Prediction of graft loss in living donor liver transplantation during the early postoperative period

Raiki Yoshimura, Naotoshi Nakamura, Takeru Matsuura, Takeo Toshima, Takasuke Fukuhara, Kazuyuki Aihara, Katsuhito Fujiu, Shingo Iwami and Tomoharu Yoshizumi

PLOS Computational Biology, 2025, vol. 21, issue 11, 1-20

Abstract: Liver transplantation is almost the only way to save patients with end-stage liver disease. Particularly, living donor liver transplantation (LDLT) has gained importance in recent years thanks to the shorter waiting times and better graft quality than with deceased donor liver transplantation (DDLT). However, some patients experience graft loss due to unexpected infections, sepsis, or immune-mediated rejection of the transplanted organ. An urgent need exists to clarify which patients experience graft loss. Several models have been proposed, but most analyze the classic DDLT, and knowledge about LDLT is lacking. In this study, we retrospectively analyzed clinical data from 748 patients who underwent LDLT. By adapting machine learning methods, we predicted early graft loss (within 180 days postoperatively) with better performance than conventional models. The model enabled us to stratify a highly heterogeneous sample of patients into five groups. By focusing on survival time, we next categorized the patients into three groups with early, intermediate, and late or no graft loss. Notably, we identified the intermediate-loss group as a distinct population similar to the early-loss population but with different survival times. Additionally, by proposing a hierarchical prediction method, we developed an approach to distinguish these populations using data up to 30 days postoperatively. Our findings will enable the early identification of individuals at risk of graft loss, particularly those in the early- and intermediate-loss groups. This will allow for appropriate patient care, such as switching to DDLT, identifying other living donors for LDLT, or preparing for re-transplantation, leading to a bottom-up improvement in transplant success rates.Author summary: Liver transplantation is crucial for treating end-stage liver disease, with living donor liver transplantation (LDLT) offering advantages like shorter waiting times and better graft quality compared to deceased donor liver transplantation (DDLT). However, graft loss remains a concern, often due to post-LDLT infection or immune-mediated rejection. To address this, we analyzed 748 LDLT cases using machine learning to predict early graft loss (within 180 days) with greater accuracy than conventional methods. Additionally, patients were stratified into five groups and further categorized into three survival-based groups with early, intermediate, or late/no graft loss. The intermediate-loss group shared characteristics with the early-loss population but had longer survival times. This hierarchical approach enables early risk identification, thereby supporting clinical decisions, including DDLT registration or re-transplant evaluation for patients at risk for early graft loss and intensified monitoring for patients at risk for intermediate graft loss.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1013734 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 13734&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1013734

DOI: 10.1371/journal.pcbi.1013734

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().