Background: Artificial intelligence (AI) has emerged as a transformative tool in healthcare, particularly in drug and biomarker discovery, where it can enhance precision, streamline discovery processes, and optimize treatment strategies. Despite its potential, the application of AI in glioblastoma (GB) research, especially in identifying novel biomarkers and therapeutic targets, remains underexplored. The aim of this review is to map the existing literature on AI-driven approaches for biomarker and drug discovery in GB, highlighting key trends and gaps in current research.Design: Following a PRISMA methodology, this scoping review examined studies published between 2012 and 2024. Searches were conducted across multiple databases, including MEDLINE (PubMed), Scopus, the Cochrane Library, and Web of Science (WOS). Eligible studies were screened, and relevant data were extracted and synthesized to provide a comprehensive overview of AI applications in GB research.Results: A total of 224 records were identified, including 210 from PubMed, 104 from Scopus, 4 from WOS, and 6 from the Cochrane Library. After screening and applying eligibility criteria, 33 studies were included in the final review. These studies showcased diverse AI methodologies applied to both drug discovery and biomarker identification, focusing on various aspects of GB biology and treatment.Conclusions: This scoping review reveals an increasing interest in AI-driven strategies for biomarker and drug discovery in GB, with promising initial results. However, further large-scale, rigorous studies are needed to validate real-world applications of AI and the development of standardized protocols to enhance reproducibility and clinical translation.
背景：人工智能已成为医疗健康领域的变革性工具，尤其在药物与生物标志物发现方面，能够提升精准度、优化发现流程并改进治疗策略。尽管人工智能潜力巨大，其在胶质母细胞瘤研究中的应用，特别是在识别新型生物标志物和治疗靶点方面，仍处于探索不足的状态。本综述旨在系统梳理现有关于人工智能驱动胶质母细胞瘤生物标志物与药物发现的研究文献，并指出当前研究的主要趋势与空白。 设计：本范围综述遵循PRISMA方法，纳入了2012年至2024年间发表的研究。检索覆盖多个数据库，包括MEDLINE（PubMed）、Scopus、Cochrane图书馆和Web of Science。通过筛选符合条件的研究，提取并综合相关数据，以全面概述人工智能在胶质母细胞瘤研究中的应用现状。 结果：共识别出224条记录，其中PubMed 210条、Scopus 104条、Web of Science 4条、Cochrane图书馆6条。经筛选并应用纳入标准后，最终纳入33项研究。这些研究展示了应用于药物发现和生物标志物识别的多种人工智能方法，聚焦于胶质母细胞瘤生物学和治疗的各个方面。 结论：本范围综述显示，人工智能驱动的胶质母细胞瘤生物标志物与药物发现策略正受到日益关注，并已取得初步积极成果。然而，仍需开展进一步大规模、严谨的研究，以验证人工智能的实际应用价值，并建立标准化方案来提升结果的可重复性及临床转化潜力。
肿瘤(癌症)患者之家