Improving infectious adverse event reporting for children and adolescents enrolled in clinical trials for acute lymphoblastic leukemia: A report from the Children's Oncology Group

Elgarten, Caitlin W.; Thompson, Joel C.; Angiolillo, Anne; Chen, Zhiguo; Conway, Susan J.; Devidas, Meenakshi; Gupta, Sumit; Kairalla, John A.; McNeer, Jennifer L.; O’Brien, Maureen M.; Rabin, Karen R.; Rau, Rachel E.; Rheingold, Susan R.; Wang, Cindy; Wood, Charlotte; Raetz, Elizabeth A.; Loh, Mignon L.; Alexander, Sarah; Miller, Tamara P.

doi:10.1002/pbc.29937

Cited by 3 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The source node “glucose”, a top ranked direct candidate returned by SemNet 2.0, is predominantly tied to hyperglycemia. Hyperglycemia is a relatively common event in pediatric cancer [ 63 , 64 ]. The extent of the role of hyperglycemia in modifying the infection risk is still debated in pediatric cancer.…”

Section: Resultsmentioning

confidence: 99%

An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia

Al-Hussaini,

White,

Varmeziar

et al. 2024

JCM

Self Cite

View full text Add to dashboard Cite

Background: Datasets on rare diseases, like pediatric acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL), have small sample sizes that hinder machine learning (ML). The objective was to develop an interpretable ML framework to elucidate actionable insights from small tabular rare disease datasets. Methods: The comprehensive framework employed optimized data imputation and sampling, supervised and unsupervised learning, and literature-based discovery (LBD). The framework was deployed to assess treatment-related infection in pediatric AML and ALL. Results: An interpretable decision tree classified the risk of infection as either “high risk” or “low risk” in pediatric ALL (n = 580) and AML (n = 132) with accuracy of ∼79%. Interpretable regression models predicted the discrete number of developed infections with a mean absolute error (MAE) of 2.26 for bacterial infections and an MAE of 1.29 for viral infections. Features that best explained the development of infection were the chemotherapy regimen, cancer cells in the central nervous system at initial diagnosis, chemotherapy course, leukemia type, Down syndrome, race, and National Cancer Institute risk classification. Finally, SemNet 2.0, an open-source LBD software that links relationships from 33+ million PubMed articles, identified additional features for the prediction of infection, like glucose, iron, neutropenia-reducing growth factors, and systemic lupus erythematosus (SLE). Conclusions: The developed ML framework enabled state-of-the-art, interpretable predictions using rare disease tabular datasets. ML model performance baselines were successfully produced to predict infection in pediatric AML and ALL.

show abstract

Section: Resultsmentioning

confidence: 99%

An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia

Al-Hussaini,

White,

Varmeziar

et al. 2024

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…Patients with DS younger than 31 years old are eligible for this trial regardless of presenting white blood cell count, as are patients with B‐LLy. In March 2020, the protocol was amended to mandate reporting of all grades of SARS‐CoV‐2 infection, graded according to the CTCAE v5 grading schema for “infections and infestations‐other.” For all infectious adverse events (AEs) on the trial, there is a case report form (CRF) for additional data on the infectious pathogen, and real‐time review of infectious AEs by pediatric oncologists to resolve incomplete or ambiguous submissions [9].…”

Section: Methodsmentioning

confidence: 99%

SARS‐CoV‐2 infections in patients enrolled on the Children's Oncology Group standard‐risk B‐cell acute lymphoblastic leukemia trial, AALL1731

Elgarten

Kairalla

Thompson

et al. 2023

eJHaem

Self Cite

View full text Add to dashboard Cite

Hematologic malignancy is a risk factor for severe coronavirus disease 2019 (COVID‐19) in adults; however, data specific to children with leukemia are limited. High‐quality infectious adverse event data from the ongoing Children's Oncology Group (COG) standard‐risk B acute lymphoblastic leukemia/lymphoma (ALL/LLy) trial, AALL1731, were analyzed to provide a disease‐specific estimate of SARS‐CoV‐2 infection outcomes in pediatric ALL. Of 253 patients with reported infections, the majority (77.1%) were asymptomatic or mildly symptomatic (CTCAE grade 1/2) and there was a single COVID‐19‐related death. These data suggest SARS‐CoV‐2 infection does not confer substantial morbidity among young patients with B‐lymphoblastic leukemia/lymphoma (B‐ALL/LLy).

show abstract

Blinatumomab in Standard-Risk B-Cell Acute Lymphoblastic Leukemia in Children

Gupta,

Rau,

Kairalla

et al. 2024

N Engl J Med

View full text Add to dashboard Cite

Improving infectious adverse event reporting for children and adolescents enrolled in clinical trials for acute lymphoblastic leukemia: A report from the Children's Oncology Group

Cited by 3 publications

References 24 publications

An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia

An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia

SARS‐CoV‐2 infections in patients enrolled on the Children's Oncology Group standard‐risk B‐cell acute lymphoblastic leukemia trial, AALL1731

Blinatumomab in Standard-Risk B-Cell Acute Lymphoblastic Leukemia in Children

Contact Info

Product

Resources

About