TY - JOUR
T1 - A diagnostic classifier for pediatric chronic graft-versus-host disease
T2 - results of the ABLE/PBMTC 1202 study
AU - Cuvelier, Geoffrey D.E.
AU - Ng, Bernard
AU - Abdossamadi, Sayeh
AU - Nemecek, Eneida R.
AU - Melton, Alexis
AU - Kitko, Carrie L.
AU - Lewis, Victor A.
AU - Schechter, Tal
AU - Jacobsohn, David A.
AU - Harris, Andrew C.
AU - Pulsipher, Michael A.
AU - Bittencourt, Henrique
AU - Choi, Sung Won
AU - Caywood, Emi H.
AU - Kasow, Kimberly A.
AU - Bhatia, Monica
AU - Oshrine, Benjamin R.
AU - Chaudhury, Sonali
AU - Coulter, Donald
AU - Chewning, Joseph H.
AU - Joyce, Michael
AU - Savaşan, Süreyya
AU - Pawlowska, Anna B.
AU - Megason, Gail C.
AU - Mitchell, David
AU - Cheerva, Alexandra C.
AU - Lawitschka, Anita
AU - Ostroumov, Elena
AU - Schultz, Kirk R.
N1 - Publisher Copyright:
© 2023 American Society of Hematology. All rights reserved.
PY - 2023/7/25
Y1 - 2023/7/25
N2 - The National Institutes of Health Consensus criteria for chronic graft-versus-host disease (cGVHD) diagnosis can be challenging to apply in children, making pediatric cGVHD diagnosis difficult. We aimed to identify diagnostic pediatric cGVHD biomarkers that would complement the current clinical criteria and help differentiate cGVHD from non-cGVHD. The Applied Biomarkers of Late Effects of Childhood Cancer (ABLE) study, open at 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 3 criteria: an effect ratio ≥1.3 or ≤0.75; an area under the curve (AUC) of ≥0.60; and a P value <5.814 × 10−4 (Bonferroni correction) (mixed effect) or <.05 (fixed effect). To address the complexity of cGVHD diagnosis in children, we built a machine learning–based classifier that combined multiple cellular and plasma biomarkers with clinical factors. Decreases in regulatory natural killer cells, naïve CD4 T helper cells, and naïve regulatory T cells, and elevated levels of CXCL9, CXCL10, CXCL11, ST2, ICAM-1, and soluble CD13 (sCD13) characterize the onset of cGVHD. Evaluation of the time dependence revealed that sCD13, ST2, and ICAM-1 levels varied with the timing of cGVHD onset. The cGVHD diagnostic classifier achieved an AUC of 0.89, with a positive predictive value of 82% and a 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.
AB - The National Institutes of Health Consensus criteria for chronic graft-versus-host disease (cGVHD) diagnosis can be challenging to apply in children, making pediatric cGVHD diagnosis difficult. We aimed to identify diagnostic pediatric cGVHD biomarkers that would complement the current clinical criteria and help differentiate cGVHD from non-cGVHD. The Applied Biomarkers of Late Effects of Childhood Cancer (ABLE) study, open at 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 3 criteria: an effect ratio ≥1.3 or ≤0.75; an area under the curve (AUC) of ≥0.60; and a P value <5.814 × 10−4 (Bonferroni correction) (mixed effect) or <.05 (fixed effect). To address the complexity of cGVHD diagnosis in children, we built a machine learning–based classifier that combined multiple cellular and plasma biomarkers with clinical factors. Decreases in regulatory natural killer cells, naïve CD4 T helper cells, and naïve regulatory T cells, and elevated levels of CXCL9, CXCL10, CXCL11, ST2, ICAM-1, and soluble CD13 (sCD13) characterize the onset of cGVHD. Evaluation of the time dependence revealed that sCD13, ST2, and ICAM-1 levels varied with the timing of cGVHD onset. The cGVHD diagnostic classifier achieved an AUC of 0.89, with a positive predictive value of 82% and a 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.
UR - http://www.scopus.com/inward/record.url?scp=85183636598&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85183636598&partnerID=8YFLogxK
U2 - 10.1182/bloodadvances.2022007715
DO - 10.1182/bloodadvances.2022007715
M3 - Article
C2 - 36219586
AN - SCOPUS:85183636598
SN - 2473-9529
VL - 7
SP - 3612
EP - 3623
JO - Blood Advances
JF - Blood Advances
IS - 14
ER -