Can Machine Learning Models Predict Asparaginase-associated Pancreatitis in Childhood Acute Lymphoblastic Leukemia

Rikke L. Nielsen, Benjamin O. Wolthers, Marianne Helenius, Birgitte K. Albertsen, Line Clemmensen, Kasper Nielsen, Jukka Kanerva, Riitta Niinimäki, Thomas L. Frandsen, Andishe Attarbaschi, Shlomit Barzilai, Antonella Colombini, Gabriele Escherich, Derya Aytan-Aktug, Hsi-Che Liu, Anja Möricke, Sujith Samarasinghe, Inge M. van der Sluis, Martin Stanulla, Morten TulstrupRachita Yadav, Ester Zapotocka, Kjeld Schmiegelow, Ramneek Gupta

Research output: Contribution to journalJournal articleResearchpeer-review

276 Downloads (Pure)

Abstract

Asparaginase-associated pancreatitis (AAP) frequently affects children treated for acute lymphoblastic leukemia (ALL) causing severe acute and persisting complications. Known risk factors such as asparaginase dosing, older age and single nucleotide polymorphisms (SNPs) have insufficient odds ratios to allow personalized asparaginase therapy. In this study, we explored machine learning strategies for prediction of individual AAP risk. We integrated information on age, sex, and SNPs based on Illumina Omni2.5exome-8 arrays of patients with childhood ALL (N =1564, 244 with AAP aged 1.0 to 17.9 y) from 10 international ALL consortia into machine learning models including regression, random forest, AdaBoost and artificial neural networks. A model with only age and sex had area under the receiver operating characteristic curve (ROC-AUC) of 0.62. Inclusion of 6 pancreatitis candidate gene SNPs or 4 validated pancreatitis SNPs boosted ROCAUC somewhat (0.67) while 30 SNPs, identified through our AAP genome-wide association study cohort, boosted performance (0.80). Most predictive features included rs10273639 (PRSS1-PRSS2), rs10436957 (CTRC), rs13228878 (PRSS1/PRSS2), rs1505495 (GALNTL6), rs4655107 (EPHB2) and age (1 to 7 y). Second AAP following asparaginase re-exposure was predicted with ROC-AUC: 0.65. The machine learning models assist individual-level risk assessment of AAP for future prevention trials, and may legitimize asparaginase re-exposure when AAP risk is predicted to be low.
Original languageEnglish
JournalJournal of Pediatric Hematology/Oncology
Volume44
Issue number3
Pages (from-to)e628-e636
Number of pages9
ISSN1077-4114
DOIs
Publication statusPublished - 2022

Keywords

  • Pediatric hematology/oncology
  • Acute lymphoblastic leukemia
  • Treatment toxicity
  • Translational research
  • Artificial intelligence

Fingerprint

Dive into the research topics of 'Can Machine Learning Models Predict Asparaginase-associated Pancreatitis in Childhood Acute Lymphoblastic Leukemia'. Together they form a unique fingerprint.

Cite this