[Evaluation of a logistic regression model in predicting the prognosis of Graves' disease treated by antithyroid drugs].

One hundred and twelve new cases of Graves' disease were treated by tapazole for 6 months and followed up for another 12 months. The initial dose was 30 mg/d. Clinical and biochemical euthyroidism was achieved within 1 to 3 months, then a maintenance was given until cessation of drugs at 6 months. One hundred and eleven cases completed the study. Remission and relapse were defined at the end of follow-up for 1 year according to the presence or absence of clinical manifestation of hyperthyroidism and the levels of T3 and T4. The results of the 12-month follow-up showed that 46 of 111 cases were in remission, and the remaining 65 cases suffered relapse. A logistic regression model with 4 variables was established, which included thyroid suppression rate and goitre size by palpation at the end of drug treatment, the level of T3 before therapy, and the patients' age. The model had 81.5% sensitivity, 84.8% specificity and 82.9% (92/111) accuracy in predicting the outcome of Graves' disease after withdrawal of drug for 1 year. The results were much better than any other univariate analysis in this study.