Objective:

To develop an integrated radiomics-clinical model to improve survival prediction in lung adenocarcinoma patients with brain metastasis.

Approach:

• Patient Cohort: A cohort of 176 patients with lung cancer brain metastasis (LCBM) was randomly divided into a training set (n=123) and a test set (n=53).
• Risk Factor Identification: Clinical risk factors were identified using univariate and multivariate logistic regression analyses.
• Radiomics Model Development: A radiomics model was developed based on features extracted from preoperative MRI, selected using LASSO regression.
• Performance Evaluation: The combined nomogram's performance was evaluated using AUC, calibration, and decision curve analyses.

Key Findings:

• EGFR mutation status, number of brain metastases, and Lung-molGPA score were identified as independent prognostic determinants.
• The radiomics model achieved AUCs of 0.862 in the training set and 0.829 in the test set.
• The combined nomogram demonstrated superior predictive performance with AUC values of 0.904 and 0.874 in the training and test sets, respectively.

Interpretation:

The integration of radiomics with clinical parameters enhances prognostic accuracy, aiding in personalized treatment stratification for LCBM.

Limitations:

• The study is retrospective and may be subject to selection bias.
• The cohort size may limit the generalizability of the findings.

Conclusion:

The study presents a reliable predictive tool for guiding treatment selection in patients with LCBM.