Japan Journal of Medical Informatics
Online ISSN : 2188-8469
Print ISSN : 0289-8055
ISSN-L : 0289-8055
Current issue
Showing 1-5 articles out of 5 articles from the selected issue
Original Article-Technical
  • R Matsuo, Ho TB, M Ikeda, K Tanaka, W Chen
    2018 Volume 38 Issue 2 Pages 69-79
    Published: June 15, 2018
    Released: June 26, 2019

     In this paper, we consider a methodology of the object-oriented term weighting, by using a hierarchical structure of terms in medical documents according to analytical purposes. The hierarchical term classification exploits logical negation and medical information of ranking corresponding to ICD-10 codes and consists of the category of terms as the nodes. It is employed to generate weighting rules for the object-oriented term weighting and we capture the order relation among the categories by giving the weights based on analytical purposes to the categories. Specifically, we generate three weighting rules from two features of the hierarchical term classification: the term hierarchy and the exploitation of medical information of ranking, and give higher weight to terms where it is located at the deep layer, non-negative terms’ categories and the higher rank in the hierarchy as important terms for a certain analytical purpose. The experimental results on mortality prediction which is one of the analytical purposes have indicated the effectiveness of the object-oriented term weighting. Therefore, it was suggested that the proposed methodology of the object-oriented term weighting is effective. Although, we regard the terms which correspond to ICD-10 as the dependent and important terms for analytical purposes, we considered the exploitation of machine learning techniques to capture the similar dependencies regarding analytical purposes for the terms which do not correspond to ICD-10. The proposed methodology and the order relation among terms’ categories derived from the weighting rules, a dictionary of terms and the weights have potential to contribute to the enhancement of knowledge acquisition support by big data analysis in medical domain.

    Download PDF (718K)
Review Article
  • H Tsukuma, T Shimakawa, T Tanaka, M Ikeuchi
    2018 Volume 38 Issue 2 Pages 81-104
    Published: June 15, 2018
    Released: June 26, 2019

     The recent survey for the Healthcare Information Technologists (HCITs) in the Chugoku region shows that over 60% of them understand the 3C (Communication, Collaboration, Coordination) of HCIT insufficiently. The authors thus clarify what kinds of approaches to educate HCITs working at healthcare fields practically are discussed in the academic papers and proceedings concerning the medical informatics. Searching from the database of the Japan Medical Abstracts Society, the Proceedings of the Joint Conference on Medical Informatics and Japan Journal of Medical Informatics, the authors extract documents including the word “Healthcare Information Technologist”, then classify them by other keywords concerning these documents such as “management”, “the 3C”, etc. The authors found that the documents discussing the 3C and its similar concepts are hardly published after 2011. The authors assert that the way of learning the basic concepts of HCIT such as the 3C must be reviewed.

    Download PDF (2364K)
Proceedings of the Spring Meeting on Medical Informatics
  • S Nishida, K Jingushi, D Furushima, N Yamamoto, T Iwao, T Yamada
    2018 Volume 38 Issue 2 Pages 105-113
    Published: June 15, 2018
    Released: June 26, 2019

     In clinical studies, data management is very important for ensuring the data quality and adequate statistical analyses. When performing a data check, either a sight check using human eyes or a logical check using a computer is carried out. In recent years, electronic data capture (EDC) systems having been used to assess the data consistency or to check for missing data at the same time as data entry; however, this check method is not sufficient. Therefore, data managers are required to check the data files exported from EDC systems. However, most clinical data managers are medical experts without advanced programming skills at academic data coordinating centers. The objective of this study was to develop a versatile software program with a graphical user interface to help data managers clean up data easily and efficiently for clinical research. In order to achieve versatility, the program needed to be able to unify the data structure, merge multiple files, and automatically create a specifications check file. We applied the developed software program to two different types of clinical trials and verified its function and effectiveness. Compared with a sight check, our program was thus found to be cost-efficient in terms of time and labor.

    Download PDF (1386K)
Interest Material
  • Y Kuramoto, Y Nakanishi, K Udo, Y Iwasaki, Carlisle St M, S Otsuka
    2018 Volume 38 Issue 2 Pages 115-124
    Published: June 15, 2018
    Released: June 26, 2019

     In the past, collecting medical statistics based on patients’ main complaints was difficult, as researchers had to manually compile information from medical questionnaires. The solution was to use terminals, such as iPads. However, most of the patients visiting hospitals would be elderly people, and using such terminals was difficult for them. To address this problem, nurses will require patients to fill out their medical paper questionnaires as before, and then using OCR technology, the nurses will scan the questionnaires on a scanner; these will then be digitized and verified by a system that we developed. Demonstrating that the system could be used as a primary method to collect medical records and can also be used as a secondary method to aid and support management is possible. It is also an advantage that this system can easily be introduced in the form of adding it to the existing electronic medical record without accompanying large-scale repair of the electronic medical record.

    Download PDF (1223K)
  • S Matsushima, M Ito, H Yoshida, R Fukuda, N Yamashita
    2018 Volume 38 Issue 2 Pages 125-136
    Published: June 15, 2018
    Released: June 26, 2019

     [Objective] The objective was to reveal the perspective from which members of the community examine information about health food products and to investigate related factors.

     [Method] Participants were 188 community residents in their 40s to 60s in Ehime Prefecture. An anonymous, self-report questionnaire was administered on participant attributes, perspective on information when buying health food products, health literacy, health consciousness, health status, and experience using health food products.

     [Results] The most checked items when buying health food products were notes on intake method, intake amount, and warnings, with 77.7% of participants, followed by nutritional composition and the amount of other ingredients at 76.9%. The least checked items were whether there were articles reported about the product at 33.1%, followed by whether there was research with human subjects at 59.2%. Participants’ sex, experience using health food products, and health literacy were significantly related to their perspective on information when buying health food.

     [Conclusion] As confirmation of items related to scientific evidence were insufficient and health literacy was related to perspective on information, it is necessary to educate people on the way of looking at information and the method of obtaining information is necessary.

    Download PDF (839K)