Lung cancer remains one of the leading causes of cancer-related mortality worldwide and is strongly associated with tobacco smoke exposure. In recent years, electronic cigarettes have gained popularity as seemingly safer alternatives to conventional cigarettes; however, their impact on tumor biology remains controversial. A central process in lung cancer progression is the epithelial–mesenchymal transition (EMT), which promotes cellular invasion, migration, and therapy resistance. This review summarizes current evidence on how nicotine, polycyclic aromatic hydrocarbons (PAHs), carbonyl compounds, and reactive oxygen species (ROS) modulate EMT through key signaling pathways, including PI3K/AKT, MAPK/ERK, Wnt/β-catenin, Notch, and HIF-1α. Moreover, it discusses the role of thermal processes during tobacco combustion and e-liquid heating in generating carcinogenic by-products. Emerging data indicate that both traditional and electronic cigarettes release bioactive agents capable of inducing EMT, thereby contributing to lung cancer pathogenesis and revealing potential therapeutic targets.

Background/Objectives: Drug repositioning has emerged as a promising strategy to address the innovation crisis in pharmaceutical development. While artificial intelligence enables efficient in silico hypothesis generation, clinical translation remains challenging. This study aims to evaluate the role of Real-World Evidence (RWE) in validating AI-generated drug-repositioning candidates. Methods: A comprehensive literature review was conducted in PubMed using a predefined search strategy integrating drug repositioning, artificial intelligence, and real-world data. After multi-stage screening, 22 original research articles were included for analysis. Results: Network-based algorithms and natural language processing dominated AI-driven hypothesis generation. Validation using Electronic Health Records and insurance databases enabled retrospective assessment of drug efficacy across large populations. Successful applications were identified in neurodegenerative, metabolic, infectious, autoimmune, and psychiatric diseases. Conclusions: The integration of AI-based analytics with RWE provides a promising framework for the preliminary verification of computational predictions, potentially informing the translational pathway toward clinical practice. However, the effectiveness of this approach remains dependent on data quality and the specific therapeutic context, requiring further standardization of clinical data.

Background: The neutrophil-to-lymphocyte ratio (NLR) and monocyte-to-lymphocyte ratio (MLR) reflect the balance between innate and adaptive immunity and may indicate systemic inflammation. Objectives: To evaluate longitudinal changes in NLR and MLR in MS patients during relapse compared with relapse-free controls. Methods: In this retrospective single-center observational study, patients with MS were followed for 2 years. Individuals with at least one relapse and complete blood count data at predefined time points were included. Controls without relapse were selected in a 2:1 ratio and matched for age, sex, disease duration, EDSS score, and disease-modifying therapy category. NLR and MLR were assessed 3 months before relapse (or index date), during relapse, and 3 months after. Results: The study included 34 patients with relapse and 68 controls. During relapse, patients showed higher neutrophil and monocyte counts, lower lymphocyte counts, and elevated NLR and MLR compared with controls (all p < 0.001). NLR increased from 2.75 pre-relapse to 3.62 during relapse, then decreased to 2.67 (p = 0.0002). MLR rose from 0.45 to 0.54 and declined to 0.40 (p = 0.002). No significant changes were observed in controls. Conclusions: NLR and MLR demonstrated dynamic changes during MS relapse. These non-specific indices may serve as exploratory, complementary markers of relapse-associated inflammation, but require validation in larger prospective studies including MRI correlates.