Effects of three plant extracts (Hordeum vulgare L., Apocynum Venetum L., Brasenia schreberi J.F.G mel.) on human gingival fibroblasts were examined. As a result, we observed the promoting effect of the extract of Hordeum vulgare L. and the extract of Apocynum Venetum L. respectively on FGF2 and FGF7 production. Moreover, the mixture of the three plant extracts showed the effect of improving the changes in type I collagen gene expression and matrix metalloproteinase 1 gene expression by LPS addition. Next, a dentifrice containing the three plant extracts was subjected to human efficacy trials. We measured periodontal pocket depth, attachment level, bleeding on probing and saliva TNFα as an indicator of periodontal disease. The results suggest that the dentifrice formulated with the three plant extracts were effective for the improvement of periodontal disease.

Objective:The topic model is a well-known method used in the field of natural language processing (NLP)that defines adocument as constructed of topics that combine specific t erms. This method is used to model topic co-occurrencemathematically. In this study,we extracted topics from featu re vectors of explicit documents called medical package insertsby using cluster analysis. Methods:We counted the terms(nouns)recognized by the morphological analysis engine MeCab and created a documentterm matrix. A value of“tf・idf”was calculated in this matrix for term weighting to avoid the effect of term frequency. We reduced the dimensionality of the matrix using singular v alue decomposition,which removed unnecessary data,and weextracted feature vectors attributed to each medical package insert. The distance between feature vectors was calculatedusing cosine distance,and cluster analysis was performed based on the distance between the vectors.Results:Cluster analysis on our document-term matrix show ed that medical package inserts of drugs that have the sameefficacy or active ingredient were included in the same cl uster. Moreover, using term weighting and dimensionalityreduction,we could extract topics from medical package inserts.Conclusion:We obtained a foothold to apply our findings t o the recommendation of similar drugs. Cluster analysis ofmedical package inserts using NLP can contribute to the pro per application of drugs. In addition,our study revealed thesimilarities of drugs and suggested possibilities for new applications from several points of view.