FRIDAY, April 24, 2026 (HealthDay News) -- Machine learning models can predict the risk for developing moderate-to-severe persistent asthma and allergic rhinitis in children diagnosed with early-life atopic dermatitis, according to a study published online April 17 in the Journal of Allergy and Clinical Immunology.
Wansu Chen, Ph.D., from Kaiser Permanente Southern California in Pasadena, and colleagues developed and validated machine learning models for predicting individualized risk for moderate-to-severe persistent asthma and allergic rhinitis in children aged 5 to 11 years who were diagnosed with atopic dermatitis before age 3 years. The analysis included electronic health record data from 10,688 children.
The researchers found that asthma models showed strong discrimination (area under the curve [AUC], 0.893 comprehensive model; 0.892 simplified model). At the 95 percent specificity threshold, the comprehensive model achieved 40.4 percent sensitivity and 39.3 percent positive predictive value (PPV), while the simplified model showed 36.2 percent sensitivity and 33.8 percent PPV. Rhinitis models showed moderate performance (AUC, 0.793 and 0.773, respectively); with 90 percent specificity, the comprehensive model achieved 35.5 percent sensitivity and 72.7 percent PPV, while the simplified model demonstrated 34.0 percent sensitivity and 69.2 percent PPV. There was acceptable calibration noted, with strong agreement among the highest-risk groups.
"Prediction tools integrated into clinical workflows can help providers identify children at elevated risk and prioritize them for interventions such as environmental control, allergist evaluation, or early initiation of preventative therapy," the authors write.