An approach to co-medication mechanism mining of Chinese Materia Medica and western medicines based on complex networks with the multi-source heterogeneous information

The co-medication strategy of Chinese Materia Medica (CMM) and western medicines under the holistic integrative medicine (HIM) model offers the advantages of increased efficacy and reduced toxicity, particularly in clinical practice for treating complex and challenging diseases. However, due to the mutual fragmentation of basic theories and principles of medication decision-making between traditional Chinese medicine (TCM) and western medicine, research on the mechanisms for the combined use of CMM and western medicines has become a challenging problem in modern clinical medicine research. Traditional drug combination mining models encounter numerous bottlenecks when dealing with this complex decision-making problem with multi-source information characteristics. This paper aims to mine the optimal drug combination strategy from a real-life decision-making scenario of co-medication between CMM and western medicines. It abstracts this realistic problem as a class of complex network optimal overlapping community detection problem, focusing on solving key difficulties such as the inability of existing drug complex network models to handle the multi-source information of drugs and the randomness in the community detection process. We integrate co-medication prescription information with attribute information to construct the speaker-listener label propagation algorithm based on semantic attribute features (SA-SLPA) and develop a new medicine combination identification strategy based on weighted complex networks. Using 6671 clinically real prescriptions, we conclude that the detection quality of the SA-SLPA method proposed in this paper is improved by up to 78% compared to existing methods. This improvement illustrates the scientificity and effectiveness of the model in this paper and provides new ideas for the application of theoretical models and methods of interdisciplinary disciplines such as decision science, data science, and computational science in the field of modern medicine.