For Whom the Bell Tolls: Acute Kidney Injury and Electronic Alerts for the Pediatric Nephrologist

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.

Frequency of Acute Kidney Injury and Association With Mortality Among Extremely Preterm Infants

IMPORTANCE

Neonatal acute kidney injury (AKI) is common and associated with morbidity and mortality. The temporal relationship between AKI and critical illness, as well as the frequency of AKI definition components (urine output and serum creatinine [sCr] concentration change), are unknown in extremely low-birth-weight (ELBW) (<1000 g), extremely preterm (<29 weeks' completed gestational age [GA]) infants.

OBJECTIVE

To measure the frequency of AKI from birth to death or discharge with attention to the definition components as well as the temporal relationship of AKI to critical illness and death.

DESIGN, SETTING, AND PARTICIPANTS

A single-center, multiyear, retrospective cohort study was conducted at an academic level IV neonatal intensive care unit between January 1, 2012, and January 1, 2020. Participants included inborn ELBW and infants at 22 to 28 weeks' completed GA with confirmed congenital anomalies who survived 12 hours or more.

EXPOSURES

Extremely preterm birth and ELBW.

MAIN OUTCOMES AND MEASURES

The primary outcome was AKI frequency. The timing, severity, and criteria for AKI were measured. The temporal relationship between AKI, organ dysfunction, and outcomes were quantified using odds ratios (ORs), logistic regression, and Shapley Additive Explanations. Acute kidney injury recognition, imaging, pediatric nephrology consultation, and follow-up were determined.

RESULTS

A total of 436 infants (52% male; 44% Black) met the inclusion criteria (median BW, 725 g; median GA, 25.7 wk). Acute kidney injury was common in the first week of life (44%), primarily based on the change in the sCr concentration criterion (88%), and negatively associated with GA (OR, 0.69; 95% CI, 0.60-0.78), but positively associated with antecedent critical illness (OR, 1.17; 95% CI, 1.12-1.23), severe intraventricular hemorrhage (OR, 1.86; 95% CI, 1.12-3.08), late-onset sepsis (OR, 1.03; 95% CI, 1.02-1.03), and mortality (OR, 2.77; 95% CI, 1.63-4.72). Acute kidney injury had negligible clinical contribution to death within the model (Shapley Additive Explanation, <0.5% change to outcome) relative to antecedent patient-concentration organ dysfunction (6%-15% change). Among infants with severe AKI, recognition (32%), nephrology inpatient consultation (16%), and outpatient follow-up (9%) were not common.

CONCLUSIONS AND RELEVANCE

In this cohort study of ELBW infants, AKI was common in the first week of life, inversely associated with GA, and followed organ (primarily cardiovascular) dysfunction. Acute kidney injury considered as the primary pathway to mortality was rare, and amelioration of AKI to modify death was not well supported.