A diagnostic classifier for pediatric chronic graft-versus-host disease: results of the ABLE / PBMTC 1202 study

Abstract

The NIH Consensus Criteria for chronic graft-versus-host disease (cGVHD) diagnosis can be challenging to apply in children. We aimed to discover diagnostic pediatric cGVHD biomarkers that would complement clinical criteria and differentiate cGVHD from non-cGVHD diagnoses. The Applied Biomarkers of Late Effects of Childhood Cancer (ABLE) study (27 transplant centers) prospectively evaluated 302 pediatric patients after hematopoietic cell transplant (234 evaluable). Forty-four patients developed cGVHD. Mixed and fixed effect regression analyses were performed on diagnostic cGVHD onset blood samples for cellular and plasma biomarkers, with individual markers declared relevant if they met three criteria: an effect ratio ≥1.3 or ≤0.75; an area under the curve (AUC) of ≥0.60; and a p-value <5.814x10-4 (Bonferroni correction) (mixed effect) or <0.05 (fixed effect). To address the complexity of cGVHD diagnosis in children, we further built a machine learning-based classifier that combined multiple cellular and plasma biomarkers with clinical factors. Decreases in NKREGS, naïve CD4 helper T cells, and naïve regulatory T cells; and elevations in CXCL9, CXCL10, CXCL11, ST2, ICAM-1, and sCD13 characterized the onset of cGVHD. Evaluation of time-dependence revealed that sCD13, ST2, and ICAM-1 varied with timing of cGVHD onset. The cGVHD diagnostic classifier achieved an AUC of 0.89 with a positive predictive value of 82% and negative predictive value of 80% for diagnosing cGVHD. Our polyomic approach to building a diagnostic classifier could help improve the diagnosis of cGVHD in children but requires validation in future prospective studies.