Answers are grounded in this paper and cite their sources.
• Advanced NSCLC remains incurable due to drug resistance mechanisms • Integration of AI into real-world algorithms may help clinical decision-making • Experts may facilitate translating AI output into actionable treatment decisions • Reactive and proactive strategies could benefit from AI to personalize therapies The increasing knowledge in the molecular pathophysiology of non-small-cell lung cancer (NSCLC) allowed early identification of druggable targets; however, the advanced disease remains incurable mainly due to drug resistance. Therefore, it is essential to explore new methodological approaches for pharmacological strategies based on longitudinal molecular and imaging monitoring of NSCLC evolution, which can support decision-making for personalized treatments in clinical practice and provide new insight for the design of innovative clinical trials. The advent of AI presents an extraordinary opportunity to develop algorithms capable of decoding the complex, multifaceted patterns of NSCLC progression. AI needs input information from biomarker analyses on liquid biopsies, radiomic data, actionable targets involved in cancer drug resistance, and clinically relevant information for choosing personalized next-line therapies, including existing drugs that could target previously unconsidered resistance pathways (drug repurposing), and selecting sequential or combinatorial therapeutic approaches as a fundamental part of precision medicine. This narrative review explores the opportunity of integrating AI-based multiparametric models into reactive and proactive algorithms to offer patients new therapeutic options for long-term quality-adjusted survival.
No takes yet. Share an insight, caveat, or question.
Fogli et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: