Prediction of Pulmonary Artery and Peripheral Vascular Pressure based on Echocardiography Data and Artificial Neural Network

Abbasi, Hamed; Shojaei, Shahrokh; Naderi, Nasim

doi:10.22041/ijbme.2019.98112.1421

Document Type : Full Research Paper

Authors

¹ M.Sc. Student, Biomedical Engineering Department, Central Tehran Branch, Islamic Azad University, Tehran, Iran

² Assistant Professor, Department of Medical Engineering, Central Tehran Branch, Islamic Azad University, Tehran, Iran

³ Associate Professor, Department of Cardiology and Cardiology, Shahid Rajaie Cardiology, Medical and Research Center, Tehran University of Medical Sciences, Tehran, Iran

https://doi.org/10.22041/ijbme.2019.98112.1421

Abstract

Today, in order to decide on many cardiac surgeries, and whether the patient is able to get under surgery or the time of surgery is passed, it is necessary to measure pulmonary vascular resistance and if the resistance is above a threshold, the patient is considered to be non-surgery; and sometimes, some therapies are used to reduce the resistance of the pulmonary arteries to the initial disease of the arteries, in which, in order to track down the resistance of the pulmonary vascular, a re-measurement of this parameter is required. Currently, the golden standard of this measure is the use of catheterization procedures, which are aggressive and associated with complications. The purpose of this study is to replace a non-invasive method, rather than an invasive method of cardiac catheterization, by predicting pulmonary vascular resistance based on echocardiographic data by artificial neural networks. Research was performed on 591 patients. Echocardiography was recorded for all subjects, and the echocardiographic data (mPAP, dPAP, sPAP, PCWP, CO) as the neural network input and pulmonary vascular resistance of all patients who were subjected to previous catheterization was evaluated as the output of the neural network and thus, it was obtained, the relationship between echocardiography data and PVRcath. The proposed neural network was typically learned with 75% of the data, and was tested with 25% of the data, and these ratios were modified to better learn the neural network. As a result of implementation, the mean squared error, respectively, for the learning and testing data for the proposed neural network, was 0.37 and 0.27 for the first model, 14.67 and 10.76 for the second model, and 15.82 and 9.58 for the third model.

Keywords

Main Subjects

Neural Network / Biological & Artificial Neural Network / BNN & ANN

References

[1] تشنه‌لب، محمد، شبکه‌های عصبی و کنترل‌کننده‌های عصبی پیشرفته با رویکرد شبکه‌های راف،، چاپ اول، تهران: انتشارات دانشگاه خواجه نصیرطوسی، 1394.

[2] N. Ajam, Heart Diseases Diagnoses using Artificial Neural Network. IISTE Network and Complex Systems, 5(4), 2015.

[3] Y. Sharafi, S. Setayeshi, A. Falahiazar, An Improved Model of Brain Emotional Learning Algorithm Based on Interval Knowledge. Journal of mathematics and computer science 14, 42-53, 2015.

[4] E. Choi, A. Schuetz, W.F. Stewart, and J. Sun, Using recurrent neural network models for early detection of heart failure onset. Journal of the American Medical Informatics Association, 24(2), 361-370, 2016.

[5] P. Naing, H. Kuppusamy, G. Scalia, G.S. Hillis, G.S. Playford, non- Invasive Assessment of Pulmonary Vascular Resistance in Pulmonary Hypertension: Current Knowledge and Future Direction, Heart, Lung and Circulation, 2016.

[6] K. Yasui, S. Yuda, K. Abe, A. Muranaka, M. Otsuka, H. Ohnishi, & T. Miura, Pulmonary vascular resistance estimated by Doppler echocardiography predicts mortality in patients with interstitial lung disease. Journal of cardiology, 68(4), 300-307, 2016.

[7] Y. Chaowu, X. Zhongying, J. Jinglin, L. Jinglin, L. Qiong,.et al. A feasible method for non-invasive measurement of pulmonary vascular resistance in pulmonary arterial hypertension: Combined use of transthoracic Doppler-echocardiography and cardiac magnetic resonance. Non-invasive estimation of pulmonary vascular resistance. IJC Heart & Vasculature. Cardiovascular Institute and Fuwai Hospital, Chinese Academy of Medical Sciences, Beijing 100037, China, 2015.

[8] A.E. Abbas, L.M. Franey, T. Marwick, M.T. Maeder, D.M. Kaye, A.P. Vlahos, & S.J. Lester, Noninvasive assessment of pulmonary vascular resistance by Doppler echocardiography. Journal of the American Society of Echocardiography, 26(10)2013.

[9] P. Lindqvist, S. Söderberg, M. C. Gonzalez, E. Tossavainen, M.Y. Henein, “Echocardiography based estimation of pulmonary vascular resistance in patients with pulmonary hypertension: a simultaneous Doppler echocardiography and cardiac catheterization study,” ,2011.

[10]R.R. Vanderpool, and R. Naeije, Hematocrit-corrected Pulmonary Vascular Resistance. American journal of respiratory and critical care medicine, 2018.

[11]N. Naderi, Z. Ojaghi Haghighi, A. Amin, Naghashzadeh, H. Bakhshandeh, S. Taghavi, & M. Maleki, Utility of right ventricular strain imaging in predicting pulmonary vascular resistance in patients with pulmonary hypertension. Congestive Heart Failure, 19(3), 116-122, 2013.

[12]W. Huang, R.K. Oliveira, H. Lei, D.M. Systrom, and Waxman, A.B., Pulmonary vascular resistance during exercise predicts long-term outcomes in heart failure with preserved ejection fraction. Journal of cardiac failure, 24(3), 169-176, 2018.

[13]L.R. Bekhet, Y. Wu, N. Wang, X. Geng, W.J. Zheng, F. Wang, H. Wu, H. Xu, and Zhi, D., A study of Generalizability of Recurrent Neural Network-Based Predictive Models for Heart Failure Onset Risk using a Large and Heterogeneous EHR Data set. Journal of biomedical informatics, 2018.

[14]Y. Cheng, F. Wang, P. Zhang, and J. Hu, June. Risk prediction with electronic health records: A deep learning approach. In Proceedings of the 2016 SIAM International Conference on Data Mining (pp. 432-440). Society for Industrial and Applied Mathematics, 2016.

[15]Acharya, U.R., Fujita, H., Oh, S.L., Hagiwara, Y., Tan, J.H., Adam, M. and Tan, R.S., Deep convolutional neural network for the automated diagnosis of congestive heart failure using ECG signals. Applied Intelligence, 1-12, 2018.

[16]D. Markush, R.D. Ross, R. Thomas, and S. Aggarwal, Noninvasive echocardiographic measures of pulmonary vascular resistance in children and young adults with cardiomyopathy. Journal of the American Society of Echocardiography, 2018.

[17]J, Muneuchi, Y. Ochiai, N. Masaki, S. Okada, C. Iida, Y. Sugitani, Y. Ando, and M. Watanabe, Pulmonary arterial compliance is a useful predictor of pulmonary vascular disease in congenital heart disease. Heart and vessels, 1-7, 2018.

[18]D.P. Perrin, A. Bueno, A. Rodriguez, G.R. Marx, and J. Pedro, March. Application of convolutional artificial neural networks to echocardiograms for differentiating congenital heart diseases in a pediatric population. In Medical Imaging 2017: Computer-Aided Diagnosis. International Society for Optics and Photonics, 2017.

[19]کاکوئی, امیررضا و مهدی جعفری شهباززاده، ۱۳۹۴، طبقه‌بندی اتوماتیک تومور مغزی در تصاویر MRI با استفاده از شبکه عصبی مصنوعی ANN، کنفرانس بین‌المللی پژوهش در مهندسی، علوم و تکنولوژی، استانبول، موسسه مدیران ایده پرداز پایتخت ویرا.

Iranian Journal of Biomedical Engineering

Prediction of Pulmonary Artery and Peripheral Vascular Pressure based on Echocardiography Data and Artificial Neural Network

References

References

Volume 13, Issue 2
August 2019
Pages 105-115

Prediction of Pulmonary Artery and Peripheral Vascular Pressure based on Echocardiography Data and Artificial Neural Network

References

References

Volume 13, Issue 2August 2019Pages 105-115

Volume 13, Issue 2
August 2019
Pages 105-115