Dataset Information

Pretransplant prediction of posttransplant survival for liver recipients with benign end-stage liver diseases: a nonlinear model.

ABSTRACT:

Background

The scarcity of grafts available necessitates a system that considers expected posttransplant survival, in addition to pretransplant mortality as estimated by the MELD. So far, however, conventional linear techniques have failed to achieve sufficient accuracy in posttransplant outcome prediction. In this study, we aim to develop a pretransplant predictive model for liver recipients' survival with benign end-stage liver diseases (BESLD) by a nonlinear method based on pretransplant characteristics, and compare its performance with a BESLD-specific prognostic model (MELD) and a general-illness severity model (the sequential organ failure assessment score, or SOFA score).

Methodology/principal findings

With retrospectively collected data on 360 recipients receiving deceased-donor transplantation for BESLD between February 1999 and August 2009 in the west China hospital of Sichuan university, we developed a multi-layer perceptron (MLP) network to predict one-year and two-year survival probability after transplantation. The performances of the MLP, SOFA, and MELD were assessed by measuring both calibration ability and discriminative power, with Hosmer-Lemeshow test and receiver operating characteristic analysis, respectively. By the forward stepwise selection, donor age and BMI; serum concentration of HB, Crea, ALB, TB, ALT, INR, Na(+); presence of pretransplant diabetes; dialysis prior to transplantation, and microbiologically proven sepsis were identified to be the optimal input features. The MLP, employing 18 input neurons and 12 hidden neurons, yielded high predictive accuracy, with c-statistic of 0.91 (P<0.001) in one-year and 0.88 (P<0.001) in two-year prediction. The performances of SOFA and MELD were fairly poor in prognostic assessment, with c-statistics of 0.70 and 0.66, respectively, in one-year prediction, and 0.67 and 0.65 in two-year prediction.

Conclusions/significance

The posttransplant prognosis is a multidimensional nonlinear problem, and the MLP can achieve significantly high accuracy than SOFA and MELD scores in posttransplant survival prediction. The pattern recognition methodologies like MLP hold promise for solving posttransplant outcome prediction.

SUBMITTER: Zhang M

PROVIDER: S-EPMC3291549 | biostudies-literature | 2012

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pretransplant prediction of posttransplant survival for liver recipients with benign end-stage liver diseases: a nonlinear model.

Zhang Ming M Yin Fei F Chen Bo B Li You Ping YP Yan Lu Nan LN Wen Tian Fu TF Li Bo B

PloS one 20120301 3

<h4>Background</h4>The scarcity of grafts available necessitates a system that considers expected posttransplant survival, in addition to pretransplant mortality as estimated by the MELD. So far, however, conventional linear techniques have failed to achieve sufficient accuracy in posttransplant outcome prediction. In this study, we aim to develop a pretransplant predictive model for liver recipients' survival with benign end-stage liver diseases (BESLD) by a nonlinear method based on pretranspl ...[more]

PMID: 22396731

Similar Datasets

Project description:Clostridioides difficile infection (CDI) has a higher incidence in solid organ transplant recipients than other hospitalized patients and can lead to poor outcomes. Perturbations to the intestinal microbiome are common in patients undergoing liver transplant (LT); however, the impacts of microbial diversity and composition on risk of CDI in this patient population is incompletely understood. Here, we assessed patients in an established, longitudinal LT cohort for development of CDI within 1 year of transplant. Clinical data were compared for patients with and without CDI using univariable models. 16S rRNA sequencing of fecal samples was performed at multiple pre- and posttransplant time points to compare microbiome α- and β-diversity and enrichment of specific taxa in patients with and without CDI. Of 197 patients who underwent LT, 18 (9.1%) developed CDI within 1 year. Pre-LT Child-Pugh class C liver disease, postoperative biliary leak, and use of broad-spectrum antibiotics were significantly associated with CDI. Patients who developed CDI had significantly lower α-diversity than patients without CDI overall and in samples collected at months 1, 3, and 6. Microbial composition (β-diversity) differed between patients with and without CDI and across sampling time points, particularly later in their posttransplant course. We also identified 15 (8%) patients with toxigenic C. difficile colonization who did not develop CDI and may have had additional protective factors. In summary, clinical and microbiome factors are likely to converge to impart CDI risk. Along with enhanced preventive measures, there may be a role for microbiome modulation to restore microbial diversity in high-risk LT patients. IMPORTANCE Liver transplant (LT) recipients have high rates of Clostridioides difficile infection (CDI), which has been associated with poor outcomes, including graft-related complications and mortality, in prior studies. Susceptibility to CDI is known to increase following perturbations in intestinal commensal bacteria that enable germination of C. difficile spores and bacterial overgrowth. In LT patients, changes in the intestinal microbiome resulting from advanced liver disease, surgery, and other clinical factors is common and most pronounced during the early posttransplant period. However, the relationship between microbiome changes and CDI risk after LT remains unclear. In this study, we investigated clinical and microbiome factors associated with development of CDI within the first year after LT. The importance of this work is to identify patients with high-risk features that should receive enhanced preventive measures and may benefit from the study of novel strategies to reconstitute the intestinal microbiome after LT.

Dataset Information

Pretransplant prediction of posttransplant survival for liver recipients with benign end-stage liver diseases: a nonlinear model.

Background

Methodology/principal findings

Conclusions/significance

Publications

Pretransplant prediction of posttransplant survival for liver recipients with benign end-stage liver diseases: a nonlinear model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets