Improving The Diagnosis of Thyroid Cancer by Machine Learning and Clinical Data
This work addresses the need for more reliable preoperative diagnosis in thyroid cancer treatment to reduce surgical errors, though it appears incremental as it applies existing machine learning methods to a new dataset.
The study tackled the problem of inaccurate preoperative diagnosis of thyroid cancer by developing a machine learning framework that predicts thyroid nodule malignancy using a novel clinical dataset, showing it outperforms human expert assessment.
Thyroid cancer is a common endocrine carcinoma that occurs in the thyroid gland. Much effort has been invested in improving its diagnosis, and thyroidectomy remains the primary treatment method. A successful operation without unnecessary side injuries relies on an accurate preoperative diagnosis. Current human assessment of thyroid nodule malignancy is prone to errors and may not guarantee an accurate preoperative diagnosis. This study proposed a machine framework to predict thyroid nodule malignancy based on a novel clinical dataset we collected. The 10-fold cross-validation, bootstrap analysis, and permutation predictor importance were applied to estimate and interpret the model performance under uncertainty. The comparison between model prediction and expert assessment shows the advantage of our framework over human judgment in predicting thyroid nodule malignancy. Our method is accurate, interpretable, and thus useable as additional evidence in the preoperative diagnosis for thyroid cancer.