Noninvasive prediction of EGFR 19Del and 21L858R subtypes in lung adenocarcinoma: a comparative study of logistic regression and decision tree models.

Objective: Despite the increasing interest in radiogenomic prediction, few studies have directly compared the performance of logistic regression and decision tree models in distinguishing epidermal growth factor receptor (EGFR) mutation subtypes. This study provides the first systematic comparison of the predictive performance of these two models in identifying exon 19 deletions (19Del) and exon 21 L858R point mutations (21L858R) in patients with lung adenocarcinoma. By leveraging imaging and clinical parameters, we aimed to address a critical gap in the literature by establishing an optimal prediction model and providing a noninvasive tool to support personalized treatment strategies for patients with unknown EGFR mutation status. Materials and methods: We retrospectively collected clinical and radiological data from 193 patients with histologically confirmed lung adenocarcinoma who were admitted to the Second Affiliated Hospital of Anhui Medical University between May 2018 and June 2024. Based on EGFR genotyping results, patients were stratified into two groups: the EGFR 19Del mutation group and the EGFR 21L858R mutation group. Comparative statistical analyses-including Student's Results: In the decision tree model, age and brain metastasis emerged as key decision nodes for differentiating 19Del and 21L858R mutations, with an AUC of 0.712 (95% CI: 0.639-0.785). In contrast, the logistic regression model identified age, pleural thickening, lymphadenopathy, and brain metastasis as independent predictors, achieving a higher AUC of 0.740 (95% CI: 0.671-0.810). The NRI and IDI values were 0.498 ( Conclusion: Both logistic regression and decision tree models demonstrated value in predicting EGFR 19Del and 21L858R mutations in lung adenocarcinoma, each offering distinct methodological advantages. The logistic regression model exhibited higher interpretability and statistical robustness, making it well-suited for clinical decision-making. Meanwhile, the decision tree model offered superior visual clarity and intuitive structure, which may enhance practical utility. A combined modeling approach that harnesses the strengths of both methods may provide a more accurate and comprehensive tool for early mutation identification and individualized treatment planning in patients with lung adenocarcinoma.