Interpretable machine learning algorithms reveal gut microbiome features associated with atopic dermatitis.

Background: The "gut-skin axis" has been proposed to play an important role in the development and symptoms of atopic dermatitis. Therefore, we have constructed an interpretable machine learning framework to quantitatively screen key gut flora.

Methods: The 16S rRNA dataset, after applying the centered log-ratio transformation, was analyzed using five different machine learning models: random forest, light gradient boosting machine, extreme gradient boosting, support vector machine with radial kernel, and logistic regression. Interpretable machine learning methods, such as SHAP values, were used to identify significant features associated with atopic dermatitis.

Results: Random forest performed better than the other "tree" models in the validation partitions. The SHAP global dependency plot indicated that ranked as the strongest predictive factor across all prediction horizons, although the SHAP values for some features were still higher in support vector machine and logistic regression models. The SHAP partial dependency plot for "tree" models showed that the best segmentation point for was further from the origin compared to other features in the respective models, quantitatively reflecting differences in gut microbiota.

Conclusion: Machine learning models combined with SHAP could be used to quantitatively screen key gut flora in atopic dermatitis patients, providing doctors with an intuitive understanding of 16S rRNA sequencing data to support precision medicine in care and recovery.