Using machine learning to predict the risk of short-term and long-term death in acute kidney injury patients after commencing CRRT.

BACKGROUND: The mortality rate and prognosis of short-term and long-term acute kidney injury (AKI) patients who undergo continuous renal replacement therapy (CRRT) are different. Setting up risk stratification tools for both short-term and long-term deaths is highly important for clinicians. METHOD: A total of 1535 AKI patients receiving CRRT were included in this study, with 1144 from the training set (the Dryad database) and 391 from the validation set (MIMIC IV database). A model for predicting mortality within 10 and 90 days was built using nine different machine learning (ML) algorithms. AUROC, F1-score, accuracy, sensitivity, specificity, precision, and calibration curves were used to assess the predictive performance of various ML models. RESULTS: A total of 420 (31.1%) deaths occurred within 10 days, and 1080 (68.8%) deaths occurred within 90 days. The random forest (RF) model performed best in both predicting 10-day (AUROC: 0.80, 95% CI: 0.74-0.84; accuracy: 0.72, 95% CI: 0.67-0.76; F1-score: 0.59) and 90-day mortality (AUROC: 0.78, 95% CI: 0.73-0.83; accuracy: 0.73, 95% CI: 0.69-0.78; F1-score: 0.80). The importance of the feature shows that SOFA scores are rated as the most important risk factor for both 10-day and 90-day mortality. CONCLUSION: Our study, utilizing multiple machine learning models, estimates the risk of short-term and long-term mortality among AKI patients who commence CRRT. The results demonstrated that the prognostic factors for short-term and long-term mortality are different. The RF model has the best prediction performance and has valuable potential for clinical application.

WWP2 deletion aggravates acute kidney injury by targeting CDC20/autophagy axis.

INTRODUCTION: Acute kidney injury (AKI) is associated with high morbidity and mortality rates. The molecular mechanisms underlying AKI are currently being extensively investigated. WWP2 is an E3 ligase that regulates cell proliferation and differentiation. Whether WWP2 plays a regulatory role in AKI remains to be elucidated. OBJECTIVES: We aimed to investigate the implication of WWP2 in AKI and its underlying mechanism in the present study. METHODS: We utilized renal tissues from patients with AKI and established AKI models in global or tubule-specific knockout (cKO) mice strains to study WWP2's implication in AKI. We also systemically analyzed ubiquitylation omics and proteomics to decipher the underlying mechanism. RESULTS: In the present study, we found that WWP2 expression significantly increased in the tubules of kidneys with AKI. Global or tubule-specific knockout of WWP2 significantly aggravated renal dysfunction and tubular injury in AKI kidneys, whereas WWP2 overexpression significantly protected tubular epithelial cells against cisplatin. WWP2 deficiency profoundly affected autophagy in AKI kidneys. Further analysis with ubiquitylation omics, quantitative proteomics and experimental validation suggested that WWP2 mediated poly-ubiquitylation of CDC20, a negative regulator of autophagy. CDC20 was significantly decreased in AKI kidneys, and selective inhibiting CDC20 with apcin profoundly alleviated renal dysfunction and tubular injury in the cisplatin model with or without WWP2 cKO, indicating that CDC20 may serve as a downstream target of WWP2 in AKI. Inhibiting autophagy with 3-methyladenine blocked apcin's protection against cisplatin-induced renal tubular cell injury. Activating autophagy by rapamycin significantly protected against cisplatin-induced AKI in WWP2 cKO mice, whereas inhibiting autophagy by 3-methyladenine further aggravated apoptosis in cisplatin-exposed WWP2 KO cells. CONCLUSION: Taken together, our data indicated that the WWP2/CDC20/autophagy may be an essential intrinsic protective mechanism against AKI. Further activating WWP2 or inhibiting CDC20 may be novel therapeutic strategies for AKI.