Predicting Primary Graft Dysfunction in Lung Transplantation: Machine Learning-Guided Biomarker Discovery.

Autor:	Nord D; Division of Pulmonary Medicine, University of Florida, Gainesville, FL., Brunson JC; Laboratory for Systems Medicine, University of Florida, Gainesville, FL., Langerude L; Division of Pulmonary Medicine, University of Florida, Gainesville, FL., Moussa H; Division of Pulmonary Medicine, University of Florida, Gainesville, FL., Gill B; Division of Pulmonary Medicine, University of Florida, Gainesville, FL., Machuca T; Department of Surgery, University of Miami, Miami, FL., Rackauskas M; Department of Surgery, University of Florida, Gainesville, FL., Sharma A; Department of Surgery, University of Florida, Gainesville, FL., Lin C; Department of Medicine, University of California San Diego, San Diego, CA., Emtiazjoo A; Division of Pulmonary Medicine, University of Florida, Gainesville, FL., Atkinson C; Department of Surgery, Northwestern University, Chicago, IL.
Jazyk:	angličtina
Zdroj:	BioRxiv : the preprint server for biology [bioRxiv] 2024 Sep 23. Date of Electronic Publication: 2024 Sep 23.
DOI:	10.1101/2024.05.24.595368
Abstrakt:	Background –: There is an urgent need to better understand the pathophysiology of primary graft dysfunction (PGD) so that point-of-care methods can be developed to predict those at risk. Here we utilize a multiplex multivariable approach to define cytokine, chemokines, and growth factors in patient-matched biospecimens from multiple biological sites to identify factors predictive of PGD. Methods –: Biospecimens were collected from patients undergoing bilateral LTx from three distinct sites: donor lung perfusate, post-transplant bronchoalveolar lavage (BAL) fluid (2h), and plasma (2h and 24h). A 71-multiplex panel was performed on each biospecimen. Cross-validated logistic regression (LR) and random forest (RF) machine learning models were used to determine whether analytes in each site or from combination of sites, with or without clinical data, could discriminate between PGD grade 0 ( n = 9) and 3 ( n = 8). Results –: Using optimal AUROC, BAL fluid at 2h was the most predictive of PGD (LR, 0.825; RF, 0.919), followed by multi-timepoint plasma (LR, 0.841; RF, 0.653), then perfusate (LR, 0.565; RF, 0.448). Combined clinical, BAL, and plasma data yielded strongest performance (LR, 1.000; RF, 1.000). Using a LASSO of the predictors obtained using LR, we selected IL-1RA, BCA-1, and Fractalkine, as most predictive of severe PGD. Conclusions –: BAL samples collected 2h post-transplant were the strongest predictors of severe PGD. Our machine learning approach not only identified novel cytokines not previously associated with PGD, but identified analytes that could be used as a point-of-care cytokine panel aimed at identifying those at risk for developing severe PGD.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu