Developing approaches to incorporate donor-lung computed tomography images into machine learning models to predict severe primary graft dysfunction after lung transplantation

Primary graft dysfunction (PGD) is a common complication after lung transplantation associated with poor outcomes. Although risk factors have been identified, the complex interactions between clinical variables affecting PGD risk are not well understood, which can complicate decisions about donor-lung acceptance. Previously, we developed a machine learning model to predict grade 3 PGD using donor and recipient electronic health record data, but it lacked granular information from donor-lung computed tomography (CT) scans, which are routinely assessed during offer review. In this study, we used a gated approach to determine optimal methods for analyzing donor-lung CT scans among patients receiving first-time, bilateral lung transplants at a single center over 10 years. We assessed 4 computer vision approaches and fused the best with electronic health record data at 3 points in the machine learning process. A total of 160 patients had donor-lung CT scans for analysis. The best imaging-only approach employed a 3D ResNet model, yielding median (interquartile range) areas under the receiver operating characteristic and precision-recall curves of 0.63 (0.49-0.72) and 0.48 (0.35-0.6), respectively. Combining imaging with clinical data using late fusion provided the highest performance, with median areas under the receiver operating characteristic and precision-recall curves of 0.74 (0.59-0.85) and 0.61 (0.47-0.72), respectively.

Authors

Institutions

Publication Details

Journal
American Journal of Transplantation
Published
2025-02-07
DOI
https://doi.org/10.1016/j.ajt.2025.01.039
Citations
10
Primary Topic
Transplantation: Methods and Outcomes
Type
article
Field-Weighted Citation Impact
20.06
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Developing approaches to incorporate donor-lung computed tomography images into machine learning models to predict severe primary graft dysfunction after lung transplantation

Aristeidis Sotiras, Andrew P. Michelson, Ruben G. Nava, Hao Lü et al.
10 citations
American Journal of Transplantation
Transplantation: Methods and Outcomes
20.06
article

Developing approaches to incorporate donor-lung computed tomography images into machine learning models to predict severe primary graft dysfunction after lung transplantation

Aristeidis Sotiras, Andrew P. Michelson, Ruben G. Nava, Hao Lü, Muhammad Khalid Khan Niazi, Laura Halverson, Albert M. Lai, Daniel Kreisel, Inez Y. Oh, Derek E. Byers, Philip Payne, Metin N. Gürcan, Rodrigo Vazquez Guillamet, Ramsey R. Hachem, Andrew E. Gelman, Varun Puri, Sayantan Kumar, Chad A. Witt, W. F. Mader, Yixuan Luo, Aditi Gupta
article en
10 citations

Abstract

Primary graft dysfunction (PGD) is a common complication after lung transplantation associated with poor outcomes. Although risk factors have been identified, the complex interactions between clinical variables affecting PGD risk are not well understood, which can complicate decisions about donor-lung acceptance. Previously, we developed a machine learning model to predict grade 3 PGD using donor and recipient electronic health record data, but it lacked granular information from donor-lung computed tomography (CT) scans, which are routinely assessed during offer review. In this study, we used a gated approach to determine optimal methods for analyzing donor-lung CT scans among patients receiving first-time, bilateral lung transplants at a single center over 10 years. We assessed 4 computer vision approaches and fused the best with electronic health record data at 3 points in the machine learning process. A total of 160 patients had donor-lung CT scans for analysis. The best imaging-only approach employed a 3D ResNet model, yielding median (interquartile range) areas under the receiver operating characteristic and precision-recall curves of 0.63 (0.49-0.72) and 0.48 (0.35-0.6), respectively. Combining imaging with clinical data using late fusion provided the highest performance, with median areas under the receiver operating characteristic and precision-recall curves of 0.74 (0.59-0.85) and 0.61 (0.47-0.72), respectively.

American Journal of TransplantationVol. 25(6)
Washington University in St. Louis (US), University of Utah (US), University of Utah Hospital (US), University of Utah Health Care (US), Wake Forest University (US), The Ohio State University (US)
Openalex Percentile: Top 0%
Transplantation: Methods and Outcomes
20.06
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.