Predicting Lung Cancer Recurrence After Surgical Treatment Via a Machine Learning Model

Lung cancer recurrence after curative surgical treatment ranges from 30% to 55% and remains a significant challenge in patient management. Accurate prediction of recurrence risk is critical to guide treatment decisions such as the use of neoadjuvant chemotherapy or immunotherapy (IO), the extent of lung resection, and follow-up strategies. The results of a study that used a preoperative machine learning model consisting of patient computed tomography (CT) images and demographic features to predict lung cancer recurrence were presented at the ESMO Congress 2023.

The researchers collected a dataset of 588 patients with clinical stage I-IIIA lung cancer who underwent surgical treatment for lung cancer, of whom 147 had lung cancer recurrence. The retrospectively collected CT images and associated demographic and pathologic data were taken from patients in both screening and clinical settings from the US National Lung Screening Trial and the North Estonia Medical Centre. The preoperative model was trained to predict the likelihood of recurrence on a diverse set of features, including radiomic features extracted from CT images and relevant clinical variables. As a baseline, the researchers compared the preoperative model with ranked clinical TNM staging, and performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, and specificity. Lung cancer recurrence prediction results are shown in the table.

Based on their retrospective analysis, the researchers concluded the preoperative model outperformed clinical staging prediction of lung cancer recurrence in preoperative settings. “With further development, this algorithm could prove [to be] a valuable tool to aid the management of lung cancer patients.”

Source: Valter A, Kordemets T, Gasimova A, et al. Machine learning model for predicting lung cancer recurrence after surgical treatment: a retrospective study using NLST and European hospital data. Abstract of a poster presented at the ESMO Congress 2023; October 20-24, 2023; Madrid, Spain.