By analyzing the existing prefix-tree data structure, an improved pattern tree was introduced for processing new transactions. It firstly stored transactions in a lexicographic order tree and then restructured the tre...By analyzing the existing prefix-tree data structure, an improved pattern tree was introduced for processing new transactions. It firstly stored transactions in a lexicographic order tree and then restructured the tree by sorting each path in a frequency-descending order. While updating the improved pattern tree, there was no need to rescan the entire new database or reconstruct a new tree for incremental updating. A test was performed on synthetic dataset T1014D100K with 100 000 transactions and 870 items. Experimental results show that the smaller the minimum sup- port threshold, the faster the improved pattern tree achieves over CanTree for all datasets. As the minimum support threshold increased from 2% to 3.5%, the runtime decreased from 452.71 s to 186.26 s. Meanwhile, the runtime re- quired by CanTree decreased from 1 367.03 s to 432.19 s. When the database was updated, the execution time of im- proved pattern tree consisted of construction of original improved pattern trees and reconstruction of initial tree. The experiment results showed that the runtime was saved by about 15% compared with that of CanTree. As the number of transactions increased, the runtime of improved pattern tree was about 25% shorter than that of FP-tree. The improved pattern tree also required less memory than CanTree.展开更多
Objective To analyze the basic characteristics,drug features,prescription rules,and drug-symptom relationships of patients in the splenic deficiency and impairment stage,by data mining of medical records under the New...Objective To analyze the basic characteristics,drug features,prescription rules,and drug-symptom relationships of patients in the splenic deficiency and impairment stage,by data mining of medical records under the New Theory on Spleen Dampness Syndrome(Pi Dan Xin Lun,《脾瘅新论》).Methods Medical records listed in the“New Theory on Spleen Dampness Syndrome-Under-standing and Treatment of Metabolic Syndrome from the Perspective of Traditional Chinese Medicine”,and which were diagnosed with the spleen dampness syndrome at the splenic de-ficiency and impairment stage,during January 2004 and December 2016 were selected.These patients’data,including basic information,clinical symptoms,laboratory examination res-ults,traditional Chinese medicine(TCM)and western medicine diagnoses,treatment meth-ods,prescriptions,etc.,were collected.The collected data were subsequently compiled into a medical record database using the Epidata 3.1 data management software,followed by the use of Apriori algorithm provided in the SPSS Modeler 14.2 statistical software to investigate the association rules between drug-drug,drug-symptom,and drug-western medicine indices.Results(i)A total of 51 medical records were included,involving 17 types of syndromes.Among them,the top three with frequency≥3 included“Phlegm and blood stasis,and thoracic obstruction”“Deficiency-weakness of the spleen Qi,and static blood blocking collat-erals”,and“Deficiency-weakness of the spleen Qi,and static blood blocking collaterals”.Al-ternatively,of the 14 treatment methods,the top three treatments with frequency of≥3 in-cluded“Activating Yang and eliminating turbidity,and removing phlegm and dredging chan-nel blockage”“Strengthening the spleen and benefiting Qi,and eliminating phlegm to activ-ate the channels”,and“Warming Yang and benefiting Qi,and expelling cold to remove ob-structions”.Among the 15 prescriptions,the top three used with frequency≥3 included Huangqi Guizhi Wuwu Tang(黄芪桂枝五物汤),Gualou Xiebai Banxia Tang(瓜蒌薤白半夏汤),and Ganjiang Huangqin Huanglian Renshen Tang(干姜黄芩黄连人参汤).Lastly,of the 83 drugs used for a total of 476 times,those with frequency≥15 included Huanglian(Coptid-is Rhizoma),Huangqi(Astragali Radix),Jiudahuang(Wine-processed Rhei Radix et Rhizoma),Jixueteng(Spatholobi Caulis),Shengjiang(Zingiberis Rhizoma Recens),Huangqin(Scutellariae Radix),and Guizhi(Cinnamomi Ramulus).(ii)For the drug-drug associations,under the criteria of support≥15%and confidence=100%,seven second-order association rules,seven third-order rules,and six fourth-order roles were identified.The top-ranking rule of each was“Huangqin(Scutellariae Radix)→Huanglian(Coptidis Rhizoma)”“Ganjiang(Zingiberis Rhizoma)+Huangqin(Scutellariae Radix)→Huanglian(Coptidis Rhizoma)”,and“Baishao(Paeoniae Radix Alba)+Guizhi(Cinnamomi Ramulus)+Jixueteng(Spatho-lobi Caulis)→Huangqin(Scutellariae Radix)”,respectively.Alternatively,the drug-symptom associations were analyzed under the criteria of support≥5%and confidence=100%,which derived eight second-order association rules,31 third-order rules,and 30 fourth-order rules.The top-ranking association rule of each order was“Huangqi(Astragali Radix)→Limb ed-ema”“Guizhi(Cinnamomi Ramulus)+Jixueteng(Spatholobi Caulis)→Limb numbness and pain”,and“Guizhi(Cinnamomi Ramulus)+Jixueteng(Spatholobi Caulis)+Huangqi(As-tragali Radix)→Limb numbness and pain”,respectively.Similarly,the drug-western medi-cine index associations were investigated under the criteria of support≥5%and confidence=100%,and five second-order association rules,16 third-order rules,and 16 fourth-order rules were identified.In this category,the top-ranking association rule of each order was“Qinpi(Fraxini Cortex)→Uric acid”“Huanglian(Coptidis Rhizoma)+Ganjiang(Zingiberis Rhizoma)→Glycated hemoglobin”,and“Huanglian(Coptidis Rhizoma)+Ganjiang(Zing-iberis Rhizoma)+Huangqin(Scutellariae Radix)→Glycated hemoglobin”,respectively.Conclusion Through association rule mining,this study objectively and quantitatively demonstrated the drug-drug,drug-symptom,and drug-physicochemical index associations of patients with the spleen dampness syndrome at the splenic deficiency and impairment stage treated by Academician TONG Xiaolin.The results indicated that treatment for these patients adopted the“state-target”syndrome differentiation method.The drug combination was characterized by“small prescriptions”,targeting both the patient’s symptoms and signs(syndrome target)and western medicine indices(treatment target).This study could provide references for future research on the academic thoughts and medical experience of Academi-cian TONG Xiaolin.展开更多
Objective:To analyze the component law of Chinese patent medicines for anti-influenza and develop new prescriptions for anti-influenza by unsupervised data mining methods. Methods: Chinese patent medicine recipes for ...Objective:To analyze the component law of Chinese patent medicines for anti-influenza and develop new prescriptions for anti-influenza by unsupervised data mining methods. Methods: Chinese patent medicine recipes for anti-influenza were collected and recorded in the database, and then the correlation coefficient between herbs, core combinations of herbs and new prescriptions were analyzed by using modified mutual information, complex system entropy cluster and unsupervised hierarchical clustering, respectively. Results: Based on analysis of 126 Chinese patent medicine recipes, the frequency of each herb occurrence in these recipes, 54 frequently-used herb pairs, 34 core combinations were determined, and 4 new recipes for influenza were developed. Conclusion: Unsupervised data mining methods are able to mine the component law quickly and develop new prescriptions.展开更多
基金Supported by National Natural Science Foundation of China (No.50975193)Specialized Research Fund for Doctoral Program of Higher Education of China (No.20060056016)
文摘By analyzing the existing prefix-tree data structure, an improved pattern tree was introduced for processing new transactions. It firstly stored transactions in a lexicographic order tree and then restructured the tree by sorting each path in a frequency-descending order. While updating the improved pattern tree, there was no need to rescan the entire new database or reconstruct a new tree for incremental updating. A test was performed on synthetic dataset T1014D100K with 100 000 transactions and 870 items. Experimental results show that the smaller the minimum sup- port threshold, the faster the improved pattern tree achieves over CanTree for all datasets. As the minimum support threshold increased from 2% to 3.5%, the runtime decreased from 452.71 s to 186.26 s. Meanwhile, the runtime re- quired by CanTree decreased from 1 367.03 s to 432.19 s. When the database was updated, the execution time of im- proved pattern tree consisted of construction of original improved pattern trees and reconstruction of initial tree. The experiment results showed that the runtime was saved by about 15% compared with that of CanTree. As the number of transactions increased, the runtime of improved pattern tree was about 25% shorter than that of FP-tree. The improved pattern tree also required less memory than CanTree.
基金The Construction of First-class Integrated Traditional Chinese and western Medicine Disciplines in Guangxi(Scientific Research Project No.12 of Guangxi Ministry of Education[2018])Qihuang High-level Talent Team Training Projects of Guangxi University of Chinese Medicine−Application of Systems Biology in Chinese Medicine Research(2021005).
文摘Objective To analyze the basic characteristics,drug features,prescription rules,and drug-symptom relationships of patients in the splenic deficiency and impairment stage,by data mining of medical records under the New Theory on Spleen Dampness Syndrome(Pi Dan Xin Lun,《脾瘅新论》).Methods Medical records listed in the“New Theory on Spleen Dampness Syndrome-Under-standing and Treatment of Metabolic Syndrome from the Perspective of Traditional Chinese Medicine”,and which were diagnosed with the spleen dampness syndrome at the splenic de-ficiency and impairment stage,during January 2004 and December 2016 were selected.These patients’data,including basic information,clinical symptoms,laboratory examination res-ults,traditional Chinese medicine(TCM)and western medicine diagnoses,treatment meth-ods,prescriptions,etc.,were collected.The collected data were subsequently compiled into a medical record database using the Epidata 3.1 data management software,followed by the use of Apriori algorithm provided in the SPSS Modeler 14.2 statistical software to investigate the association rules between drug-drug,drug-symptom,and drug-western medicine indices.Results(i)A total of 51 medical records were included,involving 17 types of syndromes.Among them,the top three with frequency≥3 included“Phlegm and blood stasis,and thoracic obstruction”“Deficiency-weakness of the spleen Qi,and static blood blocking collat-erals”,and“Deficiency-weakness of the spleen Qi,and static blood blocking collaterals”.Al-ternatively,of the 14 treatment methods,the top three treatments with frequency of≥3 in-cluded“Activating Yang and eliminating turbidity,and removing phlegm and dredging chan-nel blockage”“Strengthening the spleen and benefiting Qi,and eliminating phlegm to activ-ate the channels”,and“Warming Yang and benefiting Qi,and expelling cold to remove ob-structions”.Among the 15 prescriptions,the top three used with frequency≥3 included Huangqi Guizhi Wuwu Tang(黄芪桂枝五物汤),Gualou Xiebai Banxia Tang(瓜蒌薤白半夏汤),and Ganjiang Huangqin Huanglian Renshen Tang(干姜黄芩黄连人参汤).Lastly,of the 83 drugs used for a total of 476 times,those with frequency≥15 included Huanglian(Coptid-is Rhizoma),Huangqi(Astragali Radix),Jiudahuang(Wine-processed Rhei Radix et Rhizoma),Jixueteng(Spatholobi Caulis),Shengjiang(Zingiberis Rhizoma Recens),Huangqin(Scutellariae Radix),and Guizhi(Cinnamomi Ramulus).(ii)For the drug-drug associations,under the criteria of support≥15%and confidence=100%,seven second-order association rules,seven third-order rules,and six fourth-order roles were identified.The top-ranking rule of each was“Huangqin(Scutellariae Radix)→Huanglian(Coptidis Rhizoma)”“Ganjiang(Zingiberis Rhizoma)+Huangqin(Scutellariae Radix)→Huanglian(Coptidis Rhizoma)”,and“Baishao(Paeoniae Radix Alba)+Guizhi(Cinnamomi Ramulus)+Jixueteng(Spatho-lobi Caulis)→Huangqin(Scutellariae Radix)”,respectively.Alternatively,the drug-symptom associations were analyzed under the criteria of support≥5%and confidence=100%,which derived eight second-order association rules,31 third-order rules,and 30 fourth-order rules.The top-ranking association rule of each order was“Huangqi(Astragali Radix)→Limb ed-ema”“Guizhi(Cinnamomi Ramulus)+Jixueteng(Spatholobi Caulis)→Limb numbness and pain”,and“Guizhi(Cinnamomi Ramulus)+Jixueteng(Spatholobi Caulis)+Huangqi(As-tragali Radix)→Limb numbness and pain”,respectively.Similarly,the drug-western medi-cine index associations were investigated under the criteria of support≥5%and confidence=100%,and five second-order association rules,16 third-order rules,and 16 fourth-order rules were identified.In this category,the top-ranking association rule of each order was“Qinpi(Fraxini Cortex)→Uric acid”“Huanglian(Coptidis Rhizoma)+Ganjiang(Zingiberis Rhizoma)→Glycated hemoglobin”,and“Huanglian(Coptidis Rhizoma)+Ganjiang(Zing-iberis Rhizoma)+Huangqin(Scutellariae Radix)→Glycated hemoglobin”,respectively.Conclusion Through association rule mining,this study objectively and quantitatively demonstrated the drug-drug,drug-symptom,and drug-physicochemical index associations of patients with the spleen dampness syndrome at the splenic deficiency and impairment stage treated by Academician TONG Xiaolin.The results indicated that treatment for these patients adopted the“state-target”syndrome differentiation method.The drug combination was characterized by“small prescriptions”,targeting both the patient’s symptoms and signs(syndrome target)and western medicine indices(treatment target).This study could provide references for future research on the academic thoughts and medical experience of Academi-cian TONG Xiaolin.
基金supported by Scientific Research Special Project of TCM Profession (200907001E)Science and Technology Special Major Project for "Significant New Drugs Formulation" (2009ZX09301-005-02)
文摘Objective:To analyze the component law of Chinese patent medicines for anti-influenza and develop new prescriptions for anti-influenza by unsupervised data mining methods. Methods: Chinese patent medicine recipes for anti-influenza were collected and recorded in the database, and then the correlation coefficient between herbs, core combinations of herbs and new prescriptions were analyzed by using modified mutual information, complex system entropy cluster and unsupervised hierarchical clustering, respectively. Results: Based on analysis of 126 Chinese patent medicine recipes, the frequency of each herb occurrence in these recipes, 54 frequently-used herb pairs, 34 core combinations were determined, and 4 new recipes for influenza were developed. Conclusion: Unsupervised data mining methods are able to mine the component law quickly and develop new prescriptions.
