Most recent treatment options such as driver mutation targeting therapy and immune checkpoint inhibitors (ICIs) have changed the medical treatment strategies for NSCLC (1). ICI-based immunotherapy has significantly enhanced survival outcomes. Predictive biomarkers such as programmed cell death protein-1 (PD-1) and its ligand, programmed cell death protein-1 ligand (PD-L1), have been widely utilized in clinical trials to guide ICI-based treatment strategies (2,3). However, the elevated treatment failure rates and increased costs, and related complications highlight the need for improved patient selection methods for this treatment....

Methodology: Data Collection: The study involved 228 lung cancer patients, with tumor segmentation and feature extraction performed on their pre-biopsy CT images (figure 1-3). Preprocessing: To address interscanner variability, ComBat analysis was used. To ensure data completeness, missing values were imputed using the mean strategy. Feature Selection: The initial number of features was reduced from 230 to 162 by removing features with more than 50% missing values. To select the most critical features and improve model training, the dataset was refined by Iterative Feature Elimination...

The HRFC model achieved the highest performance, with an F1 score of 86.96%, significantly outperforming Random Forest (F1 score: 77.58 %) and XGBoost (F1 score: 80.15 %). The F1 score, a measure of a model's accuracy, is particularly important in our study as it balances precision and recall, providing a comprehensive and robust evaluation of the model's performance, and instilling confidence in its accuracy (figure-4).

Clinical Implications and Future DirectionsThe ability to predict PD-L1 expression non-invasively using CT-based radiomics has significant clinical implications. Currently, PD-L1 assessment requires invasive procedures such as biopsy or surgical resection, followed by immunohistochemical staining. These methods are not only resource-intensive but also carry risks of complications and sampling errors. Our model offers a promising alternative, enabling clinicians to identify patients likely to benefit from immune checkpoint inhibitors (ICIs) without the need for invasive procedures. This is particularly relevant for patients with advanced disease or those...

I. Kızıldağ Yırgın: Nothing to disclose M. Durmaz: Nothing to disclose M. Emec: Nothing to disclose G. Kaval: Nothing to disclose I. Bunul: Nothing to disclose A. Ibis: Nothing to disclose Ş. Karaman: Nothing to disclose N. Dagoglu Sakin: Nothing to disclose S. M. Ertürk: Nothing to disclose

1- A. Rittmeyer, F. Barlesi, D. Waterkamp, et al., Atezolizumab versus docetaxel in patients with previously treated non-small-cell lung cancer (OAK): a phase 3, openlabel, multicentre randomised controlled trial, Lancet 389 (10066) (2017) 255–265.2- A. Tunger, M. Kießler, R. Wehner, et al., Immune monitoring of cancer patients prior to and during CTLA-4 or PD-1/PD-L1 inhibitor treatment, Biomedicines 6 (1) (2018) 26.3- D.S. Chen, B.A. Irving, F.S. Hodi, Molecular pathways: next-generation immunotherapy–inhibiting programmed death-ligand 1 and programmed death-1, Clin. Cancer Res 18 (24) (2012) 6580–65874- D.B....