Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Design of Post-TAVR Digital Twin Navigating Platform for Predicting Patient Complications

환자의 합병증 예측을 위한 Post-TAVR디지털 트윈 추적 관리 플랫폼 설계

  • Min Hyuk Jung (Dept. of Computer Engineering, Gachon University) ;
  • KangYoon Lee (Dept. of Computer Engineering, Gachon University)
  • Received : 2024.04.17
  • Accepted : 2024.08.16
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Aortic valve stenosis is disease caused by the calcification of the aortic valve, which is located between the left ventricle of the heart and the aorta, preventing the backflow of blood. Transcatheter Aortic Valve Replacement (TAVR) has become the standard non-surgical procedure for treating aortic stenosis. However, patients who undergo TAVR are still face the risk of complication, which calls for a systematic solution for complication prediction and management. In this study, we designed a platform that manages patient complication risks using various prediction models, and we utilized explainable AI to ensure reliable prediction models and solutions. For the implementation of this platform, digital twin technology was employed, allowing for complication prediction and monitoring based on a patient's digital twin model constructed from Real-World Data (RWD). The digital twin platform has been developed with a microservice architecture using Kubernetes, enhancing the flexibility and availability of the platform. Additionally, we propose a feedback system for continuous improvement of prediction model performance and TAVR procedures to ensure ongoing development.

대동맥판막 협착증은 심장의 좌심실과 대동맥 사이에 위치하여 혈액의 역류룰 막아주는 대동맥 판막이 석회화가 되어 제 기능을 다하지 못해 발생하는 질병으로, 경피적 대동맥판막 치환술(TAVR)은 이러한 대동맥판막 협착증을 치료하기 위한 표준적인 비수술적 시술로 자리잡고 있다. 하지만 TAVR 시술 후의 환자에게는 여전히 합병증이 발병할 위험이 있으며, 이를 예측하고 관리하기 위한 체계적인 솔루션이 필요하다. 이 연구에서는 다양한 합병증 예측 모델들을 운용하여 환자의 합병증 위험도를 관리할 수 있는 플랫폼을 설계하였으며, Explainable AI를 이용하여 신뢰가능한 예측 모델과 솔루션을 구성하였다. 본 연구에서는 이러한 플랫폼을 구현하기 위하여 디지털 트윈을 활용하였으며, 실사용 데이터(RWD)를 바탕으로 구축한 환자의 디지털 트윈 모델을 통해 합병증을 예측하고 모니터링 하는 방안을 제안한다. 본 디지털 트윈 플랫폼은 쿠버네티스를 이용하여 마이크로 서비스 아키텍처로 구현되었으며 이를 통해 플랫폼의 유연성과 가용성을 강화하였다. 또한, 지속적인 예측 모델의 성능 향상과 TAVR 시술의 개선을 위한 피드백 시스템을 구성하여 지속 발전 가능 방안을 제시한다.

Keywords

Acknowledgement

본연구는 보건복지부의 재원으로 한국보건산업진흥원의 보건의료기술연구개발사업(과제 : HI22C1651)과 한국연구재단의 기초연구사업(grant number: NRF-2022R1F1A1069069) 지원에 의하여 이루어진 것임

References

  1. Kitai T, Honda S, Okada Y, et al, "Clinical Outcomes in non-surgically managed patients with very severe versus severe aoritc stenosis," Heart, Vol. 97, Issue 24, pp. 2029-2032, 2011. https://heart.bmj.com/content/97/24/2029.short
  2. Grube, E, Sinning, J. "The "Big Five" Complications After Transcatheter Aortic Valve Replacement: Do We Still Have to Be Afraid of Them?," JACC: Cardiovascular Interventions, Vol. 12, Issue 4, pp. 362-369, Feb. 2019. https://doi.org/10.1016/j.jcin.2018.12.019
  3. Vien T.Truong MD, Daniel Beyerbach MD, et al, "Machine learning method for predicting pacemaker implantation following transcatheter aortic valve replacement," PACE, Vol. 44, 2021. https://doi.org/10.1111/pace.14163
  4. Joshua D. Aymond, Francis Benn, et al, "Epidemiology, evaluation, and management of conduction disturbances after transcatheter aortic valve replacement," Progress in Cardiovascular Diseases, Vol. 66, pp. 37-45, Jun. 2021. https://doi.org/10.1016/j.pcad.2021.06.004
  5. Huang HD, Mansour M. "Pacemaker Implantation After Transcatheter Aortic Valve Replacement: A Necessary Evil Perhaps But Are We Making Progress?," Journal of the American Heart Association, Vol. 9, May 2020. https://doi.org/10.1161/JAHA.120.016700
  6. Vincent Auffret, Rishi Puri, et al, "Conduction Disturbances After Transcatheter Aortic Valve Replacement," Circulation, Vol. 136, No. 11, Sep. 2017. https://doi.org/10.1161/CIRCULATIONAHA.117.028352
  7. Karyofillis P, Kostopoulou A, et al, "Conduction abnormalities after transcatheter aortic valve implantation," J Geriatr Cardiol, Vol. 15(1), pp. 105-112, Jan. 2018. https://doi.org/10.11909/j.issn.1671-5411.2018.01.004
  8. Sa MP, Jacquemyn X, Van den Eynde J, et al, "Impact of Paravalvular Leak on Outcomes After Transcatheter Aortic Valve Implantation: Meta-Analysis of KaplanMeier-derived Individual Patient Data," Structural Heart, Vol. 7(2), Mar. 2023. https://doi.org/10.1016/j.shj.2022.100118
  9. Cilingiroglu M, Paixao A, "PVL closure after TAVR: Yes, we can do it," CatheterizationCardiovascular Interventions, vol. 90, Issue 5, pp. 878, Nov. 1, 2017. https://doi.org/10.1002/ccd.27365
  10. Bernard Cosyns, "Paravalvular Leak Assessment After TAVR: Can You Please Ask the Echocardiographer to Get Out of the Catheterization Laboratory?," JACC Cardiovacular Interventions, Vol. 13(11), pp. 1312-1313, Jun. 2020. https://www.jacc.org/doi/full/10.1016/j.jcin.2020.03.046
  11. F. Tao, Bin Xiao, et al, "Digital Twin Modeling," Journal of Manufacturing Systems, Vol. 64, pp. 372-389, Jul. 2022. https://doi.org/10.1016/j.jmsy.2022.06.015
  12. D. -Y. Jeong et al., "Digital Twin: Technology Evolution Stages and Implementation Layers With Technology Elements," IEEE Access, Vol. 10, pp. 52609-52620, 2022. https://doi.org/10.1109/ACCESS.2022.3174220
  13. G. Blinowski, A. Ojdowska and A. Przybylek, "Monolithic vs. Microservice Architecture: A Performance and Scalability Evaluation," IEEE Access, Vol. 10, pp. 20357-20374, 2022. https://doi.org/10.1109/ACCESS.2022.3152803
  14. Florian Auer, Valentina Lenarduzzi, et al, "From monolithic systems to Microservices: An assessment framework," Information and Software Technology, Vol. 137, 2021. https://doi.org/10.1016/j.infsof.2021.106600
  15. Xu F, Uszkoreit H, "Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges," Natural Language Processing and Chinese Computing, Vol. 11839, 2019. https://doi.org/10.1007/978-3-030-32236-6_51
  16. Seunghee Lee, Suehyun Lee, et al, "Explainable Artificial Intelligence for Patient Safety: A Review of Application in Pharmacovigilance," IEEE Access, Vol. 11, pp. 50830-50840, 2024. https://doi.org/10.1109/ACCESS.2023.3271635
  17. Minje Seok, Wooseong Kim, et al, "Machine Learning for Sarcopenia Prediction in the Elderly Using Socioeconomic, Infrastructure, and Quality-of-Life Data," Healthcare, Vol. 11(21), 2881, 2023. https://doi.org/10.3390/healthcare11212881
  18. F. Tao, Q. Qinglin, "Make more Digital Twins," Nature, 573, pp. 490-491, 2019. https://doi.org/10.1038/d41586-019-02849-1