1.中国中医科学院中医临床基础医学研究所,北京市东城区东直门内南小街16号,100700
2.北京中医药大学
3.北京交通大学计算机与信息技术学院
4.首都医科大学附属北京中医医院/北京市中医药研究所北京中医药循证医学中心
5.四川大学华西医院
liuqingquan2003@126.com
收稿:2023-05-06,
修回:2023-08-28,
纸质出版:2023-11-02
移动端阅览
赵国桢,郭诗琪,庞华鑫等.基于中医临床诊疗数据的真实世界及人工智能研究思路与挑战[J].中医杂志,2023,64(21):2170-2175.
ZHAO Guozhen,GUO Shiqi,PANG Huaxin,et al.Research Ideas and Challenge of Real World Study and Artificial Intelligence Based On Clinical Diagnosis and Treatment Data of Traditional Chinese Medicine[J].Journal of Traditional Chinese Medicine,2023,64(21):2170-2175.
赵国桢,郭诗琪,庞华鑫等.基于中医临床诊疗数据的真实世界及人工智能研究思路与挑战[J].中医杂志,2023,64(21):2170-2175. DOI: 10.13288/j.11-2166/r.2023.21.002.
ZHAO Guozhen,GUO Shiqi,PANG Huaxin,et al.Research Ideas and Challenge of Real World Study and Artificial Intelligence Based On Clinical Diagnosis and Treatment Data of Traditional Chinese Medicine[J].Journal of Traditional Chinese Medicine,2023,64(21):2170-2175. DOI: 10.13288/j.11-2166/r.2023.21.002.
随着真实世界研究方法学的进步和人工智能技术的成熟,以中医诊疗数据为基础,开展“定量”研究指导临床实践的方法正在逐步形成,但在研究总体设计、临床转化等方面仍需进一步完善。提出基于中医临床诊疗数据的真实世界及人工智能研究的总体设计思路及应用方法,包括5个步骤:建设高质量大样本的具有中医特色的研究型数据库、核心处方的挖掘及分类、队列研究评价核心处方疗效、病例对照研究明确优势人群、建立预测模型实现精准医疗。此外,研究人员还需要建立标准化的中医变量采集和数据处理体系,优化混杂因素的确定及测量方法,进一步完善及推广方法学,加强跨学科人才的培养。真实世界研究与人工智能研究的研究基础相似,临床应用互补,未来将是二者的融合。
With the continuous progress of research methodology in the real world and the growing maturity of artificial intelligence technology, a method for conducting “quantitative” research to guide clinical practice based on traditional Chinese medicine (TCM) diagnosis and treatment data was gradually developed. However, there is still a need for further improvements in the overall design of studies and the transformation of findings into clinical practice. Based on this, we put forward a comprehensive overall design concept and application approach for real-world study and artificial intelligence research based on clinical diagnosis and treatment data of TCM. This approach consists of five steps: Constructing a research-based database with a large sample size and high data quality; Mining and classification of core prescriptions; Conducting cohort studies to evaluate the effectiveness of core prescriptions; Utilizing case-control studies to clarify the dominant population; Establishing predictive models to achieve precision medicine. Additionally, it is imperative for researchers to establish a standardized system for collecting TCM variables and processing data, optimize the determination and measurement methods of confounding factors, further improve and promote methodologies, and strengthen the training of interdisciplinary talents. By following this research method, we anticipate that the clinical translation of research findings will be facilitated, leading to advancements in TCM precision medicine. Real-world study and artificial intelligence research share similar research foundations, and clinical applications complement each other. In the future, the two will merge together.
SUN X , TAN J , TANG L , et al . Real world evidence: experience and lessons from China [J]. BMJ , 2018 , 360 : j5262 . doi: 10.1136/bmj.j5262 http://dx.doi.org/10.1136/bmj.j5262 .
刘保延 . 真实世界的中医临床科研范式 [J]. 中医杂志 , 2013 , 54 ( 6 ): 451 - 455 .
LEE P , BUBECK S , PETRO J . Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine [J]. N Engl J Med , 2023 , 388 ( 13 ): 1233 - 1239 .
谷晓红 , 于河 , 卜德超 , 等 . 应用混合方法构建名老中医道术传承研究与推广范式 [J]. 中医杂志 , 2022 , 63 ( 15 ): 1406 - 1411 .
吴阶平医学基金会中国胸部肿瘤研究写作组 . 真实世界研究指南(2018年版) [EB/OL]. ( 2018-09-20 )[ 2023-04-05 ]. http://www.xayxfw.com/uploadfiles/2018/09/201809071442494249.pdf http://www.xayxfw.com/uploadfiles/2018/09/201809071442494249.pdf .
TIAN J , YAN S , WANG H , et al . Hanshiyi Formula, a medicine for Sars-CoV2 infection in China, reduced the proportion of mild and moderate COVID-19 patients turning to severe status: a cohort study [J]. Pharmacol Res , 2020 , 161 : 105127 . doi: 10.1016/j.phrs.2020.105127 http://dx.doi.org/10.1016/j.phrs.2020.105127 .
MOONS KG , ROYSTON P , VERGOUWE Y , et al . Prognosis and prognostic research: what, why, and how? [J]. BMJ , 2009 , 338 : b375 . doi: 10.1136/bmj.b375 http://dx.doi.org/10.1136/bmj.b375 .
梁洁 , 和思敏 , 陈淑婷 , 等 . 纵向研究中控制时依混杂的G方法 [J]. 中华流行病学杂志 , 2021 , 42 ( 10 ): 1871 - 1875 .
田之魁 , 张鑫海 , 孙璇 , 等 . 基于舌象的糖尿病足风险预测模型的构建 [J]. 中医杂志 , 2022 , 63 ( 19 ): 1840 - 1846 .
高群 , 张华军 , 张立晶 , 等 . 基于十二井穴生物电阻抗值构建冠心病患者抗血栓治疗出血风险预测模型 [J]. 中医杂志 , 2023 , 64 ( 7 ): 710 - 715 .
HUANG L , HAN R , AI T , et al . Serial quantitative chest CT assessment of COVID-19: a deep learning approach [J]. Radiol Cardiothorac Imaging , 2020 , 2 ( 2 ): e200075 .
赵国桢 , 郭诗琪 , 庞华鑫 , 等 . 人工智能技术在辅助中医诊疗及诊疗标准化中的应用 [J]. 中医杂志 , 2022 , 63 ( 24 ): 2306 - 2310 .
王阶 , 李谦一 , 张振鹏 , 等 . 基于循环神经网络的智能中医开方模型训练方法及装置 : CN112466436A [P]. 2021-03-09 .
张姝艳 , 皮婷婷 . 医疗领域中人工智能应用的可解释性困境与治理 [J]. 医学与哲学 , 2023 , 44 ( 3 ): 25 - 29, 35 .
国家药品监督管理局药品审评中心 . 国家药监局药审中心关于发布《用于产生真实世界证据的真实世界数据指导原则(试行)》的通告 [EB/OL]. ( 2020-04-15 )[ 2023-04-15 ]. https://www.cde.org.cn/zdyz/domesticinfopage?zdyzIdCODE=7d2e46cea0e459358257760383526e9d https://www.cde.org.cn/zdyz/domesticinfopage?zdyzIdCODE=7d2e46cea0e459358257760383526e9d .
田贵华 , 商洪才 . 智能中医学概论 [M]. 北京 : 人民卫生出版社 , 2021 : 132 - 133 .
PAJOUHESHNIA R , GROENWOLD RHH , PEELEN LM , et al . When and how to use data from randomised trials to develop or validate prognostic models [J]. BMJ , 2019 , 365 : I2154 . doi: 10.1136/bmj. l2154 http://dx.doi.org/10.1136/bmj.l2154 .
王树月 , 陈明珠 , 张兴会 , 等 . 药物流行病学研究混杂因素的控制 [J]. 药物流行病学杂志 , 2021 , 30 ( 8 ): 503 - 507 .
RILEY RD , ENSOR J , SNELL KIE , et al . Calculating the sample size required for developing a clinical prediction model [J]. BMJ , 2020 , 368 : m441 . doi: 10.1136/bmj.m441 http://dx.doi.org/10.1136/bmj.m441 .
赵国桢 , 卢海天 , 闫世艳 , 等 . 基于相似度匹配算法对真实世界草药处方分类的探索及实例解读 [J]. 中国中药杂志 , 2023 , 48 ( 4 ): 1132 - 1136 .
范红敏 . 队列研究在医学科研中的理论、设计和实践 [J]. 北京医学 , 2020 , 42 ( 8 ): 756 - 761 .
ZHANG Y , LIU Y , LI M , et al . Timely treatment and higher compliance to traditional Chinese medicine: new influencing factors for reducing severe COVID-19 based on retrospective cohorts in 2020 and 2021 [J]. Pharmacol Res , 2022 , 178 : 106174 . doi: 10.1016/j.phrs. 2022. 106174 http://dx.doi.org/10.1016/j.phrs.2022.106174 .
JAGER KJ , ZOCCALI C , MACLEOD A , et al . Confounding: what it is and how to deal with it [J]. Kidney Int , 2008 , 73 ( 3 ): 256 - 260 .
杨宇飞 . 晚期消化道恶性肿瘤中医优势人群特征及诊疗路径研究 [J]. 北京中医药大学学报 , 2022 , 45 ( 5 ): 433 - 437 .
孙凌云 , 张达 , 郝洁 , 等 . 晚期结直肠癌患者中医证型、中医体质与生存结局相关性分析 [J]. 中国中西医结合杂志 , 2017 , 37 ( 9 ): 1059 - 1062 .
VAN GELOVEN N , SWANSON SA , RAMSPEK CL , et al . Prediction meets causal inference: the role of treatment in clinical prediction models [J]. Eur J Epidemiol , 2020 , 35 ( 7 ): 619 - 630 .
HERNÁN MA , ROBINS JM . Using big data to emulate a target trial when a randomized trial is not available [J]. Am J Epidemiol , 2016 , 183 ( 8 ): 758 - 764 .
YUAN L , YANG L , ZHANG S , et al . Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study [J]. E Clinical Medicine , 2023 , 57 : 101834 . doi: 10.1016/j.eclinm.2023.101834 http://dx.doi.org/10.1016/j.eclinm.2023.101834 .
WANG Y , XU J , ZHANG J , et al . SIAP: an intelligent algorithm for multiple prescription pattern recognition based on weighted similarity distances [J]. BMC Med Inform Decis Mak , 2023 , 23 ( 1 ): 79 .
吴涛涛 , 王琦 , 李岩 , 等 . 基于体病相关探讨临床预测模型的构建 [J]. 中医杂志 , 2022 , 63 ( 16 ): 1507 - 1510,1531 .
刘颖 , 刘旭 , 汪颖 , 等 . 《因果推断研究中混杂因素控制与结果报告指南》解读 [J]. 中华危重病急救医学 , 2021 , 33 ( 1 ): 113 - 116 .
落楠 . 探寻中医药疗效评价新范式 [N]. 中国医药报 , 2022-12-14 (004).
FENG L , HUANG ZH , ZHONG YM , et al . Research and application of tongue and face diagnosis based on deep learning [J]. Digit Health , 2022 , 8 : 205520 76221124436 . doi: 10.1177/20552076221124436 http://dx.doi.org/10.1177/20552076221124436 .
张婷婷 , 王亚强 , 温川飙 , 等 . 论智能中医辨证可解释研究的挑战和研究思路 [J]. 中医杂志 , 2022 , 63 ( 6 ): 506 - 510 .
周明瀚 , 刘旺华 , 李花 , 等 . 原发性高血压阴虚阳亢证舌象客观化研究 [J]. 中华中医药杂志 , 2022 , 37 ( 6 ): 3401 - 3404 .
陈清光 , 蔡梦洁 , 袁培琼 , 等 . 不同糖代谢人群的舌象客观化特征研究 [J]. 辽宁中医杂志 , 2021 , 48 ( 3 ): 88 - 91 .
关茜 , 杨帅 , 郭元成 , 等 . 阴虚、阳虚体质人群的舌诊图像特征分析 [J]. 中华中医药杂志 , 2021 , 36 ( 8 ): 4860 - 4862 .
崔骥 , 费兆馥 , 张志枫 , 等 . 平、滑、弦脉的脉图分类参数范围研究 [J]. 上海中医药杂志 , 2016 , 50 ( 12 ): 15 - 17 .
黄丽红 , 魏永越 , 陈峰 . 如何控制观察性疗效比较研究中的混杂因素:(一)已测量混杂因素的统计学分析方法 [J]. 中华流行病学杂志 , 2019 , 40 ( 10 ): 1304 - 1309 .
洪翔 , 尹洁晨 , 王蓓 . “探针变量”:观察性研究中混杂因素识别的工具 [J]. 中华流行病学杂志 , 2021 , 42 ( 4 ): 735 - 739 .
VANDER-WEELE TJ , DING P . Sensitivity analysis in observational research: introducing the E-Value [J]. Ann Intern Med , 2017 , 167 ( 4 ): 268 - 274 .
0
浏览量
6
下载量
17
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010102007558号