Gupta Divyanshi, Wal Pranay, Wal Ankita, K R Sribhavani, Kumar Mudit, Panda Krishna Chandra, Sharma Mukesh Chandra
PSIT-Pranveer Singh Institute of Technology, Pharmacy NH19 Kanpur Agra highway, NH19 Bhauti Kanpur, UP, India.
Department of Pharmacology, Indrayani Vidya Mandir's Krishnarao Bhegade Institute of Pharmaceutical Education and Research, Talegaon Dabhade, Pune District, Maharashtra, India.
Curr Drug Discov Technol. 2024 Oct 28. doi: 10.2174/0115701638314252241016165345.
Artificial intelligence (AI) is one of the fastest-growing fields in various industries, including engineering, architecture, medical and clinical research, aerospace, and others. AI, which is a combination of machine learning (ML), deep learning (DL), and human intelligence (HI), is revolutionizing drug discovery and development by making it more cost-effective and efficient. It is also being used in fields such as medicinal chemistry, molecular and cell biology, pharmacology, pharmacokinetics, formulation development, and toxicology. AI plays a crucial role in clinical testing by enhancing patient stratification, patient sample evaluation, and trial design, assisting in the identification of biomarkers, determining efficacy criteria, dose selection, trial length, and target patient population selection. The primary objective of this study is to emphasize the importance of AI in clinical trials and drug development, while also exploring the existing challenges and potential advancements in AI within the healthcare industry. A comprehensive literature review was conducted, covering the period from 1998 to 2023. The Science Direct, PubMed, and Google Scholar databases were searched for relevant information. A variety of publications, including Research Gate, Nature, MDPI, and Springer Link, provided pertinent data. This study aimed to gain a deeper understanding of the use of AI in clinical research and drug development, as well as its potential and limitations. We also discuss the benefits and main data limitations of the traditional trial and drug development approach. AI approaches are currently being used to overcome research obstacles and eliminate conceptual or methodological limitations. After discussing possible obstacles and coping mechanisms, we provide several recommendations to help individuals understand the challenges and difficulties associated with clinical research and drug development. It is essential for pharmaceutical companies to have a cutting-edge AI strategy if AI is to become a routine tool for clinical research and drug development.
人工智能（AI）是包括工程、建筑、医学与临床研究、航空航天等在内的各个行业中发展最快的领域之一。人工智能是机器学习（ML）、深度学习（DL）和人类智能（HI）的结合，它正在通过提高成本效益和效率来彻底改变药物发现与开发。它还被应用于药物化学、分子与细胞生物学、药理学、药代动力学、制剂开发和毒理学等领域。人工智能在临床试验中发挥着关键作用，可加强患者分层、患者样本评估和试验设计，协助识别生物标志物、确定疗效标准、剂量选择、试验时长以及目标患者群体选择。本研究的主要目的是强调人工智能在临床试验和药物开发中的重要性，同时探讨医疗行业中人工智能现有的挑战和潜在进展。我们进行了一项全面的文献综述，涵盖1998年至2023年期间。在科学Direct、PubMed和谷歌学术数据库中搜索了相关信息。包括Research Gate、《自然》《MDPI》和施普林格链接在内的各种出版物提供了相关数据。本研究旨在更深入地了解人工智能在临床研究和药物开发中的应用及其潜力和局限性。我们还讨论了传统试验和药物开发方法的益处和主要数据局限性。目前正在使用人工智能方法来克服研究障碍并消除概念或方法上的局限性。在讨论了可能的障碍和应对机制后，我们提供了一些建议，以帮助人们理解与临床研究和药物开发相关的挑战和困难。如果人工智能要成为临床研究和药物开发的常规工具，制药公司拥有前沿的人工智能战略至关重要。
