Differentiated thyroid cancer (DTC) poses significant management challenges due to the variable risk of recurrence. This study uses a dataset comprising clinical, pathological, and treatment data from 383 patients to develop and validate machine learning models, combined with feature selection algorithms, for predicting differentiated thyroid cancer recurrence. We evaluated models based on a variety of machine learning technologies (light gradient boosting machine, random forest, k-nearest neighbor, logistic regression, stochastic gradient descent, and an emerging deep learner optimized for tabular data: Gandalf) combined with several feature selection methods. Our feature selection technologies include an emerging redundancy-aware wrapper-based feature selection technique, achieving thyroid cancer recurrence prediction accuracy of 94.8 to 95.9% across two validation methods, based only on whether the patient’s tumor’s response was structurally incomplete, whether their tumor’s stage was advanced (III, IVA, or IVB), and the patient’s age. The results underline the potential for machine learning to enhance the precision of recurrence prediction in DTC while developing technologies whose predictive capacity is more easily explained. Using the same dataset, machine learning and feature selection techniques, this study also provides an analysis on predicting American Thyroid Association (ATA) risk scores. The technologies developed as part of this study have potential for improving the personalization of healthcare through the creation of models based on detailed patient-specific clinical attributes.
Penner et al. (Wed,) studied this question.