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

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.

Association between body composition and chemotherapy-related toxicity in children with lymphoma and rhabdomyosarcoma

BACKGROUND

Body composition is associated with chemotherapy toxicity (chemotoxicity) in adults with cancer; this association remains unexplored in children with cancer.

METHODS

Using baseline computed tomography scans of 107 children with Hodgkin lymphoma (n = 45), non-Hodgkin lymphoma (n = 42), or rhabdomyosarcoma (n = 20), this study examined body composition (skeletal muscle index [SMI], skeletal muscle density [SMD], and height-adjusted total adipose tissue [hTAT]) to determine its association with chemotoxicity. Clinical characteristics and chemotoxicities were abstracted from medical records. Primary outcomes included grade 4 or higher hematologic toxicities and grade 3 or higher nonhematologic toxicities within 6 months of the diagnosis. Logistic regression models accounting for repeated measures were constructed to examine the association between body composition indices and chemotoxicities; adjustments were made for age at diagnosis, sex, race/ethnicity, cancer type, risk group, body mass index (measured as a percentile), or body surface area.

RESULTS

The median SMI was 41.0 cm² /m² (range, 25.8-68.6 cm² /m² ), the median SMD was 54.1 HU (range, 35-69.4 HU), and the median hTAT was 19.5 cm² /m² (range, 0-226.7 cm² /m² ). Grade 4 or higher hematologic toxicities and grade 3 or higher nonhematologic toxicities were observed in 74.7% and 66.3% of the chemotherapy cycles, respectively. A higher SMD at diagnosis was associated with lower odds of grade 4 or higher hematologic toxicity (odds ratio [OR], 0.90; 95% confidence interval [CI], 0.85-0.97; P = .004). SMI (OR, 0.99; 95% CI, 0.95-1.04; P = .7) and hTAT (OR, 1.00; 95% CI, 0.99-1.01; P = .9) were not associated with hematologic toxicities. Nonhematologic toxicities did not show any association with body composition.

CONCLUSIONS

The association between low SMD and hematologic toxicities in children with lymphoma or rhabdomyosarcoma could be due to body composition-based biodistribution of chemotherapeutic agents and needs further investigation.

LAY SUMMARY

Body composition at cancer diagnosis in children with lymphoma and rhabdomyosarcoma may provide information that could identify those at risk for serious side effects from chemotherapy. Routinely used measures such as body mass index and body surface area show poor correlations with body composition assessed via computed tomography scans.

Optimal approach to the treatment of young adults with acute lymphoblastic leukemia in 2020

Akin to the introduction of tyrosine kinase inhibitors to Philadelphia chromosome-positive acute lymphoblastic leukemia (ALL), pediatric-based asparaginase-heavy approaches have revolutionized the treatment of young adults with the Philadelphia chromosome-negative subset the past decades. Once again, we are approaching a new era. An era of precision medicine with immunotherapy and other molecularly targeted treatments that offers unique opportunities to customize treatment intensity with or without hematopoietic stem cell transplantation, reduce the burden of toxicities, and combat persistent residual disease. Recently approved agents for refractory/relapsed B-cell precursor ALL include the chimeric antigen receptor-modified T-cells, the anti-CD22 monoclonal antibody-drug conjugate, inotuzumab ozogamicin, and the bispecific anti-CD19 T-cell engager, blinatumomab. These agents are expected to move widely into the frontline setting along with the proteasome inhibitors, bortezomib and carfilzomib, as well as tyrosine kinase inhibitors for Philadelphia-like rearrangements that are especially frequent among young adults. To this add the BH3 mimetics, venetoclax and navitoclax, which are being widely explored in refractory/relapsed as well as frontline settings for B- and T-cell ALL. The promising anti-CD38 monoclonal antibody, daratumumab, is entering the scene of refractory/relapsed T-ALL, whereas the old purine analogue, nelarabine, is being evaluated in a new upfront setting. This review focuses on 2 main questions: How do we optimize frontline as well as salvage ALL treatment of young adults in the 2020s? Not least, how do we address the current burden of serious toxicities unique to young adults?