Ralph Saber

Background/Objectives: Immune checkpoint inhibitors (ICIs) have revolutionized the treatment landscape of advanced non-small cell lung cancer (NSCLC), yet 70% of patients experience disease progression, underscoring the critical need for predictive biomarkers. Programmed death-ligand 1 (PD-L1) expression remains the most adopted biomarker for ICIs. With the emergence of machine learning, the development of radiomics algorithms based on CT scan images has demonstrated potential as a novel addition to the biomarker landscape in oncology. In this study, we aimed to develop a non-invasive surrogate of PD-L1 expression (rad-PDL1) derived from computed tomography (CT) scan imaging and compare its predictive value to pathological assessments. Furthermore, we evaluated its generalizability across advanced and limited-stage NSCLC. Methods: Radiomics features extracted from pretreatment CT were analyzed using a self-training pipeline that incorporated the feature tokenizer Transformer model to classify tumors as high vs. low PD-L1 expression. We included 482 advanced NSCLC patients treated with ICIs across three medical centers who were divided into training and hold-out validation sets. The algorithm was then further validated in an independent cohort of 51 patients with limited NSCLC treated with neoadjuvant ICI and chemotherapy. Results: Our pipeline demonstrated strong predictive performance in primary and independent validation (AUC = 0.75 and 0.68, accuracy = 0.73 and 0.69, respectively), highlighting its generalizability and adaptability to various disease stages. Kaplan–Meier curves revealed a longer progression-free survival for patients in the high rad-PDL1. Conclusions: These results demonstrate the feasibility of a CT-based radiomic surrogate of PD-L1 expression, showing partial generalization to an independent neoadjuvant cohort, while highlighting the need for larger prospective multi-site validation before clinical implementation.

Background and Objectives: Drug permeability across the blood–brain barrier (BBB) remains a significant challenge in drug discovery, prompting extensive efforts to develop in silico predictive models. Most existing models rely on molecular descriptors to characterize drug properties. Feature selection algorithms play a crucial role in identifying the most relevant descriptors, thereby enhancing prediction accuracy. Methods: In this study, we compare the effectiveness of sequential feature selection (SFS) and genetic algorithms (GAs) in optimizing descriptor selection for BBB permeability prediction. Five different classifiers were initially trained on a dataset using eight molecular descriptors. Each classifier was then retrained using the descriptors selected by SFS and GA separately. Results: The results indicate that the GA method outperformed SFS, leading to a higher prediction accuracy (96.23%) when combined with a support vector machine (SVM) classifier. Furthermore, the GA approach, utilizing a fitness function based on classifier performance, consistently improved prediction accuracy across all tested models, whereas SFS showed lower effectiveness. Additionally, this study highlights the critical role of polar surface area in determining drug permeability across the BBB. Conclusions: These findings suggest that genetic algorithms provide a more robust approach than sequential feature selection for identifying key molecular descriptors in BBB permeability prediction.