Rough set theory is a powerful tool to deal with incomplete information system, which can be applied to prescription data analysis. In this paper, we suggested an improved rough set model called WVP-T model. The model combined the variable precision model with the tolerance relation model. It can overcome the shortcoming of classical model. Furthermore, attribute importance and entropy of information were combined as heuristic information. Medicine was mapped to rough set attribute in order to value its importance. Then, combined with curative effect, attribute reduction was used to investigate the relationship between prescription and medicine and the relationship between symptom and syndrome. The experimental results showed that algorithm proposed in this paper can be used in prescription data analysis and can accurately reveal the compatibility rules to guide the clinical medication.

Methods: First, this paper establishes a dataset of abnormal morphology for Chinese medicine diagnosis, with images from public resources and labeled with category labels by several Chinese medicine experts, including three categories: normal, shoulder abnormality, and leg abnormality. Second, the key points of human body are extracted by Light-Atten-Pose algorithm. Light-Atten-Pose algorithm uses lightweight EfficientNet network and polarized self-attention (PSA) mechanism on the basis of AlphaPose, which reduces the computation amount by using EfficientNet network, and the data is finely processed by using PSA mechanism in spatial and channel dimensions. Finally, according to the theory of TCM inspection, the abnormal morphology standard based on the joint angle difference is defined, and the classification of abnormal morphology of Chinese medical diagnosis is realized by calculating the angle between key points. Accuracy, frames per second (FPS), model size, parameter set (Params), and giga floating-point operations per second (GFLOPs) are chosen as the evaluation indexes for lightweighting. Results: Validation of the Light-Atten-Pose algorithm on the dataset showed a classification accuracy of 96.23%, which is close to the original AlphaPose model. However, the FPS of the improved model reaches 41.6 fps from 16.5 fps, the model size is reduced from 155.11 MB to 33.67 MB, the Params decreases from 40.5 M to 8.6 M, and the GFLOPs reduces from 11.93 to 2.10. Conclusion The Light-Atten-Pose algorithm achieves lightweight while maintaining high robustness, resulting in lower complexity and resource consumption and higher classification accuracy, and the experiments prove that the Light-Atten-Pose algorithm has a better overall performance and has practical application in the pose estimation task.

Scutellaria barbata D. Don is widely used in TCM clinical practice, so it is important to delve the information of its system biology. In this paper, we integrate its natural compounds and genomics information. The Herb-Prince complex networks algorithm is used to delve potential associated genes, gene families and KEGG signal pathways for Scutellaria barbata D. Don, and the information is verified by literature. The top 100 genes, 4 gene families and 10 KEGG signaling pathways were found. The related results are highly consistent with the clinical and pharmacological studies of Scutellaria barbata D. Don, which provide decision support for researchers to study pharmacological activities of Scutellaria barbata D. Don at the molecular level.

Objective A knowledge graph construction pipeline of traditional Chinese medicine(TCM)diagnosis and treatment was designed and applied,aiming at the automatic construction of the"disease-symptom-pathogenesis-and medicine"knowledge graph based on the medical records of famous TCM physicians,to analyze,organize and present medical records efficiently.Methods Firstly,The entity extraction method of medical records combining Deep Learning and Regular Expression was designed to extract disease,symptom,pathogenesis,and TCM entities from unstructured medical records automatically;secondly,entity relationships were defined and the correlations between entities were calculated using HAN method,and then the"entity-relation-entity"triplets were built;the graph database Neo4j and Gephi were used for knowledge storage and visual display separately;Finally,the application was verified in the Medical records of lung cancer treated by the old famous TCM physicians.Results The precision,Recall and F1 of the knowledge extraction model for medical records entities extraction are 88.49%,90.02%and 89.25%,respectively,and each index is better than the comparison methods.A total of 1077 triples are extracted through entity correlation calculation,and the knowledge graph is successfully constructed.It can reflect the relationship between 'disease-symptom-pathogenesis-medicine' in the treatment of lung cancer by the famous specialists of TCM.Conclusion The method in this paper can effectively solve the extraction,organization and expression of clinical medical records of famous TCM physicians,and realize the automatic construction process from the text of medical records to the knowledge graph.Relevant research ideas and methods proposed in this paper could provide a reference for the construction of the diagnosis and treatment knowledge graph of famous TCM physicians based on medical records.

Objective Aiming at the problems of many items and long time to fill in the Constitution in Chinese Medicine Questionnaire(CCMQ)when evaluating individual constitution,the research uses artificial intelligence technology to select attributes,and to help construct a short version of the CCMQ.Methods Analyzing the constitution data provided by the Physical Examination Department of Jiangsu Province Hospital of Traditional Chinese Medicine,there are specific target variables as the classification of constitution types.Feature selection of genetic algorithm,cross-validation and KNN classification algorithm are used as filters to select problems,and the effect is evaluated by problem subset size,KNN classification accuracy and filling time.Results The method selected a short version of the CCMQ with 31 problems,and the average classification accuracy in the model was 86.16%,and the time was improved by 47.7%.Conclusion The algorithm can effectively find a better problem subset,achieve dimensionality reduction and have certain accuracy,thus helping to simplify the CCMQ.

Objective To propose a drug pair extraction algorithm integrating co-occurrence and semantic information for prescription data.Methods The prescription data were transformed into matrix data,and the association information between drugs was calculated as the initial screening index.Then the word vector was constructed based on the prescription data,and the semantic similarity between drugs was calculated as the second screening index,so as to extract potential drug pairs.The algorithm of this paper and the classical Apriori algorithm were experimented on 1090 lung cancer outpatient prescriptions respectively,and the experimental extraction results were compared and analyzed,so as to verify the usability and effectiveness of this drug pair extraction algorithm.Results Compared with the Apriori algorithm,the present algorithm had better effect in extracting drug pairs,which could reasonably help to narrow down the range of options of potential drug pairs under the situation of large difference in drug frequencies,and successfully extracted 88 groups of drug pairs in medical cases under the range of recommended threshold settings.Conclusion The method of word frequency combined with semantic information for extracting potential drug pairs is feasible and effective,and can provide methodological reference for experience mining in clinical prescription medication.

Objective To construct a precise model for identifying traditional Chinese medicine(TCM)constitutions,thereby offering optimized guidance for clinical diagnosis and treatment plan-ning,and ultimately enhancing medical efficiency and treatment outcomes. Methods First,TCM full-body inspection data acquisition equipment was employed to col-lect full-body standing images of healthy people,from which the constitutions were labelled and defined in accordance with the Constitution in Chinese Medicine Questionnaire(CCMQ),and a dataset encompassing labelled constitutions was constructed.Second,heat-suppres-sion valve(HSV)color space and improved local binary patterns(LBP)algorithm were lever-aged for the extraction of features such as facial complexion and body shape.In addition,a dual-branch deep network was employed to collect deep features from the full-body standing images.Last,the random forest(RF)algorithm was utilized to learn the extracted multifea-tures,which were subsequently employed to establish a TCM constitution identification mod-el.Accuracy,precision,and F1 score were the three measures selected to assess the perfor-mance of the model. Results It was found that the accuracy,precision,and F1 score of the proposed model based on multifeatures for identifying TCM constitutions were 0.842,0.868,and 0.790,respectively.In comparison with the identification models that encompass a single feature,either a single facial complexion feature,a body shape feature,or deep features,the accuracy of the model that incorporating all the aforementioned features was elevated by 0.105,0.105,and 0.079,the precision increased by 0.164,0.164,and 0.211,and the F1 score rose by 0.071,0.071,and 0.084,respectively. Conclusion The research findings affirmed the viability of the proposed model,which incor-porated multifeatures,including the facial complexion feature,the body shape feature,and the deep feature.In addition,by employing the proposed model,the objectification and intel-ligence of identifying constitutions in TCM practices could be optimized.