Validation of the STARZ neonatal acute kidney injury risk stratification score

Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates

Therapeutic hypothermia (TH) significantly reduces mortality and morbidities in neonates with Neonatal Encephalopathy (NE). NE may result in neonatal death and multisystem organ impairment, including acute kidney injury (AKI). Our study aimed to utilize machine learning (ML) methods to predict the outcome of TH-treated NE neonates developing AKI and death during TH. In this retrospective multinational study, 1149 TH-treated NE neonates and 801 controls were included. AKI was classified using KDIGO neonatal criteria based on serum creatinine measurements. The ML model incorporated gestational age, birth weight, postnatal age, and serum creatinine values. The algorithm used all these covariates to predict one of five outcomes: survival with/without AKI, mortality with/without AKI, and hospitalized non-NE controls. The XGBoost model achieved an AUC of 95% and an accuracy of 75.08% in predicting AKI and survival, surpassing other ML classifiers that demonstrated accuracy levels ranging from 54% to 65%. To our knowledge this is the first ML model trained on multicenter, multinational data specifically aimed at predicting neonates' AKI, death, and survival within the first three days. Our ML scoring systems' code and user interface are freely available ( https://github.com/NUBagciLab/Therapeutic-Hypothermia-Outcome-Classification , https://thprediction.streamlit.app/ ). This tool has potential to support neonatologists to personalize therapies, and to optimize pharmacotherapy for renally cleared drugs.

Artificial intelligence in early detection and prediction of pediatric/neonatal acute kidney injury: current status and future directions

Acute kidney injury (AKI) has a significant impact on the short-term and long-term clinical outcomes of pediatric and neonatal patients, and it is imperative in these populations to mitigate the pathways leading to AKI and be prepared for early diagnosis and treatment intervention of established AKI. Recently, artificial intelligence (AI) has provided more advent predictive models for early detection/prediction of AKI utilizing machine learning (ML). By providing strong detail and evidence from risk scores and electronic alerts, this review outlines a comprehensive and holistic insight into the current state of AI in AKI in pediatric/neonatal patients. In the pediatric population, AI models including XGBoost, logistic regression, support vector machines, decision trees, naïve Bayes, and risk stratification scores (Renal Angina Index (RAI), Nephrotoxic Injury Negated by Just-in-time Action (NINJA)) have shown success in predicting AKI using variables like serum creatinine, urine output, and electronic health record (EHR) alerts. Similarly, in the neonatal population, using the "Baby NINJA" model showed a decrease in nephrotoxic medication exposure by 42%, the rate of AKI by 78%, and the number of days with AKI by 68%. Furthermore, the "STARZ" risk stratification AI model showed a predictive ability of AKI within 7 days of NICU admission of AUC 0.93 and AUC of 0.96 in the validation and derivation cohorts, respectively. Many studies have reported the superiority of using biomarkers to predict AKI in pediatric patients and neonates as well. Future directions include the application of AI along with biomarkers (NGAL, CysC, OPN, IL-18, B2M, etc.) in a Labelbox configuration to create a more robust and accurate model for predicting and detecting pediatric/neonatal AKI.

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.

CARPEDIEM® for continuous kidney replacement therapy in neonates and small infants: a French multicenter retrospective study

BACKGROUND

The Cardio-Renal Pediatric Dialysis Emergency Machine (CA.R.P.E.D.I.E.M.®) device is a continuous kidney replacement therapy (CKRT) equipment dedicated to neonates and small infants. This study aimed to assess the effectiveness, feasibility, outcomes, and technical considerations relating to CARPEDIEM® use.

METHODS

This retrospective multicenter study included 19 newborns and six infants receiving CARPEDIEM® in five French pediatric and neonatal intensive care units. Laboratory parameters were collected at the initiation and end of the first CARPEDIEM® session. Results are presented as median [IQR] (range).

RESULTS

At initiation, age was 4 days [2-13] (1-1134) with a body weight of 3.3 kg [2.5-4] (1.3-11.1). Overall, 131 sessions and 2125 h of treatment were performed. Treatment duration per patient was 42 h [24-91] (8-557). Continuous veno-venous hemofiltration (CVVH) was performed in 20 children. Blood flow rate was 8 mL/kg/min [6-9] (3-16). The effluent flow rate for CVVH was 74 mL/kg/h [43-99] (28-125) and net ultrafiltration (UF) 6 mL/kg/h [2-8] (1-12). In the five children treated by hemodialysis, the blood and dialysate flow rates were 6 mL/kg/min [5-7] (4-7) and 600 mL/h [300-600] (120-600), respectively, while session duration was 8 h [6-12] (2-24). Most infants required a catheter between 4.5 and 6.5 French. Hemodynamic instability with a need for volume replacement occurred in 31 sessions (23%). Thrombocytopenia was observed in 29 sessions (22%). No hemorrhage occurred; all the patients survived the sessions, but only eight patients (32%) were alive at hospital discharge.

CONCLUSIONS

These data confirm that the use of CARPEDIEM® is safe and effective in critically ill neonates and infants. A higher resolution version of the Graphical abstract is available as Supplementary information.

Neonatal AKI: An update

Neonatal acute kidney injury (AKI) is a common complication, especially in the neonatal intensive care unit, that is associated with long term consequences and poor outcomes. Early detection and treatment is critical. Currently, neonatal AKI is defined with urinary markers and serum creatinine, with limitations on early detection and individual treatment. There have been numerous biomarkers and risk factor scores that have been studied for their ability to predict neonatal AKI. To move towards personalized medicine, neonatal AKI must be categorized into phenotypes and subphenotypes that fully encapsulate the diverse causes and specific treatments. This review aims to advance our understanding of neonatal AKI detection through the use of biomarkers, subphenotypes, and phenotypes to move towards personalized treatment strategies.

Perspectives: Neonatal acute kidney injury (AKI) in low and middle income countries (LMIC)

Neonatal AKI (NAKI) remains a challenge in low- and middle-income countries (LMICs). In this perspective, we address issues of diagnosis and risk factors particular to less well-resourced regions. The conservative management pre-kidney replacement therapy (pre-KRT) is prioritized and challenges of KRT are described with improvised dialysis techniques also included. Special emphasis is placed on ethical and palliation principles.