TLDA: A transfer learning based dual-augmentation strategy for traditional Chinese Medicine syndrome differentiation in rare disease.

The Traditional Chinese Medicine (TCM) has demonstrated its significant medical value over the decades, particularly during the COVID-19 pandemic. TCM-AI interdisciplinary models have been proposed to model TCM knowledge, diagnosis, and treatment experiments in clinical practice. Among them, numerous models have been developed to simulate the syndrome differentiation process of human TCM doctors for automatic syndrome diagnosis. However, these models are designed for normal scenarios and trained using a supervised learning paradigm which needs tens of thousands of training samples. They fail to effectively differentiate syndromes in rare disease scenarios where the available TCM electronic medical records (EMRs) are very limited for each unique syndrome. To address the challenge of rare diseases, this study proposes a simple yet effective method called Transfer Learning based Dual-Augmentation (TLDA). TLDA aims to augment the limited EMRs at both the sample-level and feature-level, enriching the pathological and medical information during training. Extended experiments involving 11 comparison models, including the state-of-the-art model, demonstrate the effectiveness of TLDA. TLDA outperforms all comparison models by a significant margin. Furthermore, TLDA can also be extended to other medical tasks when the EMRs for diagnosis are limited in samples.

Reveal the Patterns of Prescriptions for Recurrent Respiratory Tract Infections' Treatment Based on Multiple Illustrious Senior Traditional Chinese Medicine Practitioners.

Background: Recurrent respiratory tract infections (RRTIs) are one of the most common diseases in children and adolescents. The causes of RRTIs are various. In addition to the factors related to infection, basic diseases such as respiratory system, immune system, and digestive system are also involved. The cost of patients' frequent medical treatment and hospitalization has been deemed to be a heavy burden to the society and family. In China, traditional Chinese medicine (TCM) is commonly used to treat RRTIs. TCM treatment has been appraised to be effective, for reducing the number of hospital stays. Illustrious senior TCM practitioners of pediatrics are recognized as a group of outstanding physicians with significantly better patient outcomes. However, different illustrious senior TCM practitioners can lead to differences in treatment strategies due to factors such as region, prescription theory, and individual differences of patients. This makes it difficult for the experience of illustrious senior TCM practitioners to be popularized. However, there have been no prescription mining studies for the treatment of RRTIs based on different and multiple illustrious senior TCM practitioners. We explored the core prescriptions and drug mechanisms through data mining based on the prescriptions of illustrious senior TCM practitioners treating RRTIs from different clinical settings. This is important to promote the effective treatment of RRTIs with TCM. The objective of this study is to reveal the strategies (core prescriptions) from the prescriptions of multiple illustrious senior TCM practitioners for the treatment of RRTIs. We hope that this core prescription can help all TCM pediatricians to improve RRTIs children's outcome. Meanwhile, it could provide a new way for researchers to study the treatment of RRTIs. Methods: In this study, we prospectively collected 400 children's prescriptions with RRTIs receiving TCM treatment from four illustrious senior TCM practitioners in different hospitals. We described and analyzed the characteristics of TCM prescriptions. The prescription regularity was analyzed by hierarchical clustering and association rules. Network pharmacology methods has been used to reveal the pathway mechanism of core prescriptions which have been mined and visualized with the help of SymMap, Genecards, KEGG, Metascape databases, and R. The execution of all methods was completed in May 2022. Results: According to RRTIs multiple clinical syndromes, five new prescriptions were obtained based on illustrious senior TCM practitioners. Among them, the prescription composed of Scutellariae radix (Huangqin), Armeniacae semen amarum (Kuxingren), Peucedani radix (Qianhu), and Pheretima (Dilong) is the core strategy for the treatment of RRTIs. Cold herbs and heat herbs in the core prescription are approximately equal. Scutellariae radix (Huangqin) was dominant, and other herbs exert synergistic effects. The core prescription covered 76 pathways and 226 herb-disease genes. It promotes the differentiation of Th1, Th2, and Th17 cells and the secretion of inflammatory factors through toll-like receptor signaling pathway in the immune system, T cell receptor signaling pathway, and PPAR signaling pathway in the endocrine system, thereby exerting immune regulation and anti-inflammation. Conclusion: In this study, we revealed the prescription regularity of TCM in the treatment of RRTIs and analyzed the mechanism of core prescriptions, which provided new ideas for the treatment of RRTIs.

Exploring the Core Prescription and Underlying Mechanism of Traditional Chinese Medicine in Treating Allergic Rhinitis in Children: A Real- World Study Based on an Illustrious Senior Traditional Chinese Medicine Practitioner.

BACKGROUND: Traditional Chinese medicine (TCM) is widely used to treat allergic rhinitis (AR) in China, especially in children. However, due to the complicated composition rules and unclear underlying mechanisms, effective herbal prescriptions' popularization and application are limited. PURPOSE: This study tried to detect the core prescription of herbs in treating AR in children, reveal its mechanism based on the ingredients' network, and explore the main signaling pathways. METHODS: We screened medical records of children patients with AR who were treated by TCM in DongZhiMen Hospital from Aug 2009 to Jan 2020 and adopted a descriptive analysis method on herbal characteristics. We used association rules to mine core prescriptions and used network pharmacology to establish the ingredient-target-pathway network through online databases and TCMSP, Genecards, KEGG pathway, Excel, R-Studio, and Cytoscape software. RESULTS: The analysis of 1,092 clinical visits highlighted that the principle of formulating prescription was as follows: 'pungent and warm herbs were used more frequently while cold-natured herbs were paid equal attention as warm-natured herbs.' The core prescription was formed by FangFeng, BaiZhi, CangErzi, and ChanTui. These herbs covered 130 underlying targets and 141 signaling pathways of AR, which mainly had an effect on signal transduction and immunoregulation. CONCLUSION: The core prescription based on these real-world clinical records includes FangFeng, BaiZhi, CangErzi, and ChanTui. It principally acts on targets of signal transduction pathways and immune pathways.

On the Core Prescriptions and Their Mechanisms of Traditional Chinese Medicine in Hepatitis B, Liver Cirrhosis, and Liver Cancer Treatment.

Background: As a frequent cause of death in cancer patients, liver cancer usually occurs in hepatitis B and cirrhosis. In China, Chinese people have been using traditional Chinese medicine (TCM) in treating various chronic liver diseases, which could effectively improve the symptoms and slow down the progression of liver diseases. However, due to the complexity rules of TCM prescription, their action mechanisms are still not clearly understood, which may affect the popularization of effective prescriptions. This study aims to identify the core TCM herbs in the treatment of hepatitis B, liver cirrhosis, and liver cancer so as to clarify the mechanism of action of the core herb networks. Methods: There were 1,673 prescriptions for chronic liver diseases collected in this study, of which 854 were hepatic B prescriptions, 530 were for liver cirrhosis, and 289 were for liver cancer. The basic characteristics of herbal medicine were firstly explained via descriptive analysis, then the core prescriptions of herbal medicine were analyzed through association rule, and finally, the mechanism of core prescriptions was explored with the help of systematic network pharmacology and by applying such databases as TCMIP, HERB, OMIM, GeneCards, KEGG, and software like RStudio and Cytoscape. Results: The rule of the core prescriptions in these cases was characterized by the application of herbs with both cold and warm properties, in which bitter herbs with cold property took priority. Tonifying deficiency, clearing heat, and activating blood circulations to remove stasis were common treatment principles for the three liver diseases. Turmeric Root Tuber (YuJin), White Peony Root (BaiShao), Bupleurum (ChaiHu), Salvia miltiorrhiza (DanShen), and Astragali Radix (HuangQi) were prescribed the most in hepatitis B treatment to invigorate the spleen and soothe the liver. Astragali Radix (HuangQi), Tuckahoe (FuLing), Atractylodis Macrocephalae Rhizoma (BaiZhu), Fructus Polygoni Orientalis (ShuiHongHuaZi), and Curcumae Rhizome (EZhu) were most frequently applied in liver cirrhosis treatment to replenish qi and activate blood. Oldenlandia (BaiHuaSheSheCao), Bearded Scutellaria (BanZhiLian), Curcumae Rhizome (EZhu), and Cardamom (DouKou) were most frequently prescribed to eliminate cancer toxin, invigorate the spleen, and activate blood. These core herbs mainly act through signal transduction and immune system pathways, in which the PI3K-Akt pathway plays a key role. The core prescription for liver cirrhosis regulated more endocrine system pathways than the hepatitis B prescription, and liver cancer prescription regulated more nervous system-related pathways. Conclusion: Three core prescriptions for hepatitis B, liver cirrhosis, and liver cancer treatment were identified, which acted mainly through signal transduction and immune system pathways to regulate immunity and cell growth and participate in inflammation inhibition, in which liver cancer prescription regulated more pathways, especially more nervous system-related pathways than the other two.

A novel transfer learning model for traditional herbal medicine prescription generation from unstructured resources and knowledge.

Traditional Chinese medicine (TCM) is an essential part of the world's traditional medicine. However, there are still many issues in the promotion and development of TCM, such as a lot of unique TCM treatments are taught only between the master and an apprentice in practice, it takes dozens of years for a TCM practitioner to master them and the complicated TCM treatment principles. Intelligent TCM models, as a promising method, can overcome these issues. The performance of previously proposed AI models for intelligent TCM is restricted since they rely on clinical medical records, which are limited, hard to collect, and unavailable for intelligent TCM researchers. In this work, we propose a two-stage transfer learning model to generate TCM prescriptions from a few medical records and TCM documentary resources, called TCMBERT for short. First, the TCMBERT is trained on TCM books. Then, it is fine-tuned on a limited number of medical records to generate TCM prescriptions. The experimental results show that the proposed model outperforms the state-of-the-art methods in all comparison baselines on the TCM prescription generation task. The TCMBERT and the training process can be used in TCM tasks and other medical tasks for dealing with textual resources.

TCMNER and PubMed: A Novel Chinese Character-Level-Based Model and a Dataset for TCM Named Entity Recognition.

Intelligent traditional Chinese medicine (TCM) has become a popular research field by means of prospering of deep learning technology. Important achievements have been made in such representative tasks as automatic diagnosis of TCM syndromes and diseases and generation of TCM herbal prescriptions. However, one unavoidable issue that still hinders its progress is the lack of labeled samples, i.e., the TCM medical records. As an efficient tool, the named entity recognition (NER) models trained on various TCM resources can effectively alleviate this problem and continuously increase the labeled TCM samples. In this work, on the basis of in-depth analysis, we argue that the performance of the TCM named entity recognition model can be better by using the character-level representation and tagging and propose a novel word-character integrated self-attention module. With the help of TCM doctors and experts, we define 5 classes of TCM named entities and construct a comprehensive NER dataset containing the standard content of the publications and the clinical medical records. The experimental results on this dataset demonstrate the effectiveness of the proposed module.

Data Mining and Systematic Pharmacology to Reveal the Mechanisms of Traditional Chinese Medicine in Recurrent Respiratory Tract Infections' Treatment.

Traditional Chinese medicine (TCM) was widely used in the treatment of recurrent respiratory tract infections (RRTIs) in East Asia, but its mechanism was not clear because of its complex prescription rules. This research prospectively collected 100 prescriptions of RRTI children treated with TCM. The characteristics of TCM in prescriptions were described and analyzed, and the rules of prescriptions were analyzed by hierarchical clustering and association rules. The results showed that the principle of RRTI was to pay equal attention to cold and mild, and six new meaningful prescriptions were obtained. Among them, the new prescription composed of Astragali Radix (Huangqi), Atractylodis Macrocephalae Rhizoma (Baizhu), Saposhnikoviae Radix (Fangfeng), Angelicae Sinensis Radix (Danggui), and Paeoniae Radix Rubra (Chishao) was an important method to treat RRTI. In order to explore the mechanism of the new prescription, the research obtained the action target of each herb of the core prescription on Integrative Pharmacology-based Research Platform of Traditional Chinese Medicine, TCMIP v2.0. The target genes were enriched by Metascape, and 93 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways were obtained. According to the classification and statistics of KEGG type, it was found that the new prescription mainly intervened in the metabolic pathway dominated by amino acid metabolism. In addition, there were also many interventions in the nervous system-, endocrine system-, and digestive system-related pathways. This study summarized the prescription rule of TCM in the treatment of RRTI, analyzed the mechanism of supplementing deficiency, and provided a new idea for the treatment of RRTI.

Study on Intervention Mechanism of Yiqi Huayu Jiedu Decoction on ARDS Based on Network Pharmacology.

BACKGROUND: Yiqi Huayu Jiedu (YQHYJD) is a traditional Chinese medicine decoction made up of eight traditional Chinese medicines. Although YQHYJD is effectively used to prevent and treat ARDS/acute lung injury (ALI) in rats, the molecular mechanisms supporting its clinical application remain elusive. The purpose of the current study was to understand its lung protective effects at the molecular level using network pharmacology approach. METHODS: In an ARDS animal model, the beneficial pharmacological activities of YQHYJD were confirmed by reduced lung tissue damage levels observed on drug treated rats versus control group. We then proposed a network analysis to discover the key nodes based on drugs and disease network. Subsequently, we analyzed interaction networks and screened key targets. Using Western blot to detect the expression level of key targets, the intervention effect of changes in expression level of key targets on ARDS was evaluated. RESULTS: Pathway enrichment analysis of highly ranked genes showed that ErbB pathways were highly related to ARDS. Finally, western blot results showed decreased level of the AKT1 and KRAS/NRAS/HRAS protein in the lung after treatment which confirmed the hypothesis. CONCLUSION: In conclusion, our results suggest that YQHYJD can exert lung tissue protective effect against the severe injury through multiple pathways, including the endothelial cells permeability improvement, inflammatory reaction inhibition, edema, and lung tissue hemorrhage reduction.

Study on the Protective Effect of Special Electromagnetic Field Treated Water and Far Infrared Rays on LPS-Induced ARDS Rats.

OBJECTIVE: To explore the protective effect of special electromagnetic field treated water (SEW) and far infrared rays (IFR) on endotoxin (lipopolysaccharide, LPS) induced ARDS rats and the effect on inflammatory factors. METHODS: 40 healthy male SD rats were randomly divided into 4 groups with 10 in each group. Preventive experiment: Adaptive feeding was carried out for 1 week according to animal feeding standards. Rats in SEW group drank SEW daily. Samely, rats in SEW and FIR group also drank SEW daily. Besides, rats in SEW and FIR group were also given far infrared rays for 20min/d. Rats in model group drank distilled water daily. After 7 days, rats in each group were injected with LPS (2 mg/kg) via the tail vein for making models. Rats in blank control group were given distilled water for 7 days, without modeling. All rats in the 4 groups were put to death under anesthesia 16 hours after modeling. Lung tissue and abdominal aortic blood were taken from these rats. RESULTS: Pathological observation of lung and lung tissue indicated that rats in model group showed great pathological difference from rats in blank group. Rats in intervention group showed more symptomatic improvement in relation to alveolar and pulmonary interstitial congestion, edema, and inflammatory cell infiltration than rats in model group. The level of inflammatory factors like IL-1ß and IL-6 in serum of rats in model group increased compared to blank control group (p<0.05). Comparing SEW group and SEW and FIR group with model group, levels of IL-1ß and IL-6 in serum of rats both decreased remarkably (IL-Iß: P < 0.05; IL-6: P < 0.01) while there was no obvious difference between SEW group and SEW and FIR group (p>0.05). The lung coefficient (LI) in SEW and FIR group was significantly lower than that in model group (P<0.01), which was higher than that of blank control group (P < 0.05), while there was no obvious difference between model group and SEW group (P>0.05). Compared with blank control group, lung permeability index (LPI) in model group showed no obvious difference (P>0.05). CONCLUSION: Special electromagnetic field treated water and far infrared rays can alleviate lung tissue damage of endotoxin-induced ARDS rats, relieving symptoms of alveolar and pulmonary interstitial congestion, edema, and inflammatory cell infiltration. The protective effect of special electromagnetic field treated water and far infrared rays on endotoxin-induced acute respiratory distress syndrome may result from their role in reducing the levels of IL-1ß and IL-6 in serum and the expression level of p65 protein in lung tissue, in addition to reliving inflammatory response, lung coefficient, and lungs edema.