Predicting Recurrence in Differentiated Thyroid Cancer: A Machine Learning Approach

A predictive model refers to a mathematical or computational model that is designed to make predictions or forecasts based on input data. These models are used in various fields such as finance, healthcare, marketing, and many others to analyze historical data and make predictions about future events or trends. This study focuses on developing a predictive model for well-differentiated thyroid cancer recurrence using machine learning algorithms. Leveraging a dataset with clinicopathologic features spanning a 15-year period, the study aims to contribute to the advancement of predictive modeling in thyroid cancer prognosis. The Various algorithms, including logistic regression, decision tree, random forest, support vector machine, k-nearest neighbors, and XGBoost, are evaluated for their performance in binary classification. The highest-performing model is then utilized to predict thyroid cancer recurrence in new data. Integrating this with frontend tools has resulted in an intuitive interface that streamlines the process of uploading datasets, executing the predictive model, and presenting the results. This integration has made the prediction process more accessible and user-friendly, ultimately benefiting clinicians and researchers in the field of thyroid cancer research.