External Validation of a Predictive Model for Thyroid Cancer Risk with Decision Curve Analysis

Background/Objectives: Thyroid cancer ranks among the most prevalent endocrine neoplasms, with a significant rise in incidence observed in recent decades, particularly in papillary thyroid carcinoma (PTC). This increase is largely attributed to the enhanced detection of subclinical cancers through advanced imaging techniques and fine-needle aspiration biopsies. The present study aims to externally validate a predictive model previously developed by our group, designed to assess the risk of a thyroid nodule being malignant. Methods: By utilizing clinical, analytical, ultrasound, and histological data from patients treated at the Puerto Real University Hospital, this study seeks to evaluate the performance of the predictive model in a distinct dataset and perform a decision curve analysis to ascertain its clinical utility. Results: A total of 455 patients with thyroid nodular pathology were studied. Benign nodular pathology was diagnosed in 357 patients (78.46%), while 98 patients (21.54%) presented with a malignant tumor. The most frequent histological type of malignant tumor was papillary cancer (71.4%), followed by follicular cancer (6.1%). Malignant nodules were predominantly solid (95.9%), hypoechogenic (72.4%), with irregular or microlobed borders (36.7%), and associated with suspicious lymph nodes (24.5%). The decision curve analysis confirmed the model's accuracy and its potential impact on clinical decision-making. Conclusions: The external validation of our predictive model demonstrates its robustness and generalizability across different populations and clinical settings. The integration of advanced diagnostic tools, such as AI and ML models, improves the accuracy in distinguishing between benign and malignant nodules, thereby optimizing treatment strategies and minimizing invasive procedures. This approach not only facilitates the early detection of cancer but also helps to avoid unnecessary surgeries and biopsies, ultimately reducing patient morbidity and healthcare costs.