Open AccessCan Machine Learning Models Predict Asparaginase-associated Pancreatitis in Childhood Acute Lymphoblastic Leukemia
Author(s) -
Ruby I. Nielsen,
Benjamin Ole Wolthers,
Marianne Helenius,
Birgitte Klug Albertsen,
Line Katrine Harder Clemmensen,
Kasper Nielsen,
Jukka Kanerva,
Riitta Niinimäki,
Thomas Leth Frandsen,
Andishe Attarbaschi,
Shlomit Barzilai,
Antonella Colombini,
Gabriele Escherich,
Derya Aytan-Aktug,
HsiChe Liu,
Anja Möricke,
Sujith Samarasinghe,
Inge M. van der Sluis,
Martin Stanulla,
Morten Tulstrup,
Rachita Yadav,
Ester Zápotocká,
Kjeld Schmiegelow,
Ramneek Gupta
Publication year - 2021
Publication title -
journal of pediatric hematology/oncology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.388
H-Index - 78
eISSN - 1536-3678
pISSN - 1077-4114
DOI - 10.1097/mph.0000000000002292
Subject(s) - medicine , receiver operating characteristic , single nucleotide polymorphism , acute pancreatitis , area under the curve , logistic regression , oncology , machine learning , pancreatitis , lymphoblastic leukemia , pediatrics , leukemia , genetics , genotype , gene , biology , computer science
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 1.0 to 17.9 yo) 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 ROC-AUC 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.