The Development and Evaluation of a Prediction Model for Kidney Transplant-Based Pneumocystis carinii Pneumonia Patients Based on Hematological Indicators.

BACKGROUND: This study aimed to develop a simple predictive model for early identification of the risk of adverse outcomes in kidney transplant-associated Pneumocystis carinii pneumonia (PCP) patients. METHODS: This study encompassed 103 patients diagnosed with PCP, who received treatment at our hospital between 2018 and 2023. Among these participants, 20 were categorized as suffering from severe PCP, and, regrettably, 13 among them succumbed. Through the application of machine learning techniques and multivariate logistic regression analysis, two pivotal variables were discerned and subsequently integrated into a nomogram. The efficacy of the model was assessed via receiver operating characteristic (ROC) curves and calibration curves. Additionally, decision curve analysis (DCA) and a clinical impact curve (CIC) were employed to evaluate the clinical utility of the model. The Kaplan-Meier (KM) survival curves were utilized to ascertain the model's aptitude for risk stratification. RESULTS: Hematological markers, namely Procalcitonin (PCT) and C-reactive protein (CRP)-to-albumin ratio (CAR), were identified through machine learning and multivariate logistic regression. These variables were subsequently utilized to formulate a predictive model, presented in the form of a nomogram. The ROC curve exhibited commendable predictive accuracy in both internal validation (AUC = 0.861) and external validation (AUC = 0.896). Within a specific threshold probability range, both DCA and CIC demonstrated notable performance. Moreover, the KM survival curve further substantiated the nomogram's efficacy in risk stratification. CONCLUSIONS: Based on hematological parameters, especially CAR and PCT, a simple nomogram was established to stratify prognostic risk in patients with renal transplant-related PCP.

Machine Learning Models for Prediction of Severe Pneumocystis carinii Pneumonia after Kidney Transplantation: A Single-Center Retrospective Study.

BACKGROUND: The objective of this study was to formulate and validate a prognostic model for postoperative severe Pneumocystis carinii pneumonia (SPCP) in kidney transplant recipients utilizing machine learning algorithms, and to compare the performance of various models. METHODS: Clinical manifestations and laboratory test results upon admission were gathered as variables for 88 patients who experienced PCP following kidney transplantation. The most discriminative variables were identified, and subsequently, Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbor (KNN), Light Gradient Boosting Machine (LGBM), and eXtreme Gradient Boosting (XGB) models were constructed. Finally, the models' predictive capabilities were assessed through ROC curves, sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and F1-scores. The Shapley additive explanations (SHAP) algorithm was employed to elucidate the contributions of the most effective model's variables. RESULTS: Through lasso regression, five features-hemoglobin (Hb), Procalcitonin (PCT), C-reactive protein (CRP), progressive dyspnea, and Albumin (ALB)-were identified, and six machine learning models were developed using these variables after evaluating their correlation and multicollinearity. In the validation cohort, the RF model demonstrated the highest AUC (0.920 (0.810-1.000), F1-Score (0.8), accuracy (0.885), sensitivity (0.818), PPV (0.667), and NPV (0.913) among the six models, while the XGB and KNN models exhibited the highest specificity (0.909) among the six models. Notably, CRP exerted a significant influence on the models, as revealed by SHAP and feature importance rankings. CONCLUSIONS: Machine learning algorithms offer a viable approach for constructing prognostic models to predict the development of severe disease following PCP in kidney transplant recipients, with potential practical applications.

Risk factors for BK virus infection in DCD donor kidney transplant recipients.

Background: BK virus infection after kidney transplantation can negatively impact the prognosis of patients. However, current risk factor analyses primarily focus on BK virus nephropathy, while BK viruria and BK viruria progressing to BK viremia receive less attention. This study aims to analyze the risk factors associated with BK viruria and BK viruria progressing to BK viremia in recipients of donation after cardiac death (DCD), with the goal of facilitating early intervention. Methods: Donor characteristics and clinical data of recipients before and after transplantation were evaluated, and logistic univariate and multivariate analyses were performed to determine the risk factors associated with BK viruria and the progression of BK viruria to BK viremia. Additionally, machine learning techniques were employed to identify the top five features associated with BK viruria evolving into BK viremia. Results: During a median follow-up time of 1,072 days (range 739-1,418), 69 transplant recipients (15.6% incidence rate) developed BK viruria after transplantation, with 49.3% of cases occurring within 6 months post-transplantation. Moreover, 19 patients progressed to BK viremia. Donor age [OR: 1.022 (1.000, 1.045), p = 0.047] and donor procalcitonin (PCT) levels [0.5-10 ng/ml; OR: 0.482 (0.280, 0.828), p = 0.008] were identified as independent risk factors for BK viruria. High BK viruria [OR: 11.641 (1.745, 77.678), p = 0.011], recipient age [OR: 1.106 (1.017, 1.202), p = 0.018], and immunoinduction regimen [ATG; OR: 0.063 (0.006, 0.683), p = 0.023] were independent risk factors for BK viruria progressing to BK viremia. Machine learning analysis confirmed the importance of high BK viruria, recipient age, and immunoinduction regimen (ATG) in predicting the progression of BK viruria to BK viremia. Conclusion: The development and progression of BK virus in DCD kidney transplant recipients is influenced by multiple factors. Early intervention and treatment could potentially extend the lifespan of the transplanted organ.

Ubiquitin-specific protease 29 attenuates hepatic ischemia-reperfusion injury by mediating TGF-ß-activated kinase 1 deubiquitination.

Background and aims: In the course of clinical practice, hepatic ischemia/reperfusion (I/R) injury is a prevalent pathophysiological event and is caused by a combination of complex factors that involve multiple signaling pathways such as MAPK and NF-κB. USP29 is a deubiquitinating enzyme important during the development of tumors, neurological diseases, and viral immunity. However, it is unknown how USP29 contributes to hepatic I/R injury. Methods and results: We systematically investigated the role of the USP29/TAK1-JNK/p38 signaling pathway in hepatic I/R injury. We first found reduced USP29 expression in both mouse hepatic I/R injury and the primary hepatocyte hypoxia-reoxygenation (H/R) models. We established USP29 full knockout mice (USP29-KO) and hepatocyte-specific USP29 transgenic mice (USP29-HTG), and we found that USP29 knockout significantly exacerbates the inflammatory infiltration and injury processes during hepatic I/R injury, whereas USP29 overexpression alleviates liver injury by decreasing the inflammatory response and inhibiting apoptosis. Mechanistically, RNA sequencing results showed the effects of USP29 on the MAPK pathway, and further studies revealed that USP29 interacts with TAK1 and inhibits its k63-linked polyubiquitination, thereby preventing the activation of TAK1 and its downstream signaling pathways. Consistently, 5z-7-Oxozeaneol, an inhibitor of TAK1, blocked the detrimental effects of USP29 knockout on H/R-induced hepatocyte injury, further confirming that USP29 plays a regulatory role in hepatic I/R injury by targeting TAK1. Conclusion: Our findings imply that USP29 is a therapeutic target with promise for the management of hepatic I/R injury via TAK1-JNK/p38 pathway-dependent processes.