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.

Bioinformatics

Center for Biological Sequence Analysis Technical University of Denmark

Children's Hospital Helsinki University Central Hospital University of Helsinki Helsinki

Clinic of Pediatric Hematology and Oncology University Medical Center Eppendorf Hamburg

Department of Applied Mathematics and Computer Science Kgs Lyngby

Department of Pediatric Hematology and Oncology Hannover Medical School Hannover Germany

Department of Pediatric Hematology and Oncology St Anna Children's Hospital and Department of Pediatric and Adolescent Medicine Medical University of Vienna Wien Austria

Department of Pediatric Hematology Oncology University Hospital Motol Prague Czech Republic

Department of Pediatrics and Adolescent Medicine Aarhus University Hospital Aarhus Denmark

Department of Pediatrics and Adolescent Medicine University Hospital Rigshospitalet

Department of Pediatrics Christian Albrechts University Kiel and University Medical Center Schleswig Holstein Kiel

Department of Pediatrics Ospedale San Gerardo University of Milano Bicocca Fondazione MBBM Monza Italy

Departments of Health Technology

Division of Pediatric Hematology Oncology Mackay Memorial Hospital Taipei Taiwan

Dutch Childhood Oncology Group The Hague and Princess Máxima Center for Pediatric Oncology Utrecht The Netherlands

Great Ormond Street Hospital for Children London UK

Institute of Clinical Medicine Faculty of Health and Medical Sciences University of Copenhagen

Oulu University Hospital Department of Children and Adolescents and University of Oulu PEDEGO Research Unit Oulu Finland

Pediatric Hematology and Oncology Schneider Children's Medical Center of Israel Petah Tikva Israel and Sackler Faculty of Medicine Tel Aviv University Tel Aviv Yafo Israel

Sino Danish Center for Education and Research University of Chinese Academy of Sciences Huairou China

See more in PubMed

Pieters R, Hunger SP, Boos J, et al. . L-asparaginase treatment in acute lymphoblastic leukemia: a focus on Erwinia asparaginase. Cancer. 2011;117:238–249. PubMed PMC

Müller HJ, Boos J. Use of L-asparaginase in childhood ALL. Crit Rev Oncol Hematol. 1998;28:97–113. PubMed

Hijiya N, van der Sluis IM. Asparaginase-associated toxicity in children with acute lymphoblastic leukemia. Leuk Lymphoma. 2016;57:748–757. PubMed PMC

Liu C, Yang W, Devidas M, et al. . Clinical and genetic risk factors for acute pancreatitis in patients with acute lymphoblastic leukemia. J Clin Oncol. 2016;34:2133–2140. PubMed PMC

Rank CU, Wolthers BO, Grell K, et al. . Asparaginase-associated pancreatitis in acute lymphoblastic leukemia: results from the NOPHO ALL2008 treatment of patients 1-45 years of age. J Clin Oncol. 2020;38:145–154. PubMed PMC

Gupta S, Wang C, Raetz EA, et al. . Impact of asparaginase discontinuation on outcome in childhood ALL: a report from the Children’s Oncology Group (COG). J Clin Oncol. 2019;37 (suppl):10005. PubMed PMC

Gottschalk Højfeldt S, Grell K, Abrahamsson J, et al. . Relapse risk following truncation of pegylated-asparaginase in childhood acute lymphoblastic leukemia. Blood. 2021;137:2373–2382. PubMed

Wolthers BO, Frandsen TL, Baruchel A, et al. . Asparaginase-associated pancreatitis in childhood acute lymphoblastic leukaemia: an observational Ponte di Legno Toxicity Working Group study. Lancet Oncol. 2017;18:1238–1248. PubMed

Abaji R, Gagné V, Xu CJ, et al. . Whole-exome sequencing identified genetic risk factors for asparaginase-related complications in childhood ALL patients. Oncotarget. 2017;8:43752–43767. PubMed PMC

Wolthers BO, Frandsen TL, Patel CJ, et al. . Trypsin-encoding PRSS1-PRSS2 variations influence the risk of asparaginase-associated pancreatitis in children with acute lymphoblastic leukemia: a ponte di legno toxicity working group report. Haematologica. 2019;104:556–563. PubMed PMC

Wesołowska-Andersen A, Borst L, Dalgaard MD, et al. . Genomic profiling of thousands of candidate polymorphisms predicts risk of relapse in 778 Danish and German childhood acute lymphoblastic leukemia patients. Leukemia. 2015;29:297–303. PubMed PMC

Pan L, Liu G, Lin F, et al. . Machine learning applications for prediction of relapse in childhood acute lymphoblastic leukemia. Sci Rep. 2017;7:1–9. PubMed PMC

Albertsen BK, Grell K, Abrahamsson J, et al. . Intermittent versus continuous PEG-asparaginase to reduce asparaginase-associated toxicities: a NOPHO ALL2008 randomized study. J Clin Oncol. 2019;37:1638–1646. PubMed

Schmiegelow K, Attarbaschi A, Barzilai S, et al. . Consensus definitions of 14 severe acute toxic effects for childhood lymphoblastic leukaemia treatment: a Delphi consensus. Lancet Oncol. 2016;17:e231–e239. PubMed

Python Software Foundation. Python, version 3.6.8. 2018. Available at: www.python.org/. Accessed January 6, 2020.

Pedregosa F, Varoquaux G, Gramfort A, et al. . Scikit-learn: Machine Learning in Python. J Mach Learn Res. 2011;12:2825–2830.

Whitcomb DC, Larusch J, Krasinskas AM, et al. . Common genetic variants in the CLDN2 and PRSS1-PRSS2 loci alter risk for alcohol-related and sporadic pancreatitis. Nat Genet. 2012;44:1349–1354. PubMed PMC

Derikx MH, Kovacs P, Scholz M, et al. . Polymorphisms at PRSS1-PRSS2 and CLDN2-MORC4 loci associate with alcoholic and non-alcoholic chronic pancreatitis in a European replication study. Gut. 2015;64:1426–1433. PubMed

Rosendahl J, Kirsten H, Hegyi E, et al. . Genome-wide association study identifies inversion in the CTRB1-CTRB2 locus to modify risk for alcoholic and non-alcoholic chronic pancreatitis. Gut. 2018;67:1855–1863. PubMed PMC

Zator Z, Whitcomb DC. Insights into the genetic risk factors for the development of pancreatic disease. Therap Adv Gastroenterol. 2017;10:323–336. PubMed PMC

The GTEx Consortium. The Genotype-Tissue Expression (GTEx) project. Nat Genet. 2013;45:580–585. PubMed PMC

Yates A, Beal K, Keenan S, et al. . The Ensembl REST API: Ensembl Data for Any Language. Bioinformatics. 2015;31:143–145. PubMed PMC

Van Den SP, Rudd PM, Dwek RA, et al. . Concepts and Principles of O-Linked Glycosylation. Crit Rev Biochem Mol Biol. 1998;33:151–208. PubMed

UniProtKB-Q49A17 (GLTL6_HUMAN). Integrated into UniProtKB/Swiss-Prot: March 18, 2008. 2010. Available at: https://www.uniprot.org/uniprot/Q49A17. Accessed November 22, 2019.

Himanen J, Chumley MJ, Lackmann M, et al. . Repelling class discrimination: ephrin-A5 binds to and activates EphB2 receptor signaling. Nat Neurosci. 2004;7:501–509. PubMed

UniProtKB-P29323 (EPHB2_HUMAN). Integrated into UniProtKB/Swiss-Prot: December 1, 1992. 2005. Available at: www.uniprot.org/uniprot/P29323. Accessed November 22, 2019.

Prosperi M, Min JS, Bian J, et al. . Big data hurdles in precision medicine and precision public health. BMC Med Inform Decis Mak. 2018;18:1–15. PubMed PMC