Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT Registry

Optimizing lung transplant candidate selection is crucial for maximizing resource efficiency and improving patient outcomes. Using data from the International Society for Heart and Lung Transplantation (ISHLT) registry (29,364 patients), we developed a deep learning model to predict 1-year survival...

Full description

Saved in:
Bibliographic Details
Main Authors: Hye Ju Yeo, Dasom Noh, Eunjeong Son, Sunyoung Kwon, Woo Hyun Cho
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Transplant International
Subjects:
Online Access:https://www.frontierspartnerships.org/articles/10.3389/ti.2025.14121/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706238291476480
author Hye Ju Yeo
Hye Ju Yeo
Dasom Noh
Eunjeong Son
Eunjeong Son
Sunyoung Kwon
Sunyoung Kwon
Sunyoung Kwon
Woo Hyun Cho
Woo Hyun Cho
author_facet Hye Ju Yeo
Hye Ju Yeo
Dasom Noh
Eunjeong Son
Eunjeong Son
Sunyoung Kwon
Sunyoung Kwon
Sunyoung Kwon
Woo Hyun Cho
Woo Hyun Cho
author_sort Hye Ju Yeo
collection DOAJ
description Optimizing lung transplant candidate selection is crucial for maximizing resource efficiency and improving patient outcomes. Using data from the International Society for Heart and Lung Transplantation (ISHLT) registry (29,364 patients), we developed a deep learning model to predict 1-year survival after lung transplantation. Initially, 25 pretransplant factors were identified, and their importance was assessed using SHapley Additive exPlanations values. We refined the model by selecting the top 10 most influential factors and compared its performance with the original model. Additionally, we conducted external validation using an independent in-house dataset. Among the 29,364 patients, 4,729 (16.1%) died within 1 year, while 24,635 survived. The Gradient Boosting Machine (GBM) model achieved the highest performance (AUC: 0.958, accuracy: 0.949). Notably, the streamlined model using only the top 10 factors maintained identical performance (AUC: 0.958, accuracy: 0.949). The in-house dataset used for external validation showed significant compositional differences compared to the ISHLT dataset. Despite these differences, the GBM model performed well (AUC: 0.852, accuracy: 0.764). Notably, the Multilayer Perceptron model demonstrated superior generalization with an AUC of 0.911 and accuracy of 0.870. Our machine learning-based approach effectively predicts 1-year mortality in lung transplant recipients using a minimal set of pretransplant factors.
format Article
id doaj-art-783419f6dca64e5ba2a65e0f0e744895
institution DOAJ
issn 1432-2277
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Transplant International
spelling doaj-art-783419f6dca64e5ba2a65e0f0e7448952025-08-20T03:16:15ZengFrontiers Media S.A.Transplant International1432-22772025-06-013810.3389/ti.2025.1412114121Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT RegistryHye Ju Yeo0Hye Ju Yeo1Dasom Noh2Eunjeong Son3Eunjeong Son4Sunyoung Kwon5Sunyoung Kwon6Sunyoung Kwon7Woo Hyun Cho8Woo Hyun Cho9Transplant Research Center, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Yangsan, Republic of KoreaDepartment of Internal Medicine, School of Medicine, Pusan National University, Busan, Republic of KoreaDepartment of Information Convergence Engineering, Pusan National University, Yangsan, Republic of KoreaTransplant Research Center, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Yangsan, Republic of KoreaDepartment of Internal Medicine, School of Medicine, Pusan National University, Busan, Republic of KoreaDepartment of Information Convergence Engineering, Pusan National University, Yangsan, Republic of KoreaSchool of Biomedical Convergence Engineering, Pusan National University, Yangsan, Republic of KoreaCenter for Artificial Intelligence Research, Pusan National University, Busan, Republic of KoreaTransplant Research Center, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, Yangsan, Republic of KoreaDepartment of Internal Medicine, School of Medicine, Pusan National University, Busan, Republic of KoreaOptimizing lung transplant candidate selection is crucial for maximizing resource efficiency and improving patient outcomes. Using data from the International Society for Heart and Lung Transplantation (ISHLT) registry (29,364 patients), we developed a deep learning model to predict 1-year survival after lung transplantation. Initially, 25 pretransplant factors were identified, and their importance was assessed using SHapley Additive exPlanations values. We refined the model by selecting the top 10 most influential factors and compared its performance with the original model. Additionally, we conducted external validation using an independent in-house dataset. Among the 29,364 patients, 4,729 (16.1%) died within 1 year, while 24,635 survived. The Gradient Boosting Machine (GBM) model achieved the highest performance (AUC: 0.958, accuracy: 0.949). Notably, the streamlined model using only the top 10 factors maintained identical performance (AUC: 0.958, accuracy: 0.949). The in-house dataset used for external validation showed significant compositional differences compared to the ISHLT dataset. Despite these differences, the GBM model performed well (AUC: 0.852, accuracy: 0.764). Notably, the Multilayer Perceptron model demonstrated superior generalization with an AUC of 0.911 and accuracy of 0.870. Our machine learning-based approach effectively predicts 1-year mortality in lung transplant recipients using a minimal set of pretransplant factors.https://www.frontierspartnerships.org/articles/10.3389/ti.2025.14121/fulllung transplantationmortalitymachine learningrisk factorsprediction model
spellingShingle Hye Ju Yeo
Hye Ju Yeo
Dasom Noh
Eunjeong Son
Eunjeong Son
Sunyoung Kwon
Sunyoung Kwon
Sunyoung Kwon
Woo Hyun Cho
Woo Hyun Cho
Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT Registry
Transplant International
lung transplantation
mortality
machine learning
risk factors
prediction model
title Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT Registry
title_full Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT Registry
title_fullStr Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT Registry
title_full_unstemmed Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT Registry
title_short Machine Learning for 1-Year Mortality Prediction in Lung Transplant Recipients: ISHLT Registry
title_sort machine learning for 1 year mortality prediction in lung transplant recipients ishlt registry
topic lung transplantation
mortality
machine learning
risk factors
prediction model
url https://www.frontierspartnerships.org/articles/10.3389/ti.2025.14121/full
work_keys_str_mv AT hyejuyeo machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT hyejuyeo machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT dasomnoh machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT eunjeongson machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT eunjeongson machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT sunyoungkwon machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT sunyoungkwon machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT sunyoungkwon machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT woohyuncho machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry
AT woohyuncho machinelearningfor1yearmortalitypredictioninlungtransplantrecipientsishltregistry