Explainable multi-modal machine learning for predicting occult pulmonary metastases in differentiated thyroid cancer: a SHAP-based approach prior to radioactive iodine scans
Youwu Su, Yukun Cai, Shui Jin, Xuemei Ye, Jaesik Jeong, Ye Yuan, Heqing Yi
Frontiers in Medical Technology
초록
The logistic model (LR) showed the best performance in predicting occult lung metastases of thyroid cancer patients before <sup>131</sup>I-WBS. Lymph nodes metastases and throglobulin have the most significant impact on the prediction.