北京生物醫(yī)學工程

中醫(yī)信息系統對多囊卵巢綜合征的分型研究

Classification of polycystic ovary syndrome by TCM information system

作者：郭姍珊陳厚儒王書云姚笛吳勝男朱光耀俞而慨顏建軍

單位：上海中醫(yī)藥大學附屬龍華醫(yī)院(上海 200032)<br />華東理工大學(上海 200237)<br />同濟大學附屬第一婦嬰保健院(上海 200092)<br />通信作者：俞而慨，E-mail: [email protected]；顏建軍，E-mail: [email protected]

關鍵詞：多囊卵巢綜合征；中醫(yī)信息系統；中醫(yī)分型

分類號：R318.04

出版年·卷·期（頁碼）：2023·42·2（170-177）

摘要：

目的通過評估全數字化分析中醫(yī)基本癥候的準確率，來驗證全數字化分析中醫(yī)基本證候與傳統中醫(yī)理論對于PCOS的分型有較高的準確率，從而可以客觀地輔助臨床對PCOS的診療。方法收集PCOS病例，數字化記錄癥狀、體征、辨證分型結果；并采用多標記學習法中的多標記k近鄰方法(multi-label k-nearest neighbor, ML-kNN)、多標記貝葉斯學習算法（multi-label naive Bayesian, MLNB）法和深度森林算法 (multi-grained cascade forest, gcForest)，通過計算平均準確率(average precision)、覆蓋距離(coverage)、漢明損失(Hamming loss)、首標記錯誤和排序損失(ranking loss)5個數值來評估全數字化分析中醫(yī)基本癥候的準確率。結果用ML-kNN、MLNB和gcForest將臨床采集的數據建立數學模型，經過計算后得出158例PCOS確診患者中醫(yī)臨床辨證分型為腎虛、脾虛、肝郁、痰濕和血瘀，其中腎虛無兼癥的患者52例，腎虛和肝郁并存的患者48例，腎虛和痰濕并存的患者58例。用ML-kNN得出的證型準確率分別為：腎虛66.6%±10.2%、脾虛86.15%±2.9%、肝郁59.8%±9.7%、痰濕72.2%±11.6%，血瘀82.4%±4.6%。用MLNB得出的證型準確率分別為：腎虛65.5%±8.0%、脾虛85.6%±7.1%、肝郁74.2%±7.7%、痰濕70.5%±4.5%，血瘀81.8%±7.7%。用gcForest得出的證型準確率分別為：腎虛87.2%±5.0%、脾虛86.6%±4.8%、肝郁79.2%±6.5%、痰濕79.4%±6.8%，血瘀82.3%±5.9%。結論用中醫(yī)信息系統計算的PCOS的中醫(yī)癥候有腎虛、脾虛、肝郁、痰濕、血瘀，與曹玲仙教授對PCOS的分型有較高的準確率。說明全數字化采集PCOS患者證候信息并通過現代數據挖掘方法進行辨證論治，可以對PCOS中醫(yī)臨床證候進行有效規(guī)律總結，對臨床診療有一定的幫助。

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.

參考文獻：

[1]張美微,侯麗輝,馬建,等.1 068例多囊卵巢綜合征患者不同亞型臨床及代謝特征的差異性研究[J].中華中醫(yī)藥雜志, 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,談勇.多囊卵巢綜合征中醫(yī)證型分布規(guī)律及性激素水平、糖代謝特點[J].中國中西醫(yī)結合雜志,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]楊玲,王隆卉,楊藝嬌,等.曹玲仙主任論治肥胖型多囊卵巢綜合征經驗總結[J].西部中醫(yī)藥, 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]曹陽,廖維,曹玲仙.曹玲仙治療多囊卵巢綜合征常用對藥擷萃[J]. 中國中醫(yī)藥信息雜志, 2015, 22(6): 111-113.
[5]黃萍,周青,商洪濤.中醫(yī)四診儀對肥胖人群的中醫(yī)體質分型[J]. 慢性病學雜志, 2015, 16(5): 589-590.
[6]錢海明,龔剛,袁利峰.數據挖掘技術在中醫(yī)藥領域研究中的應用[J].中醫(yī)藥管理雜志, 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]章浩偉,王子楠,劉穎,等.多囊卵巢綜合癥輔助診斷系統的開發(fā)[J]. 生物醫(yī)學工程研究, 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] 鐘濤. 基于復雜系統方法的慢性胃炎中醫(yī)問診證候建模研究[D].上海：華東理工大學, 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] 任晉滔. 基于多標記學習的中醫(yī)問診系統的研究[D].上海：華東理工大學, 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.曹玲仙教授論治多囊卵巢綜合征的辨證特色及其分型與性激素的關系[J].上海中醫(yī)藥大學學報, 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]陳迪,張詔,王儀雯,等. 基于數據挖掘探索多囊卵巢綜合征臨床用藥規(guī)律[J].中醫(yī)藥導報, 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]章浩偉,王子楠,劉穎,等.基于數據挖掘的曹玲仙治療多囊卵巢綜合征用藥規(guī)律研究[J].北京生物醫(yī)學工程, 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] 張雯,李娜,許朝霞. 多囊卵巢綜合征的中醫(yī)證治研究進展[J].世界科學技術——中醫(yī)藥現代化, 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]張東琦,賈麗妍,常惠,等. 針藥聯合治療PCOS不孕癥臨床研究進展[J]. 江蘇中醫(yī)藥, 2020, 52(1): 91-93.
[16]徐瑋斐,劉國萍,王憶勤,等. 近5年中醫(yī)證候診斷客觀化研究述評[J]. 中醫(yī)雜志, 2016, 57(5): 442-445.
[17]崔佳,叢培瑋,吳兆利.多囊卵巢綜合征從痰瘀論治的理論探析及臨床應用[J].中國醫(yī)藥導報,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] 應海瓊,諸小麗,季雙雙，等. 溫州市中醫(yī)院育齡期多囊卵巢綜合征患者危險因素分析[J].中國醫(yī)藥導報,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.

服務與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频