Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of the Impact of Reflected Waves on Deep Neural Network-Based Heartbeat Detection for Pulsatile Extracorporeal Membrane Oxygenator Control

반사파가 박동형 체외막산화기 제어에 사용되는 심층신경망의 심장 박동 감지에 미치는 영향 분석

  • Seo Jun Yoon (Dept. of Mechanical, Biomedical & Mechatronics Eng., Kangwon National University) ;
  • Hyun Woo Jang (Dept. of Smart Health Science and Technology, Kangwon National Univerisity) ;
  • Seong Wook Choi (Dept. of Mechanical, Biomedical & Mechatronics Eng., Kangwon National University)
  • 윤서준 (강원대학교 기계의용메카트로닉스공학과) ;
  • 장현우 (강원대학교 스마트헬스과학기술융합학과) ;
  • 최성욱 (강원대학교 기계의용메카트로닉스공학과)
  • Received : 2024.05.14
  • Accepted : 2024.06.17
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

It is necessary to develop a pulsatile Extracorporeal Membrane Oxygenator (p-ECMO) with counter-pulsation control(CPC), which ejects blood during the diastolic phase of the heart rather than the systolic phase, due to the known issues with conventional ECMO causing fatal complications such as ventricular dilation and pulmonary edema. A promising method to simultaneously detect the pulsations of the heart and p-ECMO is to analyze blood pressure waveforms using deep neural network technology(DNN). However, the accurate detection of cardiac rhythms by DNNs is challenging due to various noises such as pulsations from p-ECMO, reflected waves in the vessels, and other dynamic noises. This study aims to evaluate the accuracy of DNNs developed for CPC in p-ECMO, using human-like blood pressure waveforms reproduced in an in-vitro experiment. Especially, an experimental setup that reproduces reflected waves commonly observed in actual patients was developed, and the impact of these waves on DNN judgments was assessed using a multiple DNN (m-DNN) that provides accurate determinations along with a separate index for heartbeat recognition ability. In the experimental setup inducing reflected waves, it was observed that the shape of the blood pressure waveform became increasingly complex, which coincided with an increase in harmonic components, as evident from the Fast Fourier Transform results of the blood pressure wave. It was observed that the recognition score (RS) of DNNs decreased in blood pressure waveforms with significant harmonic components, separate from the frequency components caused by the heart and p-ECMO. This study demonstrated that each DNN trained on blood pressure waveforms without reflected waves showed low RS when faced with waveforms containing reflected waves. However, the accuracy of the final results from the m-DNN remained high even in the presence of reflected waves.

Keywords

Acknowledgement

본 연구는 2024년도 중소벤처기업부의 기술개발사업 과제의 지원을 받아 수행하였음[1425177252].

References

  1. Gibbon Jr, John H. The development of the heart-lung apparatus. The American Journal of Surgery 1978;135(5): 608-619.
  2. Acharya D, et al. Extracorporeal membrane oxygenation in myocardial infarction complicated by cardiogenic shock: analysis of the ELSO registry. Journal of the American College of Cardiology 2020;76(8):1001-1002.
  3. Li Y, et al. Effect of an intra-aortic balloon pump with venoarterial extracorporeal membrane oxygenation on mortality of patients with cardiogenic shock: a systematic review and meta-analysis. European Journal of Cardio-Thoracic Surgery 2019;55(3):395-404.
  4. Yoo CY, Kang SM, Choi SW. Preload control of the increased outflow of a dual pulsatile extracorporeal membrane oxygenator. Journal of Mechanical Science and Technology 2022;36(7):3767-3772.
  5. Mynard J. P, et al. Measurement, analysis and interpretation of pressure/flow waves in blood vessels. Frontiers in Physiology 2020;11:1085.
  6. Burkhoff D, Sayer G, Doshi D, Uriel N. Hemodynamics of mechanical circulatory support. Journal of the American College of Cardiology 2015;66(23):2663-2674.
  7. Trost J. C, Hillis L. D. Intra-aortic balloon counterpulsation. The American journal of cardiology 2006;97(9):1391-1398.
  8. Jang H, Yoo C.Y., Kang S.M., Choi S. Neural Network-Driven Counter-Pulsation in Pulsatile Extracorporeal Membrane Oxygenator (ECMO): Enhancing Real-time Pulse Discrimination and Control Efficiency. unpublished manuscript. Retrieved from https://doi.org/10.21203/rs.3.rs-4203221/v1
  9. London G. M, Guerin A. P. Influence of arterial pulse and reflected waves on blood pressure and cardiac function. American heart journal 1999;138(3):220-224.
  10. Choi SW. Estimation of blood pressure diagnostic methods by using the four elements blood pressure model simulating aortic wave reflection.Journal of Biomedical Engineering Research 2015;36(5):183-190.
  11. Kim JY, Kang SM, Choi SW. Application of a phase-locked loop counterpulsation control algorithm to a pneumatic pulsatile VAD. Journal of Mechanical Science and Technology 2019;33:3673-3678.
  12. Her K, Kim JY, Lim KM, Choi SW. Windkessel model of hemodynamic state supported by a pulsatile ventricular assist device in premature ventricle contraction. Biomedical engineering online 2018;17:1-13.
  13. Xu KW, et al. Mock circulatory loop applications for testing cardiovascular assist devices and in vitro studies. Frontiers in Physiology 2023;14:1175919.