Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese Medicine.

Chinese medicine (CM) diagnosis intellectualization is one of the hotspots in the research of CM modernization. The traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues, however, it is difficult to solve the problems such as excessive or similar categories. With the development of natural language processing techniques, text generation technique has become increasingly mature. In this study, we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation issues. The semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory (BILSTM) with Transformer as the backbone network. Meanwhile, the CM diagnosis generation model Knowledge Graph Enhanced Transformer (KGET) was established by introducing the knowledge in medical field to enhance the inferential capability. The KGET model was established based on 566 CM case texts, and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence (LSTM-seq2seq), Bidirectional and Auto-Regression Transformer (BART), and Chinese Pre-trained Unbalanced Transformer (CPT), so as to analyze the model manifestations. Finally, the ablation experiments were performed to explore the influence of the optimized part on the KGET model. The results of Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation 1 (ROUGE1), ROUGE2 and Edit distance of KGET model were 45.85, 73.93, 54.59 and 7.12, respectively in this study. Compared with LSTM-seq2seq, BART and CPT models, the KGET model was higher in BLEU, ROUGE1 and ROUGE2 by 6.00-17.09, 1.65-9.39 and 0.51-17.62, respectively, and lower in Edit distance by 0.47-3.21. The ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model performance. Additionally, the manual assessment indicated that the CM diagnosis results of the KGET model used in this study were highly consistent with the practical diagnosis results. In conclusion, text generation technology can be effectively applied to CM diagnostic modeling. It can effectively avoid the problem of poor diagnostic performance caused by excessive and similar categories in traditional CM diagnostic classification models. CM diagnostic text generation technology has broad application prospects in the future.

Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese Medicine / 中国结合医学杂志

Chinese medicine (CM) diagnosis intellectualization is one of the hotspots in the research of CM modernization. The traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues, however, it is difficult to solve the problems such as excessive or similar categories. With the development of natural language processing techniques, text generation technique has become increasingly mature. In this study, we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation issues. The semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory (BILSTM) with Transformer as the backbone network. Meanwhile, the CM diagnosis generation model Knowledge Graph Enhanced Transformer (KGET) was established by introducing the knowledge in medical field to enhance the inferential capability. The KGET model was established based on 566 CM case texts, and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence (LSTM-seq2seq), Bidirectional and Auto-Regression Transformer (BART), and Chinese Pre-trained Unbalanced Transformer (CPT), so as to analyze the model manifestations. Finally, the ablation experiments were performed to explore the influence of the optimized part on the KGET model. The results of Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation 1 (ROUGE1), ROUGE2 and Edit distance of KGET model were 45.85, 73.93, 54.59 and 7.12, respectively in this study. Compared with LSTM-seq2seq, BART and CPT models, the KGET model was higher in BLEU, ROUGE1 and ROUGE2 by 6.00-17.09, 1.65-9.39 and 0.51-17.62, respectively, and lower in Edit distance by 0.47-3.21. The ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model performance. Additionally, the manual assessment indicated that the CM diagnosis results of the KGET model used in this study were highly consistent with the practical diagnosis results. In conclusion, text generation technology can be effectively applied to CM diagnostic modeling. It can effectively avoid the problem of poor diagnostic performance caused by excessive and similar categories in traditional CM diagnostic classification models. CM diagnostic text generation technology has broad application prospects in the future.

[Analysis of traditional Chinese medicine diagnosis and treatment for erectile dysfunction related to COVID-19 infection].

The incidence of erectile dysfunction (ED) has been reported to increase after COVID-19 infection, and it is common in COVID-19 patients during recovery. This paper presents a summary of the latest research progress on COVID-19-induced ED and explores the traditional Chinese medicine (TCM) diagnosis and treatment approach based on TCM theory and clinical experience. COVID-19 infection may lead to ED through endothelial dysfunction, testicular injury, hormonal imbalance, and psychological factors. The pathogenesis of COVID-19-related ED is mainly characterized by deficiency of the body's essence and excess of pathogenic factors. In the early stage, it is dominated by deficiency of qi and yin, while in the middle stage, it is mainly due to deficiency of qi and blood stasis. In the long-term, ED is based on the imbalance of yin and yang, with liver stagnation and qi stagnation often co-existing. Clinical manifestations of ED vary, and treatment should focus on tonifying qi and nourishing yin, promoting blood circulation, regulating yin and yang, and soothing liver depression according to TCM diagnosis and treatment principles.

Guidelines for Traditional Chinese Medicine Diagnosis and Treatment of Metastatic Colorectal Cancer / 中国实验方剂学杂志

Colorectal cancer is one of the most common malignant tumors of digestive tract. In 2020， 1.93 million new cases of colorectal cancer were diagnosed globally， ranking third in the global incidence spectrum， and 930 000 new deaths were reported， ranking second in the global cause of death spectrum. Meanwhile， the medical cost of metastatic colorectal cancer is the highest among all stages. A large number of studies have demonstrated that traditional Chinese medicine（TCM） treatment can bring clinical benefits to patients with metastatic colorectal cancer with unique efficacy. In order to further standardize the TCM diagnosis and treatment for metastatic colorectal cancer and improve the level of TCM diagnosis and treatment， Xiyuan Hospital， China Academy of Chinese Medical Sciences， together with other relevant units in China， according to the guideline development process of the World Health Organization Handbook for Guideline Development and the relevant requirements of the Clinical Evidence Grading Criteria on TCM Based on Evidence Body， the Regulations for Group Standards of China Association of Chinese Medicine and others， combined with the characteristics of TCM diagnosis and treatment and the actual situation in China， the Guidelines for TCM Diagnosis and Treatment of Metastatic Colorectal Cancer was developed in accordance with the Catalogue of TCM Diagnosis and Treatment Plans for 105 Diseases in 24 Specialties issued by Department of Medical Administration of National Administration of TCM.

Current status and trends in the modernization of pulse diagnosis research: a bibliometric analysis based on CiteSpace and VOSviewer / 数字中医药（英文）

Objective@#To provide ideas for the modernization of pulse diagnosis in traditional Chinese medicine (TCM) by comparing and analyzing the current status and trends of modern research on pulse diagnosis in China and abroad, using bibliometric and visualization software.@*Methods@#Modern research literature on pulse diagnosis was searched in China National Knowledge Infrastructure (CNKI) database from the foundation to May 31, 2023, and in Science Citation Index Expanded (SCIE) from January 1, 2003, to May 31, 2023. After further screening, Microsoft Excel 2019 was used for statistical analysis of publication volume, and CiteSpace (6.1.R6) and VOSviewer (1.6.20) softwares were employed for visual analysis of journals, countries/regions, authors, institutions, keywords, etc.@*Results@#This study included a total of 764 articles in Chinese and 1 459 articles in English. The publication trend of pulse diagnosis research in SCIE database showed an overall fluctuating upward trend, while it exhibited a fluctuating downward trend after 2007 in CNKI database. The volume of English research literature has consistently exceeded that of Chinese literature since 2009. Publications on pulse diagnosis research involved 74 countries/regions. The related journals covered various disciplinary fields, including mathematics, physics, chemistry, and computer science. The most prolific author in CNKI database was WANG Yiqin (Shanghai University of Traditional Chinese Medicine), while the highest number of publications was attributed to ZHANG David (The Hong Kong Polytechnic University) in SCIE database. High-volume institutions in pulse diagnosis research in China and abroad were predominantly TCM research institutions. However, comprehensive universities and other research institutions also made noteworthy contributions. In recent years, hot topics in the modernization of pulse diagnosis research in China included pulse waves, sensors, and artificial intelligence. Foreign research focused on pulse diagnosis systems, sensors, pulse feature extraction, pulse signal analysis, pulse detection, and efficiency of use.@*Conclusion@#Chinese scholars have shown notable participation and emphasis in the modernization research of pulse diagnosis, involving a wide range of disciplinary fields and indicating a characteristic of multidisciplinary cross-fusion development. The hotspots andtrends in the modernization of pulse diagnosis research primarily concentrate on the study of pulse condition and signal acquisition, the integration, development, and optimization of various algorithms with pulse diagnosis equipment, and the practical application research of existing objectified outcomes of pulse diagnosis.

[A novel PPG pulse diagnosis instrument which can be used to assist the application of acupuncture and moxibustion].

For a long time, Chinese medicine has attached great importance to "pulse diagnosis for patients before acupuncture treatment", which emphasizes the close relationship between pulse diagnosis and acupuncture. Pulse diagnosis information is closely related to acupuncture research and runs through the whole process of diagnosis and treatment. However, the lack of repeatable and quantifiable real-time detection means of pulse diagnosis information has affected the application of pulse diagnosis in acupuncture research. Photo plethysmo graphy (PPG) technology has the advantages of convenient acquisition, low price, non-invasive, easy to use and so on. Under the guidance of TCM diagnosis theory, this paper discussed the principle and characteristics of fingertip volumetric pulse wave, studied its relationship with Cunkou pulse diagnosis, developed a new fingertip blood volumetric pulse wave measuring instrument, explored the acquisition and measurement methods of volumetric pulse wave signal, and proposed the relationship between the measuring instrument and acupuncture research. It can provide basic tools and data analysis and support for acupuncture research.

Analysis of Traditional Chinese Medicine Diagnosis and Treatment Strategies for COVID-19 Based on "The Diagnosis and Treatment Program for Coronavirus Disease-2019" from Chinese Authority.

In December 2019, coronavirus disease-2019 (COVID-19) broke out in Wuhan and other places. Seven versions of the Diagnosis and Treatment Program for Coronavirus Disease-2019 successively issued by the Chinese government have designated traditional Chinese medicine (TCM) as a necessary medical strategy. Based on the changes in TCM diagnosis and treatment strategies in these seven versions of Diagnosis and Treatment Program for Coronavirus Disease-2019, this paper collected data reported by the Chinese government media; analyzed the understanding of the etiology, pathogenesis, syndrome differentiation, treatment methods, and prescriptions of COVID-19 by TCM and evaluated the clinical efficacy of TCM strategies. COVID-19 is associated with TCM disease of pestilence, and its pathogenesis can be summarized as an "epidemic pathogen invading the body, followed by entering the internal organs and transforming into heat, resulting in pathogen trapping in the interior and healthy qi collapsing, and deficiency of qi and yin". Pathological processes should be emphasized in syndrome differentiation. The manifestations of qi deficiency and yin deficiency are exhibited during the recovery period. TCM strategies represented by Qing Fei Pai Du Tang have shown apparent advantages in improving symptoms, promoting virus clearance, and shortening hospitalization, as well as surprising efficacy of zero patient progressing from mild to severe cases in a TCM cabin hospital. Clinical data illustrate the effectiveness of TCM strategies proposed by the Chinese government. This major epidemic may bring new opportunities for TCM development.

Effectiveness of Acupuncture on Pain, Functional Disability, and Quality of Life in Rheumatoid Arthritis of the Hand: Results of a Double-Blind Randomized Clinical Trial.

BACKGROUND: Rheumatoid arthritis (RA) is characterized by pain, functional disability, poor quality of life (QoL), high socioeconomic impact, and annual costs of over $56 billion in the United States. Acupuncture (AC) is widely in use; however, studies show severe methodological shortcomings, did not consider the functional diagnosis for the allocation of acupoints and their results showed no differences between verum and control groups. OBJECTIVE: The authors aimed to objectively assess the safety and efficacy of AC treatments for RA. METHODS: 105 RA patients with a functional diagnosis of a "Pivot syndrome" or "Turning Point syndrome" were randomly assigned to (1) verum-AC (verum acupoints), (2) control-AC (sham acupoints-points outside of the conduits/meridians and of the extra-conduits), or (3) waiting list (each group n = 35). AC groups experienced the exact same number, depth, and stimulation of needles. Assessments took place before and 5 min after AC with follow-ups over 4 weeks. RESULTS: (1) Verum-AC significantly improved self-reported pain (Z = -5.099, p < 0.001) and pressure algometry (Z = -5.086, p < 0.001); hand grip strength (Z = -5.086, p < 0.001) and arm strength (Z = -5.086, p < 0.001); health status improved significantly (p < 0.001, Z = -4.895); QoL improved significantly in 7/8 survey domains; and number of swollen joints (Z = -2.862, p = 0.004) and tender joints (Z = -3.986, p < 0.001) significantly decreased. (2) Control-AC showed no significant changes, except in self-reported pain improvement. (3) Waiting list group showed an overall worsening. CONCLUSION: This is the first double-blind controlled study on AC in RA of the hand that objectively and specifically assesses positive effects supporting its integration in rheumatology. Acupoint allocation according to Chinese Medicine functional diagnoses is extremely relevant to assess AC effectiveness in a patient group primarily defined by a "western" medicine diagnosis. Based on clear allocation criteria for acupoints, the authors minimized the possible bias of unspecific and suggestive effects on the control group, showed the specific effects of the points chosen, improved efficacy, and identified an evidence base for AC.

[Evaluation of implementation effect of clinical practice guideline on traditional Chinese medicine therapy alone or combined with antibiotics for acute tonsillitis].

The purpose of this article is to evaluate the clinical effect of clinical practice guideline on traditional Chinese medicine therapy alone or combined with antibiotics for acute tonsillitis. The applicability and application of the Guideline were evaluated based on the clinicians by using the electronic questionnaire. Questionnaires about 538 on application evaluation and 502 questionnaires on applicability evaluation were completed from April 28 to July 9, 2018. The subjects in the questionnaires include the clinicians with junior title, intermediate title, and senior title that have used this Guideline. The descriptive statistical analysis of the collected questionnaire was carried out. In the applicability evaluation, according to the classification of professional titles, the application rate was highest in intermediate title clinicians (26.77%), followed by junior (23.98%) and deputy senior (19.33%) professional title clinicians. In the quality evaluation, the rationality of application scope (98.61%) and the terminology accuracy (98.81%) scores were higher, and the rationality of differentiation and classification (96.05%) was the lowest. The applicability evaluation suggested that clinicians believed this Guideline had high safety (98.42%), reasonable content (98.03%), significant effect (99.6%), reduced use of antibiotics in Western medicine (93.89%), and a high applicability ratio (96.44%). In the application evaluation, Department of lung disease showed the highest application rate (44.24%); rationality of the Guideline was more than 97% in treatment rules and prophylaxis except the syndrome differentiation (92.75%); a high ratio of clinicians believed the recommended scheme was good: curative effect 97.4%, safety 97.59%, and economy 93.87%. The study shows that the clinical practice guideline on traditional Chinese medicine therapy alone or combined with antibiotics for acute tonsillitis is of good quality, high clinical use and good effect. It can be used as a standardized treatment scheme for acute tonsillitis in traditional Chinese medicine. But there are some unsuitable contents and need to be further improved. The Guideline should strengthen the revision on differentiation of symptoms and signs as well as prophylaxis.

Evaluation of implementation effect of clinical practice guideline on traditional Chinese medicine therapy alone or combined with antibiotics for acute tonsillitis / 中国中药杂志

The purpose of this article is to evaluate the clinical effect of clinical practice guideline on traditional Chinese medicine therapy alone or combined with antibiotics for acute tonsillitis. The applicability and application of the Guideline were evaluated based on the clinicians by using the electronic questionnaire. Questionnaires about 538 on application evaluation and 502 questionnaires on applicability evaluation were completed from April 28 to July 9, 2018. The subjects in the questionnaires include the clinicians with junior title, intermediate title, and senior title that have used this Guideline. The descriptive statistical analysis of the collected questionnaire was carried out. In the applicability evaluation, according to the classification of professional titles, the application rate was highest in intermediate title clinicians (26.77%), followed by junior (23.98%) and deputy senior (19.33%) professional title clinicians. In the quality evaluation, the rationality of application scope (98.61%) and the terminology accuracy (98.81%) scores were higher, and the rationality of differentiation and classification (96.05%) was the lowest. The applicability evaluation suggested that clinicians believed this Guideline had high safety (98.42%), reasonable content (98.03%), significant effect (99.6%), reduced use of antibiotics in Western medicine (93.89%), and a high applicability ratio (96.44%). In the application evaluation, Department of lung disease showed the highest application rate (44.24%); rationality of the Guideline was more than 97% in treatment rules and prophylaxis except the syndrome differentiation (92.75%); a high ratio of clinicians believed the recommended scheme was good: curative effect 97.4%, safety 97.59%, and economy 93.87%. The study shows that the clinical practice guideline on traditional Chinese medicine therapy alone or combined with antibiotics for acute tonsillitis is of good quality, high clinical use and good effect. It can be used as a standardized treatment scheme for acute tonsillitis in traditional Chinese medicine. But there are some unsuitable contents and need to be further improved. The Guideline should strengthen the revision on differentiation of symptoms and signs as well as prophylaxis.

Study of TCM clinical records based on LSA and LDA SHTDT model.

Description of syndromes and symptoms in traditional Chinese medicine are extremely complicated. The method utilized to diagnose a patient's syndrome more efficiently is the primary aim of clinical health care workers. In the present study, two models were presented concerning this issue. The first is the latent semantic analysis (LSA)-based semantic classification model, which is employed when the classification and words used to depict these classfications have been confirmed. The second is the symptom-herb-therapies-diagnosis topic (SHTDT), which is employed when the classification has not been confirmed or described. The experimental results showed that this method was successful, and symptoms can be diagnosed to a certain extent. The experimental results indicated that the topic feature reflected patient characteristics and the topic structure was obtained, which was clinically significant. The experimental results showed that when provided with a patient's symptoms, the model can be used to predict the theme and diagnose the disease, and administer appropriate drugs and treatments. Additionally, the SHTDT model prediction results did not yield completely accurate results because this prediction is equivalent to multi-label prediction, whereby the drugs, treatment and diagnosis are considered as labels. In conclusion, diagnosis, and the drug and treatment administered are based on human factors.

Risk factors and clinical features in ischemic stroke patients with different tongue conditions.

OBJECTIVE: To investigate the risk factors and clinical features in ischemic stroke patients with different tongue conditions. METHODS: A total of 168 successive acute ischemic stroke inpatients (within 7 days of stroke onset) were recruited. Patients were assigned to groups according to tongue color (pink, pale, red, purple), tongue coating (no coating, thin coating, thick coating) and sublingual vessel (normal, abnormal). Risk factors and clinical features including National Institutes of Health Stroke Scale (NIHSS), modified Rankin Scale (mRS) and Barthel Index (BI), clinical classification, laboratory data and pulmonary infection complications were compared. RESULTS: There were no significant differences in risk factors and clinical features among groups with different tongue colors. The incidence of smoking (4.5%) was lower in the no coating group compared with the thin (30.0%) and thick (39.3%) coating groups (P<0.017). NIHSS (19.05±10.68) in the no coating group was higher than the thin (6.40±6.18) and thick (7.41±7.05) coating groups (P<0.017), BI (20.91±29.99) was lower than the thin (67.61±28.78) and thick (63.02±33.54) coating groups (P<0.017), and the percentage of mRS >3 (90.9%) was higher than the thin (42.2%) and thick (42.9%) coating groups (P<0.017). The percentage of partial anterior circulation infarction patients in the no coating group was higher than the thin coating group (77.3% vs. 42.2%), and the percentage of lacunar infarction patients was lower than the thin coating group (4.5% vs. 37.8%, P<0.017). NIHSS in the abnormal sublingual vessel group was lower than the normal group (5.28±4.38 vs. 10.57±9.58, P=0.000), and BI was higher than the normal group (67.61±29.29 vs. 54.64±36.23, P=0.015). CONCLUSION: Tongue conditions of acute stroke patients were relevant to clinical features.

Application of Data Mining Technology for Data Analysis of TCM Diagnosis and Treatment / 中国中医药信息杂志

Through several thousand years’ inheritance and development by Chinese people, traditional Chinese medicine (TCM) has formed its unique theoretic system, whose efficacy has been widely accepted. However, because TCM theory focuses on the relationships among syndromes, treatment and efficacy, instead of the cause-and-effect relationship explored by modern natural science, the scientificity of TCM has always been questioned. In recent years, because virtual-world clinical research mode and the concept of “big data” were emphasized, increasing researchers began to put their research emphasis on the correlativity between intervening measures of diseases and outcome indicators. This change and the advancement of computer data mining and analysis technology, bring great opportunities for the further development of TCM theory and practice. This article concluded data mining technology used in TCM diagnosis and treatment in recent years, such as clustering analysis, decision tree, Bayesian network, neural network and multi-instance learning, which showed how to apply these methods to reveal rules of TCM diagnosis and treatment from a large number of TCM syndrome data, find knowledge hidden in data, and show TCM effectiveness supported by data.

Using a questionnaire among patient, resident doctor and senior supervisor: Are their answers the same?

OBJECTIVES: This study aims to contribute to the development of objective diagnostic standards in Traditional Chinese Medicine (TCM), in order to improve the training of physicians. METHODS: We devised a questionnaire study to evaluate the accuracy of resident doctors' diagnostic skills by comparing their assessment of patients with those of their senior supervising physician and the patients themselves. We selected 39 patients with systemic lupus erythematosus (SLE) at Chang Gung Memorial Hospital, Taiwan, between November 1, 2008 and June 30, 2012, and had the resident doctors (R), their senior supervisor (S) and their patients (P) fill out questionnaires before treatment (V1), immediately after treatment (V5) and two months after treatment (V6), in order to record their assessments on the patients' condition. The R and S questionnaires covered subjective symptoms, tongue, and pulse, while the P questionnaires only included general symptoms. We then compared the assessment records to determine the level of agreement between them. RESULTS: The agreements of inquiry during the study for P and S were 0.78 (V1) to 0.84 (V6) and 0.87 (V1) to 0.94 (V6) for R and S, respectively, the agreements between R and S for tongue diagnosis and pulse diagnosis were 0.87 (V1) to 0.90 (V6) and 0.91 (V1) to 0.95 (V6), respectively. All the above agreements improved with time from V1 to V6. CONCLUSIONS: The results show that the patient input was feasible and effective and that the questionnaire method provided an objective assessment standard to determine how successfully the resident doctor was trained. Furthermore, it facilitated a training process that could help resident doctors improve their skills.

Contemporary Chinese pulse diagnosis: a modern interpretation of an ancient and traditional method.

Contemporary Chinese pulse diagnosis™ (CCPD) is a system of pulse diagnosis utilized by Dr. John He Feng Shen, OMD, and documented by Dr. Leon Hammer, MD, in the book Chinese Pulse Diagnosis, A Contemporary Approach. It is the traditional method of the Ding medical lineage from the Shanghai region and dates to the 15th century in Chinese language texts. The fundamentals of this system are, however, much older and can be directly traced to the Neijing Suwen. Having been passed from the last direct inheritor of Ding knowledge (Dr. Shen) to modern practitioners of Chinese medicine by way of Dr. Hammer and his students, it represents an important system of advanced diagnosis. Although modern diagnostic technology provides very sophisticated diagnoses, for these instruments to be effective, the disease process must already have a physical manifestation. CCPD, on the other hand, provides the earliest warnings of physiological processes, which if left unchecked may result in the subsequent appearance of a disease. This article describes the derivation and the principles of this system of pulse diagnosis and explores its successful integration into the modern practice of Chinese medicine.