The incidence of thyroid cancer is on the rise, and it now represents the fourth most common cancer in women in Italy. In particular, differentiated thyroid cancer have an excellent prognosis, with a five-year survival rate of 98.1% and low rates of recurrence. The challenge today is to develop increasingly individualized treatment strategies with due emphasis on quality of life. A first step toward this goal involves classification of cases according to the risk of recurrence.
A three-tiered risk system (low, intermediate, high) was proposed for structural disease recurrence in patients without structurally identifiable disease after initial therapy. In this system, the risk of structural disease recurrence has been associated with selected clinico-pathological features and reflects an estimate based on the published literature. However, large multicenter and prospective studies on proper evaluation of risk of recurrence in thyroid cancer patients are missing.
The overall aim of the project is to reliably predict thyroid cancer recurrence after initial patient treatment. Secondary aim is the identification of predictors of the outcome treatment. Novel technologies such as machine learning and artificial intelligence algorithms will be applied to data from the web-based thyroid cancer database of the Italian Thyroid Cancer Observatory (ITCO). ITCO dataset includes prospective and observational data from consecutive patients diagnosed with thyroid cancer since 2013.
This project will provide follow-up data on the largest thyroid cancer dataset, thus allowing an accurate risk assessment to be used to guide initial prognostication, disease management, and proper follow-up strategies. The proper risk assessment will minimize overtreatment in the majority of at low-risk patients and will appropriately allow for treating and monitoring those patients at higher risk. Employment of innovative technologies will allow for identification of unknown risk predictors
Large multicenter and prospective studies on proper evaluation of risk assessment in thyroid cancer patients are missing. To address this issue, we plan to employ the web-based thyroid cancer database of the Italian Thyroid Cancer Observatory (ITCO) and novel technologies such as machine learning and artificial intelligence.
ITCO database has been opened in 2013 at the Thyroid cancer center of SAPIENZA University of Rome (the network¿s coordinating center) and currently includes 48 thyroid cancer centers (primary and tertiary centers) located throughout Italy. ITCO database includes prospectively updated, observational data on a consecutive series of patients with newly diagnosed thyroid cancer. To date, data on 6,490 Italian patients with histologically confirmed diagnosis of papillary, follicular, poorly differentiated, and anaplastic thyroid cancer have been collected. The median of the follow-up is 15 months (range: 3-89 months) with an enrolment rate of approximately 130 newly diagnosed thyroid cancer patients per month.
This project will provide clinic-pathological, molecular and follow-up data on the largest prospective thyroid cancer dataset, thus allowing an accurate risk assessment to be used to guide initial prognostication, disease management, and proper follow-up strategies. Having a prospective and multicenter dataset of a contemporary cohort of patients is essential to have a real time analysis on the actual treatment of the thyroid cancer. For the machine learning to be accurate it is crucial to have access on real data, letting the artificial intelligence to learn current clinical practices and be of some impact on current patients.
The proper risk assessment will minimize overtreatment in the majority of at low-risk DTC patients and will appropriately allow for treating and monitoring those patients at higher risk. Notably, the employment of machine learning will allow for identification of unknown risk predictors.