中医诊断技术发展及四诊信息融合研究
|
摘要
近20余年来,中医诊断技术取得了突破性进展,在舌诊、面诊、声诊、嗅诊、问诊、脉诊客观化信息采集设备和数据处理软件方面成果丰硕,并开展了相应的临床研究,但在诊断技术及指标的规范化方面尚处于起步阶段,目前仅出台舌诊仪相关国际标准1项、中医脉诊压力传感器国际标准1项。随着计算机信息处理技术在中医领域的深入渗透,模式识别方法在四诊信息融合中得到应用和发展,四诊合参辅助诊疗及中医四诊检测系统的研发,建立了更适合中医思维的辨证模型和人工智能识别平台;未来,借助物联网技术、云平台技术、可穿戴技术,四诊信息采集设备必将向小型化、可穿戴式发展,并可研发中医诊疗机器人,以期在中医临床及各级医疗平台、慢性病管理、健康风险评估等方面发挥更大的作用。
In the past 20 years,the diagnostic technology of traditional Chinese medicine( TCM) has made breakthrough progress. It has achieved fruitful results in the objective information collection equipments and data processing softwares for tongue diagnosis,face diagnosis,voice diagnosis,olfactory diagnosis,inquiry and pulse diagnosis,and has carried out the corresponding clinical research.However,in the standardization of diagnostic techniques and indicators,it is still in its infancy. At present,only one international standard for tongue diagnosis apparatus and one international standard for pulse diagnosis pressure sensor are published. With the deep penetration of computer information processing technology in TCM field,the pattern recognition method has been applied and developed in the four-diagnosis information fusion,and the auxiliary diagnosis and treatment system based on comprehensive analysis of data gained by four diagnostic methods and the TCM four-diagnosis detection system have been developed. These research results contribute to the establishment of syndrome differentiation model and artificial intelligence recognition platform which is more suitable for TCM thinking.In the future,with the help of internet of things technology,cloud platform technology and wearable technology,the four-diagnostic information collection equipments should be developed to be miniaturized and wearable,and the TCM robot for diagnosis and treatment can be developed. It is expected to play a greater role in TCM clinic in all levels of medical platforms,chronic disease management and health risk assessment.
In the past 20 years,the diagnostic technology of traditional Chinese medicine( TCM) has made breakthrough progress. It has achieved fruitful results in the objective information collection equipments and data processing softwares for tongue diagnosis,face diagnosis,voice diagnosis,olfactory diagnosis,inquiry and pulse diagnosis,and has carried out the corresponding clinical research.However,in the standardization of diagnostic techniques and indicators,it is still in its infancy. At present,only one international standard for tongue diagnosis apparatus and one international standard for pulse diagnosis pressure sensor are published. With the deep penetration of computer information processing technology in TCM field,the pattern recognition method has been applied and developed in the four-diagnosis information fusion,and the auxiliary diagnosis and treatment system based on comprehensive analysis of data gained by four diagnostic methods and the TCM four-diagnosis detection system have been developed. These research results contribute to the establishment of syndrome differentiation model and artificial intelligence recognition platform which is more suitable for TCM thinking.In the future,with the help of internet of things technology,cloud platform technology and wearable technology,the four-diagnostic information collection equipments should be developed to be miniaturized and wearable,and the TCM robot for diagnosis and treatment can be developed. It is expected to play a greater role in TCM clinic in all levels of medical platforms,chronic disease management and health risk assessment.
引文
[1]卫保国,沈兰荪,王艳清,等.数字化中医舌象分析仪[J].中国医疗器械杂志,2002,26(3):164-166.
[2]宫爱民.中医舌面一体检测系统研制及健康青年人群四季面色观察[D].上海:上海中医药大学,2010.
[3]天津大学.三维全息舌象获取方法及舌象仪[P].中国专利:201210006553.9,2012-01-10.
[4]姜华.一种便携式舌象获取装置[P].中国专利:201120162169.9,2011-12-21.
[5]曹美玲.新型中医舌诊仪的研制和舌图像的颜色重现[D].北京:北京工业大学,2008.
[6]牛欣.一种获取识别脉动信息与舌诊信息的装置及其方法[P].中国专利:200710151375.8,2008-02-27.
[7]沈兰荪,蔡铁珩,卫保国,等.中医舌象分析技术的研究[J].世界科学技术-中药现代化,2003,5(1):15-19.
[8]王永刚,杨杰,周越,等.中医舌象颜色识别的研究[J].生物医学工程学杂志,2005,22(6):1116-1120.
[9]卫保国,沈兰荪.舌体胖瘦的自动分析[J].计算机工程,2004,30(11):25-26,68.
[10]谢涛.基于图像处理的舌像分割及润燥识别研究[D].上海:华东理工大学,2017.
[11]夏雨.基于机器视觉的望诊分析系统研究[D].上海:华东理工大学,2014.
[12]杨琼,朱惠蓉,燕海霞,等.31例原发性肺癌患者舌象特征参数与生命质量量表的相关性分析[J].中华中医药学刊,2011,29(4):786-789.
[13]程悦蕾,朱惠蓉,杨琼,等.100例湿热蕴结型大肠癌患者治疗前后舌脉象参数特征分析[J].辽宁中医杂志,2015,42(2):230-235.
[14]付晶晶,李福凤,陆雄,等.慢性胃炎中医证候舌象信息特征研究[J].中国中医基础医学杂志,2015,21(9):1107-1108.
[15]李福凤,邸丹,王忆勤,等.基于计算机技术的中医面诊信息采集与识别研究[J].世界科学技术-中医药现代化,2008,10(6):71-76.
[16]蔡艺芳,李灿东.面部望诊二维坐标体系的建立[J].福建中医学院学报,2008,18(1):13-14.
[17]李福凤,李国正,周睿,等.基于PLS、LDA的中医面诊光泽识别研究[J].世界科学技术-中医药现代化,2011,13(6):977-981.
[18]李蕊玲.基于机器视觉的中医面诊神色客观化研究[D].北京:北京科技大学,2012.
[19]蔡光先.508例病理五色定量计测[J].中国医药学报,1996,11(1):20-21.
[20]田雪飞,程曙,周青.脾病名堂色反射光谱图像分析[J].中医药导报,2001,7(2):79-82.
[21]刘金涛,陈叶,金燕,等.基于数字化慢性肾炎湿热证面诊特征研究[J].中华中医药学刊,2014,32(11):2680-2683.
[22]林源,林万庆,陈旭军.哮喘病的灸疗前后二十五音频率变化的研究[J].中医药通报,2008,7(6):29-30.
[23]高也陶.五脏相音[M].北京:中医古籍出版社,2007:351-412.
[24]陈春凤,王忆勤,颜建军,等.中医闻诊信号采集与分析在虚、实证型辨别中的应用[J].中西医结合学报,2010,8(10):944-948.
[25]鲁法庭,张学娅,杨梅,等.声诊研究现状及开展咳嗽中医声诊客观化研究新思路[J].辽宁中医杂志,2010,37(7):1231-1232.
[26]沈小静.基于小波包变换和支持向量机的中医声诊客观化研究[D].上海:华东理工大学,2011.
[27]胡赣.基于特征组合的中医声诊客观化研究[D].上海:华东理工大学,2014.
[28]董伟,王忆勤,郑荣华,等.100例慢性咽炎患者语音信号的证型特征分析[J].河北中医,2015,37(11):1613-1615,1619.
[29]宋镇贵.基于小波分析的口腔气味病理特征提取与诊断方法研究[D].哈尔滨:哈尔滨工业大学,2010.
[30]林雪娟,郑哲洲,吴青海,等.基于电子鼻的2型糖尿病虚实病性间的气味识别分析[J].中华中医药杂志,2015,30(8):2687-2691.
[31]王忆勤.中医诊断学研究思路与方法[M].上海:上海科学技术出版社,2008:149-371.
[32]王哲,胡随瑜,陈泽奇.简明抑郁症中医证候自评量表初步编制[J].中国行为医学科学,2005,14(10):945.
[33]刘国萍,王忆勤,郭睿,等.中医心系问诊采集系统的研制及评价[J].世界科学技术-中医药现代化,2008,10(5):16-20.
[34]XU Z X,ZHANG N L,WANG Y Q,et al.Statistical Validation of Traditional Chinese Medicine Syndrome Postulates in the Context of Patients with Cardivascular Disease[J]. J Altern Complem Med,2013,18(11):1-6.
[35]LIU G P,YAN J J,WANG Y Q,et al. Application of Multilabel Learning Using the Relevant Feature for Each Label in Chronic Gastritis Syndrome Diagnosis[J]. Evid Based Complement Med,2012,2012:135387.doi:10.1155/2012/135387.
[36]张西洋.穿戴式脉象检测装置及其信号处理的研究[D].上海:华东理工大学,2016.
[37]周侃恒.新型三探头自加压脉象仪的研制[D].上海:华东理工大学,2015.
[38]杨杰,牛欣,司银楚,等.压力与B超整合的中医取脉装置的研究与应用[J].世界科学技术-中医药现代化,2005,7(6):44-46.
[39]中国科学院微电子研究所.中医脉诊传感器、中医脉诊诊疗系统及健康服务平台[P].中国专利:CN105662368A,2016-03-04.
[40]朱一鸣.基于心血管电网络模型的脉象信息仿真分析与识别研究[D].上海:华东理工大学,2013.
[41]郭睿,王忆勤,燕海霞,等.脉图的递归定量分析及对冠心病颈动脉血管硬化程度的评价[J].中华中医药杂志,2016,31(5):1695-1699.
[42]尚倩倩,王忆勤,燕海霞,等.159例原发性高血压合并靶器官损害患者脉图参数分析[J].世界科学技术-中医药现代化,2016,18(6):1033-1039.
[43]魏红,王宇,桂森,等.抑郁症患者中医脉象信息规律性研究[J].辽宁中医药大学学报,2017,19(3):5-9.
[44]LIU G P,LI G Z WANG Y L,et al. Modelling of inquiry diagnosis for coronary heart disease in traditional Chinese medicine by using multi-label learning[J]. BMC Complem Altern Med,2010,10:37.doi:10.1186/1472-6882-10-27.
[45]吴喜庆,陆小左.冠心病中医客观化诊疗评价方法研究[J].辽宁中医杂志,2014,4(8):1574-1583.
[46]吴喜庆,陆小左.慢性乙型肝炎中医客观化诊疗评价方法研究[J].天津中医药大学学报,2014,33(4):199-203.
[47]钱桂凤,潘秋银,郭峥嵘,等.基于数字化四诊合参得到帕金森针刺研究策略[J].中华中医药杂志,2014,29(9):2857-2850.
[48]WANG Y Q,GUO R,YAN H X,et al.Study on Intelligent Sydrome Differentiation in Traditional Chinse Medicine Based on Information Fusion Technology[C]. Hongkong:IEEE International Conference on Bioinformatics&Biomedicine Workshops,2011.
[49] MCCALLUM A K. Multi-label text classification with a mixture model trained by EM[C]. Orlando:Working Notes of the AAAI’99 workshop on Text Learning,1999.
[50]BOUTELL M R,LUO J,SHEN X P,et al. Learning multi-label scene classification[J]. Pattern Recogn, 2004, 37(9):1757-1771.
[51]READ J,PFAHRINGER B,HOLMES G,et al. Classifier chains for multi-label classification[M]. Springer:Lecture Notesin Computer Science,2009:254-269.
[52]ZHANG M L, ZHOU Z H. Multilabel neural networks with applications to functional genomics and text categorization[J].IEEE T Knowl Data En,2006,18(10):1338-1351.
[53] ELISSEEFF A,WESTON J. A kernel method for multi-labelled classification[C]. Cambridge:International Conference on Neural Information,2001:681-687.
[54]ZHANG M L. LIFT:Multi-label learning with label-specific features[C]. Barcelona:Proceedings of the 22nd International Joint Conference on Artificial Intelligence,2011.
[2]宫爱民.中医舌面一体检测系统研制及健康青年人群四季面色观察[D].上海:上海中医药大学,2010.
[3]天津大学.三维全息舌象获取方法及舌象仪[P].中国专利:201210006553.9,2012-01-10.
[4]姜华.一种便携式舌象获取装置[P].中国专利:201120162169.9,2011-12-21.
[5]曹美玲.新型中医舌诊仪的研制和舌图像的颜色重现[D].北京:北京工业大学,2008.
[6]牛欣.一种获取识别脉动信息与舌诊信息的装置及其方法[P].中国专利:200710151375.8,2008-02-27.
[7]沈兰荪,蔡铁珩,卫保国,等.中医舌象分析技术的研究[J].世界科学技术-中药现代化,2003,5(1):15-19.
[8]王永刚,杨杰,周越,等.中医舌象颜色识别的研究[J].生物医学工程学杂志,2005,22(6):1116-1120.
[9]卫保国,沈兰荪.舌体胖瘦的自动分析[J].计算机工程,2004,30(11):25-26,68.
[10]谢涛.基于图像处理的舌像分割及润燥识别研究[D].上海:华东理工大学,2017.
[11]夏雨.基于机器视觉的望诊分析系统研究[D].上海:华东理工大学,2014.
[12]杨琼,朱惠蓉,燕海霞,等.31例原发性肺癌患者舌象特征参数与生命质量量表的相关性分析[J].中华中医药学刊,2011,29(4):786-789.
[13]程悦蕾,朱惠蓉,杨琼,等.100例湿热蕴结型大肠癌患者治疗前后舌脉象参数特征分析[J].辽宁中医杂志,2015,42(2):230-235.
[14]付晶晶,李福凤,陆雄,等.慢性胃炎中医证候舌象信息特征研究[J].中国中医基础医学杂志,2015,21(9):1107-1108.
[15]李福凤,邸丹,王忆勤,等.基于计算机技术的中医面诊信息采集与识别研究[J].世界科学技术-中医药现代化,2008,10(6):71-76.
[16]蔡艺芳,李灿东.面部望诊二维坐标体系的建立[J].福建中医学院学报,2008,18(1):13-14.
[17]李福凤,李国正,周睿,等.基于PLS、LDA的中医面诊光泽识别研究[J].世界科学技术-中医药现代化,2011,13(6):977-981.
[18]李蕊玲.基于机器视觉的中医面诊神色客观化研究[D].北京:北京科技大学,2012.
[19]蔡光先.508例病理五色定量计测[J].中国医药学报,1996,11(1):20-21.
[20]田雪飞,程曙,周青.脾病名堂色反射光谱图像分析[J].中医药导报,2001,7(2):79-82.
[21]刘金涛,陈叶,金燕,等.基于数字化慢性肾炎湿热证面诊特征研究[J].中华中医药学刊,2014,32(11):2680-2683.
[22]林源,林万庆,陈旭军.哮喘病的灸疗前后二十五音频率变化的研究[J].中医药通报,2008,7(6):29-30.
[23]高也陶.五脏相音[M].北京:中医古籍出版社,2007:351-412.
[24]陈春凤,王忆勤,颜建军,等.中医闻诊信号采集与分析在虚、实证型辨别中的应用[J].中西医结合学报,2010,8(10):944-948.
[25]鲁法庭,张学娅,杨梅,等.声诊研究现状及开展咳嗽中医声诊客观化研究新思路[J].辽宁中医杂志,2010,37(7):1231-1232.
[26]沈小静.基于小波包变换和支持向量机的中医声诊客观化研究[D].上海:华东理工大学,2011.
[27]胡赣.基于特征组合的中医声诊客观化研究[D].上海:华东理工大学,2014.
[28]董伟,王忆勤,郑荣华,等.100例慢性咽炎患者语音信号的证型特征分析[J].河北中医,2015,37(11):1613-1615,1619.
[29]宋镇贵.基于小波分析的口腔气味病理特征提取与诊断方法研究[D].哈尔滨:哈尔滨工业大学,2010.
[30]林雪娟,郑哲洲,吴青海,等.基于电子鼻的2型糖尿病虚实病性间的气味识别分析[J].中华中医药杂志,2015,30(8):2687-2691.
[31]王忆勤.中医诊断学研究思路与方法[M].上海:上海科学技术出版社,2008:149-371.
[32]王哲,胡随瑜,陈泽奇.简明抑郁症中医证候自评量表初步编制[J].中国行为医学科学,2005,14(10):945.
[33]刘国萍,王忆勤,郭睿,等.中医心系问诊采集系统的研制及评价[J].世界科学技术-中医药现代化,2008,10(5):16-20.
[34]XU Z X,ZHANG N L,WANG Y Q,et al.Statistical Validation of Traditional Chinese Medicine Syndrome Postulates in the Context of Patients with Cardivascular Disease[J]. J Altern Complem Med,2013,18(11):1-6.
[35]LIU G P,YAN J J,WANG Y Q,et al. Application of Multilabel Learning Using the Relevant Feature for Each Label in Chronic Gastritis Syndrome Diagnosis[J]. Evid Based Complement Med,2012,2012:135387.doi:10.1155/2012/135387.
[36]张西洋.穿戴式脉象检测装置及其信号处理的研究[D].上海:华东理工大学,2016.
[37]周侃恒.新型三探头自加压脉象仪的研制[D].上海:华东理工大学,2015.
[38]杨杰,牛欣,司银楚,等.压力与B超整合的中医取脉装置的研究与应用[J].世界科学技术-中医药现代化,2005,7(6):44-46.
[39]中国科学院微电子研究所.中医脉诊传感器、中医脉诊诊疗系统及健康服务平台[P].中国专利:CN105662368A,2016-03-04.
[40]朱一鸣.基于心血管电网络模型的脉象信息仿真分析与识别研究[D].上海:华东理工大学,2013.
[41]郭睿,王忆勤,燕海霞,等.脉图的递归定量分析及对冠心病颈动脉血管硬化程度的评价[J].中华中医药杂志,2016,31(5):1695-1699.
[42]尚倩倩,王忆勤,燕海霞,等.159例原发性高血压合并靶器官损害患者脉图参数分析[J].世界科学技术-中医药现代化,2016,18(6):1033-1039.
[43]魏红,王宇,桂森,等.抑郁症患者中医脉象信息规律性研究[J].辽宁中医药大学学报,2017,19(3):5-9.
[44]LIU G P,LI G Z WANG Y L,et al. Modelling of inquiry diagnosis for coronary heart disease in traditional Chinese medicine by using multi-label learning[J]. BMC Complem Altern Med,2010,10:37.doi:10.1186/1472-6882-10-27.
[45]吴喜庆,陆小左.冠心病中医客观化诊疗评价方法研究[J].辽宁中医杂志,2014,4(8):1574-1583.
[46]吴喜庆,陆小左.慢性乙型肝炎中医客观化诊疗评价方法研究[J].天津中医药大学学报,2014,33(4):199-203.
[47]钱桂凤,潘秋银,郭峥嵘,等.基于数字化四诊合参得到帕金森针刺研究策略[J].中华中医药杂志,2014,29(9):2857-2850.
[48]WANG Y Q,GUO R,YAN H X,et al.Study on Intelligent Sydrome Differentiation in Traditional Chinse Medicine Based on Information Fusion Technology[C]. Hongkong:IEEE International Conference on Bioinformatics&Biomedicine Workshops,2011.
[49] MCCALLUM A K. Multi-label text classification with a mixture model trained by EM[C]. Orlando:Working Notes of the AAAI’99 workshop on Text Learning,1999.
[50]BOUTELL M R,LUO J,SHEN X P,et al. Learning multi-label scene classification[J]. Pattern Recogn, 2004, 37(9):1757-1771.
[51]READ J,PFAHRINGER B,HOLMES G,et al. Classifier chains for multi-label classification[M]. Springer:Lecture Notesin Computer Science,2009:254-269.
[52]ZHANG M L, ZHOU Z H. Multilabel neural networks with applications to functional genomics and text categorization[J].IEEE T Knowl Data En,2006,18(10):1338-1351.
[53] ELISSEEFF A,WESTON J. A kernel method for multi-labelled classification[C]. Cambridge:International Conference on Neural Information,2001:681-687.
[54]ZHANG M L. LIFT:Multi-label learning with label-specific features[C]. Barcelona:Proceedings of the 22nd International Joint Conference on Artificial Intelligence,2011.