Machine Learning en la predicción de supervivencia en el cáncer de pulmón y metástasis cerebrales

Abstract

Non-small cell lung cancer (NSCLC) is one of the most common malignant neoplasms in our setting, and its prognosis worsens significantly in the presence of brain metastases, affecting 30-60% of patients. Although there have been advances in the treatment of advanced NSCLC, patients with brain metastases have often been excluded from clinical trials, limiting knowledge of treatment effectiveness. The objective of this study was to develop a machine learning model to predict survival in NSCLC patients with brain metastases, while also evaluating the impact of local treatment. Three models were trained: Decision Tree, Random Forest, and Deepnet. The Random Forest model with 100 trees showed the best performance, with an AUC-ROC of 0. 7601. These results suggest that the use of machine learning can improve clinical decision-making in patients with brain metastases.

Date of Award	2024
Original language	Spanish
Supervisor	Remo Suppi Boldrito (Director)