The following is a summary of “Machine Learning for Predicting Distant Metastasis of Medullary Thyroid Carcinoma Using the SEER Database,” published in the December 2023 issue of Endocrinology by Guo et al.
Researchers conducted a prospective study to develop a robust machine learning (ML) model for predicting distant metastasis (DM) risk in medullary thyroid carcinoma (MTC).
They extracted demographic data of MTC patients from the Surveillance, Epidemiology, and End Results (SEER) database of the National Institutes of Health (between 2004 to 2015) to construct six ML algorithm models. Evaluation metrics were used to assess model performance, including accuracy, precision, recall rate, F1-score, and area under the receiver operating characteristic curve (AUC). They examined the association between clinicopathological characteristics and target variables using traditional logistic regression (LR) analyses.
The results showed that of 2049 patients, 138 developed DM. Multivariable LR revealed that age, sex, tumor size, extrathyroidal extension, and lymph node metastasis were predictive factors for DM in MTC. Among the six ML models assessed, random forest (RF) demonstrated superior predictive performance in evaluating the risk of DM in MTC, exhibiting higher accuracy, precision, recall rate, F1-score, and AUC compared to the traditional binary LR model.
Investigators concluded that RF outperforms traditional LR in predicting MTC patients’ risk of DM, offering valuable guidance for clinical decisions.
Source: hindawi.com/journals/ije/2023/9965578
