ABSTRACT
Objective: Chemotherapy-induced nausea and vomiting (CINV) can affect a patient’s quality of life and make them resistant to the treatment. We created an electronic patient reported outcome ePRO-linked pharmaceutical management system (PMS) for CINV (CINVePRO) for storing information, such as nausea and vomiting status, food intake, etc., and suggesting the type of anti-nausea medication and dosage changes to the physicians for controlling CINV.Design: At the Gifu University Hospital, the collaborative research institute, inpatients and pharmacists in charge used CINVePRO-PMS, and a questionnaire survey was done to assess the system’s reliability.Methods: The daily entry of data into CINVePRO shows the number and duration of vomiting, degree of nausea, and amount of food consumed and displays a list and graph of these data over time. The PMS enables pharmacists to list the presence or absence of nausea and the number of vomiting for all patients in their charge and record the intervention and display its list.Results: The questionnaire was distributed to 17 inpatients. All patients and pharmacists answered the questionnaire. According to the results of the questionnaire survey of patients, each screen of CINVePRO received a good evaluation that mentioned it was “easy to understand,” “easy to use,” and “especially useful for communicating one’s symptoms.” In addition, the results of a questionnaire survey of the pharmacists revealed that the system was rated as easy to check the patients’ symptoms and practical to use.Conclusion: CINVePRO-PMS was evaluated as a convenient and applicative system. However, linking CINVePRO to the electronic medical record of each hospital is necessary for sharing it among multiple professions.
ABSTRACT
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.