数智化技术在溶酶体贮积病辅助诊断中的应用现状  

The Application Status and Trends of Data-Intelligence Technology in the Diagnosis of Lysosomal Storage Diseases

作　　者：杜欣羽 王胜锋[1,2,3] 谢静 郭健[5] 张抒扬 DU Xinyu;WANG Shengfeng;XIE Jing;GUO Jian;ZHANG Shuyang(School of Public Health,Peking University,Beijing 100191,China;Key Laboratory of Epidemiology of Major Diseases(Peking University),Ministry of Education,Peking University,Beijing 100191,China;Institute for Artificial Intelligence,Peking University,Beijing 100871,China;Department of Rare Diseases,Peking Union Medical College Hospital,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China;State Key Laboratory of Complex Severe and Rare Diseases,Peking Union Medical College Hospital,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China;Department of Cardiology,Peking Union Medical College Hospital,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China)

机构地区：[1]北京大学公共卫生学院,北京100191 [2]北京大学重大疾病流行病学教育部重点实验室(北京大学),北京100191 [3]北京大学人工智能研究院,北京100871 [4]中国医学科学院北京协和医院罕见病医学科,北京100730 [5]中国医学科学院北京协和医院疑难重症及罕见病全国重点实验室,北京100730 [6]中国医学科学院北京协和医院心内科,北京100730

出　　处：《罕见病研究》2025年第1期112-121,共10页Journal of Rare Diseases

基　　金：国家重点研发计划(2022YFC2703100);国家自然科学基金(72342015)。

摘　　要：目的系统梳理数智化技术在溶酶体贮积病辅助诊断中的应用现状,探讨面临的机遇和挑战,以及未来发展趋势,以期为数智化驱动辅助诊断技术的发展提供参考和建议。方法通过检索PubMed、Web of Science、Embase、中国知网、万方数据知识服务平台、维普中文科技期刊数据库等中英文数据库,纳入关于数智化技术在溶酶体贮积病诊断中应用的研究,定性分析其方法和结果,并根据类别归纳总结数智化技术在溶酶体贮积病辅助诊断中的应用现状,以及存在的不足和挑战。结果数智化技术在溶酶体贮积病的早期筛查和诊断中具有巨大潜力,尤其是大数据存储及管理技术、大数据挖掘及分析技术、机器学习、自然语言处理和计算机视觉等数智化技术,可以识别潜在患者、发现新的生物标志物、识别并定量分析溶酶体贮积病症状、探索基因与溶酶体贮积病之间的关系等,提高诊断效率和准确性。结论数智化技术能够提高早期诊断的准确性,在溶酶体贮积病的诊断研究中具有广阔的应用前景。未来应在DI-HEALTH理论框架指导下,构建全方位、多层次、立体化的溶酶体贮积病辅助诊断体系和技术。Objective To summarize the applications of data-intelligence technology in diagnosing lysosomal storage disease(LSD),analyze their opportunities and challenges in clinical practice as well as their development trends,and provide insights and recommendations for advancing digitally driven auxiliary diagnostic technologies.Methods A comprehensive literature search was conducted across databases including PubMed,Web of Science,Embase,CNKI,Wanfang Database,and VIP.The studies focusing on the application of digital-intelligence technologies in LSD diagnosis were included.A qualitative analysis was performed,categorizing and summarizing research based on the types of digital-intelligence technologies employed,and exploring future development trends.Results The analysis revealed that digital-intelligence technologies,particularly in areas such as big data storage and management,data mining and analytics,machine learning,natural language processing,and computer vision,held significant potential for early screening and diagnosis of LSD.These technologies facilitated the identification of potential patients,discovery of new biomarkers,quantitative analysis of symptoms,and elucidation of gene-disease relationships,ultimately enhancing diagnostic efficiency and accuracy.Conclusions Digital-intelli-gence technologies present promising prospects for advancing LSD diagnostic research and improving diagnostic precision.Future efforts should focus on developing a comprehensive,multidimensional diagnosis system and diagnostic technologies under the guidance of the DI-HEALTH theoretical framework,in the hope of paving the way for further development of digitally assisted diagnostic solutions.

关 键 词：溶酶体贮积病 罕见病 数智化技术 诊断 

分 类 号：R44[医药卫生—诊断学] TP39[医药卫生—临床医学]