The abstract is read at the publisher; the summary is JClub's.
In a retrospective cohort of 66 lung adenocarcinoma patients without baseline brain metastasis, a Cox model predicts 12- and 24-month BM-free probabilities with optimism-corrected C-index 0.742.
- Why it matters: Brain metastasis risk in lung adenocarcinoma is hard to forecast because follow-up varies, censoring occurs, treatments change risk over time, and competing mortality can obscure event timing.
- What they did: Patients treated between 2018 and 2024 entered at a negative contrast-enhanced brain MRI; incident BM was modeled with Cox regression, predictor reduction used LASSO, and internal validation used 1,000 bootstrap resamples with Fine-Gray competing mortality and time-dependent EGFR-TKI exposure.
- The result: LASSO retained T classification, N classification, EGFR mutation status, and serum CEA; T3-4, N1-3, and EGFR mutation were linked to higher BM hazard, and time-dependent AUCs were 0.773 at 12 months and 0.758 at 24 months.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.