Using artificial intelligence to predict mortality in AKI patients: a systematic review/meta-analysis.

Background: Acute kidney injury (AKI) is associated with increased morbidity/mortality. With artificial intelligence (AI), more dynamic models for mortality prediction in AKI patients have been developed using machine learning (ML) algorithms. The performance of various ML models was reviewed in terms of their ability to predict in-hospital mortality for AKI patients. Methods: A literature search was conducted through PubMed, Embase and Web of Science databases. Included studies contained variables regarding the efficacy of the AI model [the AUC, accuracy, sensitivity, specificity, negative predictive value and positive predictive value]. Only original studies that consisted of cross-sectional studies, prospective and retrospective studies were included, while reviews and self-reported outcomes were excluded. There was no restriction on time and geographic location. Results: Eight studies with 37 032 AKI patients were included, with a mean age of 65.3 years. The in-hospital mortality was 18.0% in the derivation and 15.8% in the validation cohorts. The pooled [95% confidence interval (CI)] AUC was observed to be highest for the broad learning system (BLS) model [0.852 (0.820-0.883)] and elastic net final (ENF) model [0.852 (0.813-0.891)], and lowest for proposed clinical model (PCM) [0.765 (0.716-0.814)]. The pooled (95% CI) AUC of BLS and ENF did not differ significantly from other models except PCM [Delong's test P = .022]. PCM exhibited the highest negative predictive value, which supports this model's use as a possible rule-out tool. Conclusion: Our results show that BLS and ENF models are equally effective as other ML models in predicting in-hospital mortality, with variability across all models. Additional studies are needed.

Prevention of dialysis disequilibrium syndrome in children with advanced uremia with a structured hemodialysis protocol: A quality improvement initiative study.

BACKGROUND: Dialysis disequilibrium syndrome (DDS) is a rare but significant concern in adult and pediatric patients undergoing dialysis initiation with advanced uremia or if done after an interval. It is imperative to gain insights into the epidemiological patterns, pathophysiological mechanisms, and preventive strategies aimed at averting the onset of this ailment. DESIGN: Prospective observational quality improvement initiative cohort study. SETTING AND PARTICIPANTS: A prospective single-center study involving 50 pediatric patients under 18 years recently diagnosed with chronic kidney disease stage V with blood urea ≥200 mg/dL, admitted to our tertiary care center for dialysis initiation from January 2017 to October 2023. QUALITY IMPROVEMENT PLAN: A standardized protocol was developed and followed for hemodialysis in pediatric patients with advanced uremia. This protocol included measures such as lower urea reduction ratios (targeted at 20%-30%) with shorter dialysis sessions and linear dialysate sodium profiling. Prophylactic administration of mannitol and 25% dextrose was also done to prevent the incidence of dialysis disequilibrium syndrome. MEASURES: Incidence of dialysis disequilibrium syndrome and severe dialysis disequilibrium syndrome, mortality, urea reduction ratios (URRs), neurological outcome at discharge, and development of complications such as infection and hypotension. Long-term outcomes were assessed at the 1-year follow-up including adherence to dialysis, renal transplantation, death, and loss to follow-up. RESULTS: The median serum creatinine and urea levels at presentation were 7.93 and 224 mg/dL, respectively. A total of 20% of patients had neurological symptoms attributable to advanced uremia at the time of presentation. The incidence of dialysis disequilibrium syndrome was 4% (n = 2) with severe dialysis disequilibrium syndrome only 2% (n = 1). Overall mortality was 8% (n = 4) but none of the deaths were attributed to dialysis disequilibrium syndrome. The mean urea reduction ratios for the first, second, and third dialysis sessions were 23.45%, 34.56%, and 33.50%, respectively. The patients with dialysis disequilibrium syndrome were discharged with normal neurological status. Long-term outcomes showed 88% adherence to dialysis and 38% renal transplantation. LIMITATIONS: This study is characterized by a single-center design, nonrandomized approach, and limited sample size. CONCLUSIONS: Our structured protocol served as a framework for standardizing procedures contributing to low incidence rates of dialysis disequilibrium syndrome.

Assessment of South Asian Pediatric Acute Kidney Injury: Epidemiology and Risk Factors (ASPIRE)-a prospective study on "severe dialysis dependent pediatric AKI".

BACKGROUND: Pediatric acute kidney injury (AKI) is a global health concern with an associated mortality risk disproportionately pronounced in resource-limited settings. There is a pertinent need to understand the epidemiology of pediatric AKI in vulnerable populations. Here, we proposed a prospective study to investigate the epidemiology and associated risk factors of "severe dialysis dependent AKI" in children among South Asian nations which would be the first and largest of its kind. METHODS: The ASPIRE study (part of PCRRT-ICONIC Foundation initiative) is a multi-center, prospective observational study conducted in South Asian countries. All children and adolescents ≤ 18 years of age who required dialysis for AKI in any of the collaborating medical centers were enrolled. Data collection was performed until one of the following endpoints was observed: (1) discharge, (2) death, and (3) discharge against medical advice. RESULTS: From 2019 to 2022, a total of 308 children with severe AKI were enrolled. The mean age was 6.17 years (63% males). Secondary AKI was more prevalent than primary AKI (67.2%), which predominantly occurred due to infections, dehydration, and nephrotoxins. Common causes of primary AKI were glomerulonephritis, hemolytic uremic syndrome, lupus nephritis, and obstructive uropathy. Shock, need for ventilation, and coagulopathy were commonly seen in children with severe AKI who needed dialysis. The foremost kidney replacement therapy used was peritoneal dialysis (60.7%). The mortality rate was 32.1%. CONCLUSIONS: Common causes of AKI in children in South Asia are preventable. Mortality is high among these children suffering from "severe dialysis dependent AKI." Targeted interventions to prevent and identify AKI early and initiate supportive care in less-resourced nations are needed.

Health-related quality of life for pediatric patients with end-stage kidney disease: A systematic review and meta-analysis of the Pediatric Quality of Life Inventory (PedsQL).

INTRODUCTION: Health-related quality of life (HRQoL) studies demonstrate the impact of end-stage renal disease (ESRD) on the physical and psychosocial development of children. While several instruments are used to measure HRQoL, few have standardized domains specific to pediatric ESRD. This review examines current evidence on self and proxy-reported HRQoL among pediatric patients with ESRD, based on the Pediatric Quality of Life Inventory (PedsQL) questionnaires. METHODS: Following PRISMA guidelines, we conducted a systematic review and meta-analysis on HRQoL using the PedsQL 4.0 Generic Core Scale (GCS) and the PedsQL 3.0 ESRD Module among 5- to 18-year-old patients. We queried PubMed, Embase, Web of Science, CINAHL, and Cochrane databases. Retrospective, case-controlled, and cross-sectional studies using PedsQL were included. FINDINGS: Of 435 identified studies, 14 met inclusion criteria administered in several countries. Meta-analysis demonstrated a significantly higher total HRQoL for healthy patients over those with ESRD (SMD:1.44 [95% CI: 0.78-2.09]) across all dimensional scores. In addition, kidney transplant patients reported a significantly higher HRQoL than those on dialysis (PedsQL GCS, SMD: 0.33 [95% CI: 0.14-0.53]) and (PedsQL ESRD, SMD: 0.65 [95% CI: 0.39-0.90]) concordant with parent-proxy reports. DISCUSSION: Patients with ESRD reported lower HRQoL in physical and psychosocial domains compared with healthy controls, while transplant and peritoneal dialysis patients reported better HRQoL than those on hemodialysis. This analysis demonstrates the need to identify dimensions of impaired functioning and produce congruent clinical interventions. Further research on the impact of individual comorbidities in HRQoL is necessary for developing comprehensive, integrated, and holistic treatment programs.

Concurrent use of continuous kidney replacement therapy during extracorporeal membrane oxygenation: what pediatric nephrologists need to know-PCRRT-ICONIC practice points.

Extracorporeal membrane oxygenation (ECMO) provides temporary cardiorespiratory support for neonatal, pediatric, and adult patients when traditional management has failed. This lifesaving therapy has intrinsic risks, including the development of a robust inflammatory response, acute kidney injury (AKI), fluid overload (FO), and blood loss via consumption and coagulopathy. Continuous kidney replacement therapy (CKRT) has been proposed to reduce these side effects by mitigating the host inflammatory response and controlling FO, improving outcomes in patients requiring ECMO. The Pediatric Continuous Renal Replacement Therapy (PCRRT) Workgroup and the International Collaboration of Nephrologists and Intensivists for Critical Care Children (ICONIC) met to highlight current practice standards for ECMO use within the pediatric population. This review discusses ECMO modalities, the pathophysiology of inflammation during an ECMO run, its adverse effects, various anticoagulation strategies, and the technical aspects and outcomes of implementing CKRT during ECMO in neonatal and pediatric populations. Consensus practice points and guidelines are summarized. ECMO should be utilized in patients with severe acute respiratory failure despite the use of conventional treatment modalities. The Extracorporeal Life Support Organization (ELSO) offers guidelines for ECMO initiation and management while maintaining a clinical registry of over 195,000 patients to assess outcomes and complications. Monitoring and preventing fluid overload during ECMO and CKRT are imperative to reduce mortality risk. Clinical evidence, resources, and experience of the nephrologist and healthcare team should guide the selection of ECMO circuit.

Use of furosemide in preterm neonates with acute kidney injury is associated with increased mortality: results from the TINKER registry.

BACKGROUND: Diuretics are commonly used in neonatal AKI with the rationale to decrease positive fluid balance in critically sick neonates. The patterns of furosemide use vary among hospitals, which necessitates the need for a well-designed study. METHODS: The TINKER (The Indian Iconic Neonatal Kidney Educational Registry) study provides a database, spanning 14 centres across India since August 2018. Admitted neonates (≤ 28 days) receiving intravenous fluids for at least 48 h were included. Neonatal KDIGO criteria were used for the AKI diagnosis. Detailed clinical and laboratory parameters were collected, including the indications of furosemide use, detailed dosing, and the duration of furosemide use (in days). RESULTS: A total of 600 neonates with AKI were included. Furosemide was used in 8.8% of the neonates (53/600). Common indications of furosemide use were significant cardiac disease, fluid overload, oliguria, BPD, RDS, hypertension, and hyperkalemia. The odds of mortality was higher in neonates < 37 weeks gestational age with AKI who received furosemide compared to those who did not receive furosemide 3.78 [(1.60-8.94); p = 0.003; univariate analysis] and [3.30 (1.11-9.82); p = 0.03]; multivariate logistic regression]. CONCLUSIONS: In preterm neonates with AKI, mortality was independently associated with furosemide treatment. The furosemide usage rates were higher in neonates with associated co-morbidities, i.e. significant cardiac diseases or surgical interventions. Sicker babies needed more resuscitation at birth, and died early, and hence needed shorter furosemide courses. Thus, survival probability was higher in neonates treated with long furosemide courses vs. short courses.

Nutrition in critically ill children with acute kidney injury on continuous kidney replacement therapy: a 2023 executive summary.

OBJECTIVES: Nutrition plays a vital role in the outcome of critical illness in children, particularly those with acute kidney injury. Currently, there are no established guidelines for children with acute kidney injury treated with continuous kidney replacement therapy. Our objective was to create clinical practice points for nutritional assessment and management in critically ill children with acute kidney injury receiving continuous kidney replacement therapy. METHODS: An electronic search using PubMed and an inclusive academic library search (including MEDLINE, Cochrane, and Embase databases) was conducted to find relevant English-language articles on nutrition therapy for children (<18 y of age) receiving continuous kidney replacement therapy. RESULTS: The existing literature was reviewed by our work group, comprising pediatric nephrologists and experts in nutrition. The modified Delphi method was then used to develop a total of 45 clinical practice points. The best methods for nutritional assessment are discussed. Indirect calorimetry is the most reliable method of predicting resting energy expenditure in children on continuous kidney replacement therapy. Schofield equations can be used when indirect calorimetry is not available. The non-intentional calories contributed by continuous kidney replacement therapy should also be accounted for during caloric dosing. Protein supplementation should be increased to account for the proteins, peptides, and amino acids lost with continuous kidney replacement therapy. CONCLUSIONS: Clinical practice points are provided on nutrition assessment, determining energy needs, and nutrient intake in children with acute kidney injury and on continuous kidney replacement therapy based on the existing literature and expert opinions of a multidisciplinary panel.

Nutrition in Critically Ill Children with AKI on Continuous RRT: Consensus Recommendations.

BACKGROUND: Nutrition plays a vital role in the outcome of critically ill children, particularly those with AKI. Currently, there are no established guidelines for children with AKI treated with continuous RRT (CRRT). A thorough understanding of the metabolic changes and nutritional challenges in AKI and CRRT is required. Our objective was to create clinical practice points for nutritional assessment and management in critically ill children with AKI receiving CRRT. METHODS: PubMed, MEDLINE, Cochrane, and Embase databases were searched for articles related to the topic. Expertise of the authors and a consensus of the workgroup were additional sources of data in the article. Available articles on nutrition therapy in pediatric patients receiving CRRT through January 2023. RESULTS: On the basis of the literature review, the current evidence base was examined by a panel of experts in pediatric nephrology and nutrition. The panel used the literature review as well as their expertise to formulate clinical practice points. The modified Delphi method was used to identify and refine clinical practice points. CONCLUSIONS: Forty-four clinical practice points are provided on nutrition assessment, determining energy needs, and nutrient intake in children with AKI and on CRRT on the basis of the existing literature and expert opinions of a multidisciplinary panel.

Post-transplant recurrence of focal segmental glomerular sclerosis: consensus statements.

Focal segmental glomerular sclerosis (FSGS) is 1 of the primary causes of nephrotic syndrome in both pediatric and adult patients, which can lead to end-stage kidney disease. Recurrence of FSGS after kidney transplantation significantly increases allograft loss, leading to morbidity and mortality. Currently, there are no consensus guidelines for identifying those patients who are at risk for recurrence or for the management of recurrent FSGS. Our work group performed a literature search on PubMed/Medline, Embase, and Cochrane, and recommendations were proposed and graded for strength of evidence. Of the 614 initially identified studies, 221 were found suitable to formulate consensus guidelines for recurrent FSGS. These guidelines focus on the definition, epidemiology, risk factors, pathogenesis, and management of recurrent FSGS. We conclude that additional studies are required to strengthen the recommendations proposed in this review.