Background: Growing evidence suggests that pediatric palliative care (PPC) teams influence the care received by children and young adults with chronic, life-limiting illnesses. Little is known about how PPC involvement affects advance care planning (ACP) and circumstances of death in pediatric populations with a wide range of diagnoses. Objective: To determine the relationship between PPC involvement, ACP, and circumstances of death for pediatric patients. Design: A retrospective chart review of 558 pediatric patients who died between January 1, 2012 and December 31, 2016 was conducted. Descriptive statistics were used to characterize the sample. A multivariable logistic regression was used to obtain associations between PPC involvement and ACP. Setting: Large, multidisciplinary tertiary care center in a rural state. Measurements: Data abstracted for each patient included the following: demographic information, diagnosis, location of primary unit, hospice involvement, goals of care (GOC), code status, Physician Orders for Life-Sustaining Treatment (POLST) completion, and location of death. Results: Patients with PPC involvement were more likely to have had ACP addressed before death. After adjusting for covariates in the model, patients with PPC were more likely to have their GOC documented (odds ratio [OR] = 96.93), completion of POLST (OR = 24.06), do-not-resuscitate code status (OR = 7.71), and hospice involvement at the time of death (OR = 11.70) compared with those who did not receive PPC. Conclusions: Pediatric patients are more likely to have ACP addressed if they have PPC involvement. Patients with chronic complex conditions are most likely to receive palliative care.

Background: Childhood cancer survivors (CCS) experience many long‐term health problems that can be mitigated with recommended survivorship care. However, many CCS do not have access to survivorship care nor receive recommended survivorship care. We reviewed the empirical evidence of disparities in survivorship care for CCS.Methods: This systematic review searched PubMed, CINAHL, and PsycINFO for studies on survivorship care for CCS (PROSPERO: CRD42021227965) and abstracted the reported presence or absence of disparities in care. We screened 7945 citations, and of those, we reviewed 2760 publications at full text.Results: A total of 22 studies reported in 61 publications met inclusion criteria. Potential disparities by cancer treatment (N = 14), diagnosis (N = 13), sex (N = 13), and current age (N = 13) were frequently studied. There was high quality of evidence (QOE) of survivorship care disparities associated with non‐White race, Hispanic ethnicity, and being uninsured. Moderate QOE demonstrated disparities among CCS who were unemployed and older. Lower QOE was found for disparities based on cancer diagnosis, cancer treatment, age at diagnosis, time since diagnosis, sex, insurance type, income, educational attainment, and geographic area.Conclusions: We found strong empirical evidence of disparities in survivorship care for CCS associated with race, ethnicity, and insurance status. Multiple other disparate groups, such as those by employment, income, insurance type, education, cancer diagnosis, age at diagnosis, time since diagnosis, cancer treatment, geographic area, sex, and self‐identified gender warrant further investigation. Prospective, multilevel research is needed to examine the role of other patient characteristics as potential disparities hindering adequate survivorship care in CCS.

Background: Colorectal cancer is now the leading cause of cancer-related deaths among young Americans. Accurate early prediction and a thorough understanding of the risk factors for early-onset colorectal cancer (EOCRC) are vital for effective prevention and treatment, particularly for patients below the recommended screening age. Objective: Our study aims to predict EOCRC using machine learning (ML) and structured electronic health record data for individuals under the screening age of 45 years, with the aim of exploring potential risk and protective factors that could support early diagnosis. Methods: We identified a cohort of patients under the age of 45 years from the OneFlorida+ Clinical Research Consortium. Given the distinct pathology of colon cancer (CC) and rectal cancer (RC), we created separate prediction models for each cancer type with various ML algorithms. We assessed multiple prediction time windows (ie, 0, 1, 3, and 5 y) and ensured robustness through propensity score matching to account for confounding variables including sex, race, ethnicity, and birth year. We conducted a comprehensive performance evaluation using metrics including area under the curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and F₁-score. Both linear (ie, logistic regression, support vector machine) and nonlinear (ie, Extreme Gradient Boosting and random forest) models were assessed to enable rigorous comparison across different classification strategies. In addition, we used the Shapley Additive Explanations to interpret the models and identify key risk and protective factors associated with EOCRC. Results: The final cohort included 1358 CC cases with 6790 matched controls, and 560 RC cases with 2800 matched controls. The RC group had a more balanced sex distribution (2:3 male-to-female) compared to the CC group (2:5 male-to-female), and both groups showed diverse racial and ethnic representation. Our predictive models demonstrated reasonable results, with AUC scores for CC prediction of 0.811, 0.748, 0.689, and 0.686 at 0, 1, 3, and 5 years before diagnosis, respectively. For RC prediction, AUC scores were 0.829, 0.771, 0.727, and 0.721 across the same time windows. Key predictive features across both cancer types included immune and digestive system disorders, secondary malignancies, and underweight status. In addition, blood diseases emerged as prominent indicators specifically for CC. Conclusions: Our findings demonstrate the potential of ML models leveraging electronic health record data to facilitate the early prediction of EOCRC in individuals under 45 years. By uncovering important risk factors and achieving promising predictive performance, this study provides preliminary insights that could inform future efforts toward earlier detection and prevention in younger populations.