Predicting lithium-associated thyroid dysfunction through dimension reduction to establish a practical machine learning model: A retrospective multicenter study

This study developed a simplified, clinically applicable XGBoost model for predicting lithium-associated thyroid dysfunction using 7 clinical features. SHAP analysis successfully helped the clinician identify feature contributions and take interventions to prevent thyroid dysfunctions. Future studies on different populations are warranted to extrapolate the models for clinical use.