Abstract: Objective: To analyze the risk factors of vitiligo complicated with autoimmune thyroid disease and establish a nomogram prediction model. Methods: The clinical data of 276 patients with vitiligo in our hospital from February 2017 to January 2019 were collected, and logistic regression was used to analyze the independent risk factors of vitiligo complicated with autoimmune thyroid disease. A nomogram prediction model was established through R (R 3.5.3) software package and rms package to build a nomogram prediction model. At the same time, the caret program package was used to carry out the Bootstrap method Internal verification was performed through repeated sampling 1000 times of, Bootstrap method. The consistency index (C-index) was calculated by the rms program package. The ROC curve was made through ROCR and rms package. Results: The proportion of autoimmune thyroid disease in the group of the patients was 17.75%. Hyperglycemia, duration of vitiligo, type of vitiligo, negative mood, smoking, family history of autoimmune thyroid disease and family history of other autoimmune diseases were the independent risk factors of vitiligo complicated with autoimmune thyroid disease (Ps<0.05). The nomogram prediction model based on the 7 independent risk factors, showed that the actual incidence was basically the same as the predicted incidence (χ2=3.854, P=0.724), and the C-index index was 0.857 (95% CI: 0.829-0.885). Conclusion: Efforts should be made to detect autoimmune thyriod disease among the patients with vitiligo, particularly those with the risk factors.

Key words: vitiligo, autoimmune thyroid disease, risk factors, nomogram