English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Not only the safety of medicines themselves, from the perspective of medicinal properties, but also the safety of medicine usage is important, in order to ensure the right use of the right medicines and prevent medical accidents. The author has applied data-mining techniques to the analyses of data to investigate the status about the safety of medicine usage, such as the data in the database of medical near-miss cases which have been collected by Japanese government, the investigation data to understand how patients handle the injection device for anti-diabetic drug by themselves after the guidance by a doctor, the questionnaire data asking opinions about the mark indicating a medical property on some cardiac transdermal patch, which were provided by medical experts and/or pharmaceutical companies. The analyses on such data have been traditionally based on the statistical approaches, which bring us the information about the single attribute of data, for instance, the tables showing the frequency of events under some condition and the analysis whether the difference of the frequency is statistically significant, and so on. It is, however, important to extract the information not only of the each attribute independently but also about the relations among them, since each data in the results of the investigations is supposed to be generated under complex conditions, some set of which is an essential cause. In order to find the relationships of data or the items of the data, it is useful to utilize the clustering algorithms to classify the data into some clusters, in each of which data have the same characteristics, and the decision tree algorithms to find the condition to distinguish the data based on the classes to which they belong, from in rough to in detail. By means of both algorithms, we can find a structure among the data, which kinds of data we have obtained and which conditions generate such kinds of data. In this paper, we first make a brief review of some clustering algorithms including agglomerated hierarchical clustering algorithm, TwoStep clustering algorithm and K-means algorithm with the number of seeds optimized by Bayesian information criterion (BIC) and also show how to combine them to the idea of specialization coefficients. Next, we introduce the review of the application to the data related to the safety of medicine usage shown above. Last, we summarize the principle of application of data mining to such analyses.

Application of Data Mining Techniques to the Data Analyses to Ensure Safety of Medicine Usage