摘要
在已描述的7000多种罕见疾病中仅有5%找到了治疗方法。大数据时代,随着生物医学数据的不断增加,迫切需要高效快速的数据收集、分析和识别方法。以机器学习为着重点的人工智能应用为罕见病开辟了一条全新的途径,并广泛应用于诊断与治疗。人工智能已经向人们充分展示了其学习和分析来自不同来源的数据并做出可靠预测的能力。目前已有数量可观的人工智能技术应用于罕见疾病的案例,本文旨在总结罕见病中人工智能应用的研究进展。另外,还系统地总结了人工智能应用程序的局限性,并展望了人工智能在罕见病应用领域中的发展。
It is noteworthy that only 5% of more than 7000 described rare diseases are treated. In the era of big data, there is ever-increasing data for understanding biomedicine. The need for efficient and rapid data collection, analyses and characterization methods is pressing. Rare diseases can particularly benefit from artificial intelligence(AI) application. AI, with an emphasis on machine learning, creates a path for suchefforts and is being applied to diagnosis and treatment. AI has demonstrated its potential to learn and analyze data from different sources with results in prediction. Presently, there are AI-driven technologies applied for rare diseases and this review aims to summarize these advances. Moreover, this review scrutinizes the limitation and identifies the pitfalls of AI applications in the diagnosis and treatment of rare diseases.
作者
弓孟春
焦塬石
马武仁
刘鹏
金晔
胡继发
牛灵
史文钊
张抒扬
GONG Mengchun;JIAO Yuanshi;MA Wuren;LIU Peng;JIN Ye;HU Jifa;NIU Ling;SHI Wenzhao;ZHANG Shuyang(School of Health Management,Southern Medical University,Guangzhou 510515,China;Chinese Academy of Medical Sciences,Digital China Health Technologies Corporation,Beijing 100080,China;Peking Union Medical College Hospital,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China;The Central Hospital of Wuhan,Wuhan 430014,China;The People's Hospital of Xinjiang Uygur Autonomous Region,Urumqi 830011,China)
出处
《罕见病研究》
2022年第2期101-109,共9页
Journal of Rare Diseases
基金
国家重点研发计划(2020YFC2006400)。
关键词
人工智能
机器学习
罕见病
诊断
治疗
药物重定位
药物开发
artificial intelligence
machine learning
rare disease
diagnosis
treatment
drug repositioning
drug development