Machine learning derived serum creatinine trajectories in acute kidney injury in critically ill patients with sepsis.

BACKGROUND: Current classification for acute kidney injury (AKI) in critically ill patients with sepsis relies only on its severity-measured by maximum creatinine which overlooks inherent complexities and longitudinal evaluation of this heterogenous syndrome. The role of classification of AKI based on early creatinine trajectories is unclear. METHODS: This retrospective study identified patients with Sepsis-3 who developed AKI within 48-h of intensive care unit admission using Medical Information Mart for Intensive Care-IV database. We used latent class mixed modelling to identify early creatinine trajectory-based classes of AKI in critically ill patients with sepsis. Our primary outcome was development of acute kidney disease (AKD). Secondary outcomes were composite of AKD or all-cause in-hospital mortality by day 7, and AKD or all-cause in-hospital mortality by hospital discharge. We used multivariable regression to assess impact of creatinine trajectory-based classification on outcomes, and eICU database for external validation. RESULTS: Among 4197 patients with AKI in critically ill patients with sepsis, we identified eight creatinine trajectory-based classes with distinct characteristics. Compared to the class with transient AKI, the class that showed severe AKI with mild improvement but persistence had highest adjusted risks for developing AKD (OR 5.16; 95% CI 2.87-9.24) and composite 7-day outcome (HR 4.51; 95% CI 2.69-7.56). The class that demonstrated late mild AKI with persistence and worsening had highest risks for developing composite hospital discharge outcome (HR 2.04; 95% CI 1.41-2.94). These associations were similar on external validation. CONCLUSIONS: These 8 classes of AKI in critically ill patients with sepsis, stratified by early creatinine trajectories, were good predictors for key outcomes in patients with AKI in critically ill patients with sepsis independent of their AKI staging.

Risk factors and early prediction of cardiorenal syndrome type 3 among acute kidney injury patients: a cohort study.

BACKGROUND: Type 3 cardiorenal syndrome (CRS type 3) triggers acute cardiac injury from acute kidney injury (AKI), raising mortality in AKI patients. We aimed to identify risk factors for CRS type 3 and develop a predictive nomogram. METHODS: In this retrospective study, 805 AKI patients admitted at the Department of Nephrology, Second Hospital of Shanxi Medical University from 1 January 2017, to 31 December 2021, were categorized into a study cohort (406 patients from 2017.1.1-2021.6.30, with 63 CRS type 3 cases) and a validation cohort (126 patients from 1 July 2021 to 31 Dec 2021, with 22 CRS type 3 cases). Risk factors for CRS type 3, identified by logistic regression, informed the construction of a predictive nomogram. Its performance and accuracy were evaluated by the area under the curve (AUC), calibration curve and decision curve analysis, with further validation through a validation cohort. RESULTS: The nomogram included 6 risk factors: age (OR = 1.03; 95%CI = 1.009-1.052; p = 0.006), cardiovascular disease (CVD) history (OR = 2.802; 95%CI = 1.193-6.582; p = 0.018), mean artery pressure (MAP) (OR = 1.033; 95%CI = 1.012-1.054; p = 0.002), hemoglobin (OR = 0.973; 95%CI = 0.96--0.987; p < 0.001), homocysteine (OR = 1.05; 95%CI = 1.03-1.069; p < 0.001), AKI stage [(stage 1: reference), (stage 2: OR = 5.427; 95%CI = 1.781-16.534; p = 0.003), (stage 3: OR = 5.554; 95%CI = 2.234-13.805; p < 0.001)]. The nomogram exhibited excellent predictive performance with an AUC of 0.907 in the study cohort and 0.892 in the validation cohort. Calibration and decision curve analyses upheld its accuracy and clinical utility. CONCLUSIONS: We developed a nomogram predicting CRS type 3 in AKI patients, incorporating 6 risk factors: age, CVD history, MAP, hemoglobin, homocysteine, and AKI stage, enhancing early risk identification and patient management.

Clinical significance of the lactate-to-albumin ratio on prognosis in critically ill patients with acute kidney injury.

OBJECTIVE: To explore the relationship between lactate-to-albumin ratio (LAR) at ICU admission and prognosis in critically ill patients with acute kidney injury (AKI). METHODS: A retrospective analysis was conducted. Patients were divided into low (<0.659) LAR and high LAR (≥0.659) groups. Least absolute shrinkage and selection operator regression analysis was conducted to select variables associated with the 30-day prognosis. Cox regression analyses were performed to assess the association between LAR and mortality. Kaplan-Meier curves were plotted to compare cumulative survival rates between high and low LAR groups. Subgroup analysis was employed to assess the stability of the results. ROC curve was used to determine the diagnostic efficacy of LAR on prognosis. RESULTS: A nonlinear relationship was observed between LAR and the risk of 30-day and 360-day all-cause mortality in AKI patients (p < 0.001). Cox regulation showed that high LAR (≥ 0.659) was an independent risk factor for 30-day and 360-day all-cause mortality in patients with AKI (p < 0.001). The Kaplan-Meier survival curves demonstrated a noteworthy decrease in cumulative survival rates at both 30 and 360 days for the high LAR group in comparison to the low LAR group (p < 0.001). Subgroup analyses demonstrated the stability of the results. ROC curves showed that LAR had a diagnostic advantage when compared with lactate or albumin alone (p < 0.001). CONCLUSION: High LAR (≥0.659) at ICU admission was an independent risk factor for both short-term (30-day) and long-term (360-day) all-cause mortality in patients with AKI.

Predictive performance of two types of urinary biomarkers for renal non-recovery in sepsis-associated acute kidney injury: a prospective observational study.

BACKGROUND AND PURPOSE: Renal non-recovery is known to have negative prognostic implications in patients suffering from acute kidney injury (AKI). Nevertheless, the identification of biomarkers for predicting renal non-recovery in sepsis-associated AKI (SA-AKI) within clinical settings remains unresolved. This study aims to evaluate and compare the predictive ability for renal non-recovery, use of kidney replacement therapy (KRT) in the Intensive Care Unit (ICU), and 30-day mortality after SA-AKI by two urinary biomarkers, namely C-C motif chemokine ligand 14 (CCL14) and [TIMP-2]•[IGFBP7]. METHODS: We prospectively screened adult patients who met the criteria for AKI stage 2-3 and Sepsis-3.0 in two ICUs from January 2019 to May 2022. Patients who developed new-onset SA-AKI after ICU admission were enrolled and urinary biomarkers including [TIMP-2]•[IGFBP7] and CCL14 were detected at the time of SA-AKI diagnosis. The primary endpoint was non-recovery from SA-AKI within 7 days. The secondary endpoints were the use of KRT in the ICU and 30-day mortality after SA-AKI. The individual discriminative ability of [TIMP-2]•[IGFBP7] and CCL14 to predict renal non-recovery were evaluated by the area under receiver operating characteristics curve (AUC). RESULTS: 141 patients with stage 2-3 SA-AKI were finally included, among whom 54 (38.3%) experienced renal non-recovery. Urinary CCL14 exhibited a higher predictive capability for renal non-recovery compared to [TIMP-2]•[IGFBP7], with CCL14 showing an AUC of 0.901, versus an AUC of 0.730 for [TIMP-2]•[IGFBP7] (P = 0.001). Urinary CCL14 and [TIMP-2]•[IGFBP7] demonstrated a moderate predictive value for the need for KRT in ICU, with AUC values of 0.794 and 0.725, respectively; The AUC of [TIMP-2]•[IGFBP7] combined with CCL14 reached up to 0.816. Urinary CCL14 and [TIMP-2]•[IGFBP7] exhibited poor predictive power for 30-day mortality, with respective AUC values of 0.623 and 0.593. CONCLUSION: Urinary CCL14 had excellent predictive value for renal non-recovery in SA-AKI patients. For predicting the use of KRT in the ICU, the predictive capability of urinary [TIMP-2]•[IGFBP7] or CCL14 was fair. However, a combination of [TIMP-2]•[IGFBP7] and CCL14 showed good predictive ability for the use of KRT.

Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in Critically Ill Elderly Patients During Hospitalization: Internet-Based and Interpretable Model Study.

BACKGROUND: Acute kidney disease (AKD) affects more than half of critically ill elderly patients with acute kidney injury (AKI), which leads to worse short-term outcomes. OBJECTIVE: We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps. METHODS: Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South University were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators within 24 hours of the first diagnosis of AKI and the fluctuation range of some indicators, namely delta (day 3 after AKI minus day 1), as features. Six machine learning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpreting; and the Heroku platform for deploying the best-performing models as web-based apps. RESULTS: For the model of predicting the risk of AKD in elderly patients with AKI during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841-0.865), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addition, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.868, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed users to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model's top 10 influencing factors conducted based on the SHAP value, partial dependence plots revealed the optimal cutoff of some interventionable indicators. The top 5 factors predicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitrogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 factors determining in-hospital mortality were age, BUN on day 1, vasopressor use, BUN on day 3, and partial pressure of carbon dioxide (PaCO2). CONCLUSIONS: We developed and validated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively. The top 10 factors that influenced the AKD risk and mortality during hospitalization were identified and explained visually, which might provide useful applications for intelligent management and suggestions for future prospective research.

Urinary L-FABP as an Early Biomarker for Pediatric Acute Kidney Injury Following Cardiac Surgery with Cardiopulmonary Bypass: A Systematic Review and Meta-Analysis.

Acute kidney injury (AKI) following surgery with cardiopulmonary bypass (CPB-AKI) is common in pediatrics. Urinary liver-type fatty acid binding protein (uL-FABP) increases in some kidney diseases and may indicate CPB-AKI earlier than current methods. The aim of this systematic review with meta-analysis was to evaluate the potential role of uL-FABP in the early diagnosis and prediction of CPB-AKI. Databases Pubmed/MEDLINE, Scopus, and Web of Science were searched on 12 November 2023, using the MeSH terms "Children", "CPB", "L-FABP", and "Acute Kidney Injury". Included papers were revised. AUC values from similar studies were pooled by meta-analysis, performed using random- and fixed-effect models, with p < 0.05. Of 508 studies assessed, nine were included, comprising 1658 children, of whom 561 (33.8%) developed CPB-AKI. Significantly higher uL-FABP levels in AKI versus non-AKI patients first manifested at baseline to 6 h post-CPB. At 6 h, uL-FABP correlated with CPB duration (r = 0.498, p = 0.036), postoperative serum creatinine (r = 0.567, p < 0.010), and length of hospital stay (r = 0.722, p < 0.0001). Importantly, uL-FABP at baseline (AUC = 0.77, 95% CI: 0.64-0.89, n = 365), 2 h (AUC = 0.71, 95% CI: 0.52-0.90, n = 509), and 6 h (AUC = 0.76, 95% CI: 0.72-0.80, n = 509) diagnosed CPB-AKI earlier. Hence, higher uL-FABP levels associate with worse clinical parameters and may diagnose and predict CPB-AKI earlier.

Development and validation of a race-agnostic computable phenotype for kidney health in adult hospitalized patients.

Standard race adjustments for estimating glomerular filtration rate (GFR) and reference creatinine can yield a lower acute kidney injury (AKI) and chronic kidney disease (CKD) prevalence among African American patients than non-race adjusted estimates. We developed two race-agnostic computable phenotypes that assess kidney health among 139,152 subjects admitted to the University of Florida Health between 1/2012-8/2019 by removing the race modifier from the estimated GFR and estimated creatinine formula used by the race-adjusted algorithm (race-agnostic algorithm 1) and by utilizing 2021 CKD-EPI refit without race formula (race-agnostic algorithm 2) for calculations of the estimated GFR and estimated creatinine. We compared results using these algorithms to the race-adjusted algorithm in African American patients. Using clinical adjudication, we validated race-agnostic computable phenotypes developed for preadmission CKD and AKI presence on 300 cases. Race adjustment reclassified 2,113 (8%) to no CKD and 7,901 (29%) to a less severe CKD stage compared to race-agnostic algorithm 1 and reclassified 1,208 (5%) to no CKD and 4,606 (18%) to a less severe CKD stage compared to race-agnostic algorithm 2. Of 12,451 AKI encounters based on race-agnostic algorithm 1, race adjustment reclassified 591 to No AKI and 305 to a less severe AKI stage. Of 12,251 AKI encounters based on race-agnostic algorithm 2, race adjustment reclassified 382 to No AKI and 196 (1.6%) to a less severe AKI stage. The phenotyping algorithm based on refit without race formula performed well in identifying patients with CKD and AKI with a sensitivity of 100% (95% confidence interval [CI] 97%-100%) and 99% (95% CI 97%-100%) and a specificity of 88% (95% CI 82%-93%) and 98% (95% CI 93%-100%), respectively. Race-agnostic algorithms identified substantial proportions of additional patients with CKD and AKI compared to race-adjusted algorithm in African American patients. The phenotyping algorithm is promising in identifying patients with kidney disease and improving clinical decision-making.

Biomarkers of acute kidney injury: From discovery to the future of clinical practice.

Purpose of this review Acute kidney injury (AKI) is a complex syndrome whose development is associated with an increased morbidity and mortality. Recent studies show that this syndrome is a common complication in critically ill and surgical patients the trajectory of which may differ. As AKI can be induced by different triggers, it is complex and therefore challenging to manage patients with AKI. This review strives to provide a brief historical perspective on AKI, elucidate recent developments in diagnosing and managing AKI, and show the current usage of novel biomarkers in both clinical routine and research. In addition, we provide a perspective on potential future developments and their impact of AKI understanding and management. Recent findings/developments Recent studies show the merits of stress and damage biomarkers, highlighting limitations of the current KDIGO definition that only uses the functional biomarkers serum creatinine and urine output. The use of novel biomarkers led to the introduction of the concept of "subclinical AKI". This new classification may allow a more distinct management of affected or at risk patients. Ongoing studies, such as BigpAK-2 and PrevProgAKI, investigate the implementation of biomarker-guided interventions in clinical practice and may demonstrate an improvement in patients' outcome. Summary The ongoing scientific efforts surrounding AKI have deepened our understanding of the syndrome prompting an expansion of existing concepts. A future integration of stress and damage biomarkers in AKI management, may lead to an individualized therapy in this area.

Tissue Inhibitor Metalloproteinase-2·IGF-Binding Protein 7 for the Prediction of Acute Kidney Injury following Cardiac Surgery.

INTRODUCTION: Cardiac surgery-associated acute kidney injury (CSA-AKI) is a common complication associated with increased morbidity and mortality. Tissue inhibitor metalloproteinase-2·insulin-like growth factor-binding protein 7 (TIMP-2·IGFBP7) determines tubular stress markers, which may occur prior to tubular damage. Previous studies on the use of TIMP-2·IGFBP7 for the prediction of CSA-AKI showed divergent results. Therefore, this study aimed to explore the predictive value of TIMP-2·IGFBP7 measurements for the early detection of acute kidney injury (AKI) and short-term adverse outcomes after cardiac surgery. METHODS: In the prospective cohort study, blood and urine samples were collected 6-12 h after cardiac surgery. Blood samples to monitor serum creatinine levels were additionally extracted from days 1 to 7. AKI was defined based on the KDIGO consensus guidelines. AKI within 7 days following surgery was the primary outcome. The initiation of renal replacement therapy, in intensive care unit mortality, and the combination of both were secondary outcomes. RESULTS: A total of 557 patients were enrolled; 134 (24.06%) of them developed AKI and 33 (5.9%) had moderate or severe AKI. AKI developed more frequently in elderly patients with diabetes or with higher baseline serum creatinine levels. Patients with AKI had higher EuroSCORE II, Cleveland Clinic Score, and simplified renal index (SRI) than those without AKI. Urinary TIMP-2·IGFBP7 was significantly higher in patients with AKI. The area under the curve was 0.66 in predicting all AKI and 0.70 in predicting stages 2 and 3 AKI. The resulting sensitivity and specificity were 44.0% and 83.9%, respectively, for a calculated threshold TIMP-2·IGFBP7 value of 0.265 (ng/mL)2/1,000. The TIMP-2·IGFBP7 values, SRI score, and age were significantly associated with AKI within 7 days postoperatively. A total of 33 patients reached the composite endpoint; the percentage of patients who reached the composite endpoint in the TIMP-2·IGFBP7 of >0.265 (ng/ml)2/1,000 group was significantly higher than that of ≤0.265 (ng/mL)2/1,000 group. CONCLUSIONS: Postoperative implementation of TIMP-2·IGFBP7 improved the prediction of CSA-AKI and may aid in identifying patients at risk of short-term adverse outcomes. We identified an ideal calculated cutoff value of 0.265 (ng/mL)2/1,000 for the prediction of CSA-AKI among all AKI patients.

Obesity is associated with acute kidney injury in ST-segment-elevation myocardial infarction undergoing percutaneous coronary intervention: A national representative cohort study.

BACKGROUND: Acute kidney injury (AKI) is a frequent and potentially life-threatening complication after percutaneous coronary intervention (PCI) in patients with ST-segment-elevation myocardial infarction (STEMI). However, the relationship between obesity and the risk of AKI in this specific patient population has not been previously examined. METHODS: We queried the National Inpatient Sample (2016-2019) using ICD-10 codes to obtain a sample of adults with STEMI undergoing PCI. All patients were further subcategorized into obese and nonobese cohorts. The primary outcome was the incidence of AKI. Multivariate regression analysis was performed to assess the impact of obesity on AKI. The consistency of this correlation between subgroups was investigated using subgroup analysis and interaction testing. RESULTS: A total of 62,599 (weighted national estimate of 529,016) patients were identified, of which 9.80% (n = 6137) had AKI. Obesity comprised 19.78% (n = 1214) of the AKI cohort. Obese patients were on average younger, male, white, and had more comorbidities. Additionally, there was a significant positive association between obesity and AKI incidence (adjusted odds ratio [aOR]: 1.24, 95% confidence interval [CI]: 1.15-1.34), which was more pronounced in female patients (aOR: 1.56, 95% CI: 1.33-1.82, p < 0.001, p-interaction = 0.008). The AKI incidence in these patients increased steadily during the 4-year study period, and it was consistently higher in obese patients than in nonobese patients (p-trend < 0.001 for all). CONCLUSIONS: Obesity was independently associated with a greater risk of AKI among adults with STEMI undergoing PCI, particularly in female patients.

Association between triglyceride glucose and acute kidney injury in patients with acute myocardial infarction: a propensity score­matched analysis.

BACKGROUND: Acute kidney injury (AKI) in patients with acute myocardial infarction (AMI) often indicates a poor prognosis. OBJECTIVE: This study aimed to investigate the association between the TyG index and the risk of AKI in patients with AMI. METHODS: Data were taken from the Medical Information Mart for Intensive Care (MIMIC) database. A 1:3 propensity score (PS) was set to match patients in the AKI and non-AKI groups. Multivariate logistic regression analysis, restricted cubic spline (RCS) regression and subgroup analysis were performed to assess the association between TyG index and AKI. RESULTS: Totally, 1831 AMI patients were included, of which 302 (15.6%) had AKI. The TyG level was higher in AKI patients than in non-AKI patients (9.30 ± 0.71 mg/mL vs. 9.03 ± 0.73 mg/mL, P < 0.001). Compared to the lowest quartile of TyG levels, quartiles 3 or 4 had a higher risk of AKI, respectively (Odds Ratiomodel 4 = 2.139, 95% Confidence Interval: 1.382-3.310, for quartile 4 vs. quartile 1, Ptrend < 0.001). The risk of AKI increased by 34.4% when the TyG level increased by 1 S.D. (OR: 1.344, 95% CI: 1.150-1.570, P < 0.001). The TyG level was non-linearly associated with the risk of AKI in the population within a specified range. After 1:3 propensity score matching, the results were similar and the TyG level remained a risk factor for AKI in patients with AMI. CONCLUSION: High levels of TyG increase the risk of AKI in AMI patients. The TyG level is a predictor of AKI risk in AMI patients, and can be used for clinical management.

Acute liver failure.

ABSTRACT: Acute liver failure, commonly caused by acetaminophen overdose, is associated with numerous systemic complications including cerebral edema, hypotension, acute kidney injury, and infection. Management is primarily supportive, with an emphasis on excellent neurocritical care. Although some antidotes and targeted treatments exist, the only definitive treatment remains orthotopic liver transplant.

Serum Nostrin-A risk factor of death, kidney replacement therapy and acute kidney disease in acute kidney injury.

BACKGROUND: The prediction of Acute Kidney Injury (AKI)-related outcomes remains challenging. Persistent kidney excretory dysfunction for longer than 7 days has been defined as Acute Kidney Disease (AKD). In this study, we prospectively quantified serum Nostrin, an essential regulator of endothelial NO metabolism, in hospitalized patients with AKI. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: In-hospital subjects with AKI of various etiology were identified through the in-hospital AKI alert system of the Brandenburg University Hospital. Serum Nostrin, and serum NGAL and KIM-1 were measured within a maximum of 48 hours from the timepoint of initial diagnosis of AKI. The following endpoints were defined: in-hospital death, need of kidney replacement therapy (KRT), recovery of kidney function (ROKF) until discharge. RESULTS: AKI patients had significantly higher serum Nostrin levels compared to Controls. The level of serum Nostrin increased significantly with the severity of AKI. Within the group of AKI patients (n = 150) the in-hospital mortality was 16.7%, KRT was performed in 39.3%, no ROKF occurred in 28%. Patients who required KRT had significantly higher levels of serum Nostrin compared to patients who did not require KRT. Significantly higher levels of serum Nostrin were also detected in AKI patients without ROKF compared to patients with ROKF. In addition, low serum Nostrin levels at the timepoint of AKI diagnosis were predictive of in-hospital survival. For comparison, the serum concentrations of NGAL and KIM-1 were determined in parallel to the Nostrin concentrations and the results confirm the prognostic properties of serum Nostrin in AKI. CONCLUSIONS: The current study suggests serum Nostrin as novel biomarker of AKI-associated mortality, KRT and Acute Kidney Disease.

Machine learning for prediction of acute kidney injury in patients diagnosed with sepsis in critical care.

BACKGROUND AND OBJECTIVE: Acute Kidney Injury (AKI) is a common and severe complication in patients diagnosed with sepsis. It is associated with higher mortality rates, prolonged hospital stays, increased utilization of medical resources, and financial burden on patients' families. This study aimed to establish and validate predictive models using machine learning algorithms to accurately predict the occurrence of AKI in patients diagnosed with sepsis. METHODS: This retrospective study utilized real observational data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. It included patients aged 18 to 90 years diagnosed with sepsis who were admitted to the ICU for the first time and had hospital stays exceeding 48 hours. Predictive models, employing various machine learning algorithms including Light Gradient Boosting Machine (LightGBM), EXtreme Gradient Boosting (XGBoost), Random Forest (RF), Decision Tree (DT), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Logistic Regression (LR), were developed. The dataset was randomly divided into training and test sets at a ratio of 4:1. RESULTS: A total of 10,575 sepsis patients were included in the analysis, of whom 8,575 (81.1%) developed AKI during hospitalization. A selection of 47 variables was utilized for model construction. The models derived from LightGBM, XGBoost, RF, DT, ANN, SVM, and LR achieved AUCs of 0.801, 0.773, 0.772, 0.737, 0.720, 0.765, and 0.776, respectively. Among these models, LightGBM demonstrated the most superior predictive performance. CONCLUSIONS: These machine learning models offer valuable predictive capabilities for identifying AKI in patients diagnosed with sepsis. The LightGBM model, with its superior predictive capability, could aid clinicians in early identification of high-risk patients.

Acute kidney failure reveals primary renal non-Hodgkin lymphoma.

A male patient in his 60s was admitted to our hospital with symptoms of dyspnoea, asthenia, diaphoresis and acute kidney failure. No tumour or infection was detected in initial screening. However, laboratory examination suggested that the acute kidney failure was due to an intrarenal cause, exhibiting a tubular injury pattern and indications of tumour lysis syndrome. Initial hydration therapy, paired with intravenous rasburicase, rapidly improved the kidney function. Unfortunately, the kidney function deteriorated once again, prompting a kidney biopsy that revealed an aggressive diffuse large B-cell non-Hodgkin lymphoma of the kidney. The chemotherapy, comprised of R-CHOP scheme, led to a full recovery of the kidney function and complete remission of the lymphoma. Primary renal non-Hodgkin lymphoma without nodal manifestation is rare, and its pathophysiology is poorly understood. Therapy schemes can vary significantly between cases, relying primarily on non-renal-specific haemato-oncological guidelines. Therefore, further studies are needed to develop the best therapeutic approaches.

Evaluating biomarkers for contrast-induced nephropathy following coronary interventions: an umbrella review on meta-analyses.

BACKGROUND: Contrast-induced nephropathy (CIN) is a form of acute kidney injury (AKI) occurring in patients undergoing cardiac catheterization, such as coronary angiography (CAG) or percutaneous coronary intervention (PCI). Although the conventional criterion for CIN detection involves a rise in creatinine levels within 72 h after contrast media injection, several limitations exist in this definition. Up to now, various meta-analyses have been undertaken to assess the accuracy of different biomarkers of CIN prediction. However, the existing body of research lacks a cohesive overview. To address this gap, a comprehensive umbrella review was necessary to consolidate and summarize the outcomes of prior meta-analyses. This umbrella study aimed to offer a current, evidence-based understanding of the prognostic value of biomarkers in predicting CIN. METHODS: A systematic search of international databases, including PubMed, Scopus, and Web of Science, from inception to December 12, 2023, was conducted to identify meta-analyses assessing biomarkers for CIN prediction. Our own meta-analysis was performed by extracting data from the included studies. Sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio were assessed using Meta-Disc and CMA softwares. RESULTS: Twelve studies were ultimately included in the umbrella review. The results revealed that neutrophil gelatinase-associated lipocalin (NGAL) exhibited the highest area under the curve (AUC), followed by cystatin-C, urinary kidney injury molecule-1 (uKIM-1), and brain natriuretic peptide (BNP) with AUCs of 0.91, 0.89, 0.85, and 0.80, respectively. NGAL also demonstrated the highest positive likelihood ratio [effect size (ES): 6.02, 95% CI 3.86-9.40], followed by cystatin-C, uKIM-1, and BNP [ES: 4.35 (95% CI 2.85-6.65), 3.58 (95% CI 2.75-4.66), and 2.85 (95% CI 2.13-3.82), respectively]. uKIM-1 and cystatin-C had the lowest negative likelihood ratio, followed by NGAL and BNP [ES: 0.25 (95% CI 0.17-0.37), ES: 0.25 (95% CI 0.13-0.50), ES: 0.26 (95% CI 0.17-0.41), and ES: 0.39 (0.28-0.53) respectively]. NGAL emerged as the biomarker with the highest diagnostic odds ratio for CIN, followed by cystatin-C, uKIM-1, BNP, gamma-glutamyl transferase, hypoalbuminemia, contrast media volume to creatinine clearance ratio, preprocedural hyperglycemia, red cell distribution width (RDW), hyperuricemia, neutrophil-to-lymphocyte ratio, C-reactive protein (CRP), high-sensitivity CRP, and low hematocrit (P < 0.05). CONCLUSION: NGAL demonstrated superior diagnostic performance, exhibiting the highest AUC, positive likelihood ratio, and diagnostic odds ratio among biomarkers for CIN, followed by cystatin-C, and uKIM-1. These findings underscore the potential clinical utility of NGAL, cystatin-C and uKIM-1 in predicting and assessing CIN.

Sustained acute kidney injury as an independent risk factor for neurodevelopmental and growth outcomes in a single NICU center.

PURPOSE: Acute kidney injury (AKI) is commonly seen in neonatal intensive care units (NICUs) and is potentially associated with adverse prognoses in later stages of life. Our study evaluated the impact of sustained AKI (SAKI) on both neurodevelopmental impairment (NDI) and early growth restriction (EGR) in neonates. METHODS: This case-control study retrospectively analyzed the medical records of neonates diagnosed with SAKI in the NICU of a tertiary medical center during the period from January 2007 to December 2020. Cases without subsequent follow-up and those resulting in death were excluded. We analyzed demographic, biochemical, and clinical outcome data. RESULTS: Of the 93 neonates with SAKI, 51 cases (54.8%) were included in this study, while 42 cases (45.2%) were excluded due to a lack of follow-up or death. An age-matched control group comprised 103 neonates, who had never experienced AKI or SAKI, were selected at random. In total, 59 (38.3%) cases were identified as NDI and 43 (27.9%) as EGR. Multivariate analysis revealed that patients with SAKI had significantly higher risks of developing NDI (odds ratio, [OR] = 4.013, p = 0.001) and EGR (OR = 4.894, p < 0.001). The AKI interval had an area under the receiver operating characteristic curve of 0.754 for NDI at 9.5 days and 0.772 for EGR at 12.5 days. CONCLUSIONS: SAKI is an independent risk factor for both NDI and EGR in neonates. Consequently, regular monitoring, neurological development assessments, and appropriate nutritional advice are crucial to these infants who have experienced renal injury.