设为首页 |  加入收藏
首页首页 期刊简介 消息通知 编委会 电子期刊 投稿须知 广告合作 联系我们
中医信息系统对多囊卵巢综合征的分型研究

Classification of polycystic ovary syndrome by TCM information system

作者: 郭姗珊  陈厚儒  王书云  姚笛  吴胜男  朱光耀  俞而慨  颜建军 
单位:上海中医药大学附属龙华医院(上海 200032)<br />华东理工大学(上海 200237)<br />同济大学附属第一妇婴保健院(上海 200092)<br />通信作者:俞而慨,E-mail: yuerkai@hotmail.com;颜建军,E-mail: jjyan@ecust.edu.cn
关键词: 多囊卵巢综合征;中医信息系统;中医分型 
分类号:R318.04
出版年·卷·期(页码):2023·42·2(170-177)
摘要:

目的 通过评估全数字化分析中医基本症候的准确率,来验证全数字化分析中医基本证候与传统中医理论对于PCOS的分型有较高的准确率,从而可以客观地辅助临床对PCOS的诊疗。方法 收集PCOS病例,数字化记录症状、体征、辨证分型结果;并采用多标记学习法中的多标记k近邻方法(multi-label k-nearest neighbor, ML-kNN)、多标记贝叶斯学习算法(multi-label naive Bayesian, MLNB)法和深度森林算法 (multi-grained cascade forest, gcForest),通过计算平均准确率(average precision)、覆盖距离(coverage)、汉明损失(Hamming loss)、首标记错误和排序损失(ranking loss)5个数值来评估全数字化分析中医基本症候的准确率。结果 用ML-kNN、MLNB和gcForest将临床采集的数据建立数学模型,经过计算后得出158例PCOS确诊患者中医临床辨证分型为肾虚、脾虚、肝郁、痰湿和血瘀,其中肾虚无兼症的患者52例,肾虚和肝郁并存的患者48例,肾虚和痰湿并存的患者58例。用ML-kNN得出的证型准确率分别为:肾虚66.6%±10.2%、脾虚86.15%±2.9%、肝郁59.8%±9.7%、痰湿72.2%±11.6%,血瘀82.4%±4.6%。用MLNB得出的证型准确率分别为:肾虚65.5%±8.0%、脾虚85.6%±7.1%、肝郁74.2%±7.7%、痰湿70.5%±4.5%,血瘀81.8%±7.7%。用gcForest得出的证型准确率分别为:肾虚87.2%±5.0%、脾虚86.6%±4.8%、肝郁79.2%±6.5%、痰湿79.4%±6.8%,血瘀82.3%±5.9%。结论 用中医信息系统计算的PCOS的中医症候有肾虚、脾虚、肝郁、痰湿、血瘀,与曹玲仙教授对PCOS的分型有较高的准确率。说明全数字化采集PCOS患者证候信息并通过现代数据挖掘方法进行辨证论治,可以对PCOS中医临床证候进行有效规律总结,对临床诊疗有一定的帮助。

Objective By evaluating the accuracy of full digital analysis of basic symptoms of traditional Chinese medicine, to verify that the full digital analysis of basic symptoms of traditional Chinese medicine is basically consistent with the classification of PCOS in traditional Chinese medicine theory, so as to objectively assist the clinical diagnosis and treatment of PCOS. Methods PCOS cases were collected and the symptoms, signs and syndrome differentiation results were recorded digitally. The multi labeled k-nearest neighbor method (ML-kNN), multi labeled Bayesian learning algorithm (MLNB) and multi-grained cascade forest algorithm (gcForest) were used to evaluate the accuracy of fully digital analysis of basic symptoms of traditional Chinese medicine by calculating five values: average precision, coverage, Hamming loss, first labeling error and ranking loss. Results ML-kNN, MLNB and gcForest were used to establish a mathematical model based on the clinical data collected. After calculation, 158 patients with PCOS were divided into kidney deficiency, spleen deficiency, liver depression, phlegm dampness and blood stasis, including 52 patients with no concurrent disease of kidney deficiency, 48 patients with kidney deficiency and liver depression, and 58 patients with kidney deficiency and phlegm dampness. The accuracy rates of syndrome types obtained by ML-kNN were: kidney deficiency 66.6% ± 10.2%, spleen deficiency 86.15% ± 2.9%, liver depression 59.8% ± 9.7%, phlegm dampness 72.2% ± 11.6%, blood stasis 82.4% ± 4.6%. The accuracy rates of syndrome types obtained by MLNB were: kidney deficiency 65.5% ± 8.0%, spleen deficiency 85.6% ± 7.1%, liver depression 74.2% ± 7.7%, phlegm dampness 70.5% ± 4.5%, blood stasis 81.8% ± 7.7%. The accuracy of spleen deficiency syndrome and blood stasis syndrome were 79.4% ± 8.8%, respectively. Conclusions the TCM symptoms of PCOS calculated by TCM information system include kidney deficiency, spleen deficiency, liver depression, phlegm dampness and blood stasis. The accuracy is high, which is basically consistent with the classification of PCOS in traditional Chinese medicine theory. It shows that fully digital collection of syndrome information of PCOS patients and syndrome differentiation and treatment through modern data mining methods are basically consistent with the classification of PCOS by traditional Chinese medicine theory. It can summarize the effective laws of TCM clinical syndrome of PCOS and be helpful for clinical diagnosis and treatment.

参考文献:

[1]张美微,侯丽辉,马建,等.1 068例多囊卵巢综合征患者不同亚型临床及代谢特征的差异性研究[J].中华中医药杂志, 2019, 34(7): 3021-3025.
Zhang MW, Hou LH, Ma J, et al. Difference study on characteristics of different subtypes in clinic and metabolic of 1 068 PCOS patients[J]. China Journal of Traditional Chinese Medicine and Pharmacy, 2019, 34(7): 3021-3025.?
[2]唐培培,谈勇.多囊卵巢综合征中医证型分布规律及性激素水平、糖代谢特点[J].中国中西医结合杂志,2016, 36(7): 801-805.
Tang PP, Tan Y. Distribution laws of PCOS syndrome types and features of sex hormone levels and glucose metabolism[J]. Chinese Journal of Integrated Traditional and Western Medicine, 2016, 36(7): 801-805.
[3]杨玲,王隆卉,杨艺娇,等.曹玲仙主任论治肥胖型多囊卵巢综合征经验总结[J].西部中医药, 2020, 33(10): 59-61.
Yang L, Wang LH, Yang YJ, et al. Cao Lingxian's experience of discussing and treating obese PCOS[J]. Western ?Journal of Traditional Chinese Medicine, 2020, 33(10): 59-61.
[4]曹阳,廖维,曹玲仙.曹玲仙治疗多囊卵巢综合征常用对药撷萃[J]. 中国中医药信息杂志, 2015, 22(6): 111-113.
[5]黄萍,周青,商洪涛.中医四诊仪对肥胖人群的中医体质分型[J]. 慢性病学杂志, 2015, 16(5): 589-590.
[6]钱海明,龚刚,袁利峰.数据挖掘技术在中医药领域研究中的应用[J].中医药管理杂志, 2022, 30(22): 179-181.
[7]The Rotterdam ESHRE/ASRM-Sponsored PCOS consensus workshop group. Revised 2003 consensus on diagnostic criteria and long-term health risks related to polycystic ovary syndrome (PCOS)[J]. Human Reproduction, 2004, 19(1): 41-47.
[8]章浩伟,王子楠,刘颖,等.多囊卵巢综合症辅助诊断系统的开发[J]. 生物医学工程研究, 2017, 36(1): 83-85, 94.
Zhang HW, Wang ZN, Liu Y, et al. The development of polycystic ovarian syndrone auxiliary diagnositc system[J]. Journal of Biomedical Engineering Research, 2017, 36(1): 83-85, 94.
[9] 钟涛. 基于复杂系统方法的慢性胃炎中医问诊证候建模研究[D].上海:华东理工大学, 2014.
Zhong T. Modeling of inquiry diagnosis for chronic gastritis in traditional Chinese medicine by complex system methods[D]. Shanghai: East China University of Science and Technology, 2014.
[10] 任晋滔. 基于多标记学习的中医问诊系统的研究[D].上海:华东理工大学, 2012.
Ren JT. Research of Traditional Chinese Medicine inquiry based on multi-label learning[D]. Shanghai: East China University of Science and Technology, 2012.
[11]姚笛,俞而慨,曹玲仙,等.曹玲仙教授论治多囊卵巢综合征的辨证特色及其分型与性激素的关系[J].上海中医药大学学报, 2017, 31(5): 1-5.
Yao D, Yu EK, Cao LX, et al. Professor Cao Lingxian's experience in the syndrome differentiation and treatment of polycystic ovary syndrome and the relationship between classification and sex hormones[J]. Acta Universitatis Traditionis Medicalis Sinensis Pharmacologiaeque Shanghai, 2017, 31(5): 1-5.
[12]陈迪,张诏,王仪雯,等. 基于数据挖掘探索多囊卵巢综合征临床用药规律[J].中医药导报, 2018, 24(23): 70-73.
Chen D, Zhang Z, Wang YW, et al. Discussion of the medication law on modern clinical in treatment of polycystic ovary syndrome based on date mining[J]. Guiding Journal of Traditional Chinese Medicine and Pharmacology, 2018, 24(23): 70-73.
[13]章浩伟,王子楠,刘颖,等.基于数据挖掘的曹玲仙治疗多囊卵巢综合征用药规律研究[J].北京生物医学工程, 2017, 36(5): 465-470, 494.
Zhang HW, Wang Z, Liu Y, et al. Medication rules of CAO Lingxian's treatment on polycystic ovarian syndrone with data mining[J]. Beijing Biomedical Engineering, 2017,36(5): 465-470, 494.
[14] 张雯,李娜,许朝霞. 多囊卵巢综合征的中医证治研究进展[J].世界科学技术——中医药现代化, 2018, 20(5): 810-815.?
Zhang W, Li N, Xu ZX. Research progress in TCM syndrome treatment of polycystic ovary syndrome[J]. World Science and Technology—Modernization of Traditional Chinese Medicine and Materia Medica, 2018, 20(5): 810-815.
[15]张东琦,贾丽妍,常惠,等. 针药联合治疗PCOS不孕症临床研究进展[J]. 江苏中医药, 2020, 52(1): 91-93.
[16]徐玮斐,刘国萍,王忆勤,等. 近5年中医证候诊断客观化研究述评[J]. 中医杂志, 2016, 57(5): 442-445.
[17]崔佳,丛培玮,吴兆利.多囊卵巢综合征从痰瘀论治的理论探析及临床应用[J].中国医药导报,2022,19(34): 126-129.
Cui J, Cong PW, WU ZL. Theoretical analysis and clinical application of treating polycystic ovary syndrome based on phlegm and stasis[J].China Medical Herald, 2022,19(34): 126-129.
[18] 应海琼,诸小丽,季双双,等. 温州市中医院育龄期多囊卵巢综合征患者危险因素分析[J].中国医药导报,2022,19(32): 55-58.
Ying HQ, Zhu XL, Ji SS, et al. Analysis of risk factors in patients with polycystic ovary syndrome of reproductive age in Wenzhou Hospital of Traditional Chinese Medicine[J].China Medical Herald, 2022,19(32): 55-58.

服务与反馈:
文章下载】【加入收藏
提示:您还未登录,请登录!点此登录
 
友情链接  
地址:北京安定门外安贞医院内北京生物医学工程编辑部
电话:010-64456508  传真:010-64456661
电子邮箱:llbl910219@126.com