Prediction model on disease recurrence for low risk resected stage I lung adenocarcinoma

• DOI: 10.1111/resp.14508
• Publication Date: 2023-04-28T05:07:58Z
• Authors: Wang Chun Kwok; Ting Fung Ma; James Chung Man Ho; David Chi Leung Lam; Ko Yung Sit; Mary Sau Man Ip; Timmy Wing Kuk Au; Terence Chi Chun Tam
• Keywords: Adjuvant Therapy; Recursive partitioning

Although stage I non-small cell lung carcinoma (NSCLC) typically carries a good prognosis following complete resection, early disease recurrence can occur. An accurate survival prediction model would help refine follow-up strategy and personalize future adjuvant therapy. We developed post-operative based on readily available clinical information for patients with adenocarcinoma.We retrospectively studied the disease-free (DFS) of 408 pathologically confirmed low-risk adenocarcinoma who underwent curative resection from 2013 to 2017. A tree-based method was employed partition cohort into subgroups distinct DFS outcome stepwise risk ratio. These covariates were included in multivariate analysis build scoring system predict recurrence. The subsequently validated using 2011-2012 cohort.Non-smoker status, IA disease, epidermal-growth factor receptor mutants female gender associated better DFS. Multivariate identified smoking as factors necessary yielded 3 groups [99.4 (95% CI 78.3-125.3), 62.9 48.2-82.0), 33.7 24.6-46.1) months, p < 0.005]. External validation an area under curve by receiver operating characteristic 0.863 0.755-0.972).The could categorize information, may