Assessment of iodine nutrition status in individual adults using machine learning: a cross-sectional study integrating multidimensional features.

OBJECTIVE: From a public health perspective, the relationship between individual iodine nutritional and its associated risk factors has not been fully elucidated. The aim of this study is to utilize multiple biomarkers to represent individual iodine nutritional status, identify contributing factors for iodine imbalance, and develop a predictive assessment model for iodine nutrition evaluation in different water iodine districts. METHODS: A total of 2,692 participants were recruited from Shandong and Anhui provinces in China. The study population was initially stratified into high-iodine and low-iodine groups based on water iodine concentrations of their residence. Thyroid function indicators and thyroid volume were used as assessment parameters. Both studies first utilized univariate regression to screen variables. After filtering out noisy features, the remaining significant variables were used to split the data into training and testing sets at a 7:3 ratio. Using random forest and eXtreme Gradient Boosting (XGBoost) models, we analyzed how modifiable factors (diet, medical history, lifestyle) relate to iodine homeostasis. Model performance was validated on the testing sets, with accuracy, sensitivity, and area under the curve (AUC) as key metrics. RESULTS: Integrated analysis of univariate regression, random forest, and XGBoost models revealed significant associations between drinking water sources and disrupted iodine homeostasis. In high-iodine areas, the XGBoost model demonstrated exceptional predictive performance for thyroid volume (R²=0.98, RMSE = 3.53). The results of the random forest classification model showed that the AUC was 0.76 (95% CI: 0.68–0.85) when TSH was used as the assessment indicator, while the AUC for TGAb and TPOAb were 0.74 (95% CI: 0.63–0.84) and 0.67 (95% CI: 0.54–0.80), respectively. In iodine-deficient areas, the XGBoost model maintained good predictive ability for thyroid volume (R2 = 0.97, RMSE = 3.28). The random forest model demonstrated moderate diagnostic accuracy among the biomarkers: TSH (AUC = 0.66; 95% CI: 0.51–0.80), TGAb (AUC = 0.69; 95% CI: 0.55–0.83), and TPOAb (AUC = 0.69; 95% CI: 0.56–0.83). CONCLUSION: This study established an individualized iodine nutrition assessment model by integrating multi-dimensional biochemical indicators with advanced machine learning algorithms. The model represented by thyroid volume effectively identified the key factors disrupting iodine homeostasis and was capable of accurately predicting individual iodine nutritional status. Its dual utility provides: (1) evidence-based quantitative metrics that can offer personalized guidance for iodine supplementation in clinical practice; and (2) a decision-support framework for regions with varying iodine levels, which can inform the optimization of iodine supplementation programs in specific areas.