The number of papers in all areas of science increased over the last ten years, leading it to be considered Big Data. Thus, according to the PubMed database, the number of papers in the field of medicine and biology over the last year amounted to more than a million. MeSH indexing terms (the main headings and subheadings) are served as a rich resource for extracting a broad range of domain knowledge. Automated analysis and comparison of MeSH terms of the papers allowed the formation of groups of relevant papers in accordance with user-defined criteria and highlighting key concepts within the groups of papers, expressed in the form of relationship between MeSH or other concepts.
Using text-mining algorithm in automatic mode, publications available in the PubMed retrieved by the keywords “Precision medicine”, “Personalized medicine” and “Digital medicine” were analyzed for decipher the trends of scientific articles in the field of personalized medicine over the past. The simple idea of using text-mining tools allows users to form concept-centered semantic networks (maps) based on real-time Pubmed-available knowledge. Networks represent relationships between various objects: genes (proteins), MeSH, chemical compounds, diseases, etc. Semantic networks were visualized using Cytoscape according to the matrix of similarity, and the distance between the nodes (concepts) was correlated with the normalized number of scientific articles. Analysis of changes in time the concept-centered semantic networks allows us to find the main trends and key concepts in a given subject area.
Acknowledgement. This work supported by RFBR grant (#19-29-01138).