Development and validation of a deep neural network-based model to predict acute kidney injury following intravenous administration of iodinated contrast media in hospitalized patients with chronic kidney disease: a multicohort analysis.

BACKGROUND: Stratification of chronic kidney disease (CKD) patients [estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2] at risk for post-contrast acute kidney injury (PC-AKI) following intravenous administration of iodinated contrast media (ICM) is important for clinical decision-making and clinical trial enrollment. METHODS: The derivation and internal validation cohorts originated from the Second Xiangya Hospital. The external validation cohort was generated from the Xiangya Hospital and the openly accessible database Medical Information Mart for Intensive CareIV. PC-AKI was defined based on the serum creatinine criteria of the Kidney Disease: Improving Global Outcomes (KDIGO). Six feature selection methods were used to identify the most influential predictors from 79 candidate variables. Deep neural networks (DNNs) were used to establish the model and compared with logistic regression analyses. Model discrimination was evaluated by area under the receiver operating characteristic curve (AUC). Low-risk and high-risk cutoff points were set to stratify patients. RESULTS: Among 4218 encounters studied, PC-AKI occurred in 10.3, 10.4 and 11.4% of encounters in the derivation, internal and external validation cohorts, respectively. The 14 variables-based DNN model had significantly better performance than the logistic regression model with AUC being 0.939 (95% confidence interval: 0.916-0.958) and 0.940 (95% confidence interval: 0.909-0.954) in the internal and external validation cohorts, respectively, and showed promising discrimination in subgroup analyses (AUC ≥ 0.800). The observed PC-AKI risks increased significantly from the low- to intermediate- to high-risk group (<1.0 to >50%) and the accuracy of patients not developing PC-AKI was 99% in the low-risk category in both the internal and external validation cohorts. CONCLUSIONS: A DNN model using routinely available variables can accurately discriminate the risk of PC-AKI of hospitalized CKD patients following intravenous administration of ICM.

Effects of intravenous hydration in preventing post-contrast acute kidney injury in patients with eGFR < 30 mL/min/1.73 m2.

OBJECTIVES: To investigate the effects of intravenous hydration in preventing post-contrast outcomes in patients with estimated glomerular filtration rate (eGFR) < 30 mL/min/1.73 m2 undergoing intravenous administration of iodinated contrast media (ICM). METHODS: Hospitalized patients with eGFR < 30 mL/min/1.73 m2 and intravenous ICM exposure between 2015 and 2021 were included. Post-contrast outcomes include post-contrast acute kidney injury (PC-AKI) (defined by 2012 Kidney Disease: Improving Global Outcomes (KDIGO) or European Society of Urogenital Radiology (ESUR)), chronic dialysis at discharge, and in-hospital mortality. Confounding effects between the two groups were reduced to a minimum using propensity score-based matching and overlap weighting. Association between intravenous hydration and outcomes was analyzed using logistic regression. RESULTS: In total, 794 patients were included in the study, with 284 receiving intravenous hydration, and 510 not. After 1:1 propensity score matching, 210 pairs were generated. No significant differences were found in the outcomes between the intravenous hydration and no intravenous hydration groups: PC-AKI by KDIGO, 25.2% vs 24.8% (odds ratio (OR), 0.93; 95% confidence interval (CI), 0.57-1.50); PC-AKI by ESUR, 31.0% vs 25.2% (OR, 1.34; 95% CI, 0.86-2.08); chronic dialysis at discharge, 4.3% vs 3.3% (OR, 1.56; 95% CI, 0.56-4.50); in-hospital mortality, 1.9% vs 0.5% (OR, 4.08; 95% CI, 0.58-81.08). Overlap propensity score-weighted analysis also showed no significant effects of intravenous hydration on the incidences of the post-contrast outcomes. CONCLUSIONS: Intravenous hydration was not associated with lower risks of PC-AKI, chronic dialysis at discharge, and in-hospital mortality in patients with eGFR < 30 mL/min/1.73 m2 undergoing intravenous administration of ICM. CLINICAL RELEVANCE STATEMENT: This study provides new evidence in supporting that intravenous hydration is not beneficial to patients with eGFR < 30 mL/min/1.73 m2 before and after intravenous administration of iodinated contrast media. KEY POINTS: • Intravenous hydration before and after intravenous administration of ICM is not associated with lower risks in PC-AKI, chronic dialysis at discharge, and in-hospital mortality in patients with eGFR < 30 mL/min/1.73 m2. • Withholding intravenous hydration may be considered in patients with eGFR < 30 mL/min/1.73 m2 around intravenous administration of ICM.

Association of underweight and obesity with adverse postoperative renal outcomes in infants and young children undergoing congenital heart surgery.

Postoperative acute kidney injury (AKI) is a prevalent condition and associated with increased morbidity and mortality following cardiac surgery. This study aimed to investigate the association of underweight and obesity with adverse postoperative renal outcomes in infants and young children undergoing congenital heart surgery. This retrospective cohort study included patients aged from 1 month to 5 years who underwent congenital heart surgery with cardiopulmonary bypass at the Second Xiangya Hospital of Central South University from January 2016 to March 2022. On the basis of the percentile of body mass index (BMI) for age and sex, eligible participants were divided into three nutritional groups: normal bodyweight, underweight (BMI P5), and obesity (BMI P95). Primary outcomes included postoperative AKI and major adverse kidney events within 30 days (MAKE30). Multivariable logistic regression was performed to determine the association of underweight and obesity with postoperative outcomes. The same analyses were reproduced for classifying patients using weight-for-height instead of BMI. A total of 2,079 eligible patients were included in the analysis, including 1,341 (65%) patients in the normal bodyweight group, 683 (33%) patients in the underweight group, and 55 (2.6%) patients in the obesity group. Postoperative AKI (16% vs. 26% vs. 38%; P < 0.001) and MAKE30 (2.5% vs. 6.4% vs. 9.1%; P < 0.001) were more likely to occur in the underweight and obesity groups. After adjusting for potential confounders, underweight (OR1.39; 95% CI 1.08-1.79; P = 0.008) and obesity (OR 3.85; 95% CI 1.97-7.50; P < 0.001) were found to be associated with an increased risk of postoperative AKI. In addition, both underweight (OR 1.89; 95% CI 1.14-3.14; P = 0.014) and obesity (OR 3.14; 95% CI 1.08-9.09; P = 0.035) were independently associated with MAKE30. Similar results were also found when weight-for-height was used instead of BMI.    Conclusion: In infants and young children undergoing congenital heart surgery, underweight and obesity are independently associated with postoperative AKI and MAKE30. These results may help assess prognosis in underweight and obese patients, and will guide future quality improvement efforts. What is Known: • Postoperative acute kidney injury (AKI) is prevalent and associated with increased morbidity and mortality following pediatric cardiac surgery. • Major adverse kidney events within 30 days (MAKE30) have been recommended as a patient-centered endpoint for evaluating AKI clinical trajectories. A growing concern arises for underweight and obesity in children with congenital heart disease. What is New: • Prevalence of underweight and obesity among infants and young children undergoing congenital heart surgery was 33% and 2.6%, respectively. • Both underweight and obesity were independently associated with postoperative AKI and MAKE30 following congenital heart surgery.

Machine Learning-Based Prediction of Acute Kidney Injury Following Pediatric Cardiac Surgery: Model Development and Validation Study.

BACKGROUND: Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication following pediatric cardiac surgery, which is associated with increased morbidity and mortality. The early prediction of CSA-AKI before and immediately after surgery could significantly improve the implementation of preventive and therapeutic strategies during the perioperative periods. However, there is limited clinical information on how to identify pediatric patients at high risk of CSA-AKI. OBJECTIVE: The study aims to develop and validate machine learning models to predict the development of CSA-AKI in the pediatric population. METHODS: This retrospective cohort study enrolled patients aged 1 month to 18 years who underwent cardiac surgery with cardiopulmonary bypass at 3 medical centers of Central South University in China. CSA-AKI was defined according to the 2012 Kidney Disease: Improving Global Outcomes criteria. Feature selection was applied separately to 2 data sets: the preoperative data set and the combined preoperative and intraoperative data set. Multiple machine learning algorithms were tested, including K-nearest neighbor, naive Bayes, support vector machines, random forest, extreme gradient boosting (XGBoost), and neural networks. The best performing model was identified in cross-validation by using the area under the receiver operating characteristic curve (AUROC). Model interpretations were generated using the Shapley additive explanations (SHAP) method. RESULTS: A total of 3278 patients from one of the centers were used for model derivation, while 585 patients from another 2 centers served as the external validation cohort. CSA-AKI occurred in 564 (17.2%) patients in the derivation cohort and 51 (8.7%) patients in the external validation cohort. Among the considered machine learning models, the XGBoost models achieved the best predictive performance in cross-validation. The AUROC of the XGBoost model using only the preoperative variables was 0.890 (95% CI 0.876-0.906) in the derivation cohort and 0.857 (95% CI 0.800-0.903) in the external validation cohort. When the intraoperative variables were included, the AUROC increased to 0.912 (95% CI 0.899-0.924) and 0.889 (95% CI 0.844-0.920) in the 2 cohorts, respectively. The SHAP method revealed that baseline serum creatinine level, perfusion time, body length, operation time, and intraoperative blood loss were the top 5 predictors of CSA-AKI. CONCLUSIONS: The interpretable XGBoost models provide practical tools for the early prediction of CSA-AKI, which are valuable for risk stratification and perioperative management of pediatric patients undergoing cardiac surgery.

Utilization of interpretable machine learning model to forecast the risk of major adverse kidney events in elderly patients in critical care.

Major adverse kidney events within 30 d (MAKE30) implicates poor outcomes for elderly patients in the intensive care unit (ICU). This study aimed to predict the occurrence of MAKE30 in elderly ICU patients using machine learning. The study cohort comprised 2366 elderly ICU patients admitted to the Second Xiangya Hospital of Central South University between January 2020 and December 2021. Variables including demographic information, laboratory values, physiological parameters, and medical interventions were used to construct an extreme gradient boosting (XGBoost) -based prediction model. Out of the 2366 patients, 1656 were used for model derivation and 710 for testing. The incidence of MAKE30 was 13.8% in the derivation cohort and 13.2% in the test cohort. The average area under the receiver operating characteristic curve of the XGBoost model was 0.930 (95% CI: 0.912-0.946) in the training set and 0.851 (95% CI: 0.810-0.890) in the test set. The top 8 predictors of MAKE30 tentatively identified by the Shapley additive explanations method were Acute Physiology and Chronic Health Evaluation II score, serum creatinine, blood urea nitrogen, Simplified Acute Physiology Score II score, Sequential Organ Failure Assessment score, aspartate aminotransferase, arterial blood bicarbonate, and albumin. The XGBoost model accurately predicted the occurrence of MAKE30 in elderly ICU patients, and the findings of this study provide valuable information to clinicians for making informed clinical decisions.

Temporal trends of post-contrast acute kidney injury in patients with intravenous administration of iodinated contrast medium.

Little is known about whether preventative practices for post-contrast acute kidney injury (PC-AKI) recommended in guidelines have been adopted in clinical practice and translated into a lower incidence of PC-AKI. The aim of this study was to examine the yearly trends in the incidence of PC-AKI, and comorbidities and care practices associated with PC-AKI in hospitalized patients who received intravenous administration of iodinated contrast medium (ICM). Adult patients receiving intravenous ICM at the Second Xiangya Hospital of Central South University in China between 2015 and 2021 were included. Temporal trends in the incidence and risk factors for PC-AKI were evaluated using logistic regression analyses with adjustments for relevant variables. The incidence of PC-AKI has declined significantly from 5.3% in 2015 to 4.1% in 2021 (p < 0.001). This decreasing trend persisted after extensive multivariable adjustments. Of the comorbidities associated with PC-AKI, the proportion of patients with congestive heart failure or hypertension increased, while the proportion of patients older than 75 years, or with an estimated glomerular filtration rate (eGFR) < 30 mL/min/1.73 m2, diabetic nephropathy, or renal stone disease decreased. Among the care practices associated with PC-AKI, the proportion of patients using nephrotoxic drugs decreased, whereas the proportion of patients receiving intravenous fluids > 1000 mL on the day of ICM administration or using iso-osmolar ICM increased. In conclusion, a declining trend in PC-AKI incidence was observed in patients receiving intravenous ICM between 2015 and 2021, which may be related to increased awareness and efforts to prevent PC-AKI.

Apelin-13 alleviates contrast-induced acute kidney injury by inhibiting endoplasmic reticulum stress.

Contrast-induced acute kidney injury (CI-AKI) is a severe complication associated with significant morbidity and mortality, and effective therapeutic strategies are still lacking. Apelin is an endogenous physiological regulator with antioxidative, anti-inflammatory and antiapoptotic properties. However, the role of apelin-13 in CI-AKI remains unclear. In our study, we found that the protein expression levels of apelin were significantly downregulated in rat kidney tissues and HK-2 cells during contrast media treatment. Moreover, we explored the protective effect of apelin-13 on renal tubule damage using in vitro and in vivo models of CI-AKI. Exogenous apelin-13 ameliorated endoplasmic reticulum stress, reactive oxygen species and apoptosis protein expression in contrast media-treated cells and rat kidney tissues. Mechanistically, the downregulation of endoplasmic reticulum stress contributed critically to the antiapoptotic effect of apelin-13. Collectively, our findings reveal the inherent mechanisms by which apelin-13 regulates CI-AKI and provide a prospective target for the prevention of CI-AKI.

Metal-Free Reductive Coupling of para-Quinone Methides with 4-Cyanopyridines Enabled by Pyridine-Boryl Radicals: Access to Pyridylated Diarylmethanes with Anti-Cancer Activity.

Reported herein is a streamlined protocol to produce pyridylated diarylmethanes through pyridine-boryl radical induced reductive coupling between para-quinone methides (p-QMs) and 4-cyanopyridines using bis(pinacolato)diboron (B2 pin2 ) as a templated reagent. The metal-free process is characterized by an operationally simple approach, excellent chemoselectivity (1,2- vs. 1,6-selectivity), and a broad substrate scope with good functional group compatibility. The mechanistic studies provided important insights into the reductive cross-coupling process between diarylmethyl radical and pyridine-boryl radical. Moreover, part of the obtained pyridylated diarylmethane products were screened against a panel of cancer cell lines, and 3 v was confirmed to significantly inhibit the proliferation of head and neck squamous cell carcinoma (HNSCC) cells. This method offers a platform for the preparation of new lead compounds with antitumor activity.

Is intravenous iodinated contrast medium administration really harmful in hospitalized acute kidney injury patients: a propensity score-matched study.

OBJECTIVES: To evaluate the effects of intravenous iodinated contrast medium (ICM) administration on the deterioration of renal function (DRF), new renal replacement therapy (RRT) induction and mortality of hospitalized acute kidney injury (AKI) patients. METHODS: Adult hospitalized patients undergoing a contrast-enhanced or unenhanced CT scan within 7 days after AKI diagnosis from January 2015 to December 2019 were identified in this retrospective study. Propensity score matching was performed. Outcomes in 7 and 30 days after CT scan were compared between the contrast and non-contrast groups. Additional analyses were also performed in patients stratified by SCr levels at AKI diagnosis, times and time of CT scan, and in patients without chronic kidney disease or RRT requirement prior to CT scan. RESULTS: In total, 1172 pairs were generated after 1:1 propensity score matching from 1336 cases exposed to ICM and 2724 unexposed. No significant differences were found in the outcomes between the two groups: DRF, 7.8% vs 9.0% (odds ratio (OR) 0.83, 95% confidence interval (CI) 0.62-1.11) in 7 days, 5.1% vs 5.4% (OR 0.93, 95%CI 0.64-1.34) in 30 days; new RRT induction, 2.3% vs 3.3% (OR 0.72,95%CI 0.43-1.18) in 7 days, 4.2% vs 4.5% (OR 0.95,95%CI 0.64-1.41) in 30 days; and mortality, 3.9% vs 4.8% (OR 0.83,95%CI 0.56-1.22) in 7 days, 9.0% vs 10.2% (OR 0.88,95%CI 0.68-1.15) in 30 days. Subset analyses showed similar results. CONCLUSION: Intravenous ICM administration during AKI duration did not increase the risks of DRF, new RRT induction, and mortality in 7 and 30 days after CT scan. KEY POINTS: • Intravenous ICM administration in hospitalized AKI patients does not increase the risks of deterioration of renal function, RRT induction, and mortality in 7 and 30 days after CT scan. • The effects of intravenous ICM on adverse outcomes are minimal even in AKI patients with high level of SCr values or multiple CT scans.

Epoxyeicosatrienoic acids inhibit the activation of NLRP3 inflammasome in murine macrophages.

Epoxyeicosatrienoic acids (EETs) derived from arachidonic acid exert anti-inflammation effects. We have reported that blocking the degradation of EETs with a soluble epoxide hydrolase (sEH) inhibitor protects mice from lipopolysaccharide (LPS)-induced acute lung injury (ALI). The underlying mechanisms remain essential questions. In this study, we investigated the effects of EETs on the activation of nucleotide-binding domain leucine-rich repeat-containing receptor, pyrin domain-containing-3 (NLRP3) inflammasome in murine macrophages. In an LPS-induced ALI murine model, we found that sEH inhibitor 1-trifluoromethoxyphenyl-3-(1-propionylpiperidin-4-yl), TPPU, profoundly attenuated the pathological injury and inhibited the activation of the NLRP3 inflammasome, characterized by the reduction of the protein expression of NLRP3, ASC, pro-caspase-1, interleukin precursor (pro-IL-1ß), and IL-1ß p17 in the lungs of LPS-treated mice. In vitro, primary peritoneal macrophages from C57BL/6 were primed with LPS and activated with exogenous adenosine triphosphate (ATP). TPPU treatment remarkably reduced the expression of NLRP3 inflammasome-related molecules and blocked the activation of NLRP3 inflammasome. Importantly, four EETs (5,6-EET, 8,9-EET, 11,12-EET, and 14,15-EET) inhibited the activation of NLRP3 inflammasome induced by LPS + ATP or LPS + nigericin in macrophages in various degree. While the inhibitory effect of 5,6-EET was the weakest. Mechanismly, EETs profoundly decreased the content of reactive oxygen species (ROS) and restored the calcium overload in macrophages receiving LPS + ATP stimulation. In conclusion, this study suggests that EETs inhibit the activation of the NLRP3 inflammasome by suppressing calcium overload and ROS production in macrophages, contributing to the therapeutic potency to ALI.

Uniparental Genetic Analyses Reveal the Major Origin of Fujian Tanka from Ancient Indigenous Daic Populations.

The Fujian Tanka people are officially classified as a southern Han ethnic group, whereas they have customs similar to Daic and Austronesion people. Whether they originated in Han or Daic people, there is no consensus. Three hypotheses have been proposed to explain the origin of this group: (1) the Han Chinese origin, (2) the ancient Daic origin, (3) and the admixture between Daic and Han. This study addressed this issue by analyzing the paternal Y chromosome and maternal mtDNA variation of 62 Fujian Tanka and 25 neighboring Han in Fujian. The southern East Asian predominant haplogroups (e.g., Y-chromosome O1a1a-P203 and O1b1a1a-M95, and mtDNA F2a, M7c1, and F1a1) had relatively high frequencies in Tanka. The interpopulation comparison revealed that the Tanka have a closer affinity with Daic populations than with Han Chinese in paternal lineages but are closely clustered with southern Han populations such as Hakka and Chaoshanese in maternal lineages. Network and haplotype-sharing analyses also support the admixture hypothesis. The Fujian Tanka mainly originate from the ancient indigenous Daic people and have only limited gene flows from Han Chinese populations. Notably, the divergence time inferred by the Tanka-specific haplotypes indicates that the formation of Fujian Tanka was a least 1033.8-1050.6 years before present (the early Northern Song dynasty), indicating that they are an indigenous population, not late Daic migrants from southwestern China.

Inhibition of glycolysis alleviates lipopolysaccharide-induced acute lung injury in a mouse model.

Gluconic metabolic reprogramming, immune response, and inflammation are intimately linked. Glycolysis involves in the pathologic progress in acute and chronic inflammatory diseases. However, the involvement of glycolysis in the acute lung injury (ALI) is still unclear. This study investigated the role of glycolysis in an animal model of ALI. First, we found that lactate content in serum was remarkably increased in ALI patients and a murine model induced by intratracheal administration of lipopolysaccharide (LPS). The key proteins involving in glycolysis were robustly elevated, including HK2, PKM2, and HIF-1α. Intriguingly, inhibition of glycolysis by 2-deoxyglucose (2-DG) pronouncedly attenuated the lung tissue pathological injury, accumulation of neutrophil, oxidative stress, expression of proinflammatory factors in the lung of ALI mice induced by LPS. The 2-DG treatment also strongly suppressed the activation of the NOD-like receptor (NLR) family and pyrin domain-containing protein 3 (NLRP3) inflammasome. Furthermore, we investigated the role of glycolysis in the inflammatory response of primary murine macrophages activated by LPS in vitro. We found that the 2-DG treatment remarkably reduced the expression of proinflammatory factors induced by LPS, including tumor necrosis factor-α messenger RNA (mRNA), pro-interleukin (IL)-1ß mRNA, pro-IL-18 mRNA, NLRP3 mRNA, caspase-1 mRNA, and IL-1ß protein. Altogether, these data provide a novel link between gluconic metabolism reprogramming and uncontrolled inflammatory response in ALI. This study suggests glycolytic inhibition as an effective anti-inflammatory strategy in treating ALI.

Cold Exposure Differentially Stimulates Angiogenesis in BAT and WAT of Mice: Implication in Adrenergic Activation.

BACKGROUND/AIMS: To characterize the temporal profile of cold-induced angiogenesis in brown and white adipose tissues of mice in vivo and the temporal changes of angiogenic factors in primary mice brown (BA) and white adipocytes (WA) treated with ß3-adrenoceptor agonist (CL316,243) in vitro. METHODS: 8-week old male C57BL/6J mice were individually housed in conventional cages under cold exposure (4°C) for 1, 2, 3, 4 and 5 days. Interscapular brown adipose tissue (iBAT), inguinal subcutaneous (sWAT) and epididymal white adipose tissues (eWAT) were harvested for immunohistochemical and gene expression analysis. In vitro, primary mice BA and WA treated with or without CL316,243 were harvested for gene expression and protein secretion analysis. RESULTS: A combination of morphological and genetic (Vegfa, Vegfr2, Hif-1α, Pai1 and Pedf) analyses demonstrated depot-specific angiogenesis in response to cold exposure. Upon CL316,243 treatment, angiogenic factors (Vegfa, Vegfr2, Hif-1α, Pai1 and Pedf) and secreted protein VEGFA were transiently increased in both BA and WA. CONCLUSION: Our results show that iBAT is highly responsive to cold-induced angiogenesis that is mainly supported by sWAT with a lesser extent by eWAT. Moreover, the angiogenesis is a transient process with the angiogenic factors may work in an autocrine/paracrine manner.

Circadian disruption during fetal development promotes pathological cardiac remodeling in male mice.

Disruption of circadian rhythms during fetal development may predispose mice to developing heart disease later in life. Here, we report that male, but not female, mice that had experienced chronic circadian disturbance (CCD) in utero were more susceptible to pathological cardiac remodeling compared with mice that had developed under normal intrauterine conditions. CCD-treated males showed ventricular chamber dilatation, enhanced myocardial fibrosis, decreased contractility, higher rates of induced tachyarrhythmia, and elevated expression of biomarkers for heart failure and myocardial remodeling. In utero CCD exposure also triggered sex-dependent changes in cardiac gene expression, including upregulation of the secretoglobin gene, Scgb1a1, in males. Importantly, cardiac overexpression of Scgb1a1 was sufficient to induce myocardial hypertrophy in otherwise naive male mice. Our findings reveal that in utero CCD exposure predisposes male mice to pathological remodeling of the heart later in life, likely as a consequence of SCGB1A1 upregulation.

Outcome prediction for acute kidney injury among hospitalized children via eXtreme Gradient Boosting algorithm.

Acute kidney injury (AKI) is common among hospitalized children and is associated with a poor prognosis. The study sought to develop machine learning-based models for predicting adverse outcomes among hospitalized AKI children. We performed a retrospective study of hospitalized AKI patients aged 1 month to 18 years in the Second Xiangya Hospital of Central South University in China from 2015 to 2020. The primary outcomes included major adverse kidney events within 30 days (MAKE30) (death, new renal replacement therapy, and persistent renal dysfunction) and 90-day adverse outcomes (chronic dialysis and death). The state-of-the-art machine learning algorithm, eXtreme Gradient Boosting (XGBoost), and the traditional logistic regression were used to establish prediction models for MAKE30 and 90-day adverse outcomes. The models' performance was evaluated by split-set test. A total of 1394 pediatric AKI patients were included in the study. The incidence of MAKE30 and 90-day adverse outcomes was 24.1% and 8.1%, respectively. In the test set, the area under the receiver operating characteristic curve (AUC) of the XGBoost model was 0.810 (95% CI 0.763-0.857) for MAKE30 and 0.851 (95% CI 0.785-0.916) for 90-day adverse outcomes, The AUC of the logistic regression model was 0.786 (95% CI 0.731-0.841) for MAKE30 and 0.759 (95% CI 0.654-0.864) for 90-day adverse outcomes. A web-based risk calculator can facilitate the application of the XGBoost models in daily clinical practice. In conclusion, XGBoost showed good performance in predicting MAKE30 and 90-day adverse outcomes, which provided clinicians with useful tools for prognostic assessment in hospitalized AKI children.

Acute Kidney Disease in Hospitalized Pediatric Patients With Acute Kidney Injury in China.

Objective: The epidemiology and outcomes of acute kidney disease (AKD) after acute kidney injury (AKI) in hospitalized children are poorly described. The aim of this study is to investigate the prevalence, predictive factors, and clinical outcomes of AKD in hospitalized children with AKI. Methods: Children (1 month-18 years) with AKI during hospitalization in the Second Xiangya Hospital from January 2015 to December 2020 were identified. AKD was defined based on the consensus report of the Acute Disease Quality Initiative 16 workgroup. The endpoints include adverse outcomes in 30 and 90 days. Multivariable logistic regression analyses were used to estimate the odds ratio of 30- and 90-day adverse outcomes associated with AKD and identify the risk factors of AKD. Results: AKD was developed in 42.3% (419/990) of the study patients, with 186 in AKD stage 1, 107 in AKD stage 2, and 126 in AKD stage 3. Pediatric patients with AKD stages 2-3 had significantly higher rates of developing 30- and 90-day adverse outcomes than those with AKD stage 0 and 1. The adjusted odds ratio of AKD stage 2-3 was 12.18 (95% confidence interval (CI), 7.38 - 20.09) for 30-day adverse outcomes and decreased to 2.49 (95% CI, 1.26 - 4.91) for 90-day adverse outcomes. AKI stages 2 and 3, as well as glomerulonephritis, were the only predictive factors for AKD stage 2-3. Conclusion: AKD is frequent among hospitalized pediatric AKI patients. AKD stage 2-3 represents a high-risk subpopulation among pediatric AKI survivors and is independently associated with 30- and 90-day adverse outcomes. Awareness of the potential risks associated with AKD stage 2-3 and its risk factors may help improve outcomes through careful monitoring and timely intervention.

Development and Validation of Machine Learning Models for Real-Time Mortality Prediction in Critically Ill Patients With Sepsis-Associated Acute Kidney Injury.

Background: Sepsis-associated acute kidney injury (SA-AKI) is common in critically ill patients, which is associated with significantly increased mortality. Existing mortality prediction tools showed insufficient predictive power or failed to reflect patients' dynamic clinical evolution. Therefore, the study aimed to develop and validate machine learning-based models for real-time mortality prediction in critically ill patients with SA-AKI. Methods: The multi-center retrospective study included patients from two distinct databases. A total of 12,132 SA-AKI patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) were randomly allocated to the training, validation, and internal test sets. An additional 3,741 patients from the eICU Collaborative Research Database (eICU-CRD) served as an external test set. For every 12 h during the ICU stays, the state-of-the-art eXtreme Gradient Boosting (XGBoost) algorithm was used to predict the risk of in-hospital death in the following 48, 72, and 120 h and in the first 28 days after ICU admission. Area under the receiver operating characteristic curves (AUCs) were calculated to evaluate the models' performance. Results: The XGBoost models, based on routine clinical variables updated every 12 h, showed better performance in mortality prediction than the SOFA score and SAPS-II. The AUCs of the XGBoost models for mortality over different time periods ranged from 0.848 to 0.804 in the internal test set and from 0.818 to 0.748 in the external test set. The shapley additive explanation method provided interpretability for the XGBoost models, which improved the understanding of the association between the predictor variables and future mortality. Conclusions: The interpretable machine learning XGBoost models showed promising performance in real-time mortality prediction in critically ill patients with SA-AKI, which are useful tools for early identification of high-risk patients and timely clinical interventions.

Prediction of Mortality Risk After Ischemic Acute Kidney Injury With a Novel Prognostic Model: A Multivariable Prediction Model Development and Validation Study.

Background and Objectives: Acute kidney injury (AKI) that results from ischemia is a common clinical syndrome and correlates with high morbidity and mortality among hospitalized patients. However, a clinical tool to predict mortality risk of ischemic AKI is not available. In this study, we aimed to develop and validate models to predict the 30-day and 1-year mortality risk of hospitalized patients with ischemic AKI. Methods: A total of 1,836 admissions with ischemic AKI were recruited from 277,898 inpatients admitted to three affiliated tertiary general hospitals of Central South University in China between January 2015 and December 2015. Patients in the final analysis were followed up for 1 year. Study patients were randomly divided in a 7:3 ratio to form the training cohort and validation cohort. Multivariable regression analyses were used for developing mortality prediction models. Results: Hepatorenal syndrome, shock, central nervous system failure, Charlson comorbidity index (≥2 points), mechanical ventilation, renal function at discharge were independent risk factors for 30-day mortality after ischemic AKI, while malignancy, sepsis, heart failure, liver failure, Charlson comorbidity index (≥2 points), mechanical ventilation, and renal function at discharge were predictors for 1-year mortality. The area under the receiver operating characteristic curves (AUROCs) of 30-day prediction model were 0.878 (95% confidence interval (CI): 0.849-0.908) in the training cohort and 0.867 (95% CI: 0.820-0.913) in the validation cohort. The AUROCs of the 1-year mortality prediction in the training and validation cohort were 0.803 (95% CI: 0.772-0.834) and 0.788 (95% CI: 0.741-0.835), respectively. Conclusion: Our easily applied prediction models can effectively identify individuals at high mortality risk within 30 days or 1 year in hospitalized patients with ischemic AKI. It can guide the optimal clinical management to minimize mortality after an episode of ischemic AKI.

Effects of mesenchymal stem cells in renovascular disease of preclinical and clinical studies: a systematic review and meta-analysis.

Renal artery stenosis (RAS) causes severe renovascular hypertension, worsening kidney function, and increased cardiovascular morbidity. According to recent studies, mesenchymal stem cells (MSCs) administration is a promising therapy for the improvement of RAS outcomes. The meta-analysis aims to evaluate the therapeutic effects of MSC therapy on RAS. We performed a search in MEDLINE, Web of Science, Embase, and Cochrane Library from inception to 5, October 2022. We included 16 preclinical and 3 clinical studies in this meta-analysis. In preclinical studies, the pooled results indicated that animals treated with MSCs had lower levels of systolic blood pressure (SBP) (SMD = - 1.019, 95% CI - 1.434 to - 0.604, I2 = 37.2%, P = 0.000), serum creatinine (Scr) (SMD = - 1.112, 95% CI - 1.932 to - 0.293, I2 = 72.0%, P = 0.008), and plasma renin activity (PRA) (SMD = - 0.477, 95% CI - 0.913 to 0.042, I2 = 43.4%, P = 0.032). The studies also revealed increased levels of renal blood flow (RBF) in stenotic kidney (STK) (SMD = 0.774, 95% CI - 0.351 to 1.197, I2 = 0%, P = 0.000) and the glomerular filtration rate (GFR) of STK (SMD = 1.825, 95% CI 0.963 to 2.688, I2 = 72.6%, P = 0.000). In clinical studies, the cortical perfusion and fractional hypoxia of the contralateral kidney (CLK) were alleviated by MSC therapy. Taken together, this meta-analysis revealed that MSCs therapy might be a promising treatment for RAS. However, due to the discrepancy between preclinical studies and early clinical trials outcomes, MSC therapy couldn't be recommended in clinical care for the moment, more high-quality randomized controlled clinical trials are needed to validate our conclusions and standardize MSCs protocols.

Machine learning for early discrimination between transient and persistent acute kidney injury in critically ill patients with sepsis.

Acute kidney injury (AKI) is commonly present in critically ill patients with sepsis. Early prediction of short-term reversibility of AKI is beneficial to risk stratification and clinical treatment decision. The study sought to use machine learning methods to discriminate between transient and persistent sepsis-associated AKI. Septic patients who developed AKI within the first 48 h after ICU admission were identified from the Medical Information Mart for Intensive Care III database. AKI was classified as transient or persistent according to the Acute Disease Quality Initiative workgroup consensus. Five prediction models using logistic regression, random forest, support vector machine, artificial neural network and extreme gradient boosting were constructed, and their performance was evaluated by out-of-sample testing. A simplified risk prediction model was also derived based on logistic regression and features selected by machine learning algorithms. A total of 5984 septic patients with AKI were included, 3805 (63.6%) of whom developed persistent AKI. The artificial neural network and logistic regression models achieved the highest area under the receiver operating characteristic curve (AUC) among the five machine learning models (0.76, 95% confidence interval [CI] 0.74-0.78). The simplified 14-variable model showed adequate discrimination, with the AUC being 0.76 (95% CI 0.73-0.78). At the optimal cutoff of 0.63, the sensitivity and specificity of the simplified model were 63% and 76% respectively. In conclusion, a machine learning-based simplified prediction model including routine clinical variables could be used to differentiate between transient and persistent AKI in critically ill septic patients. An easy-to-use risk calculator can promote its widespread application in daily clinical practice.