A B S T R A C T PurposeBecause adolescent and young adult (AYA) patients with cancer have experienced variable improvement in survival over the past two decades, enhancing the quality and timeliness of cancer care in this population has emerged as a priority area. To identify current trends in AYA care, we examined patterns of clinical trial participation, time to treatment, and provider characteristics in a population-based sample of AYA patients with cancer. MethodsUsing the National Cancer Institute Patterns of Care Study, we used multivariate logistic regression to evaluate demographic and provider characteristics associated with clinical trial enrollment and time to treatment among 1,358 AYA patients with cancer (age 15 to 39 years) identified through the Surveillance, Epidemiology, and End Results Program. ResultsIn our study, 14% of patients age 15 to 39 years had enrolled onto a clinical trial; participation varied by type of cancer, with the highest participation in those diagnosed with acute lymphoblastic leukemia (37%) and sarcoma (32%). Multivariate analyses demonstrated that uninsured, older patients and those treated by nonpediatric oncologists were less likely to enroll onto clinical trials. Median time from pathologic confirmation to first treatment was 3 days, but this varied by race/ethnicity and cancer site. In multivariate analyses, advanced cancer stage and outpatient treatment alone were associated with longer time from pathologic confirmation to treatment. ConclusionOur study identified factors associated with low clinical trial participation in AYA patients with cancer. These findings support the continued need to improve access to clinical trials and innovative treatments for this population, which may ultimately translate into improved survival.

Background: Machine learning (ML) has made a significant impact in medicine and cancer research; however, its impact in these areas has been undeniably slower and more limited than in other application domains. A major reason for this has been the lack of availability of patient data to the broader ML research community, in large part due to patient privacy protection concerns. High-quality, realistic, synthetic datasets can be leveraged to accelerate methodological developments in medicine. By and large, medical data is high dimensional and often categorical. These characteristics pose multiple modeling challenges. Methods: In this paper, we evaluate three classes of synthetic data generation approaches; probabilistic models, classification-based imputation models, and generative adversarial neural networks. Metrics for evaluating the quality of the generated synthetic datasets are presented and discussed. Results: While the results and discussions are broadly applicable to medical data, for demonstration purposes we generate synthetic datasets for cancer based on the publicly available cancer registry data from the Surveillance Epidemiology and End Results (SEER) program. Specifically, our cohort consists of breast, respiratory, and non-solid cancer cases diagnosed between 2010 and 2015, which includes over 360,000 individual cases. Conclusions: We discuss the trade-offs of the different methods and metrics, providing guidance on considerations for the generation and usage of medical synthetic data.

Overall, levels of guideline treatment were lower than expected and particularly low for patients with Medicaid or Medicare only. The use of guideline therapy for ovarian and cervical cancer patients and for patients with rectal cancers was unrelated to type of insurance. Of particular concern is the significantly lower use of guideline therapy for non-Hispanic black patients with Medicaid. After adjusting for other factors, only half of these patients received guideline therapy.

Initial treatment for multiple myeloma has changed markedly. Most patients now receive novel agents, with a decline in the use of traditional chemotherapy. Use of transplantation and novel agents varies with race and insurance. These findings document rapid changes in patterns of care and highlight addressable disparities in myeloma care.

Most neuroblastoma patients are registered on a risk-based open/active clinical trial. Variation in modality, systemic agents and sequence of treatment reflects the heterogeneity of therapy received by these patients.

Mortality was decreased in patients receiving guideline therapy. Although, rates of guideline-concordant therapy are low in community clinical practice, they are apparently increasing. Newer treatment (oxaliplatin, capecitabine) started to disseminate in 2000. Racial disparities, present in 1995, were not detected in 2000. Age disparities remain despite no evidence of greater chemotherapy-induced toxicity in the elderly. More equitable receipt of cancer treatment to all segments of the community will help to reduce mortality.

Community physicians began prescribing adjuvant chemotherapy and hormonal therapy in advance of publication of the NIH consensus statement in 1990. Adoption of recommended treatments for node-negative disease has been less complete compared with node-positive tumors, perhaps reflecting the more complex nature of the clinical trials data or the smaller anticipated benefit from adjuvant therapy for this disease subset.

The coronavirus disease 2019 (COVID-19) pandemic led to delayed medical care in the US. We examined changes in patterns of cancer diagnosis and surgical treatment between January 1 and December 31 in 2020 and 2019 with real-time electronic pathology report data from population-based Surveillance, Epidemiology, and End Results cancer registries from Georgia and Louisiana. During 2020, there were 29,905 fewer pathology reports than in 2019, representing a 10.2% decline. Declines were observed in all age groups, including children and adolescents less than18 years. The nadir was early April 2020, with 42.8% fewer reports than in April 2019. Numbers of reports through December 2020 never consistently exceeded those in 2019 after first declines. Patterns were similar by age group and cancer site. Findings suggest substantial delays in diagnosis and treatment services for cancers during the pandemic. Ongoing evaluation can inform public health efforts to minimize any lasting adverse effects of the pandemic on cancer diagnosis, stage, treatment, and survival.