Predicting pediatric severe asthma exacerbations: an administrative claims-based predictive model.

OBJECTIVE: Previous machine learning approaches fail to consider race and ethnicity and social determinants of health (SDOH) to predict childhood asthma exacerbations. A predictive model for asthma exacerbations in children is developed to explore the importance of race and ethnicity, rural-urban commuting area (RUCA) codes, the Child Opportunity Index (COI), and other ICD-10 SDOH in predicting asthma outcomes. METHODS: Insurance and coverage claims data from the Arkansas All-Payer Claims Database were used to capture risk factors. We identified a cohort of 22,631 children with asthma aged 5-18 years with 2 years of continuous Medicaid enrollment and at least one asthma diagnosis in 2018. The goal was to predict asthma-related hospitalizations and asthma-related emergency department (ED) visits in 2019. The analytic sample was 59% age 5-11 years, 39% White, 33% Black, and 6% Hispanic. Conditional random forest models were used to train the model. RESULTS: The model yielded an area under the curve (AUC) of 72%, sensitivity of 55% and specificity of 78% in the OOB samples and AUC of 73%, sensitivity of 58% and specificity of 77% in the training samples. Consistent with previous literature, asthma-related hospitalization or ED visits in the previous year (2018) were the two most important variables in predicting hospital or ED use in the following year (2019), followed by the total number of reliever and controller medications. CONCLUSIONS: Predictive models for asthma-related exacerbation achieved moderate accuracy, but race and ethnicity, ICD-10 SDOH, RUCA codes, and COI measures were not important in improving model accuracy.

Asthma Quality Measurement and Adverse Outcomes in Medicaid-Enrolled Children.

OBJECTIVES: To determine the association between the asthma medication ratio (AMR) quality measure and adverse outcomes among Medicaid-enrolled children with asthma in Arkansas, given concerns regarding the utility of the AMR in evaluating pediatric risk of asthma-related adverse events (AAEs). METHODS: We used the Arkansas All-Payer Claims Database to identify Medicaid-enrolled children with asthma using a nonrestrictive case definition and additionally using the standard Healthcare Effectiveness Data and Information Set (HEDIS) persistent asthma definition. We assessed the AMR using the traditional dichotomous HEDIS AMR categorization and across 4 expanded AMR categories. Regression models assessed associations between AMR and AAE including hospitalization and emergency department utilization, with models conducted overall and by race and ethnicity. RESULTS: Of the 22 788 children in the analysis, 9.0% had an AAE (6.7% asthma-related emergency department visits; 3.0% asthma-related hospitalizations). We found poor correlation between AMR and AAE, with higher rates of AAE (10.5%) among children with AMR ≥0.5 compared with AMR <0.5 (8.5%; P < .001), and similar patterns stratified by racial and ethnic subgroups. Expanded AMR categorization revealed notable differences in associations between AMR and AAEs, compared with traditional dichotomous categorization, with worse performance in Black children. CONCLUSIONS: The AMR performed poorly in identifying risk of adverse outcomes among Medicaid-enrolled children with asthma. These findings underscore concerns of the utility of the AMR in population health management and reliance on restrictive HEDIS definitions. New population health frameworks incorporating broader considerations that accurately identify at-risk children are needed to improve equity in asthma management and outcomes.