Development of a Machine Learning-Powered Optimized Lung Allocation System for Maximum Benefits in Lung Transplantation: A Korean National Data

Overview

Journal J Korean Med Sci

Specialty General Medicine

Date 2025 Feb 25

PMID 39995255

Authors

Mihyang Ha

Woo Hyun Cho

Min Wook So

Daesup Lee

Yun Hak Kim

Hye Ju Yeo

Affiliations

Soon will be listed here.

Abstract

Background: An ideal lung allocation system should reduce waiting list deaths, improve transplant survival, and ensure equitable organ allocation. This study aimed to develop a novel lung allocation score (LAS) system, the MaxBenefit LAS, to maximize transplant benefits.

Methods: This study retrospectively analyzed data from the Korean Network for Organ Sharing database, including 1,599 lung transplant candidates between September 2009 and December 2020. We developed the MaxBenefit LAS, combining a waitlist mortality model and a post-transplant survival model using elastic-net Cox regression, was assessed using area under the curve (AUC) values and Uno's C-index. Its performance was compared to the US LAS in an independent cohort.

Results: The waitlist mortality model showed strong predictive performance with AUC values of 0.834 and 0.818 in the training and validation cohorts, respectively. The post-transplant survival model also demonstrated good predictive ability (AUC: 0.708 and 0.685). The MaxBenefit LAS effectively stratified patients by risk, with higher scores correlating with increased waitlist mortality and decreased post-transplant mortality. The MaxBenefit LAS outperformed the conventional LAS in predicting waitlist death and identifying candidates with higher transplant benefits.

Conclusion: The MaxBenefit LAS offers a promising approach to optimizing lung allocation by balancing the urgency of candidates with their likelihood of survival post-transplant. This novel system has the potential to improve outcomes for lung transplant recipients and reduce waitlist mortality, providing a more equitable allocation of donor lungs.

References

Yu W, Choi S, Yeo H, Oh D, Lim S, Kim Y . Evaluation of the Current Urgency-Based Lung Allocation System in Korea with Simulation of the Eurotransplant Lung Allocation Score. Yonsei Med J. 2024; 65(8):463-471. PMC: 11284304. DOI: 10.3349/ymj.2023.0532. View

Hoffman T, Hemke A, Zanen P, Luijk B, Hoek R, Verschuuren E . Waiting List Dynamics and Lung Transplantation Outcomes After Introduction of the Lung Allocation Score in The Netherlands. Transplant Direct. 2021; 7(10):e760. PMC: 8425829. DOI: 10.1097/TXD.0000000000001205. View

Gottlieb J, Greer M, Sommerwerck U, Deuse T, Witt C, Schramm R . Introduction of the lung allocation score in Germany. Am J Transplant. 2014; 14(6):1318-27. DOI: 10.1111/ajt.12752. View

Jang J, Kim D, Son B, Park J, So M, Lee D . Analysis of the waitlist performance and post-transplant outcomes of lung transplant in elderly recipients in Korea: A nationwide cohort study. Clin Transplant. 2024; 38(9):e15299. DOI: 10.1111/ctr.15299. View

Yeo H . Allocation of Donor Lungs in Korea. J Chest Surg. 2022; 55(4):274-276. PMC: 9358154. DOI: 10.5090/jcs.22.047. View

Yeo H, Oh D, Yu W, Choi S, Jeon K, Ha M . Outcomes of Patients on the Lung Transplantation Waitlist in Korea: A Korean Network for Organ Sharing Data Analysis. J Korean Med Sci. 2022; 37(41):e294. PMC: 9592937. DOI: 10.3346/jkms.2022.37.e294. View

Yoon J, Zame W, Banerjee A, Cadeiras M, Alaa A, van der Schaar M . Personalized survival predictions via Trees of Predictors: An application to cardiac transplantation. PLoS One. 2018; 13(3):e0194985. PMC: 5874060. DOI: 10.1371/journal.pone.0194985. View

Takahashi S, Garrity E . The impact of the lung allocation score. Semin Respir Crit Care Med. 2010; 31(2):108-14. DOI: 10.1055/s-0030-1249107. View

Smits J, Nossent G, Evrard P, Lang G, Knoop C, Kwakkel-Van Erp J . Lung allocation score: the Eurotransplant model versus the revised US model - a cross-sectional study. Transpl Int. 2018; 31(8):930-937. DOI: 10.1111/tri.13262. View

10.

Gries C, Rue T, Heagerty P, Edelman J, Mulligan M, Goss C . Development of a predictive model for long-term survival after lung transplantation and implications for the lung allocation score. J Heart Lung Transplant. 2010; 29(7):731-8. PMC: 4046258. DOI: 10.1016/j.healun.2010.02.007. View

11.

Kwon E, Ha M, Jang J, Kim Y . Identification and Complete Validation of Prognostic Gene Signatures for Human Papillomavirus-Associated Cancers: Integrated Approach Covering Different Anatomical Locations. J Virol. 2020; 95(6). PMC: 8094965. DOI: 10.1128/JVI.02354-20. View

12.

Aung M, Yu Y, Ferguson K, Cantonwine D, Zeng L, McElrath T . Prediction and associations of preterm birth and its subtypes with eicosanoid enzymatic pathways and inflammatory markers. Sci Rep. 2019; 9(1):17049. PMC: 6863859. DOI: 10.1038/s41598-019-53448-z. View

13.

Yeo H, Yoon S, Lee S, Jeon D, Kim Y, Cho W . Current Status and Future of Lung Donation in Korea. J Korean Med Sci. 2017; 32(12):1953-1958. PMC: 5680493. DOI: 10.3346/jkms.2017.32.12.1953. View

14.

Parker W, Dussault N, Jablonski R, Garrity E, Churpek M . Assessing the accuracy of the lung allocation score. J Heart Lung Transplant. 2021; 41(2):217-225. PMC: 8799497. DOI: 10.1016/j.healun.2021.10.015. View

15.

Brahmbhatt J, Hee Wai T, Goss C, Lease E, Merlo C, Kapnadak S . The lung allocation score and other available models lack predictive accuracy for post-lung transplant survival. J Heart Lung Transplant. 2022; 41(8):1063-1074. PMC: 9329266. DOI: 10.1016/j.healun.2022.05.008. View

16.

Liu V, Zamora M, Dhillon G, Weill D . Increasing lung allocation scores predict worsened survival among lung transplant recipients. Am J Transplant. 2010; 10(4):915-920. PMC: 2860663. DOI: 10.1111/j.1600-6143.2009.03003.x. View

17.

Lim S, Tan S, Lim W, Lim C . An extracellular matrix-related prognostic and predictive indicator for early-stage non-small cell lung cancer. Nat Commun. 2017; 8(1):1734. PMC: 5700969. DOI: 10.1038/s41467-017-01430-6. View

18.

Lee S, Yoo K, An J, Oh Y, Lim C, Kim Y . Factors affecting mortality during the waiting time for kidney transplantation: A nationwide population-based cohort study using the Korean Network for Organ Sharing (KONOS) database. PLoS One. 2019; 14(4):e0212748. PMC: 6461220. DOI: 10.1371/journal.pone.0212748. View

19.

Merlo C, Weiss E, Orens J, Borja M, Diener-West M, Conte J . Impact of U.S. Lung Allocation Score on survival after lung transplantation. J Heart Lung Transplant. 2009; 28(8):769-75. DOI: 10.1016/j.healun.2009.04.024. View

20.

Medved D, Nugues P, Nilsson J . Simulating the Outcome of Heart Allocation Policies Using Deep Neural Networks. Annu Int Conf IEEE Eng Med Biol Soc. 2018; 2018:6141-6144. DOI: 10.1109/EMBC.2018.8513637. View