlag London Ltd, London
Nattel S, Burstein B, Dobrev D (2008) Atrial remodeling and atrial fibrillation: mechanisms and implications. Circ Arrhythm Electrophysiol 1:62–73. https://doi.org/10.1161/CIRCEP.107.754564
Rasmussen MU, Kumarathurai P, Fabricius-Bjerre A et al (2020) P-wave indices as predictors of atrial fibrillation. Ann Noninvasive Electrocardiol 25:1–9. https://doi.org/10.1111/anec.12751
Mainardi L, Leif Sörnmo SC (2006) Understanding atrial fibrillation: the signal processing contribution part II. Synth Lect Biomed Eng 1999:1–6. https://doi.org/10.1007/978-3-031-01632-5
Schläpfer J, Wellens HJ (2017) Computer-interpreted electrocardiograms: benefits and limitations. J Am Coll Cardiol 70:1183–1192. https://doi.org/10.1016/j.jacc.2017.07.723
Lee HC, Chen CY, Lee SJ et al (2022) Exploiting exercise electrocardiography to improve early diagnosis of atrial fibrillation with deep learning neural networks. Comput Biol Med. https://doi.org/10.1016/j.compbiomed.2022.105584
Simonson E (1953) Effect of moderate exercise on the electrocardiogram in healthy young and middle-aged men. J Appl Physiol 5:584–588. https://doi.org/10.1152/jappl.1953.5.10.584
Yokota M, Noda S, Koide M et al (1986) Analysis of the exercise-induced orthogonal P wave changes in normal subjects and patients with coronary artery disease. Jpn Heart J 27:443–460. https://doi.org/10.1536/ihj.27.443
Andrikopoulos GK, Dilaveris PE, Richter DJ et al (2000) Increased variance of p wave duration on the electrocardiogram distinguishes patients with idiopathic paroxysmal atrial fibrillation. Pacing Clin Electrophysiol 23:1127–1132. https://doi.org/10.1111/j.1540-8159.2000.tb00913.x
Petrenas A, Marozas V, Jaruševičius G, Sörnmo L (2015) A modified Lewis ECG lead system for ambulatory monitoring of atrial arrhythmias. J Electrocardiol 48:157–163. https://doi.org/10.1016/j.jelectrocard.2014.12.005
Jayaraman S, Gandhi U, Sangareddi V et al (2015) Unmasking of atrial repolarization waves using a simple modified limb lead system. Anatol J Cardiol 15:605–610. https://doi.org/10.5152/akd.2014.5695
Kennedy A, Finlay DD, Guldenring D et al (2016) Detecting the elusive P-wave: a new ECG lead to improve the recording of atrial activity. IEEE Trans Biomed Eng 63:243–249. https://doi.org/10.1109/TBME.2015.2450212
Venkatesh NP, Sivaraman J (2021) A study on standard and atrial lead system for improved screening of P-wave using random forest classifier. In: 2021 IEEE Bombay section signature conference IBSSC 2021. https://doi.org/10.1109/IBSSC53889.2021.9673216
Lux RL, Smith CR, Wyatt RF, Abildskov JA (1978) Limited lead selection for estimation of body surface potential maps in electrocardiography. IEEE Trans Biomed Eng BME-25:270–276. https://doi.org/10.1109/TBME.1978.326332
Simoons ML, Block P (1981) Toward the optimal lead system and optimal criteria for exercise electrocardiography. Am J Cardiol 47:1366–1374. https://doi.org/10.1016/0002-9149(81)90270-8
Finlay DD, Nugent CD, Donnelly MP et al (2006) Selection of optimal recording sites for limited lead body surface potential mapping: a sequential selection based approach. BMC Med Inform Decis Mak 6:1–9. https://doi.org/10.1186/1472-6947-6-9
Donnelly MP, Finlay DD, Nugent CD, Black ND (2008) Lead selection: old and new methods for locating the most electrocardiogram information. J Electrocardiol 41:257–263. https://doi.org/10.1016/j.jelectrocard.2008.02.004
Finlay DD, Nugent CD, Donnelly MP et al (2008) Optimal electrocardiographic lead systems: practical scenarios in smart clothing and wearable health systems. IEEE Trans Inf Technol Biomed 12:433–441. https://doi.org/10.1109/TITB.2007.896882
Kania M, Fereniec M, Janusek D et al (2009) Optimal ECG lead system for arrhythmia assessment with use of TCRT parameter. Biocybern Biomed Eng 29:73–82
Lai C, Zhou S, Trayanova NA (2021) Optimal ECG-lead selection increases generalizability of deep learning on ECG abnormality classification. Philos Trans R Soc A Math Phys Eng Sci. https://doi.org/10.1098/rsta.2020.0258
Einthoven W (1912) The different forms of the human electrocardiogram and their signification. The Lancet 179:853–861. https://doi.org/10.1016/S0140-6736(00)50560-1
Nedios S, Romero I, Gerds-Li JH et al (2014) Precordial electrode placement for optimal ECG monitoring: implications for ambulatory monitor devices and event recorders. J Electrocardiol 47:669–676. https://doi.org/10.1016/j.jelectrocard.2014.04.003
Einthoven W, Fahr G, De Waart A (1913) Über die Richtung und die manifeste Grösse der Potentialschwankungen im menschlichen Herzen und über den Einfluss der Herzlage auf die Form des Elektrokardiogramms. Pflüger’s Arch für die gesamte Physiol des Menschen und der Tiere 150:275–315
Mayuga KA, Fedorowski A, Ricci F et al (2022) Sinus tachycardia: a multidisciplinary expert focused review. Circ Arrhythm Electrophysiol 15:e007960. https://doi.org/10.1161/CIRCEP.121.007960
Williams JR (2008) The Declaration of Helsinki and public health. Bull World Health Organ 86:650–652. https://doi.org/10.2471/BLT.08.050955
Balady GJ, Arena R, Sietsema K et al (2010) Clinician’s guide to cardiopulmonary exercise testing in adults. Circulation 122:191–225. https://doi.org/10.1161/CIR.0b013e3181e52e69
Mousavi S, Afghah F, Acharya UR (2020) HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks. Comput Biol Med 127:104057. https://doi.org/10.1016/j.compbiomed.2020.104057
Pan J, Tompkins WJ (1985) A real-time QRS detection algorithm. IEEE Trans Biomed Eng 32:230–236. https://doi.org/10.1109/TBME.1985.325532
Maghawry E, Ismail R, Gharib TF (2021) An efficient approach for paroxysmal atrial fibrillation events prediction using extreme learning machine. J Intell Fuzzy Syst 40:5087–5099. https://doi.org/10.3233/JIFS-201832
Zeng C, Wei T, Zhao R et al (2003) Electrocardiographic diagnosis of left atrial enlargement in patients with mitral stenosis: the value of the P-wave area. Acta Cardiol 58:139–141. https://doi.org/10.2143/AC.58.2.2005266
Karacop E, Enhos A, Bakhshaliyev N, Ozdemir R (2021) P wave duration/P wave voltage ratio plays a promising role in the prediction of atrial fibrillation: a new player in the game. Cardiol Res Pract. https://doi.org/10.1155/2021/8876704
Mann HB, Whitney DR (1947) On a test of whether one of two random variables is stochastically larger than the other. Ann Math Stat 18:50–60
Braiek HB, Khomh F (2020) On testing machine learning programs. J Syst Softw 164:110542. https://doi.org/10.1016/j.jss.2020.110542
Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. Int Jt Conf Artif Intell 14:1137–1143
Singh D, Singh B (2020) Investigating the impact of data normalization on classification performance. Appl Soft Comput 97:105524. https://doi.org/10.1016/j.asoc.2019.105524
Erazo L, Ríos SA (2014) A benchmark on automatic obstructive sleep apnea screening algorithms in children. Procedia Comput Sci 35:739–746. https://doi.org/10.1016/j.procs.2014.08.156
Rolón RE, Larrateguy LD, Di Persia LE et al (2017) Discriminative methods based on sparse representations of pulse oximetry signals for sleep apnea–hypopnea detection. Biomed Signal Process Control 33:358–367. https://doi.org/10.1016/j.bspc.2016.12.013
Pinho A, Pombo N, Silva BMC et al (2019) Towards an accurate sleep apnea detection based on ECG signal: the quintessential of a wise feature selection. Appl Soft Comput 83:105568. https://doi.org/10.1016/j.asoc.2019.105568
Fu F, Jiang J, Shao Y, Cui B (2019) An experimental evaluation of large scale GBDT systems. Proc VLDB Endow 12:1357–1370. https://doi.org/10.14778/3342263.3342273
Prokhorenkova L, Gusev G, Vorobev A et al (2018) CatBoost: unbiased boosting with categorical features. In: Bengio S, Wallach H, Larochelle H et al (eds) Advances in neural information processing systems. Curran Associates, Inc, Red Hook
Hancock JT, Khoshgoftaar TM (2020) CatBoost for big data: an interdisciplinary review. J Big Data 7:94. https://doi.org/10.1186/s40537-020-00369-8
Curtis AB, Karki R, Hattoum A, Sharma UC (2018) Arrhythmias in patients ≥80 years of age. J Am Coll Cardiol 71:2041–2057. https://doi.org/10.1016/j.jacc.2018.03.019
Lieve KVV, Dusi V, van der Werf C et al (2020) Heart rate recovery after exercise is associated with arrhythmic events in patients with catecholaminergic polymorphic ventricular tachycardia. Circ Arrhythmia Electrophysiol 13:e007471. https://doi.org/10.1161/CIRCEP.119.007471
Aquino-Santos R, Martinez-Castro D, Edwards-Block A, Murillo-Piedrahita AF (2013) Wireless sensor networks for ambient assisted living. Sensors (Switzerland) 13:16384–16405. https://doi.org/10.3390/s131216384
Dias FM, Monteiro HLM, Cabral TW et al (2021) Arrhythmia classification from single-lead ECG signals using the inter-patient paradigm. Comput Methods Programs Biomed 202:105948. https://doi.org/10.1016/j.cmpb.2021.105948
Sepahvand M, Abdali-Mohammadi F (2022) A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillation. Inf Sci (Ny) 593:64–77. https://doi.org/10.1016/j.ins.2022.01.030
Ibrahim AA, Ridwan RL, Muhammed MM et al (2020) Comparison of the CatBoost classifier with other machine learning methods. Int J Adv Comput Sci Appl 11:738–748. https://doi.org/10.14569/IJACSA.2020.0111190
Dhananjay B, Sivaraman J (2021) Analysis and classification of heart rate using CatBoost feature ranking model. Biomed Signal Process Control 68:102610. https://doi.org/10.1016/j.bspc.2021.102610
Lundberg SM, Erion G, Chen H et al (2020) From local explanations to global understanding with explainable AI for trees. Nat Mach Intell 2:56–67. https://doi.org/10.1038/s42256-019-0138-9
Molnar C (2020) Interpretable machine learning: A guide for making black box models explainable. Available from https://christophm.github.io/interpretable-ml-book/
Dilaveris PE, Gialafos JE (2001) P-wave dispersion: a novel predictor of paroxysmal atrial fibrillation. Ann Noninvasive Electrocardiol 6:159–165. https://doi.org/10.1111/j.1542-474X.2001.tb00101.x
Magnani JW, Johnson VM, Sullivan LM et al (2011) P wave duration and risk of longitudinal atrial fibrillation in persons ≥60 years Old (from the Framingham Heart Study). Am J Cardiol 107:917-921.e1. https://doi.org/10.1016/j.amjcard.2010.10.075
Sadanaga T, Sadanaga F, Yao H, Fujishima M (2006) An evaluation of ECG leads used to assess QT prolongation. Cardiology 105:149–154. https://doi.org/10.1159/000091227
Kania M, Maniewski R, Zaczek R et al (2020) Optimal ECG lead system for exercise assessment of ischemic heart disease. J Cardiovasc Transl Res 13:758–768. https://doi.org/10.1007/s12265-019-09949-3
Chiou YA, Syu JY, Wu SY et al (2021) Electrocardiogram lead selection for intelligent screening of patients with systolic heart failure. Sci Rep 11:1–12. https://doi.org/10.1038/s41598-021-81374-6
Ruedisueli I, Ma J, Nguyen R et al (2022) Optimizing ECG lead selection for detection of prolongation of ventricular repolarization as measured by the Tpeak-end interval. Ann Noninvasive Electrocardiol. https://doi.org/10.1111/anec.12958
Acknowledgements
The authors acknowledge the support from the Ministry of Education, Government of India, to carry out this research.
Funding
The study was supported by financial grants from the Science and Engineering Research Board (SERB), Department of Science and Technology (DST), Government of India (EEQ/2019/000148).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by NPV. Conceptualization, Validation, Formal analysis, Resources, Data Curation, Writing- Review & Editing, Visualization, Supervision, Project administration, Funding acquisition are carried out by BCN, KP, RPK, JS. The first draft of the manuscript was written by NPV and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors report no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in line with the principles of the Declaration of Helsinki. Approval was granted by the Ethics Committee of National Institute of Technology Rourkela (NITR/IEC/2022/M/04; dated 09/06/2022).
Consent to participate
Informed consent was obtained from all individual participants included in the study.
Consent to publish
The authors affirm that human research participants provided informed consent for publication of the images in Figs. 3A, B, 5, 6, 7, 8.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Prasanna Venkatesh, N., Pradeep Kumar, R., Chakravarthy Neelapu, B. et al. CatBoost-based improved detection of P-wave changes in sinus rhythm and tachycardia conditions: a lead selection study. Phys Eng Sci Med 46, 925–944 (2023). https://doi.org/10.1007/s13246-023-01274-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-023-01274-z