Machine Learning-Based Prediction of Food Allergy in Children Aged <2 Years with Atopic Dermatitis.
CatBoost model using clinical features predicted food allergy in infants with atopic dermatitis
Machine Learning-Based Prediction of Food Allergy in Children Aged <2 Years with Atopic Dermatitis.
Children with atopic dermatitis (atopic dermatitis) are at increased risk of food allergy (food allergy).
This study aimed to develop and evaluate machine learning (machine learning) models for predicting food allergy in children aged <2 years with atopic dermatitis and to assess feature contribution.
This retrospective study included children aged 1 month to 2 years who were diagnosed with atopic dermatitis and underwent evaluation for food allergy.
correctly distinguished infants who did and didn't have food allergy
The median age at presentation was 7.4 months (IQR, 4.8-10.8), and food allergy was present in 101 patients (23.2%).
Using combined clinical and laboratory features, XGBoost achieved an AUC of 0.88 (95% CI, 0.79-0.95), with a sensitivity of 0.70 and a specificity of 0.96.
Using clinical features alone, LightGBM and logistic regression achieved AUCs of 0.89 (95% CI, 0.82-0.96) and 0.86 (95% CI, 0.75-0.95), respectively, with sensitivities of 0.85 and 0.65 and specificities of 0.82 and 0.88.
CatBoost demonstrated the best overall performance in predicting food allergy in children aged <2 years with atopic dermatitis using clinical features alone.
machine learning models may help identify children with atopic dermatitis who require further diagnostic evaluation for food allergy.