Assessment of Risk Factors for Acute Kidney Injury with Machine Learning Tools in Children Undergoing Hematopoietic Stem Cell Transplantation.

Background: Although acute kidney injury (AKI) is a common complication in patients undergoing hematopoietic stem cell transplantation (HSCT), its prophylaxis remains a clinical challenge. Attempts at prevention or early diagnosis focus on various methods for the identification of factors influencing the incidence of AKI. Our aim was to test the artificial intelligence (AI) potential in the construction of a model defining parameters predicting AKI development. Methods: The analysis covered the clinical data of children followed up for 6 months after HSCT. Kidney function was assessed before conditioning therapy, 24 h after HSCT, 1, 2, 3, 4, and 8 weeks after transplantation, and, finally, 3 and 6 months post-transplant. The type of donor, conditioning protocol, and complications were incorporated into the model. Results: A random forest classifier (RFC) labeled the 93 patients according to presence or absence of AKI. The RFC model revealed that the values of the estimated glomerular filtration rate (eGFR) before and just after HSCT, as well as methotrexate use, acute graft versus host disease (GvHD), and viral infection occurrence, were the major determinants of AKI incidence within the 6-month post-transplant observation period. Conclusions: Artificial intelligence seems a promising tool in predicting the potential risk of developing AKI, even before HSCT or just after the procedure.

The incidence of acute kidney injury in children undergoing allogenic hematopoietic stem cell transplantation: A pilot study.

BACKGROUND: Acute kidney injury (AKI) is a common feature in adults undergoing allogeneic hematopoietic stem cell transplantation (alloHSCT). However, accurate assessment of AKI incidence in the pediatric population still seems a challenge. OBJECTIVES: To evaluate the incidence of AKI according to the pRIFLE criteria in children undergoing alloHSCT, with special focus on differences between patients transplanted due to oncological and non-oncological indications. MATERIAL AND METHODS: A retrospective analysis of data, concerning 135 children undergoing alloHSCT due to oncological (89 patients) or other (46 patients) reasons, was performed. The values of estimated glomerular filtration rate (eGFR) were measured before alloHSCT, 24 h after, 1, 2, 3, 4, 8 weeks, 3 and 6 months after alloHSCT, and the AKI incidence was analyzed. RESULTS: Acute kidney injury was diagnosed in 54% of all patients. The Risk stage (R) was noticed at least once in 46% of oncological and 37% of non-oncological children. The Injury stage (I) concerned 12% of oncological and 6% of non-oncological patients undergoing alloHSCT. The incidence of AKI in both groups was comparable. The mean eGFR values in oncological children were higher than those in the non-oncological patients even before transplantation and until the 4th week after alloHSCT. The eGFR increased significantly in all patients 24 h after alloHSCT and returned to pre-transplantation records after 2-3 weeks. Then, oncological patients demonstrated a gradual decrement of eGFR. Six months after transplantation, eGFR values in oncological children were significantly lower compared to pre-transplantation records, whereas in non-oncological children, these values were comparable. CONCLUSIONS: Although the type of indication for alloHSCT has no impact on the AKI incidence, children undergoing alloHSCT due to oncological reasons are at greater risk of renal impairment 6 months after transplantation than non-oncological patients.

Clusterin as a New Marker of Kidney Injury in Children Undergoing Allogeneic Hematopoietic Stem Cell Transplantation-A Pilot Study.

BACKGROUND AND AIMS: The markers of renal damage defining subclinical AKI are not widely used in children undergoing allogeneic hematopoietic stem cell transplantation (alloHSCT). The aim of the study was to evaluate serum and urinary clusterin as indices of kidney injury after alloHSCT in relation to damage (kidney injury molecule (KIM)-1) and functional (cystatin C) markers. MATERIAL AND METHODS: Serum and urinary clusterin, KIM-1 and cystatin C concentrations were assessed by ELISA in 27 children before alloHSCT, 24 h, 1, 2, 3 and 4 weeks after alloHSCT and in controls. RESULTS: All parameters were significantly higher in HSCT patients compared to controls even before the transplantation. The serum concentrations increased after HSCT and this rising trend was kept until the third (clusterin) or 4th (KIM-1, cystatin C) week. Urinary clusterin and KIM-1 were elevated until the third week and then decreased yet remained higher than before HSCT. Urinary cystatin C has risen from the second week after HSCT and decreased after the third week but was still higher than before alloHSCT. CONCLUSIONS: The features of kidney injury are present even before alloHSCT. Clusterin seems useful in the assessment of subclinical AKI and may become a new early marker of sublethal kidney injury in children.

Markers of acute kidney injury in children undergoing hematopoietic stem cell transplantation.

Acute kidney injury (AKI), one of the major complications in children undergoing hematopoietic stem cell transplantation (HSCT), is an independent predictor of the patient's survival and a prognostic factor of progression to chronic kidney disease (CKD). Despite the multifaceted role of AKI, its early diagnosis in the course of HSCT remains a challenge. These difficulties may result from the inefficiency of traditional methods used to assess kidney function, like serum creatinine or estimated glomerular filtration rate. Moreover, the list of potential AKI markers tested in HSCT conditions is limited and does not involve indexes evaluated in the pediatric population. This review summarizes current knowledge on the pathophysiology of AKI developing in the course of HSCT; presents well-known markers of AKI that are potentially applicable in children who have undergone HSCT; discusses the role of new markers in diagnosing AKI and predicting the renal outcome in children undergoing HSCT; and analyzes the prospects for the use of new tools for assessing kidney injury in everyday clinical practice.