Résumé
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.
Résumé
Academic detailing is rarely practised in developing countries. A randomized control trial on healthcare service was conducted to evaluate the impact of academic detailing programme on the adherence of primary healthcare providers in Banke district, Nepal, to childhood diarrhoea treatment guidelines recommended by World Health Organization/United Nations Children’s Fund (WHO/UNICEF). The participants (N=209) were systematically divided into control and intervention groups. Four different academic detailing sessions on childhood diarrhoea management were given to participants in the intervention group. At baseline, 6% of the participants in the control and 8.3% in the intervention group were adhering to the treatment guidelines which significantly (p<0.05) increased among participants in the intervention (65.1%) than in the control group (16.0%) at the first follow-up. At the second follow-up, 69.7% of participants in the intervention group were adhering to the guidelines, which was significantly (p<0.05) greater than those in the control group (19.0%). Data also showed significant improvement in prescribing pattern of the participants in the intervention group compared to the control group. Therefore, academic detailing can be used for promoting adherence to treatment guidelines in developing countries, like Nepal.