Background: Cardiac surgery–associated acute kidney injury (CSA-AKI) is a major complication that results in increased morbidity and mortality after cardiac surgery. Most established prediction models are limited to the analysis of nonlinear relationships and fail to fully consider intraoperative variables, which represent the acute response to surgery. Therefore, this study utilized an artificial intelligence–based machine learning approach thorough perioperative data-driven learning to predict CSA-AKI. Methods: A total of 671 patients undergoing cardiac surgery from August 2016 to August 2018 were enrolled. AKI following cardiac surgery was defined according to criteria from Kidney Disease: Improving Global Outcomes (KDIGO). The variables used for analysis included demographic characteristics, clinical condition, preoperative biochemistry data, preoperative medication, and intraoperative variables such as time-series hemodynamic changes. The machine learning methods used included logistic regression, support vector machine (SVM), random forest (RF), extreme gradient boosting (XGboost), and ensemble (RF + XGboost). The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). We also utilized SHapley Additive exPlanation (SHAP) values to explain the prediction model. Results: Development of CSA-AKI was noted in 163 patients (24.3%) during the first postoperative week. Regarding the efficacy of the single model that most accurately predicted the outcome, RF exhibited the greatest AUC (0.839, 95% confidence interval [CI] 0.772–0.898), whereas the AUC (0.843, 95% CI 0.778–0.899) of ensemble model (RF + XGboost) was even greater than that of the RF model alone. The top 3 most influential features in the RF importance matrix plot were intraoperative urine output, units of packed red blood cells (pRBCs) transfused during surgery, and preoperative hemoglobin level. The SHAP summary plot was used to illustrate the positive or negative effects of the top 20 features attributed to the RF. We also used the SHAP dependence plot to explain how a single feature affects the output of the RF prediction model. Conclusions: In this study, machine learning methods were successfully established to predict CSA-AKI, which determines risks following cardiac surgery, enabling the optimization of postoperative treatment strategies to minimize the postoperative complications following cardiac surgeries.

Background: The link between elevated serum uric acid ( SUA ) levels and cardiovascular disease ( CVD )–related mortality in the elderly population remains inconclusive. Nutritional status influences both SUA and CVD outcomes. Therefore, we investigated whether SUA ‐predicted mortality and the effect‐modifying roles of malnourishment in older people. Methods and Results: A longitudinal Taiwanese cohort including 127 771 adults 65 years and older participating in the Taipei City Elderly Health Examination Program from 2001 to 2010 were stratified by 1‐mg/dL increment of SUA . Low SUA (<4 mg/dL) strata was categorized by malnourishment status defined as Geriatric Nutritional Risk Index <98, serum albumin <38 g/L, or body mass index <22 kg/m ² . Study outcomes were all‐cause and CVD ‐related mortality. Cox models were used to estimate hazard ratios ( HRs ) of mortality, after adjusting for 20 demographic and comorbid covariates. Over a median follow‐up of 5.8 years, there were 16 439 all‐cause and 3877 CVD ‐related deaths. Compared with the reference SUA strata of 4 to <5 mg/dL, all‐cause mortality was significantly higher at SUA <4 mg/dL ( HR , 1.16; 95% confidence interval, 1.07–1.25) and ≥8 mg/dL ( HR , 1.13; confidence interval, 1.06–1.21), with progressively elevated risks at both extremes. Similarly, increasingly higher CVD ‐related mortality was found at the SUA level <4 mg/dL ( HR , 1.19; confidence interval, 1.00–1.40) and ≥7 mg/dL ( HR , 1.17; confidence interval, 1.04–1.32). Remarkably, among the low SUA (<4 mg/dL) strata, only malnourished participants had greater all‐cause and CVD ‐related mortality. This modifying effect of malnourishment remained consistent across subgroups. Conclusions: SUA ≥8 or <4 mg/dL independently predicts higher all‐cause and CVD ‐related mortality in the elderly, particularly in those with malnourishment.

Recent studies concluded that dipeptidyl peptidase-4 (DPP-4) inhibitors provide glycemic control but also raised concerns about the risk for heart failure in patients with type 2 diabetes mellitus (T2DM). However, large-scale studies of the effects on cardiovascular outcomes of adding DPP-4 inhibitors versus sulfonylureas to metformin therapy remain scarce. To compare clinical outcomes of adding DPP-4 inhibitors versus sulfonylureas to metformin therapy in patients with T2DM. Nationwide study using Taiwan's National Health Insurance Research Database. Taiwan. All patients with T2DM aged 20 years or older between 2009 and 2012. A total of 10,089 propensity score-matched pairs of DPP-4 inhibitor users and sulfonylurea users were examined. Cox models with exposure to sulfonylureas and DPP-4 inhibitors included as time-varying covariates were used to compare outcomes. The following outcomes were considered: all-cause mortality, major adverse cardiovascular events (MACEs) (including ischemic stroke and myocardial infarction), hospitalization for heart failure, and hypoglycemia. Patients were followed until death or 31 December 2013. DPP-4 inhibitors were associated with lower risks for all-cause death (hazard ratio [HR], 0.63 [95% CI, 0.55 to 0.72]), MACEs (HR, 0.68 [CI, 0.55 to 0.83]), ischemic stroke (HR, 0.64 [CI, 0.51 to 0.81]), and hypoglycemia (HR, 0.43 [CI, 0.33 to 0.56]) compared with sulfonylureas as add-on therapy to metformin but had no effect on risks for myocardial infarction and hospitalization for heart failure. Observational study design. Compared with sulfonylureas, DPP-4 inhibitors were associated with lower risks for all-cause death, MACEs, ischemic stroke, and hypoglycemia when used as add-ons to metformin therapy. None.

Background—: Whether oral anticoagulant use should be considered in patients undergoing hemodialysis with atrial fibrillation (AF) remains controversial because of the uncertainty regarding risk-benefit assessments. The purpose of this study was to investigate the risk of ischemic stroke in patients undergoing hemodialysis with new-onset AF, in comparison with those without arrhythmia. Methods and Results—: This nationwide, population-based, propensity score–matched cohort study used data from Taiwan’s National Health Insurance Research Database during 1998 to 2011 for patients on hemodialysis with new-onset nonvalvular AF and matched subjects without arrhythmia. The clinical end points were ischemic stroke (fatal or nonfatal), all-cause death, and other serious adverse cardiovascular events. In comparison with the matched cohort, patients with AF (n=6772) had higher risks of ischemic stroke (adjusted hazard ratio [aHR], 1.27; 95% confidence interval [CI], 1.13–1.43), all-cause death (aHR, 1.59; 95% CI, 1.52–1.67), in-hospital cardiovascular death (aHR, 1.83; 95% CI, 1.71–1.94), myocardial infarction (aHR, 1.33; 95% CI, 1.17–1.51), and hospitalization for heart failure (aHR, 1.90; 95% CI, 1.76–2.05). After considering in-hospital death as a competing risk, AF significantly increased the risk of heart failure (HR, 1.56; 95% CI, 1.45–1.68), but not those of ischemic stroke and myocardial infarction. Additionally, the predictive value of the CHA ₂ DS ₂ –VASc score for ischemic stroke was diminished in the competing-risk model. Conclusions—: The risk of stroke was only modestly higher in patients undergoing hemodialysis with new-onset AF than in those without AF, and it became insignificant when accounting for the competing risk of in-hospital death.

BK polyomavirus nephropathy (BKVN) and allograft rejection are two closely-associated diseases on opposite ends of the immune scale in kidney transplant recipients. The principle of balancing the immune system remains the mainstay of therapeutic strategy. While patient outcomes can be improved through screening, risk factors identification, and rapid reduction of immunosuppressants, a lack of standard curative therapy is the primary concern during clinical practice. Additionally, difficulty in pathological differential diagnosis and clinicopathology’s dissociation pose problems for a definite diagnosis. This article discusses the delicate evaluation needed to optimize immunosuppression and reviews recent advances in molecular diagnosis and immunological therapy for BKVN patients. New biomarkers for BKVN diagnosis are under development. For example, measurement of virus-specific T cell level may play a role in steering immunosuppressants. The development of cellular therapy may provide prevention, even a cure, for BKVN, a complex post-transplant complication.

Ischemia-reperfusion injury (IRI) plays a significant role in the pathogenesis of acute kidney injury (AKI). The complicated interaction between injured tubular cells, activated endothelial cells, and the immune system leads to oxidative stress and systemic inflammation, thereby exacerbating the apoptosis of renal tubular cells and impeding the process of tissue repair. Stem cell therapy is an innovative approach to ameliorate IRI due to its antioxidative, immunomodulatory, and anti-apoptotic properties. Therefore, it is crucial to understand the biological effects and mechanisms of action of stem cell therapy in the context of acute ischemic AKI to improve its therapeutic benefits. The recent finding that treatment with conditioned medium (CM) derived from stem cells is likely an effective alternative to conventional stem cell transplantation increases the potential for future therapeutic uses of stem cell therapy. In this review, we discuss the recent findings regarding stem cell-mediated cytoprotection, with a focus on the anti-inflammatory effects via suppression of oxidative stress and uncompromised immune responses following AKI. Stem cell-derived CM represents a favorable approach to stem cell-based therapy and may serve as a potential therapeutic strategy against acute ischemic AKI.