This study aimed to reveal a new dimension of allergy profiles in the general population by using machine learning to explore complex relationships among various cytokines/chemokines and allergic diseases (asthma and atopic dermatitis; AD). We examined the symptoms related to asthma and AD and the plasma levels of 72 cytokines/chemokines obtained from a general population of 161 children at 6 years of age who participated in a pilot birth cohort study of the Japan Environment and Children's Study (JECS). The children whose signs and symptoms fulfilled the criteria of AD, which are mostly based on questionnaire including past symptoms, tended to have higher levels of the two chemokine ligands, CCL17 and CCL27, which are used for diagnosis of AD. On the other hand, another AD-related chemokine CCL22 level in plasma was higher only in children with visible flexural eczema, which is one of AD diagnostic criteria but was judged on the same day of blood examination unlike other criteria. Here, we also developed an innovative method of machine learning for elucidating the complex cytokine/chemokine milieu related to symptoms of allergic diseases by using clustering analysis based on the random forest dissimilarity measure that relies on artificial intelligence (AI) technique. To our surprise, the majority of children showing at least any asthma-related symptoms during the last month were divided by AI into the two clusters, either cluster-2 having elevated levels of IL-33 (related to eosinophil activation) or cluster-3 having elevated levels of CXCL7/NAP2 (related to neutrophil activation), among the total three clusters. Future studies will clarify better approach for allergic diseases by endotype classification.
All Science Journal Classification (ASJC) codes
- Immunology and Allergy
- Molecular Biology