Neuroblastoma is the most common solid tumor in children under the age of one. It displays remarkable phenotypic heterogeneity, resulting in differences in outcomes that correlate with clinical and biologic features at diagnosis. While neuroblastoma accounts for approximately 5% of all cancer diagnoses in pediatrics, it disproportionately results in about 9% of all childhood deaths. Research advances over the decades have led to an improved understanding of neuroblastoma biology. However, the initiating events that lead to the development of neuroblastoma remain to be fully elucidated. It has only been recently that advances in genetics and genomics have allowed researchers to unravel the predisposing factors enabling the development of neuroblastoma and fully appreciate the interplay between the genetics of tumor and host. In this review, we outline the current understanding of familial neuroblastoma and highlight germline variations that predispose children to sporadic disease. We also discuss promising future directions in neuroblastoma genomic research and potential clinical applications for these advances.

Background: Efforts to facilitate transition of care to adult providers for adolescents with chronic disease are not uniformly successful and many patients encounter challenges. The goal of this study was to assess transition readiness and preferences for tools to aid in the transition process with an emphasis on technology and social media. Methods: We surveyed and performed focus groups on patients aged 13–21 years from a pediatric university-based rheumatology and general pediatric practice. Demographics and transition readiness were assessed using a questionnaire. Transition readiness was assessed by examining patient knowledge and independence with care. Focus groups were conducted to elicit perspectives about desirable features of a transition program and useful tools. Results: Thirty-five patients completed surveys; and 20 patients and 13 of their parents participated in a focus group. The median patient age was 17 years and 74.3% were female. A Likert scale (0–10, 10=most) was used to evaluate concern over changing to an adult medical provider, (mean=6.4, SD=2.6), preparedness for disease self-management (mean=6.0, SD=2.8), and perceived importance of self-managing their condition (mean=7.1, SD=3.1). Themes that emerged from focus groups included a desire for support groups with other teens, a preference for using text messaging for communication and a desire for an online health management program. Conclusions: Teens with chronic disease are able to identify health maintenance tasks and strategies that will aid in developing independence with healthcare management. These findings support the idea that developing engaging applications and support groups will assist teens in the transitioning.

PURPOSE: There is a need for an improved understanding of clinical and biologic risk factors in pediatric cancer to improve patient outcomes. Machine learning (ML) represents the application of computational inference from advanced statistical methods that can be applied to increasing amount of data available for study in pediatric oncology. The goal of this systematic review was to systematically characterize the state of ML in pediatric oncology and highlight advances and opportunities in the field. METHODS: We conducted a systematic review of the Embase, Scopus, and MEDLINE databases for applications of ML in pediatric oncology. Query results from all three databases were aggregated and duplicate studies were removed. RESULTS: A total of 42 unique articles that examined the applications of ML in pediatric oncology met inclusion criteria for review. We identified 20 studies of CNS tumors, 13 of solid tumors, and nine of leukemia. ML tasks included classification, prediction of treatment response, and dose optimization with a variety of methods being used including neural network, k-nearest neighbor, random forest, naive Bayes, and support vector machines. Strengths of the identified studies included matching or outperforming physician comparators via automated analysis and predicting therapeutic response. Common limitations included significant heterogeneity in reporting standards, clinical applicability, small sample sizes, and missing external validation cohorts. CONCLUSION: We identified areas where ML can enhance clinical care in ways that may not otherwise be achievable. Although ML promises enormous potential in improving diagnostics, decision making, and monitoring for children with cancer, the field remains in early stages and future work will be aided by standards and guidelines to ensure rigorous methodologic design and maximizing clinical utility.