Ablation dosage recommendation for thyroid cancer treatment following thyroidectomy using machine learning

Abstract

This article presents an innovative approach to ascertain the most effective ablation dosages for thyroid cancer treatment following thyroidectomy. The methodology utilizes Decision Trees and places significant emphasis on the interpretability of medical decision-making. By incorporating clinical data and the Radioactive Scan Index (RSI) into Decision Tree algorithms, our methodology offers transparent treatment planning insights. By means of a case study, we illustrate the function of Decision Trees in clarifying pivotal elements that impact dosage recommendations for ablation, thereby enabling medical practitioners to make well-informed decisions. This study emphasizes the importance of decision explainability in the optimization of treatment strategies for thyroid cancer, ultimately leading to enhanced patient care and treatment outcomes.