Evaluation of Pattern Recognition Techniques in Response to Cardiac Resynchronization Therapy (CRT)
محورهای موضوعی : Data Mining
Mohammad Nejadeh
1
(Department of Computer Engineering, Islamic Azad University, Rasht Branch, Rasht, Iran)
Peyman Bayat
2
(Department of Computer Engineering, Islamic Azad University, Rasht Branch, Rasht, Iran)
Jalal Kheirkhah
3
(Department of Cardiology, Healthy Heart Research Center, School of Medicine, Guilan university of Medical Sciences, Rasht, Iran)
Hassan Moladoust
4
(Healthy Heart Research Center, School of Medicine, Guilan university of Medical Sciences, Rasht, Iran.)
کلید واژه: Cardiac resynchronization therapy, Neural Networks, Particle swarm optimization, HESHMAT_CRT dataset, Machine Learning, ,
چکیده مقاله :
Cardiac resynchronization therapy (CRT) improves cardiac function in patients with heart failure (HF), and the result of this treatment is decrease in death rate and improving quality of life for patients. This research is aimed at predicting CRT response for the prognosis of patients with heart failure under CRT. According to international instructions, in the case of approval of QRS prolongation and decrease in ejection fraction (EF), the patient is recognized as a candidate of implanting recognition device. However, regarding many intervening and effective factors, decision making can be done based on more variables. Computer-based decision-making systems especially machine learning (ML) are considered as a promising method regarding their significant background in medical prediction. Collective intelligence approaches such as particles swarm optimization (PSO) algorithm are used for determining the priorities of medical decision-making variables. This investigation was done on 209 patients and the data was collected over 12 months. In HESHMAT CRT center, 17.7% of patients did not respond to treatment. Recognizing the dominant parameters through combining machine recognition and physician’s viewpoint, and introducing back-propagation of error neural network algorithm in order to decrease classification error are the most important achievements of this research. In this research, an analytical set of individual, clinical, and laboratory variables, echocardiography, and electrocardiography (ECG) are proposed with patients’ response to CRT. Prediction of the response after CRT becomes possible by the support of a set of tools, algorithms, and variables.
Cardiac resynchronization therapy (CRT) improves cardiac function in patients with heart failure (HF), and the result of this treatment is decrease in death rate and improving quality of life for patients. This research is aimed at predicting CRT response for the prognosis of patients with heart failure under CRT. According to international instructions, in the case of approval of QRS prolongation and decrease in ejection fraction (EF), the patient is recognized as a candidate of implanting recognition device. However, regarding many intervening and effective factors, decision making can be done based on more variables. Computer-based decision-making systems especially machine learning (ML) are considered as a promising method regarding their significant background in medical prediction. Collective intelligence approaches such as particles swarm optimization (PSO) algorithm are used for determining the priorities of medical decision-making variables. This investigation was done on 209 patients and the data was collected over 12 months. In HESHMAT CRT center, 17.7% of patients did not respond to treatment. Recognizing the dominant parameters through combining machine recognition and physician’s viewpoint, and introducing back-propagation of error neural network algorithm in order to decrease classification error are the most important achievements of this research. In this research, an analytical set of individual, clinical, and laboratory variables, echocardiography, and electrocardiography (ECG) are proposed with patients’ response to CRT. Prediction of the response after CRT becomes possible by the support of a set of tools, algorithms, and variables.
[1] R. C. Deo, "Machine learning in medicine", Circulation, vol. 132, no. 20, 2015, pp. 1920-1930.
[2] H. Assodiky, I. Syarif, and T. Badriyah, "Deep Learning Algorithm for Arrhythmia Detection", International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), 2017, pp. 26-32.
[3] A. K. Flügge, K. Wasmer, S. Orwat, H. Abdul-Khaliq, P. C. Helm, U. Bauer, H. Baumgartner, and G. P. Diller, "Cardiac resynchronization therapy in congenital heart disease: Results from the German National Register for Congenital Heart Defects," International Journal of Cardiology, vol. 273, 2018, pp. 108-111.
[4] J. Rickard, A. Cheng, D. Spragg, S. Bansal, M. Niebauer, B. Baranowski, D. J. Cantillon, P. J. Tchou, R. A. Grimm, W. H. W. Tang, B. L. Wilkoff, and N. Varma, "Durability of the survival effect of cardiac resynchronization therapy by level of left ventricular functional improvement: Fate of "nonresponders"," Heart Rhythm, vol. 11, no. 3, 2014, pp. 412-416.
[5] H. X. Niu, W. Hua , F. Z. Wang , S. Zhang , K. P. Chen, and X. Chen, "Complications of cardiac resynchronization therapy in patients with congestive heart failure," Chinese Medical Journal, vol. 119, no. 6, 2006, pp. 449-453.
[6] C. Leclercq, H. Burri, A. Curnis, P. P. Delnoy, C. A. Rinaldi, J. Sperzel, K. Lee, C. Cohorn, and B. Thibault, "Rationale and design of a randomized clinical trial to assess the safety and efficacy of multipoint pacing therapy: MOre REsponse on Cardiac Resynchronization Therapy with MultiPoint Pacing (MORE-CRT MPP–PHASE II)," American Heart Journal, vol. 209, 2019, pp. 1-8.
[7] H. Huang, L. Shen, R. Zhang, F. Makedon, B. Hettleman, and J. Pearlman, "Cardiac Motion Analysis to Improve Pacing Site Selection in CRT," Academic Radiology, vol. 13, no. 9, 2006, pp. 1124–1134.
[8] M. M. Kalscheur, R. T. Kipp, M. C. Tattersall, C. Mei, K. A. Buhr, D. L. DeMets, M. E. Field, L. L. Eckhardt, and C. D. Page, "Machine Learning Algorithm Predicts Cardiac Resynchronization Therapy Outcomes: Lessons From the COMPANION Trial," Circ Arrhythm Electrophysiol, vol. 11, no. 1, 2018, pp. 1-11.
[9] S. Giffard-Roisin, H. Delingette, T. Jackson, J. Webb, L. Fovargue, J. Lee, C. A. Rinaldi, R. Razavi, N. Ayache, and M. Sermesant, "Transfer Learning From Simulations on a Reference Anatomy for ECGI in Personalized Cardiac Resynchronization Therapy," IEEE Transactions on Biomedical Engineering, vol. 66, no. 2, 2019, pp. 343-353.
[10] K. Howe, P. Gladding, N. James, C. Prabhakar, L. Dawson, A. Gavin, and T. Schlegel, "Predicting CRT Response Using Machine Learning Analysis of Pre-Implant ECG Data," Heart, Lung and Circulation, vol. 26, no. 1, 2017, pp. S25-S26.
[11] I. Kononenko, "Machine learning for medical diagnosis: history, state of the art and perspective," Artificial Intelligence in Medicine, vol. 23, no. 1, 2001, pp. 89-109.
[12] P. K. Chao, C. L. Wang, and H. L. Chan, "An intelligent classifier for prognosis of cardiac resynchronization therapy based on speckle-tracking echocardiograms," Artificial Intelligence in Medicine, vol. 54, no. 3, 2012, pp. 181-188.
[13] M. Fedorco, A. Bulava, P. Šantavý, A. Mokráček, V. Lonský, L. Dušek, and M. Táborský, "Middle-term stability of epicardial left ventricular electrodes for cardiac resynchronization therapy," Cor et Vasa, vol. 59, no. 6, 2017, pp. e530-e539.
[14] R. Zhang, S. Ma, L. Shanahan, J. Munroe, S. Horn, and S. Speedie, "Discovering and identifying New York heart association classification from electronic health records," BMC Medical Informatics and Decision Making, vol. 18, no. 2, 2018, pp. 5-13.
[15] N. M. Hawkins, M. C. Petrie, M. I. Burgess, and J. J.V. McMurray, "Selecting Patients for Cardiac Resynchronization Therapy: The Fallacy of Echocardiographic Dyssynchrony," Journal of the American College of Cardiology, vol. 53, no. 21, 2009, pp. 1944-1959.
[16] J. Rickard, H. Michtalik, R. Sharma, Z. Berger, E. Iyoha, A. R. Green, N. Haq, and K. A. Robinson, "Predictors of response to cardiac resynchronization therapy: a systematic review," International Journal of Cardiology, vol. 225, 2016, pp. 345-352.
[17] M. Tokodi, W. Schwertner, P. Perge, A. Kosztin, B. Lakatos, S. Shrestha, A. Kovacs, and B. Merkely, "Unsupervised machine learning algorithm to identify high and low risk patients following crt implantation," Journal of the American College of Cardiology, vol. 71, no. 11, 2018, pp. 947-948.
[18] M. Loutfi, M. Nawar, S. Eltahan, and A. A. Elhoda, "Predictors of response to cardiac resynchronization therapy in chronic heart failure patients," The Egyptian Heart Journal, vol. 68, no. 4, 2016, pp. 227-236.
[19] A. Grimaldi, E. Z. Gorodeski, and J. Rickard, "Optimizing Cardiac Resynchronization Therapy: an Update on New Insights and Advancements," Current Heart Failure Reports, vol. 15, no. 3, 2018, pp. 156-160.
[20] O. Adegbala, O. Olagoke, A. Adejumo, E. Akintoye, A. Oluwole, P. Alebna, K. Williams, R. Lieberman, and L. Afonso, "Incidence and outcomes of cardiac tamponade in patients undergoing cardiac resynchronization therapy," International journal of cardiology, vol. 272, 2018, pp. 137-141.
[21] C. J. Plummer, C. M. Frank, Z. Bári, Y. S. Al Hebaishi, R. N. Klepfer, R. W. Stadler, S. Ghosh, S. Liu, and S. Mittal, "A novel algorithm increases the delivery of effective cardiac resynchronization therapy during atrial fibrillation: The CRTee randomized crossover trial," Heart Rhythm, vol. 15, no. 3, 2018, pp. 369-375.
[22] E. Thomas, D. Toth, T. Kurzendorfer, K. Rhode, and P. Mountney, "Mechanical Activation Computation from Fluoroscopy for Guided Cardiac Resynchronization Therapy," in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018, pp. 592-595.
[23] D. J. van Veldhuisen, A. H. Maass, S. G. Priori, P. Stolt, I. C. van Gelder, K. Dickstein, and K. Swedberg, "Implementation of device therapy (cardiac resynchronization therapy and implantable cardioverter defibrillator) for patients with heart failure in Europe: changes from 2004 to 2008," European Journal of Heart Failure, vol. 11, no. 12, 2009, pp. 1143-1151.
[24] G. Boriani, M. Ziacchi, M. Nesti, A. Battista, F. Placentino, V. L. Malavasi, I. Diemberger, and L. Padeletti, "Cardiac resynchronization therapy: How did consensus guidelines from Europe and the United States evolve in the last 15 years?," International journal of cardiology, vol. 261, 2018, pp. 119-129.
[25] J. Gorcsan, C. P. Anderson, B. Tayal, M. Sugahara, J. Walmsley, R. C. Starling, and J. Lumens, "Systolic Stretch Characterizes the Electromechanical Substrate Responsive to Cardiac Resynchronization Therapy," JACC: Cardiovascular Imaging, vol. 12, no. 9, 2018, pp. 1741-1752.
[26] M. A. Baturova, V. Kutyifa, S. McNitt, B. Polonsky, S. Solomon, J. Carlson, W. Zareba, and P. G. Platonov, "Usefulness of Electrocardiographic Left Atrial Abnormality to Predict Response to Cardiac Resynchronization Therapy in Patients With Mild Heart Failure and Left Bundle Branch Block," The American Journal of Cardiology, vol. 122, no. 2, 2018, pp. 268-274.
[27] D. Peressutti, W. Bai, T. Jackson, M. Sohal, A. Rinaldi, D. Rueckert, and A. King, "Prospective Identification of CRT Super Responders Using a Motion Atlas and Random Projection Ensemble Learning," in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, vol. 9351, pp. 493-500.
[28] S. Shanmuganathan, "Artificial Neural Network Modelling: An Introduction," in Studies in Computational Intelligence, vol. 628, 2016, pp. 1-14.
[29] A. Dongoran, S. Rahmadani, M. Zarlis, and S. Zakarias, "Feature weighting using particle swarm optimization for learning vector quantization classifier," in 2nd International Conference on Computing and Applied Informatics, 2017 vol.978, pp.1-6.
[30] D. Weber, M. Koller, D. Theuns, S. Yap, M. Kühne, C. Sticherling, T. Reichlin, T. Szili-Torok, S. Osswald, and B. Schaer, "Predicting defibrillator benefit in patients with cardiac resynchronization therapy: A competing risk study," Heart Rhythm, vol. 16, no. 7, 2019, pp. 1057-1064.
[31] F. Leyva, A. Zegard, O. N Okafor, J. de Bono, D. McNulty, A. Ahmed, H. J Marshall, D. Ray, and T. Qiu, "Survival after cardiac resynchronization therapy: results from 50 084 implantations," EP Europace, vol. 21, no. 5, 2019, pp. 754–762.
