Is renal allograft dysfunction a risk factor for severe infection in kidney transplant recipients?

Machine learning for the prediction of severe pneumonia during posttransplant hospitalization in recipients of a deceased-donor kidney transplant

Background

Pneumonia accounts for the majority of infection-related deaths after kidney transplantation. We aimed to build a predictive model based on machine learning for severe pneumonia in recipients of deceased-donor transplants within the perioperative period after surgery.

Methods

We collected the features of kidney transplant recipients and used a tree-based ensemble classification algorithm (Random Forest or AdaBoost) and a nonensemble classifier (support vector machine, Naïve Bayes, or logistic regression) to build the predictive models. We used the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC) to evaluate the predictive performance via ten-fold cross validation.

Results

Five hundred nineteen patients who underwent transplantation from January 2015 to December 2018 were included. Forty-three severe pneumonia episodes (8.3%) occurred during hospitalization after surgery. Significant differences in the recipients' age, diabetes status, HBsAg level, operation time, reoperation, usage of anti-fungal drugs, preoperative albumin and immunoglobulin levels, preoperative pulmonary lesions, and delayed graft function, as well as donor age, were observed between patients with and without severe pneumonia (P<0.05). We screened eight important features correlated with severe pneumonia using the recursive feature elimination method and then constructed a predictive model based on these features. The top three features were preoperative pulmonary lesions, reoperation and recipient age (with importance scores of 0.194, 0.124 and 0.078, respectively). Among the machine learning algorithms described above, the Random Forest algorithm displayed better predictive performance, with a sensitivity of 0.67, specificity of 0.97, positive likelihood ratio of 22.33, negative likelihood ratio of 0.34, AUROC of 0.91, and AUPRC of 0.72.

Conclusions

The Random Forest model is potentially useful for predicting severe pneumonia in kidney transplant recipients. Recipients with a potential preoperative potential pulmonary infection, who are of older age and who require reoperation should be monitored carefully to prevent the occurrence of severe pneumonia.

Genetic variation in Micro-RNA genes of host genome affects clinical manifestation of symptomatic Human Cytomegalovirus infection

BACKGROUND

Micro-RNAs are implicated in various physiological and pathologic processes. In this study, we tested whether Micro-RNA gene variants of host-genome affect clinical manifestation of symptomatic HCMV infection.

METHODOLOGY

HCMV infection was detected by fluorescent PCR and immuno-histochemistry. The detection of genetic variants of four studied Micro-RNA tag-SNPs was done through PCR-RFLP assay and validated with DNA sequencing.

RESULTS

We observed an increased risk ranged from 3-folds to 5-folds among symptomatic HCMV cases for mutant genotype of rs2910164 (crude OR=3.11, p=0.009 and adjusted OR=3.25, p=0.007), rs11614913 (crude OR=3.20, p=0.006 and adjusted OR=3.48, p=0.004) and rs3746444 (crude OR=4.91, p=0.002 and adjusted OR=5.28, p=0.002) tag-SNPs. Interestingly, all the tag-SNPs that were significant after multiple comparisons at a FDR of 5% in symptomatic HCMV cases remained significant even after bootstrap analysis, providing internal validation to these results. Multifactor Dimensionality Reduction (MDR) analysis revealed 5-folds increased risk for symptomatic HCMV cases under the four-factor model (rs2910164, rs2292832, rs11614913 and rs3746444).

CONCLUSIONS

These results suggest that Micro-RNA gene variants of host-genome may affect clinical manifestation of symptomatic HCMV infection.

CTLA4 gene polymorphisms influence the incidence of infection after renal transplantation in Chinese recipients

Background

Immunosuppressive therapy is usually administered following renal transplantation to protect the graft from rejection. However, this often causes complications such as infections to occur. Single nucleotide polymorphisms (SNPs) within the CTLA4 gene, such as −1772T/C (rs733618), +49A/G (rs231775) and +6230 G/A (rs3087243), can affect graft rejection and the long-term clinical outcome of organ transplantation. The role of CTLA4 SNPs in T cell-mediated immunity in renal transplantation and association with infection after transplantation is unknown.

Methods

In this study, the risk of infection according to CTLA4 SNPs was investigated in 304 patients who received kidney graft transplants between 2008 and 2012.

Results

The frequency of the rs4553808 GG genotype was significantly higher in recipients with viral infection (14.89%) than in those without infections (3.50%) (Bonferroni-adjusted p = 0.005). A significant difference (p = 0.001) in patients with the rs4553808 GG genotype from those with the AA+AG genotypes was found in the viral cohort using the log-rank test. A significant association was found between the rs4553808 genotype and onset of viral infection in transplant recipients (p = 0.001). The frequencies of the CGTAG and CGCAG haplotypes were significantly higher in the viral infection group (9.6% and 5.3%) than in the non-viral infection group (3.8% and 1.4%) (p = 0.0149 and p = 0.0111). No association between any CTLA4 SNP and bacterial infection was found. Multivariate analyses revealed that one risk factor, the use of antibody induction therapy (p = 0.007), was associated with bacterial infection, and two risk factors, antibody use (p = 0.015) and recipient rs4553808 genotype (p = 0.001), were associated with viral infection.

Conclusions

The rs4553808 GG genotype may be a risk factor for viral infection in kidney transplantation. The CTLA4 haplotypes CGTAG and CGCAG were partially associated with the development of viral infection in Chinese kidney transplant recipients.