Predicting the response to cardiac resynchronization therapy (CRT) using the deep learning approach

• Autorzy: Nejadeh Mohammad , Bayat Peyman , Kheirkhah Jalal , Moladoust Hassan

Identyfikatory

DOI

10.1016/j.bbe.2021.05.002

• Języki publikacji: EN

Abstrakty

EN

Cardiac Resynchronization Therapy Defibrillator (CRT-D) is a method to improve heart rate variability and arrhythmia-related symptoms in heart failure patients. According to clinical reports, CRT is not entirely safe and risk-free like other surgery. It can reduce heart failure risks, shorten hospital stays, and enhance the patients’ quality of life. The present study aims to perform the proper selection of patients before surgery to avoid potential costs. This article focuses on the data collection of heart failure patients’ activities, the process of features effective extraction, and identifying an optimal pattern using a Deep Learning (DL) algorithm. Also, the main tasks of the proposed methods include the use of qualitative indicators for initial feature extraction, oversampling from minority class, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) hierarchical clustering, selecting features from Low error clusters, selecting samples from high error clusters, and classification using customized DL configuration. The research data collection consisted of 209 patients with 60 demographic, clinical, laboratory, ECG, and echo features. In addition, features were analyzed based on their significance in predicting CRT response status. The DL algorithm, which used dense layers and convolution for its architecture, was employed to heart failure patients optimally identify the treatment status. The proposed method predicted the response to cardiac resynchronization therapy with an error rate of 91.85% and an Area Under Curve (AUC) of 0.957 and a sensitivity of 94.22%.

Słowa kluczowe

EN

heart failure; HF; cardiac resynchronization therapy; CRT; deep learning; DL; oversampling from minority class; DBSCAN clustering

PL

niewydolność serca; HF; stymulacja serca; CRT; uczenie głębokie; DL

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 2
• Strony: 758--778
• Opis fizyczny: Bibliogr. 62 poz., rys., tab., wykr.

Twórcy

autor

Nejadeh Mohammad

• Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran

autor

Bayat Peyman

• Department of Computer Engineering, Islamic Azad University, Rasht Branch, Rasht, Iran

autor

Kheirkhah Jalal

• Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran; Department of Cardiology, Healthy Heart Research Center, School of Medicine, Guilan University of Medical Sciences, Rasht, Iran

autor

Moladoust Hassan

• Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran; Department of Medical Physics, Healthy Heart Research Center, School of Medicine, Guilan University of Medical Sciences, Rasht, Iran

Bibliografia

• [1] Adelstein EC, Althouse AD, Schwartzman D, Jain SK, Soman P, Saba S. Scar burden, not intraventricular conduction delay pattern, is associated with outcomes in ischemic cardiomyopathy patients receiving cardiac resynchronization therapy .HeartRhytm. 2018;15:1664-72.
• [2] Gold MR, Yu Y, Singh JP, Birgersdotter-Green U, Stein KM, Wold N, et al. Effect of Interventricular Electrical Delay on Atrioventricular Optimization for Cardiac Resynchronization Therapy. Circ Arrhythm Electrophysiol. 2018;11 e006055.
• [3] Baba M, Yoshida K, Hanaki Y, Yamamoto M, Shinoda Y, Takeyasu N, et al. Upgrade of cardiac resynchronization therapy by utilizing additional His-bundle pacing in patients with inotrope-dependent end-stage heart failure: a case series. Eur Heart J - Case Rep 2020;4:1–9.
• [4] Rath B, Willy K, Wolfes J, Ellermann C, Reinke F, Köbe J, et al. Predictors of response to cardiac resynchronization therapy in patients with chronic right ventricular pacing. Clin Res Cardiol 2020.
• [5] Giffard-Roisin S, Delingette H, Jackson T, Webb J, Fovargue L, Lee J, et al. Transfer learning from simulations on a reference anatomy for ECGI in personalized cardiac resynchronization therapy. IEEE Trans Biomed Eng 2018;66:343–53.
• [6] Field ME, Yu N, Wold N, Gold MR. Comparison of measures of ventricular delay on cardiac resynchronization therapy response. HeartRhythm. 2020;17:615–20.
• [7] Kalscheur MM, Kipp RT, Tattersall MC, Mei C, Buhr KA, DeMets DL, et al. Machine learning algorithm predicts cardiac resynchronization therapy outcomes: lessons from the COMPANION trial. Circulation: Arrhyth Electrophysiol 2018;11:e005499.
• [8] Wang Z, Wu Y, Zhang J. Cardiac resynchronization therapy in heart failure patients: tough road but clear future. Heart Fail Rev 2020.
• [9] Rickard J, Michtalik H, Sharma R, Berger Z, Iyoha E, Green AR, et al. Predictors of response to cardiac resynchronization therapy: a systematic review. Int J Cardiol 2016;225:345–52.
• [10] Zhu H, Zou T, Zhong Y, Yang C, Ren Y, Wang F. Prevention of non-response to cardiac resynchronization therapy: points to remember. Heart Fail Rev 2020;25:269–75.
• [11] Sus I, Vatasescu R, Siliste C, Deutsch A, Cozma D, Ciudin R, et al. Cardiac resynchronization therapy in Romania–results from the European Society of Cardiology CRT Survey II. Romanian J Cardiol 2020;30.
• [12] Peressutti D, Bai W, Jackson T, Sohal M, Rinaldi A, Rueckert D, et al. Prospective identification of CRT super responders using a motion atlas and random projection ensemble learning. Int Conf Med Image Comput Comput-Assist Intervention: Springer 2015:493–500.
• [13] Feeny AK, Rickard J, Patel D, Toro S, Trulock KM, Park CJ, et al. Machine Learning Prediction of Response to Cardiac Resynchronization Therapy: Improvement Versus Current Guidelines. Circ Arrhythm Electrophysiol. 2019;12 e007316.
• [14] Feeny AK, Rickard J, Trulock KM, Patel D, Toro S, Moennich LA, et al. Machine Learning of 12-lead Qrs Waveform Patterns to Identify Cardiac Resynchronization Therapy Patients With Differential Outcomes. Circulation. 2019;140:A10702-A.
• [15] Chao P-K, Wang C-L, Chan H-L. An intelligent classifier for prognosis of cardiac resynchronization therapy based on speckle-tracking echocardiograms. Artif Intell Med 2012;54:181–8.
• [16] Singh JP, Solomon SD, Fradley MG, Barac A, Kremer KA, Beck CA, et al. Association of Cardiac Resynchronization Therapy With Change in Left Ventricular Ejection Fraction in Patients With Chemotherapy-Induced Cardiomyopathy. JAMA 2019;322:1799–805.
• [17] Loutfi M, Nawar M, Eltahan S, Elhoda AA. Predictors of response to cardiac resynchronization therapy in chronic heart failure patients. Egypt Heart J 2016;68:227–36.
• [18] Yaghoobi Karimui R, Azadi S. Cardiac arrhythmia classification using the phase space sorted by Poincare sections. Biocybernet Biomed Eng 2017;37:690–700.
• [19] Rad MA, Baboli NT, Barzigar A, Keirkhah J, Soltanipour S, Bonakdar HR, et al. The role of the fragmented QRS complexes on a routine 12-lead ECG in predicting nonresponsiveness to cardiac resynchronization therapy. Anatolian J Cardiol 2015;15:204.
• [20] Mullens W, Auricchio A, Martens P, Witte K, Cowie MR, Delgado V, et al. Optimized implementation of cardiac resynchronization therapy: a call for action for referral and optimization of care. Eur J Heart Fail 2020;22:2349–69.
• [21] Heckman LIB, Kuiper M, Anselme F, Ziglio F, Shan N, Jung M, et al. Evaluating multisite pacing strategies in cardiac resynchronization therapy in the preclinical setting. Heart Rhythm 2020;O2(1):111–9.
• [22] van Everdingen WM, Zweerink A, Salden OAE, Cramer MJ, Doevendans PA, van Rossum AC, et al. Atrioventricular optimization in cardiac resynchronization therapy with quadripolar leads: should we optimize every pacing configuration including multi-point pacing? EP Europace. 2018;21:e11–9.
• [23] Aalen JM, Donal E, Larsen CK, Duchenne J, Lederlin M, Cvijic M, et al. Imaging predictors of response to cardiac resynchronization therapy: left ventricular work asymmetry by echocardiography and septal viability by cardiac magnetic resonance. Eur Heart J 2020;41:3813–23.
• [24] Sardu C, Paolisso P, Ducceschi V, Santamaria M, Sacra C, Massetti M, et al. Cardiac resynchronization therapy and its effects in patients with type 2 DIAbetes mellitus OPTimized in automatic vs. echo guided approach. Data from the DIAOPTA investigators. Cardiovasc Diabetol 2020;19:202.
• [25] Bereuter L, Niederhauser T, Kucera M, Loosli D, Steib I, Schildknecht M, et al. Leadless cardiac resynchronization therapy: An in vivo proof-of-concept study of wireless pacemaker synchronization. Heart Rhythm. 2019;16:936–42.
• [26] Sharma RR, Kumar A, Pachori RB, Acharya UR. Accurate automated detection of congestive heart failure using eigenvalue decomposition based features extracted from HRV signals. Biocybernet Biomed Eng 2019;39:312–27.
• [27] Kumar M, Pachori RB, Rajendra AU. Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic Wavelet transform. Biocybernet Biomed Eng 2018;38:564–73.
• [28] Tokodi M, Schwertner WR, Kovács A, Tősér Z, Staub L, Sárkány A, et al. Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: the SEMMELWEIS-CRT score. Eur Heart J 2020;41:1747–56.
• [29] Wang Y, Sharbaugh MS, Althouse AD, Mulukutla S, Saba S. Cardiac resynchronization therapy pacemakers versus defibrillators in older non-ischemic cardiomyopathy patients. Indian Pac Electrophysiol J 2019;19:4–6.
• [30] Van Veldhuisen DJ, Maass AH, Priori SG, Stolt P, Van Gelder IC, Dickstein K, et al. Implementation of device therapy (cardiac resynchronization therapy and implantable cardioverter defibrillator) for patients with heart failure in Europe: changes from 2004 to 2008. Eur J Heart Fail 2009;11:1143–51.
• [31] Zhang X, Qin Y, Zhang G, Gao W, Peng Y, Ren Q, et al. The Short-Term and Long-Term Effects of Cardiac Resynchronization Therapy in Heart Failure Patients. Cardiol Cardiovasc Res 2019;3:6.
• [32] Kisiel R, Fijorek K, Moskal P, Kukla P, Sondej T, Czarnecka D, et al. New ECG markers for predicting long-term mortality and morbidity in patients receiving cardiac resynchronization therapy. J Electrocardiol 2018;51:637–44.
• [33] Grimaldi A, Gorodeski EZ, Rickard J. Optimizing cardiac resynchronization therapy: an update on new insights and advancements. Curr Heart Fail Rep 2018;15:156–60.
• [34] Han J, Kamber M, Pei J. Data mining concepts and techniques third edition. The Morgan Kaufmann Series in Data Management Systems. 2011:1-25.
• [35] Liu Y, Zhang Y. Optimizing parameters of fuzzy c-means clustering algorithm. Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007): IEEE; 2007. p. 633-8.
• [36] Gijbels I, Hubert M. Robust and nonparametric statistical methods. Dordrecht: Springer; 2009.
• [37] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif intellig Res 2002;16:321–57.
• [38] Chang W, Liu Y, Xiao Y, Yuan X, Xu X, Zhang S, et al. A Machine-Learning-Based Prediction Method for Hypertension Outcomes Based on Medical Data. Diagnostics. 2019;9:178.
• [39] Nejadeh M, Bayat P, Kheirkhah J, Moladoust H. Evaluation of Pattern Recognition Techniques in Response to Cardiac Resynchronization Therapy (CRT). J Informat Syst Telecommun 2020;8:197–206.
• [40] Ettensperger F. Comparing supervised learning algorithms and artificial neural networks for conflict prediction: performance and applicability of deep learning in the field. Qual Quant 2020;54:567–601.
• [41] Vikram Neerugatti MR, A.Rama Mohan Reddy. Density Based Spatial Clustering Application with Noise by Varying Densities. International. J Recent Technol Eng (IJRTE). 2019;8:5886-91.
• [42] Zhang J, Liu A, Gao M, Chen X, Zhang X, Chen X. ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network. Artif Intell Med 2020;106 101856.
• [43] Yao Q, Wang R, Fan X, Liu J, Li Y. Multi-class Arrhythmia detection from 12-lead varied-length ECG using Attentionbased Time-Incremental Convolutional Neural Network. Information Fusion. 2020;53:174–82.
• [44] Rubin M, Stein O, Turko NA, Nygate Y, Roitshtain D, Karako L, et al. TOP-GAN: Stain-free cancer cell classification using deep learning with a small training set. Med Image Anal 2019;57:176–85.
• [45] Olson M, Wyner A, Berk R. Modern neural networks generalize on small data sets. Adv Neural Informat Process Syst 2018:3619–28.
• [46] Qayyum A, Qadir J, Bilal M, Al-Fuqaha A. Secure and robust machine learning for healthcare: A survey. arXiv preprint arXiv:200108103. 2020.
• [47] Geng X, Lin J, Zhao B, Kong A, Aly MMS, Chandrasekhar V. Hardware-aware softmax approximation for deep neural networks. Asian Conf Comput Vision: Springer 2018:107–22.
• [48] Kosiuk J, Krause M, Doering M, Weber A, Breithardt OA, Dinov B, et al. Outcome in patients undergoing upgrade to cardiac resynchronization therapy: predictors of Outcome after upgrade to CRT. Heart Vessels. 2020;35:104–9.
• [49] Singh AK, Mittal S, Malhotra P, Srivastava YV. Clustering Evaluation by Davies-Bouldin Index(DBI) in Cereal data using K-Means. 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC) 2020. p. 306-10.
• [50] Aha DW. Heart Disease Data Set. http://archive.ics.uci.edu/ ml/datasets/heart+disease , [Accessed Mar 2021]: The UCI Machine Learning Repository.
• [51] Arabasadi Z, Alizadehsani R, Roshanzamir M, Moosaei H, Yarifard AA. Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm. Comput Methods Programs Biomed 2017;141:19–26.
• [52] Rohila A, Sharma A. Detection of sudden cardiac death by a comparative study of heart rate variability in normal and abnormal heart conditions. Biocybern Biomed Eng 2020;40:1140–54.
• [53] Hernandez-Matamoros A, Fujita H, Escamilla-Hernandez E, Perez-Meana H, Nakano-Miyatake M. Recognition of ECG signals using Wavelet based on atomic functions. Biocybernet Biomed Eng 2020;40:803–14.
• [54] Shahid AH, Singh MP. A Novel Approach for Coronary Artery Disease Diagnosis using Hybrid Particle Swarm Optimization based Emotional Neural Network. Biocybernet Biomed Eng 2020;40:1568–85.
• [55] Jia W, Xia H, Jia L, Deng Y, Liu X. The selection of wart treatment method based on Synthetic Minority Oversampling Technique and Axiomatic Fuzzy Set theory. Biocybernet Biomed Eng 2020;40:517–26.
• [56] Ishaq A, Sadiq S, Umer M, Ullah S, Mirjalili S, Rupapara V, et al. Improving the Prediction of Heart Failure Patients’ Survival Using SMOTE and Effective Data Mining Techniques. IEEE Access 2021;9:39707–16.
• [57] Cikes M, Sanchez-Martinez S, Claggett B, Duchateau N, Piella G, Butakoff C, et al. Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy. Eur J Heart Fail 2019;21:74–85.
• [58] Chung ES, Leon AR, Tavazzi L, Sun J-P, Nihoyannopoulos P, Merlino J, et al. Results of the Predictors of Response to CRT (PROSPECT) trial. Echocardiography. 2008;2608:2616.
• [59] Thabtah F, Hammoud S, Kamalov F, Gonsalves A. Data imbalance in classification: Experimental evaluation. Inf Sci 2020;513:429–41.
• [60] Johnson JM, Khoshgoftaar TM. The Effects of Data Sampling with Deep Learning and Highly Imbalanced Big Data. Informat Syst Frontiers. 2020;22:1113–31.
• [61] Kazemi U, Boostani R. FEM-DBSCAN: An Efficient DensityBased Clustering Approach. Iran J Sci Technol, Trans Elect Eng; 2021.
• [62] Faruk N, Abdulkarim A, Emmanuel I, Folawiyo YY, Adewole KS, Mojeed HA, et al. A comprehensive survey on low-cost ECG acquisition systems: Advances on design specifications, challenges and future direction. Biocybernet Biomed Eng 202 cardiomyopathy patients receiving cardiac resynchronization therapy. HeartRhythm. 2018;15:1664–72.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).