Tutorial Lectures       


 Tutorial Lectures:

" Information Reuse in Hospital Information System: New Trends in Data-Oriented Hospital Management "

Shusaku Tsumoto
Department of Medical Informatics, Faculty of Medicine, Shimane University .


Twenty years have passed since clinical data were stored electronically as a hospital information system. Stored data give all the histories of clinical activities in a hospital, including accounting information, laboratory data and electronic patient records. Due to the traceability of all the information, a hospital cannot function without the information system. Reuse of data as data mining in hospital information is a first step to innovative intelligent hospital services, which consists of the following three layers of hospital management: services for hospital management, devices for medical staff and services for patients. Data mining in hospital information system plays a central role in achieving these layers. In this tutorial, a general framework on innovation of hospital services based on data mining is presented and applied to data extracted from HIS in order to capture the characteristics of clinical activities in hospital as shown in the following illustrative examples. First, the chronological overview of hospital activities is shown: periodical behavior of the number of orders can be viewed as a "life-cycle" of a hospital. Secondly, a pattern of long-term follow up patients is extracted with respect to the number of orders by using HIS data. Thirdly, trajectories mining technique is applied to temporal analysis the number of orders. Finally, similarity-based analysis is applied to temporal trends of the numbers of nursing orders for several diseases.

" New Concepts and Trends in the MCDM Field for Solving Actual Problems - New Hybrid MCDM Model"

Gwo-Hshiung Tzeng, Distinguished Chair Professor
Graduate Institute of Project Management, Kainan University
Institute of Management of Technology, National Chiao Tung University


   How trends in future prospects? Which problems will be improved for satisfying the users'/customers'/social needs in marketing situations and how overall considering problems in dimensions and criteria can be achieved the aspiration levels? However, we find that the traditional MCDM field ignored some important new concepts and trends, needed some assumptions limit/defects to solve actual real-world problems. Therefore in our researches some new concepts and trends in the MCDM field for solving actual problems have been proposed as follows. First, the traditional model assumes that the criteria in value-created are independent and hierarchical in structure; however, criteria are often interdependent in real-world problems; because "Statistics and Economics are unrealistic in the real world", so DEMATEL technique can be used to find the interrelationship matrix and build a influential network relation map (INRM) for solving the relationship problems in the real world. Second, the relative good solution from the existing alternatives is replaced by the aspiration levels to avoid "Choose the best among inferior choices/alternatives", i.e., avoid "Pick the best apple among a barrel of rotten apples". Third, the emphasis in the field has shifted from ranking and selection when determining the most preferable approaches to performance improvement of existing methods based on INRM, because "we need a systematic approach to problem-solving; instead of addressing the systems of the problem, we need to identify the sources of the problem". Fourth, information fusion/aggregation such as fuzzy integrals, basically, a non-additive/super-additive model, has been developed to aggregate the performances. Therefore, in order to overcome the defects of conventional MADM method, we have focused on developing a series of new Hybrid Dynamic Multiple Criteria Decision Making (HDMADM) method for solving the complication dynamic problems in real world and applying to improve the real issues in the trends and prospects. Finally some empirical real cases are illustrated to demonstrate effectiveness of the proposed new hybrid MADM methods. From those real cases, the best performance improvement strategies can be devised to provide the most suitable/reasonable effective and efficient strategies for improving the gaps to reach the aspiration level. Fifth, we proposed a new thinking of MODM models with changeable spaces to help the decision-makers for win-win planning/designing to achieve the aspiration level, which is better than to achieve the ideal point or Pareto optimal solutions.
Keywords: Information technology, Internet communication, hybrid MCDM, MADM, MODM, DEMATEL, DANP, VIKOR, changeable space, aspiration level



Copyright © ITQM 2013  All rights are reserved.