# From data to decision: an interpretable machine learning model for optimizing RAI therapy in Graves’ hyperthyroidism

## TL;DR

This paper introduces a machine learning model to predict and optimize radioactive iodine therapy outcomes for Graves’ hyperthyroidism patients.

## Contribution

A novel interpretable machine learning framework for RAI therapy optimization in Graves’ hyperthyroidism using SHAP analysis for transparency.

## Key findings

- Random Forest achieved an AUC of 0.950 and Brier score of 0.067 for RAI outcome prediction.
- RAIU 3h, FT4, age, and thyroid weight were identified as the most influential predictors.
- The model offers a personalized tool to reduce RAI treatment failure rates.

## Abstract

Radioactive iodine (RAI) therapy is a cornerstone treatment for Graves’ hyperthyroidism (GH), yet failure rates remain significant due to the complexity of individual patient responses. Traditional fixed-dose or simple calculated-dose methods often fail to account for non-linear interactions among clinical features.

We retrospectively analyzed data from 1,292 GH patients who received initial RAI therapy between June 2018 and July 2024. Comprehensive pre-treatment clinical, laboratory, and imaging data, including age, gender, FT4, 3-hour radioactive iodine uptake (RAIU 3h), thyroid weight, and thyroid receptor antibodies (TRAb), were collected. Stepwise regression with the Akaike Information Criterion (AIC) was employed for feature selection, identifying nine optimal predictors. Six machine learning algorithms were compared, with performance evaluated using AUC, Brier score, and Decision Curve Analysis (DCA). SHapley Additive exPlanations (SHAP) analysis provided model interpretability.

The final cohort, comprising 1,292 patients (61.3% female, median age 37 years), achieved a 75.8% remission rate. Nine significant variables were identified as optimal predictors: gender, age, history of antithyroid drug use, disease course over 2 years, total iodine dose (TID), free thyroxine (FT4), RAIU 3h, thyroid weight, and TRAb. Among the algorithms tested, the Random Forest (RF) model demonstrated superior performance, achieving an AUC of 0.950 on the independent test set and a Brier score of 0.067, indicating excellent discrimination and calibration. SHAP analysis confirmed RAIU 3h, FT4, age, and thyroid weight as the most influential features, providing clinical transparency.

The developed interpretable machine learning framework offers a precise, personalized tool for predicting RAI outcomes, potentially guiding optimizing dosing strategies to reduce treatment failure.