Machine learning identifies baseline clinical features that predict early hypothyroidism in patients with Graves’ disease after radioiodine therapy

Abstract

Background and objective: Radioiodine therapy (RAI) is one of the most common treatment solutions for Graves’ disease (GD). However, many pat ients will develop hypothyroidism as early as 6 months after RAI. This study aimed to implement machine learning (ML) algorithms for the early prediction of post-RAI h ypothyroidism. Methods: Four hundred and seventy-one GD patients who underwent RAI bet ween January 2016 and June 2019 were retrospectively recruited and r andomly split into the training set (310 patients) and the validation set (161 pat ients). These patients were followed for 6 months after RAI. A set of 138 clinical and lab test features from the electronic medical record (EMR) were extracted, and multipl e ML algorithms were conducted to identify the features associated with the occurren ce of hypothyroidism 6 months after RAI. Results: An integrated multivariate model containing patients’ age, thy roid mass, 24-h radioactive iodine uptake, serum concentrations of aspartate am inotransferase, thyrotropin-receptor antibodies, thyroid microsomal antibodies, and blood neutrophil count demonstrated an area under the receiver operating curve ( AUROC) of 0.72 (95% CI: 0.61–0.85), an F1 score of 0.74, and an MCC score of 0.63 in th e training set. The model also performed well in the validation set with an AUROC of 0.74 (95% CI: 0.65–0.83), an F1 score of 0.74, and a MCC of 0.63. A user-friendly nomogram w as then established to facilitate the clinical utility. Conclusion: The developed multivariate model based on EMR data could be a valuable tool for predicting post-RAI hypothyroidism, allowing them to be tre ated differently before the therapy. Further study is needed to validate the developed prognostic model at independent sites.

Keywords

• graves’ disease
• radioactive iodine therapy
• hypothyroidism
• machine learning
• electronic medical data
• predictive model