Search

PURPOSE With earlier detection and an increasing number of breast cancer (BCa) survivors, more women are living with side effects of BCa treatment. A predictive approach to studying treatment-related adverse events (AEs) may generate proactive strategies; however, many studies are descriptive in nature. Focusing on short-term AEs, we determine the performance of prediction models of disease- or treatment-related AEs among women diagnosed with BCa. METHODS We used administrative claims data from the Blue Health Intelligence National Data Repository. The study sample included female individuals age 18 years and older who were diagnosed with BCa and received cancer-directed treatment between January 1, 2014, and August 1, 2019. Using the information available in the claims data, we constructed longitudinal patient histories and identified disease- and treatment-related AEs occurring within 6 months of treatment. The following prediction models were developed: logistic regression, Lasso regression, gradient boosted tree (GBT), and random forest (RF). We compared models using the area under the receiver operating characteristic curve and its CI, among other metrics. RESULTS Data were extracted for 267,473 members meeting study inclusion criteria. The area under the curve for the logistic regression model was 0.82 (0.82-0.86), compared with 0.89 (0.87-0.90) for the Lasso, 0.91 (0.89-0.93) for the GBT, and 0.90 (0.93-0.89) for the RF models. The sensitivity was 0.96 for the GBT, Lasso, and RF models, whereas the specificity was 0.42, 0.44, and 0.39 for the GBT, Lasso, and RF models, respectively. Positive predictive values were 0.96 across all three models. CONCLUSION Prediction models developed using big data methods and grounded in a clinically guided framework have the potential to reliably predict short-term treatment-related AEs among women diagnosed with BCa.

Background and Objectives: Children with asthma who have depressed caregivers are known to be less adherent to medication regimes. However, it is less clear how adherence responds to a caregiver’s new diagnosis of severe depression or whether there is a similar relationship with other serious caregiver diagnoses. The hypothesis is that adherence worsens both with new diagnoses of depression and possibly with new diagnoses of other serious conditions. Methods: This study follows a cohort of 341,444 continuously insured children with asthma before and after a caregiver’s new diagnosis of severe depression or another serious health condition. The effect of a new depression diagnosis on a child’s medication adherence is compared to the effect of new diagnoses of other common caregiver chronic conditions including diabetes, cancer, congestive heart failure, coronary artery disease, and chronic obstructive pulmonary disease. Results: Results show that children’s medication adherence declines following a caregiver’s new diagnosis of severe depression, but that it also declines following a caregiver’s new diagnosis of diabetes. There is no association with new diagnoses of the other caregiver chronic conditions examined. Conclusions: Children whose caregivers have a new diagnosis of depression or diabetes may be at increased risk of deterioration in their medication adherence. These caregivers may benefit from additional support and follow-up. The relationship between caregivers’ health and children’s medication adherence is complex and deserves further study.