An Improved Deep Learning Model: S-TextBLCNN for Traditional Chinese Medicine Formula Classification

Classification method of traditional Chinese medicine compound decoction duration based on multi-dimensional feature weighted fusion

This paper extends a text classification method utilizing natural language processing (NLP) into the field of traditional Chinese medicine (TCM) compound decoction to effectively and scientifically extend the TCM compound decoction duration. Specifically, a TCM compound decoction duration classification named TCM-TextCNN is proposed to fuse multi-dimensional herb features and improve TextCNN. Indeed, first, we utilize word vector technology to construct feature vectors of herb names and medicinal parts, aiming to describe the herb characteristics comprehensively. Second, considering the impact of different herb features on the decoction duration, we use an improved Term Frequency-Inverse Word Frequency (TF-IWF) algorithm to weigh the feature vectors of herb names and medicinal parts. These weighted feature vectors are then concatenated to obtain a multi-dimensional herb feature vector, allowing for a more comprehensive representation. Finally, the feature vector is input into the improved TextCNN, which uses k-max pooling to reduce information loss rather than max pooling. Three fully connected layers are added to generate higher-level feature representations, followed by softmax to obtain the final results. Experimental results on a dataset of TCM compound decoction duration demonstrate that TCM-TextCNN improves accuracy, recall, and F1 score by 5.31%, 5.63%, and 5.22%, respectively, compared to methods solely rely on herb name features, thereby confirming our method's effectiveness in classifying TCM compound decoction duration.

Application of Data Fusion in Traditional Chinese Medicine: A Review

Traditional Chinese medicine is characterized by numerous chemical constituents, complex components, and unpredictable interactions among constituents. Therefore, a single analytical technique is usually unable to obtain comprehensive chemical information. Data fusion is an information processing technology that can improve the accuracy of test results by fusing data from multiple devices, which has a broad application prospect by utilizing chemometrics methods, adopting low-level, mid-level, and high-level data fusion techniques, and establishing final classification or prediction models. This paper summarizes the current status of the application of data fusion strategies based on spectroscopy, mass spectrometry, chromatography, and sensor technologies in traditional Chinese medicine (TCM) in light of the latest research progress of data fusion technology at home and abroad. It also gives an outlook on the development of data fusion technology in TCM analysis to provide references for the research and development of TCM.

Multiple prescription pattern recognition model based on Siamese network

Prescription data is an important focus and breakthrough in the study of clinical treatment rules, and the complex multidimensional relationships between Traditional Chinese medicine (TCM) prescription data increase the difficulty of extracting knowledge from clinical data. This paper proposes a complex prescription recognition algorithm (MTCMC) based on the classification and matching of TCM prescriptions with classical prescriptions to identify the classical prescriptions contained in the prescriptions and provide a reference for mining TCM knowledge. The MTCMC algorithm first calculates the importance level of each drug in the complex prescriptions and determines the core prescription combinations of patients through the Analytic Hierarchy Process (AHP) combined with drug dosage. Secondly, a drug attribute tagging strategy was used to quantify the functional features of each drug in the core prescriptions; finally, a Bidirectional Long Short-Term Memory Network (BiLSTM) was used to extract the relational features of the core prescriptions, and a vector representation similarity matrix was constructed in combination with the Siamese network framework to calculate the similarity between the core prescriptions and the classical prescriptions. The experimental results show that the accuracy and F1 score of the prescription matching dataset constructed based on this paper reach 94.45% and 94.34% respectively, which is a significant improvement compared with the models of existing methods.

Bioinformatics-based and multiscale convolutional neural network screening of herbal medicines for improving the prognosis of liver cancer: a novel approach

Background

Liver cancer is one of the major diseases threatening human life and health, and this study aims to explore new methods for treating liver cancer.

Methods

A deep learning model for the efficacy of clinical herbal medicines for liver cancer was constructed based on NDCNN, combined with the natural evolutionary rules of a genetic algorithm to obtain the herbal compound for liver cancer treatment. We obtained differential genes between liver cancer tissues and normal tissues from the analysis of TCGA database, screened the active ingredients and corresponding targets of the herbal compound using the TCMSP database, mapped the intersection to obtain the potential targets of the herbal compound for liver cancer treatment in the Venny platform, constructed a PPI network, and conducted GO analysis and KEGG analysis on the targets of the herbal compound for liver cancer treatment. Finally, the key active ingredients and important targets were molecularly docked.

Results

The accuracy of the NDCNN training set was 0.92, and the accuracy of the test set was 0.84. After combining with the genetic algorithm for 1,000 iterations, a set of Chinese herbal compound prescriptions was finally the output. A total of 86 targets of the herbal compound for liver cancer were obtained, mainly five core targets of IL-6, ESR1, JUN, IL1β, and MMP9. Among them, quercetin, kaempferol, and stigmasterol may be the key active ingredients in hepatocellular carcinoma, and the herbal compound may be participating in an inflammatory response and the immune regulation process by mediating the IL-17 signaling pathway, the TNF signaling pathway, and so on. The anticancer effects of the herbal compound may be mediated by the IL-17 signaling pathway, the TNF signaling pathway, and other signaling pathways involved in inflammatory response and immune regulation. Molecular docking showed that the three core target proteins produced stable binding to the two main active ingredients.

Conclusion

The screening of effective herbal compounds for the clinical treatment of liver cancer based on NDCNN and genetic algorithms is a feasible approach and will provide ideas for the development of herbal medicines for the treatment of liver cancer and other cancers.

Prediction and Diagnosis of Respiratory Disease by Combining Convolutional Neural Network and Bi-directional Long Short-Term Memory Methods

Objective

Based on the respiratory disease big data platform in southern Xinjiang, we established a model that predicted and diagnosed chronic obstructive pulmonary disease, bronchiectasis, pulmonary embolism and pulmonary tuberculosis, and provided assistance for primary physicians.

Methods

The method combined convolutional neural network (CNN) and long-short-term memory network (LSTM) for prediction and diagnosis of respiratory diseases. We collected the medical records of inpatients in the respiratory department, including: chief complaint, history of present illness, and chest computed tomography. Pre-processing of clinical records with “jieba” word segmentation module, and the Bidirectional Encoder Representation from Transformers (BERT) model was used to perform word vectorization on the text. The partial and total information of the fused feature set was encoded by convolutional layers, while LSTM layers decoded the encoded information.

Results

The precisions of traditional machine-learning, deep-learning methods and our proposed method were 0.6, 0.81, 0.89, and F1 scores were 0.6, 0.81, 0.88, respectively.

Conclusion

Compared with traditional machine learning and deep-learning methods that our proposed method had a significantly higher performance, and provided precise identification of respiratory disease.