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

Abstract

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.

Keywords: acute graft versus host disease; acute kidney disease; artificial intelligence; random forest classifier; tubular damage.

Figure 1

A graphical representation of the methodology for generating a random forest model. The input set is divided in a ratio of 80:20 into a training and testing set. The training set allows for generating the optimal set of input data needed for effective prediction. The testing set is used to simulate new patient data beyond the data originally available for training.

Figure 2

The satisfactory discriminatory ability of the developed model allows for its practical application. The area under the ROC curve was 0.8397, with corresponding lower and upper limits of the confidence interval (CI) of 0.6588 and 1.0000, respectively.

Figure 3

The variables: eGFR before HSCT and eGFR after HSCT appear significantly more often than average in the above tree. A random forest consists of many similar trees. In the case of the model in question, there are 17 of them. A single tree allows for selecting one predicted endpoint. Several trees cast their votes and the final result is chosen by majority rule.