TCM herbal prescription recommendation model based on multi-graph convolutional network.

ETHNOPHARMACOLOGICAL RELEVANCE: The recommendation of herbal prescriptions is a focus of research in traditional Chinese medicine (TCM). Artificial intelligence (AI) algorithms can generate prescriptions by analysing symptom data. Current models mainly focus on the binary relationships between a group of symptoms and a group of TCM herbs. A smaller number of existing models focus on the ternary relationships between TCM symptoms, syndrome-types and herbs. However, the process of TCM diagnosis (symptom analysis) and treatment (prescription) is, in essence, a "multi-ary" (n-ary) relationship. Present models fall short of considering the n-ary relationships between symptoms, state-elements, syndrome-types and herbs. Therefore, there is room for improvement in TCM herbal prescription recommendation models. PURPOSE: To portray the n-ary relationship, this study proposes a prescription recommendation model based on a multigraph convolutional network (MGCN). It introduces two essential components of the TCM diagnosis process: state-elements and syndrome-types. METHODS: The MGCN consists of two modules: a TCM feature-aggregation module and a herbal medicine prediction module. The TCM feature-aggregation module simulates the n-ary relationships between symptoms and prescriptions by constructing a symptom-'state element'-symptom graph (Se) and a symptom-'syndrome-type'-symptom graph (Ts). The herbal medicine prediction module inputs state-elements, syndrome-types and symptom data and uses a multilayer perceptron (MLP) to predict a corresponding herbal prescription. To verify the effectiveness of the proposed model, numerous quantitative and qualitative experiments were conducted on the Treatise on Febrile Diseases dataset. RESULTS: In the experiments, the MGCN outperformed three other algorithms used for comparison. In addition, the experimental data shows that, of these three algorithms, the SVM performed best. The MGCN was 4.51%, 6.45% and 5.31% higher in Precision@5, Recall@5 and F1-score@5, respectively, than the SVM. We set the K-value to 5 and conducted two qualitative experiments. In the first case, all five herbs in the label were correctly predicted by the MGCN. In the second case, four of the five herbs were correctly predicted. CONCLUSIONS: Compared with existing AI algorithms, the MGCN significantly improved the accuracy of TCM herbal prescription recommendations. In addition, the MGCN provides a more accurate TCM prescription herbal recommendation scheme, giving it great practical application value.

Comprehensive evaluation and scenario simulation for the water resources carrying capacity in Xi'an city, China.

The quantity and quality of water resources are of great importance in maintaining urban socio-economic development. Accordingly, substantial research has been conducted on the concept of the water resources carrying capacity (WRCC). In this study, analytic hierarchy process (AHP) and system dynamics (SD) models were combined to construct a multi-criteria evaluation system of the WRCC and a socio-economic/water resources SD model for Xi'an. The developmental trends of the society, economy, water supply/demand, and wastewater discharge were obtained from 2015 to 2020 using five scenarios designed for distinct purposes; these scenarios and trends were comprehensively evaluated using a combination of qualitative and quantitative analyses. The results indicated that the WRCC (0.32 in 2020) in Xi'an will shift from a normal to a poor state if the current social development pattern is maintained; therefore, we conclude that the socio-economic development of Xi'an is unsustainable. However, under a comprehensive scheme, the WRCC index (0.64 in 2020) will increase by 48% compared with the WRCC index under a business-as-usual scenario. Further, some practical suggestions, including the promotion of industrial reforms and the improvement of water-use efficiency and recycling policies, were provided for improving the regional WRCC.