Diagnostic value of traditional Chinese medical dialectical classification in hashimoto's thyroiditis complicated with suspicious nodules

Objective:To explore the diagnostic value of traditional Chinese medical(TCM)dialectical classification in Hashimoto's thyroiditis complicated with suspicious nodules.Methods:The clinical data of patients with Hashimoto's thyroiditis complicated with thyroid nodules in the Department of Breast and thyroid surgery of Weifang Hospital of traditional Chinese Medicine from January 2018 to December 2019 were collected.The patients were examined by 2 or more experienced TCM doctors,and the four diagnostic data were obtained,and then the relevant syndrome types of the patients were judged according to the data.According to the color Doppler ultrasonographic features of thyroid nodules,the patients who met the indication of fine needle aspiration biopsy of thyroid nodules were selected and underwent fine needle aspiration biopsy of thyroid nodules before operation.To analyze the clinical diagnostic value of that the ultrasonic mode used in this study and thyroid cytopathology Bethesda report system combine dialectical classification of traditional Chinese medicine in Hashimoto's thyroiditis complicated with suspected thyroid nodules.Result:A total of 89 patients with Hashimoto's thyroiditis complicated with thyroid nodules were collected.according to the ultrasonic mode,the difference between different modes was statistically significant(P<0.05).The mode of color ultrasound is also related to the dialectical classification of traditional Chinese medicine.The patients with high malignant risk score are mainly qi depression and phlegm stagnation,phlegm and blood stasis,while those with low score are exuberant liver fire and heart liver yin deficiency.According to the study of different The Bethesda System for Reporting Thyroid Cytopathology(TBSRTC)classification,the dialectical classification of patients with higher TBSRTC classification was more inclined to qi depression and phlegm stagnation,phlegm and blood stasis,and there was significant difference between different classification(P<0.05).Conclusion:Qi depression and phlegm obstruction,phlegm and blood stasis have high ultrasound malignant risk score and high TBSRTC classification grade in patients with Hashimoto's thyroiditis complicated with suspected thyroid nodules,which has important clinical diagnostic value.

Effects of traditional Chinese medicine nursing combined with conventional nursing in patients with chronic obstructive pulmonary disease:a meta-analysis

Objective: This meta-analysis aims to evaluate the effects of traditional Chinese medicine(TCM) nursing combined with conventional nursing in patients with chronic obstructive pulmonary disease(COPD).Methods: Data were collected from the databases of PubMed, Embase, the Cochrane Library, Web of Science, Google Scholar,China National Knowledge Infrastructure(CNKI), WanFang Data(WF) and VIP Database, including literature regarding the effects of TCM nursing combined with conventional nursing in patients with COPD published before January 2017. The Jadad scale was used to assess the quality of the eligible literature. The weighted mean differences and odds ratios were used to analyze St. George's Respiratory Questionnaire(SGRQ) scores, pulmonary function, hospital stay, and clinical efficacy.Results: Twenty-three randomized controlled trials comprising 3116 cases(TCM nursing combined with the conventional nursing group: 1559; conventional nursing group: 1557) met the inclusion criteria. TCM nursing combined with conventional nursing was associated with a lower SGRQ score, higher forced expiratory volume in 1 second(FEV1) value, higher FEV1/forced vital capacity(FVC) value, higher FEV1% value, higher FEV1 predicted value, shorter hospital stay, and preferable clinical efficacy.Conclusions: TCM nursing combined with conventional nursing emphasized that dialectical nursing can be performed preferably in patients with COPD.

The theory development of traditional Chinese medicine constitution: a review

Traditional Chinese medicine constitution (TCMC),as one of the most important parts of Chinese medicine theory,attracted the attention of more and more researchers and many research projects were conducted during past several decades in China's Mainland.This review provided a historic overview of TCMC theory and research progress in its classification,evaluation criteria and epidemiology,so as to give people through a different lens to understand human health.

Detection of consensuses and treatment principles of diabetic nephropathy in traditional Chinese medicine: A new approach

Objective:To propose and test a new approach based on community detection in the field of social computing for uncovering consensuses and treatment principles in traditional Chinese medicine(TCM).Methods:Three Chinese databases(CNKI,VIP,andWan Fang Data)were searched for published articles on TCM treatment of diabetic nephropathy(DN)from their inception until September 31,2014.Zheng classification and herbdatawereextractedfromincluded articlesand usedto construct a Zheng classification and treatment of diabetic nephropathy(DNZCT)network with nodes denoting Zhengs and herbs and edges denoting corresponding treating relationshipsamong them.Community detection was applied to the DNZCT and detected community structures were analyzed.Results:A network of 201 nodes and 743 edges were constructed and six communities were detected.Nodes clustered in the samecommunity captured the samesemantic topic;different communities had unique characteristics,and indicated different treatment principles.Large communities usually represented similar points of view or consensuses on common Zheng diagnoses and herb prescriptions;small communities might help to indicate unusual Zhengs and herbs.Conclusion:The results suggest that the community detection-based approach is useful and feasible for uncovering consensuses and treatment principles of DN treatment in TCM,and could be used to address other similar problems in TCM.

Relationship between symptoms of traditional Chinese medicine and indicator of western medicine about liver cirrhosis

Traditional Chinese medicine (TCM) is one of the safe and effective methods to treat liver cir-rhosis. The practitioners of TCM assess hepatic function in term of syndrome. But the course of syndrome differentiation is subjectivity. At pre-sent most of all the researches are focused on the relationship between the syndrome and the Western medicine objective indicators such as child-pugh grade. In fact syndrome is the syn-thesis of signs and symptoms and collecting signs, symptoms is easy than syndrome differ-entiation. We try to explore the relationship be-tween the objective Western medicine standard such as child-pugh grade, decompensation or compensation stage, active or inactive period and the signs and symptoms of TCM by using the data mining method. We use the information gain method to assess the attributes and use five typical classifiers such as logistic, Bayes-Net, NaiveBayes, RBF and C4.5 to obtain the classification accuracy. After attribute selection, we obtain the main symptoms and signs of TCM relating to the stage, period and child-pugh grade about liver cirrhosis. The experiment re-sults show the classification accuracy is im-proved after filtering some symptoms and signs.

Visualization analysis of the international standard ISO/TC 249 for traditional Chinese medicine

Objective This study proposes to visually review the current situation and progress of standards sets by the International Organization for Standardization/Technical Committee on Traditional Chinese Medicine(ISO/TC 249). The review aims to explore the development strategies of the standards, which will exhibit the considerable impact on the economy, trade and exchanges, and cooperation in the area of traditional Chinese medicine(TCM).Methods ISO/TC 249 standards were searched on the ISO website, and their title, proposed time, current stage, scope, and classification were obtained for further summarization. Gephi was utilized to portray the co-occurrence network graph of the ISO/TC 249 standards subject.Results In ISO/TC 249, there were 116 standards, including 81 published standards and 35 developing standards by April 30, 2022. Two withdrawal standards were published after revision, which were not counted in the total standards. The number of published standards has been increasing since the first standard was published in 2014, whose title was “Sterile acupuncture needles for single use”. Among these standards, 17.24%(20/116) standards were in review, 56.03%(65/116) in publication, 3.45%(4/116) in approval, 5.17%(6/116) in enquiry,3.45%(4/116) in committee, and 14.66%(17/116) in preparation, respectively. With 116 standards, most of the research focused on the medicament, as its classification of the International Classification for Standards(ICS) showed the proportion reaching 49.54%. The network analysis data revealed that the top five most frequent words were “materials” “root” “requirements” “products” and “system”, after removing the noise data, such as prepositions,conjunctions, and pronouns. Additionally, the word “system” co-exists with the terms “computerized” “coding” “image” “tongue” and “analysis”;the word “requirement” co-exists with“manufacturing” “decoction” “process” and “materials”;whereas the word “devices” coexists with “pulse” “electric” “skin” and “measurement”.Conclusion With the increased diversification and complexity of problems, the development of standards is also oriented to multidisciplinary fields to cultivate the interdisciplinary talents, and especially the international standardization talents of compound TCM. Multi-angle analysis, formulation, and demonstration of standards, in line with industry needs in different disciplines, enhance the availability of standards and the ability to serve the industry.

Research Progress of Treating Diabetic Nephropathy with Traditional Chinese Medicine

By collecting and sorting out the literature and journals on the clinical use of Chinese medicine in the treatment of diabetic nephropathy in recent years,it is concluded that Chinese medicine is effective in the treatment of DKD.Chinese medicine therapy has a unique role in the treatment of diabetic nephropathy.How to correct syndrome differentiation and treatment?Improving clinical effects is the research direction that all medical staff will work together in the future.

Traditional Chinese Herbal Medicine for Epilepsy Treatment Should Be Administered According to the Seizure Type and Epileptic Syndrome

Traditional Chinese herbal medicine (TCHM) has long been used to treat epilepsy. Although many clinical trials and animal studies have seemingly demonstrated its effect, the question of whether TCHM is efficacious in epileptic patients has not been certified because of insufficient supportive evidence. This insufficient supportive evidence stems from the fact that most of the current studies regarding TCHM for epilepsy treatment are not designed according to the different seizure types and epileptic syndromes (STESs). Here, we explore the reasons why many studies have not considered the various STESs and explain how to treat epilepsy according to the pharmacological mechanism for different STESs and exploit the advantage of TCHM for epilepsy treatment. Then, we explain how we treat epilepsy using TCHM according to the different STESs and Bian Zheng Lun Zi.

Construction and optimization of traditional Chinese medicine constitution prediction models based on deep learning

Objective To cater to the demands for personalized health services from a deep learning per-spective by investigating the characteristics of traditional Chinese medicine(TCM)constitu-tion data and constructing models to explore new prediction methods.Methods Data from students at Chengdu University of Traditional Chinese Medicine were collected and organized according to the 24 solar terms from January 21,2020,to April 6,2022.The data were used to identify nine TCM constitutions,including balanced constitution,Qi deficiency constitution,Yang deficiency constitution,Yin deficiency constitution,phlegm dampness constitution,damp heat constitution,stagnant blood constitution,Qi stagnation constitution,and specific-inherited predisposition constitution.Deep learning algorithms were employed to construct multi-layer perceptron(MLP),long short-term memory(LSTM),and deep belief network(DBN)models for the prediction of TCM constitutions based on the nine constitution types.To optimize these TCM constitution prediction models,this study in-troduced the attention mechanism(AM),grey wolf optimizer(GWO),and particle swarm op-timization(PSO).The models’performance was evaluated before and after optimization us-ing the F1-score,accuracy,precision,and recall.Results The research analyzed a total of 31655 pieces of data.(i)Before optimization,the MLP model achieved more than 90%prediction accuracy for all constitution types except the balanced and Qi deficiency constitutions.The LSTM model's prediction accuracies exceeded 60%,indicating that their potential in TCM constitutional prediction may not have been fully realized due to the absence of pronounced temporal features in the data.Regarding the DBN model,the binary classification analysis showed that,apart from slightly underperforming in predicting the Qi deficiency constitution and damp heat constitution,with accuracies of 65%and 60%,respectively.The DBN model demonstrated considerable discriminative power for other constitution types,achieving prediction accuracy rates and area under the receiver op-erating characteristic(ROC)curve(AUC)values exceeding 70%and 0.78,respectively.This indicates that while the model possesses a certain level of constitutional differentiation abili-ty,it encounters limitations in processing specific constitutional features,leaving room for further improvement in its performance.For multi-class classification problem,the DBN model’s prediction accuracy rate fell short of 50%.(ii)After optimization,the LSTM model,enhanced with the AM,typically achieved a prediction accuracy rate above 75%,with lower performance for the Qi deficiency constitution,stagnant blood constitution,and Qi stagna-tion constitution.The GWO-optimized DBN model for multi-class classification showed an increased prediction accuracy rate of 56%,while the PSO-optimized model had a decreased accuracy rate to 37%.The GWO-PSO-DBN model,optimized with both algorithms,demon-strated an improved prediction accuracy rate of 54%.Conclusion This study constructed MLP,LSTM,and DBN models for predicting TCM consti-tution and improved them based on different optimisation algorithms.The results showed that the MLP model performs well,the LSTM and DBN models were effective in prediction but with certain limitations.This study also provided a new technology reference for the es-tablishment and optimisation strategies of TCM constitution prediction models,and a novel idea for the treatment of non-disease.

Ophthalmic Syndrome Differentiation System and Digital Chinese Medicine

In traditional Chinese medicine(TCM),ophthalmic syndrome differentiation is an ophthalmology-specific method for identifying syndromes based on the“Five Orbiculi”theory.It was devised by Professor Qing-Hua PENG through an unprecedented combination of syndrome element differentiation and ophthalmic clinical practices,based on the Clinical Terminology of Chinese Medical Diagnosis and Treatment-Syndromes of the National Standards of the People's Republic of China.This approach integrates an ophthalmic syndrome differentiation system with digital Chinese medicine(DCM),and proposes the extraction of syndrome elements of ophthalmic diseases from research on DCM.These elements are then quantified and organized to form a model of digital diagnosis and treatment specific to ophthalmology,which should help to achieve synergistic development of the ophthalmic syndrome differentiation system and DCM.

Consensus on the integrated traditional Chinese and Western medicine criteria of diagnostic classification in polycystic ovary syndrome(draft)

Polycystic ovary syndrome （PCOS） is the most common endocrine and metabolic disorder of women, with complex pathogenesis and heterogeneous manifestations. Professor Jin Yu recently wrote an article entitled ＂Proposal of Diagnosis and Diagnostic Classification of PCOS in Integrated Traditional Chinese and Western Medicine.＂ From this, the Obstetrics and Gynecology branches of the Chinese Association of Integrative Medicine and the China Association of Chinese Medicine collaborated with the Gynecology branch of the Chinese Association for Research and Advancement of Chinese Medicine to draft a report on the consensus of criteria for the diagnosis and classification of PCOS in integrated traditional Chinese and Western medicine. The diagnosis for PCOS includes all three features： （1） oligo-ovulation or anovulation; （2） clinical and/or laboratory evidence of hyperandrogenism; （3） PCOS is classified into four types： types la, Ib, Ila, and lib. Syndrome differentiation types for PCOS in traditional Chinese medicine are as follows： Kidney deficiency with phlegm blockage syndrome, Kidney Yin deficiency with phlegm blockage and blood stasis syndrome, and Kidney deficiency with Liver Qi stagnation syndrome.

Classification of interventions in Traditional Chinese Medicine

OBJECTIVE: To describe the key systems used for Traditional Chinese Medicine(TCM) classification.METHODS: The TCM classifications used in the International Classification of Diseases-9 Clinical Modification(ICD-9-CM) volume 3, the ICD-10 Procedure Coding System, the International Classification of Health Interventions, and the Medical Subject Headings(Me SH) and Chinese Traditional Medicine and Materia Medica Subject Headings(TCMe SH) thesauruses were compared regarding descriptive terms, structure, and features of TCM interventions.RESULTS: The National Library of Medicine's Me SH thesaurus is ubiquitous. The ICD-9-CM(volume 3),ICD-10 Procedure Coding System, and International Classification of Health Interventions cover insufficient concepts of TCM, and cannot be used directly as classification systems for TCM interventions. In contrast, the TCM contents of the TCMe SH thesaurus are complete, systematic, and detailed, and its hierarchical structure can be used for effective TCM classification.CONCLUSION: TCM classification is very limited and flawed. The Me SH thesaurus helps decrease the detrimental effect of the language barrier. Similarly, the TCMe SH thesaurus can help those without full command of the Mandarin language to access Chinese literature, but the value of searches using TCMe SH could be improved by collaborative working with Information Specialists who are fluent in Mandarin and understand TCM.

Polymorphisms in PPARD,PPARG and APM1 associated with four types of Traditional Chinese Medicine constitutions

Based on the theory of constitution of Traditional Chinese Medicine （TCM）, the human population is divided into nine constitutions including one balanced constitution （Normality） and eight unbalanced constitutions （Yang-deficiency, Yin-deficiency, Phlegm-wetness, Qi-deficiency, Wetness-heat, Blood stasis, Depressed constitution, and Inherited special constitution）. Different constitutions have specific metabolic features and different susceptibility to certain diseases. However, whether a genetic basis accounts for such constitution classification is yet to be determined. Here we performed a genetic study to assess the association between genetic variations of metabolic genes including PPARD, PPARG and APM1 and the constitutions. A total of 233 individuals of the Han population in China were classified into four groups, Normality, Yang-deficiency, Yin-deficiency and Phlegm-wetness with whom 23 single nucleotide polymorphisms （SNPs） in the three genes were genotyped using polymerase chain reaction-restriction fragment length polymorphism （PCR-RFLP） method. Biased distribution of PPARD rs2267669 and rs2076167, APM1 rs7627128 and rs1063539 in Yang-deficiency, PPARG Prol2Ala in Yin-deficiency and PPARD rs2076167, APMI rs266729 and rs7627128 in Phlegm-wetness were observed. The frequencies of Haplotypel3 （Hapl3） of PPARG in Yin-deficiency, Hap25 of APM1 in Yang-deficiency and Hap2 of PPARD and Hapl4 of PPARG in Phlegm-wetness, were significantly different from those in Normality, suggesting those might be group-associated haplotypes. These results suggested that single SNP and haplotypes ofPPARD, PPARG and APM1 may underlie the genetic basis of the constitutions classified in TCM.

A data-driven method for syndrome type identification and classification in traditional Chinese medicine

The efficacy of traditional Chinese medicine （TCM） treatments for Western medicine （WM） diseases relies heavily on the proper classification of patients into TCM syndrome types. The authors developed a data-driven method for solving the classification problem, where syndrome types were identified and quantified based on statistical patterns detected in unlabeled symptom survey data. The new method is a generalization of latent class analysis （LCA）, which has been widely applied in WM research to solve a similar problem, i.e., to identify subtypes of a patient population in the absence of a gold standard. A well-known weakness of LCA is that it makes an unrealistically strong independence assumption. The authors relaxed the assumption by first detecting symptom co-occurrence patterns from survey data and used those statistical patterns instead of the symptoms as features for LCA. This new method consists of six steps： data collection, symptom co-occurrence pattern discovery, statistical pattern interpretation, syndrome identification, syndrome type identification and syndrome type classification. A software package called Lantern has been developed to support the application of the method. The method was illustrated using a data set on vascular mild cognitive impairment.

Bridging the Traditional Chinese Medicine Pattern Classification and Biomedical Disease Diagnosis with Systems Biology

Being the unique core of traditional Chinese medicine （TCM）, pattern classification exerts a direct effect on the efficacy and safety of herbal interventions. In this article, the authors integrated the pattern classification and disease diagnosis with many approaches from systems biology, integration of pattern classification with biomedical diagnosis by systems biology is not only a new direction of personalized medicine development, but also provides a new drug development model. In the further study, the pattern classifications of major diseases will be the focus of research.

Formulation and consideration of World Health Organization international classification of traditional medicine

In the 11th revision of the International Classification of Diseases(ICD),the World Health Organization included traditional medicine disorders and patterns originated from ancient Chinese medicine that are commonly used in China,Japan,Korea and elsewhere around the world.For the first time,a chapter on traditional medicine was incorporated,which has completely changed the status quo on the lack of information on traditional medicine and health statistics in the ICD.In this study,we systematically analyzed the background,structure,content and characteristics of the Traditional Medicine chapter,with focus on its positive effects on promoting the development and utilization of Traditional Chinese Medicine worldwide.

Expression profiling-based clustering of healthy subjects recapitulates classifications defined by clinical observation in Chinese medicine

Differences between healthy subjects and associated disease risks are of substantial interest in clinical medicine. Based on clinical presentations, Traditional Chinese Medicine （TCM） classifies healthy people into nine constitutions： Balanced, Qi, Yang or Yin deficiency, Phlegm-dampness, Damp-heat, Blood stasis, Qi stagnation, and Inherited special constitutions. In particular, Yang and Yin deficiency constitutions exhibit cold and heat aversion, respectively. However, the intrinsic molecular characteristics of unbal- anced phenotypes remain unclear. To determine whether gene expression-based clustering can reca- pitulate TCM-based classification, peripheral blood mononudear cells （PBMCs） were collected from Chinese Han individuals with Yang/Yin deficiency （n = 12 each） and Balanced （n = 8） constitutions, and global gene expression profiles were determined using the Affymetrix HC-UI33A Plus 2.0 array. Notably, we found that gene expression-based classifications reflected distinct TCM-based subtypes. Consistent with the clinical observation that subjects with Yang deficiency tend toward obesity, series-clustering analysis detected several key lipid metabolic genes （diacylglycerol acyltransferase （DGAT2）, acyl-CoA synthetase （ACSL1）, and ATP-hinding cassette subfamily A member 1 （ABCAI）） to be down- and up- regulated in Yin and Yang deficiency constitutions, respectively. Our findings suggest that Yin]Yang deficiency and Balanced constitutions are unique entities in their mRNA expression profiles. Moreover, the distinct physical and clinical characteristics of each unbalanced constitution can be explained, in part, by specific gene expression signatures.

Discrimination of TCM constitutions by biochemical and routine urine indexes

Objective:To investigate whether the specific traditional Chinese medicine(TCM)constitution of individuals can be defined by certain biological indexes instead of answering the questionnaire,and to explore the possibility of discriminating nine TCM constitutions from each other simultaneously using biological indexes.Methods:Blood and urine samples from 152 individuals with nine TCM constitutions were collected,and the related biological indexes were analyzed combining ANOVA,multiple comparison,discriminant analysis,and support vector machine.Results:We found that 4 out of 24 blood routine indexes,7 out of 10 urine routine indexes,and 12 out of 32 biochemical indexes showed differences among the constitutions.High-sensitivity C-reactive protein,apolipoprotein A1,and alkaline phosphatase were potential candidates for screening out individuals with unbalanced constitutions.Combining uric acid,high-density lipoprotein,apolipoprotein A1,creatine kinase,total protein,aspartate aminotransferase,total bile acid,dehydrogenase,sodium,and calcium levels had the potential to directly distinguish the nine TCM constitutions from each other.Among these indexes,the highest ratio of discriminant analysis between two constitutions was 95.5%,while the lowest was 66.1%.Conclusion:Our results suggest that some biochemical and urine indexes are related to various TCM constitutions,and thus they have the potential to be used for TCM constitution classification.

老年初治肺结核中医证型与细胞因子及免疫表达的相关性分析

目的 观察老年初治肺结核患者血清中细胞因子及TB淋巴细胞亚群的表达水平,探究中医证型与细胞因子、TB淋巴细胞表达之间的关系。方法 纳入2016年5月至2021年12月解放军总医院第八医学中心结核医学部收治的初治老年肺结核病患者322例作为研究对象,根据辨证分型分为肺阴亏虚组78例、阴虚火旺组83例、气阴两虚组79例、阴阳两虚组82例。采用酶联免疫吸附试验检测血清中γ干扰素(IFN-γ)、肿瘤坏死因子α(TNF-α)、白细胞介素1β(IL-1β)、IL-5、IL-2、IL-6、IL-8、IL-17、IL-4、IL-10等细胞因子的表达水平,流式细胞仪测定TB淋巴细胞亚群中CD3^(+)、CD4^(+)、CD8^(+)、B细胞、NK细胞的绝对数及CD4^(+)/CD8^(+)T细胞比值,并将测定结果进行统计学分析。结果 四组肺结核患者IL-β、IL-5、IL-2、IL-17、IL-4、IL-10水平差异无统计学意义(P>0.05)。气阴两虚组IFN-γ水平显著高于其他三组(P<0.05);阴阳两虚组TNF-α水平显著高于其他三组(P<0.05);阴阳两虚组、气阴两虚组、阴虚火旺组、肺阴亏虚组的IL-6水平依次降低(P<0.05);阴阳两虚组IL-8水平显著高于其他三组,气阴两虚组高于肺阴亏虚组、阴虚火旺组(P<0.05)。CD3^(+)、CD4^(+)、CD8^(+)、B细胞、NK细胞绝对数在阴阳两虚组、气阴两虚组、阴虚火旺组、肺阴亏虚组依次降低,差异均有统计学意义(P<0.05)。阴阳两虚组CD4^(+)/CD8^(+)T细胞比值显著高于其他三组,肺阴亏虚组、阴虚火旺组、气阴两虚组组间比较差异无统计学意义(P>0.05)。结论 不同证型的老年肺结核病患者细胞因子及免疫细胞表达存在差异性,可作为中医辨证论治的客观参考标准之一,为临床辨证治疗提供一定参考。

基于双阶段元学习的小样本中医舌色域自适应分类方法

舌色是中医(TCM)望诊最关注的诊察特征之一。在实际应用中,通过一台设备采集到的舌象数据训练得到的舌色分类模型应用于另一台设备时,由于舌象数据分布特性不一致,分类性能往往急剧下降。为此,该文提出一种基于双阶段元学习的小样本中医舌色域自适应分类方法。首先,设计了一种双阶段元学习训练策略,从源域有标注样本中提取域不变特征,并利用目标域的少量有标注数据对网络模型进行微调,使得模型可以快速适应目标域的新样本特性,提高舌色分类模型的泛化能力并克服过拟合。接下来,提出了一种渐进高质量伪标签生成方法,利用训练好的模型对目标域的未标注样本进行预测,从中挑选出置信度高的预测结果作为伪标签,逐步生成高质量的伪标签。最后,利用这些高质量的伪标签,结合目标域的有标注数据对模型进行训练,得到舌色分类模型。考虑到伪标签中含有噪声问题,采用了对比正则化函数,可以有效抑制噪声样本在训练过程中产生的负面影响,提升目标域舌色分类准确率。在两个自建中医舌色分类数据集上的实验结果表明,在目标域仅提供20张有标注样本的情况下,舌色分类准确率达到了91.3%,与目标域有监督的分类性能仅差2.05%。