1.北京中医药大学中医学院 北京 100029
1.北京中医药大学东方医院
1.北京中医药大学东直门医院
薛哲,女,博士,讲师
#通信作者:陈家旭,男,博士,教授,博士生导师,主要研究方向:中医证候的生物学基础,E-mail:chenjiaxu@hotmail.com
收稿:2020-10-04,
纸质出版:2021-04-30
移动端阅览
薛哲, 赵宗耀, 陈家旭, 等. 以六种疾病为例研究基于统计注意力的神经网络模型在证名诊断中的应用[J]. 北京中医药大学学报, 2021,44(4):358-365.
Zhe Xue, Zongyao Zhao, Jiaxu Chen, et al. Applied research of SANN model in the diagnosis of traditional Chinese patterns with six diseases data as examples[J]. Journal of Beijing University of traditional Chinese Medicine, 2021, 44(4): 358-365.
薛哲, 赵宗耀, 陈家旭, 等. 以六种疾病为例研究基于统计注意力的神经网络模型在证名诊断中的应用[J]. 北京中医药大学学报, 2021,44(4):358-365. DOI: 10.3969/j.issn.1006-2157.2021.04.011.
Zhe Xue, Zongyao Zhao, Jiaxu Chen, et al. Applied research of SANN model in the diagnosis of traditional Chinese patterns with six diseases data as examples[J]. Journal of Beijing University of traditional Chinese Medicine, 2021, 44(4): 358-365. DOI: 10.3969/j.issn.1006-2157.2021.04.011.
目的
2
研究基于统计注意力的神经网络(SANN)模型在中医证名诊断中的适用性与先进性,探讨其生成的特征贡献度是否符合中医原理。
方法
2
选择记载于古今医案云平台及中医药杏林园数据库的高血脂、更年期综合征、冠心病、慢性胃炎、慢性肾炎、尿路感染、脂肪肝病案共1 110例。通过人工神经网络(ANN)、随机森林(RF)、支持向量机(SVC)、K-近邻(KNN)、SANN分别建立诊断模型,对比5种模型评价指标。评价指标包括Macro-F1、Macro-Precision、Macro-Accuracy、Macro-Recall。
结果
2
SANN在6种疾病中的Macro-F1平均值为0.78、Macro-Precision平均值为0.79、Macro-Accuracy平均值为0.79、Macro-Recall平均值为0.8,均优于其他4种基准模型,其参数可解释性与导出的特征对类支持度符合中医原理。
结论
2
SANN在中医证名诊断智能化、中医数据的特征筛选、疾病量表研制等任务中具有适用性与先进性,为相关工作提供了创新性的方法参考。
Objective
2
To study the applicability and strength of the statistical attention-based neural network (SANN) model in the diagnosis of TCM patterns
and to explore whether the generated feature contribution is aligned with TCM principles.
Methods
2
A total of 1
110 cases of hyperlipidemia
menopausal syndrome
coronary heart disease
chronic gastritis
chronic nephritis
urinary tract infection
and fatty liver recorded in the ancient and modern medical records cloud platform and the Chinese medicine Xinglinyuan database were selected. Diagnostic models were established through artificial neural network (ANN)
random forest (RF)
support vector machine (SVC)
K-nearest neighbor (KNN)
and statistical attention-based neural network model (SANN) respectively. Evaluation indicators include Macro-F1
Macro-Precision
Macro-Accuracy
and Macro-Recall.
Results
2
The statistical attention-based neural network model (SANN) in the 6 diseases has an average of Macro-F1 at 0.78
Macro-Precision at 0.79
Macro-Accuracy at 0.79
and Macro-Recall at 0.8
which were better than the other 4 benchmark models. The interpretability of its parameters and the support of derived features conformed to the principles of Chinese medicine.
Conclusion
2
The neural network model based on statistical attention (SANN) is applicable and advanced in undertaking tasks such as the intelligent diagnosis of TCM patterns
feature screening of TCM data
and the development of disease evaluation scales
thus providing an innovative methodological reference for related study.
石玉琳 , 胡晓娟 , 许家佗 . 中医病证智能化诊断与分类研究进展 [J]. 中国中西医结合杂志 , 2019 , 39 ( 6 ): 763 - 768 .
YL Shi , XJ Hu , JT Xu . Intelligent diagnosis and classification research development of Chinese medical syndrome typing [J]. Chinese Journal of Integrated Traditional and Western Medicine , 2019 , 39 ( 6 ): 763 - 768 .
赵宇平 , 李楠 , 闫朋宣 , 等 . 中医药人工智能现状研究及发展思考 [J]. 中国中西医结合杂志 , 2020 , 40 ( 6 ): 746 - 749 .
YP Zhao , N Li , PX Yan , et al . Research and development of artificial intelligence in traditional Chinese Medicine [J]. Chinese Journal of Integrated Traditional and Western Medicine , 2020 , 40 ( 6 ): 746 - 749 .
蒋寅 , 赵晨 , 张晓雨 , 等 . 人工智能时代的中医临床研究问题与对策 [J/OL]. 中国中西医结合杂志 : 1 - 4 [ 2020-09-30 ]. http://kns.cnki.net/kcms/detail/11.2787.R.20200302.1000.013.html http://kns.cnki.net/kcms/detail/11.2787.R.20200302.1000.013.html .
Y Jiang , C Zhao , XY Zhang , et al . Problems and solving strategies of traditional Chinese medicine clinical research in the artificial intelligence era [J/OL]. Chinese Journal of Integrated Traditional and Western Medicine : 1 - 4 [ 2020-09-30 ]. http://kns.cnki.net/kcms/detail/11.2787.R.20200302.1000.013.html http://kns.cnki.net/kcms/detail/11.2787.R.20200302.1000.013.html .
中华中医药学会内科分会 , 中国民族医药学会肺病分会 , 中华中医药学会肺系病分会 . 特发性肺纤维化中医证候诊断标准(2019版) [J]. 中医杂志 , 2020 , 61 ( 18 ): 1653 - 1656 .
Internal Medicine Branch of CACM , Pulmonary Disease Branch of CMAM , Pulmonary Disease Branch of CACM . Syndrome diagnostic criteria of idiopathic pulmonary fibrosis in traditional Chinese medicine (2019 ed.) [J]. Journal of Traditional Chinese Medicine , 2020 , 61 ( 18 ): 1653 - 1656 .
曹云 , 卢毅 , 陈建新 , 等 . 基于机器学习的胃食管反流病中医智能辨证模型的应用 [J]. 北京中医药大学学报 , 2019 , 42 ( 10 ): 869 - 874 .
Y Cao , Y Lu , JX Chen , et al . Establishment of TCM intelligent pattern identification model of gastroesophageal reflux disease based on machine learning [J]. Journal of Beijing University of Traditional Chinese Medicine , 2019 , 42 ( 10 ): 869 - 874 .
罗晓舟 , 温小鹏 , 何家扬 , 等 . 基于机器学习的卒中后抑郁影响因素分析 [J]. 中医杂志 , 2017 , 58 ( 17 ): 1478 - 1481 .
XZ Luo , XP Wen , JY He , et al . Analysis of the influencing factors of post-stroke depression:based on machine learning [J]. Journal of Traditional Chinese Medicine , 2017 , 58 ( 17 ): 1478 - 1481 .
王至婉 , 李建生 , 陈楚湘 , 等 . 基于贝叶斯网络构建慢性阻塞性肺疾病急性加重期痰热壅肺证症状与证候间关联模式 [J]. 中医杂志 , 2018 , 59 ( 3 ): 203 - 206 .
ZW Wang , JS Li , CX Chen , et al . Constructing symptom and syndrome association mode of acute exacerbation of chronic obstructive pulmonary disease with phlegm-heat congesting lung syndrome: based on Bayesian network [J]. Journal of Traditional Chinese Medicine , 2018 , 59 ( 3 ): 203 - 206 .
辛基梁 , 张佳 , 李绍滋 , 等 . 中医健康状态辨识中的多标记分类方法研究 [J]. 中华中医药杂志 , 2019 , 34 ( 9 ): 3952 - 3955 .
JL Xin , J Zhang , SZ Li , et al . Research on multi-label classification methods for the identification of health state in traditional Chinese medicine [J]. China Journal of Traditional Chinese Medicine and Pharmacy , 2019 , 34 ( 9 ): 3952 - 3955 .
张振 , 田雪飞 , 郜文辉 , 等 . 基于决策树及贝叶斯网络建立原发性肝癌肝郁脾虚证诊断模型研究 [J]. 中国中医药信息杂志 , 2020 , 27 ( 9 ): 115 - 120 .
Z Zhang , XF Tian , WH Gao , et al . Study on diagnosis model of liver stagnation and spleen deficiency syndrome of primary liver cancer based on decision tree and Bayesian network [J]. Chinese Journal of Information on Traditional Chinese Medicine , 2020 , 27 ( 9 ): 115 - 120 .
符宇 , 邵明义 , 赵瑞霞 , 等 . 基于中医证据的中医临床疗效评价方法探讨 [J]. 中医杂志 , 2020 , 61 ( 13 ): 1124 - 1129 .
Y Fu , MY Shao , RX Zhao , et al . Discussion on the evaluation methods of clinical therapeutic effects based on evidence in traditional Chinese medicine [J]. Journal of Traditional Chinese Medicine , 2020 , 61 ( 13 ): 1124 - 1129 .
刘蕾 , 郭淑贞 , 王伟 . 中医证候研究的现状及发展趋势 [J]. 中华中医药杂志 , 2008 , 23 ( 8 ): 661 - 663 .
L Liu , SZ Guo , W Wang . The present situation and development tendency of syndrome of traditional Chinese medicine [J]. China Journal of Traditional Chinese Medicine and Pharmacy , 2008 , 23 ( 8 ): 661 - 663 .
陈家旭 , 邹小娟 . 中医诊断学 [M]. 北京 : 人民卫生出版社 , 2016 : 1 - 3 .
JX Chen , XJ Zou . Diagnostics of Traditional Chinese Medicine [M]. Beijing : People’s Medical Publishing House , 2016 : 1 - 3 .
赵宗耀 , 陈家旭 . “三基辨证”体系的提出及其理论渊源 [J]. 中医杂志 , 2020 , 61 ( 8 ): 664 - 668 .
ZY Zhao , JX Chen . Establishment and theoretical origin of a “three-basis syndrome differentiation” system [J]. Journal of Traditional Chinese Medicine , 2020 , 61 ( 8 ): 664 - 668 .
赵宗耀 , 陈家旭 . 基于“三基辨证”的证名规范化 [J]. 中医杂志 , 2020 , 61 ( 23 ): 2039 - 2043 .
ZY Zhao , JX Chen . Standardization of syndrome based on the “three-basis syndrome differentiation” [J]. Journal of Traditional Chinese Medicine , 2020 , 61 ( 23 ): 2039 - 2043 .
0
浏览量
41
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621