Predicting recurrence of thyroid cancer: how to.

What is it about?

This prospective multicenter study aimed to develop a comprehensive data-driven model to predict persistent/recurrent disease in patients with differentiated thyroid cancer. The study used the Italian Thyroid Cancer Observatory database to select consecutive cases with at least early follow-up data. A decision tree model was built to assign a risk index to each patient, which outperformed the 2015 American Thyroid Association (ATA) risk stratification system. The study found that several variables not included in the ATA system significantly impacted the prediction of disease persistence/recurrence, including age, body mass index, tumor size, sex, family history of thyroid cancer, surgical approach, presurgical cytology, and circumstances of the diagnosis.

Featured Image

Photo by patricia serna on Unsplash

Photo by patricia serna on Unsplash

Why is it important?

Current risk stratification systems may be complemented by the inclusion of other variables to improve the prediction of treatment response.