Abstract Introduction In advanced Non-Small Cell Lung Cancer (aNSCLC), Programmed Death Ligand 1 (PD-L1) remains the only used biomarker to candidate patients (pts) to immunotherapy (IO) even if its predictive accuracy is not satisfactory. Indeed, given the complex dynamics underlying the cross-talk between the tumor and its microenvironment, it is unlikely that a single biomarker could be able to profile prediction with high precision. Artificial Intelligence (AI) and machine learning (ML) are techniques able to analyze and interpret big data, which cope with this complexity. The present study aims at using AI tools to improve response and efficacy prediction in aNSCLC pts treated with IO. Methods A classification task to determine if a pt is likely to benefit from IO was formulated using complete clinical data, PD-L1, histology, molecular data, and the blood microRNA signature classifier (MSC), which include 24 different microRNAs. Pts were divided into responders (R), who obtained a partial response or stable disease as best response, and non-R, who experienced progressive disease. A forward feature selection technique based on the Akaike Information Criterion was used to extract a specific subset of the pts data, being the most informative ones for the task. To develop the final predictive model, different ML methods have been tested: K-nearest neighbors, Logistic Regression, Kernel Support Vector Machines, Feedforward Neural Network, and Random Forest. Results Of 164 enrolled pts, 73 (44.5%) were R and 91 (55.5%) non-R. At data cut-off (Nov 2020), median Overall Survival (mOS) was 10.1 (95%IC 7.0 - 13.2) months (m). mOS for R pts was 38.5 m (95%IC 23.9 - 53.1) vs 3.8 m (95%IC 2.8 - 4.7) of non-R, p<0.001. Overall, the best model was the Logistic Regression and included 5 features (3 clinical, 1 tissue and 1 blood features): ECOG performance status, IO-line of therapy, the neutrophil-to-lymphocyte ratio (NLR), the MSC test and PD-L1 with the following corresponding parameters w= (0.692, 0.718, 1.058, 0.566, -0.471), respectively. The intercept of the model is w_0 = 0.467, and the model achieves a 75% accuracy, computed using a leave-one-out approach. PD-L1 alone has an accuracy of 65%. We also evaluated the accuracy of the models excluding PD-L1 (74% accuracy), MSC (73% accuracy), and excluding both PD-L1 and MSC considering only clinical features (71% accuracy). Conclusions The results suggest that the data integration provided by AI techniques is a powerful tool to improve personalized selection of pts candidates to IO. In particular, the model shows that higher ECOG, NLR value, IO-line, and MSC test level correlate negatively while higher PD-L1 correlates positively with the response. The model confirms PD-L1 and MSC as relevant biomarkers to improve the accuracy of pts response. Considering the difference in survival among R and non-R groups, these results suggest that the model can also be used to indirectly predict OS. Citation Format: Arsela Prelaj, Mattia Boeri, Alessandro Robuschi, Claudia Proto, Giuseppe Lo Russo, Roberto Ferrara, Giulia Galli, Alessandro De Toma, Marta Brambilla, Mario Occhipinti, Sara Manglaviti, Alice Labianca, Teresa Beninato, Marta Bini, Mavis Mensah, Monica Ganzinelli, Nicoletta Zilembo, Filippo de Braud, Gabriella Sozzi, Marcello Restelli, Alessandra Pedrocchi, Marina Chiara Garassino, Francesco Trovo. Artificial intelligence to improve selection for NSCLC patients treated with immunotherapy [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-065.