Towards data: a human/machine-oriented approach of medical data collection

Abstract

More than twenty years have passed since clinical data were computerized as a hospital information system, whose stored data include all the histories of clinical activities in a hospital, including accounting information, medical image, laboratory data and electronic patient records. Due to the traceability of all the information, a hospital cannot function without its information system. Furthermore, if it is extended into electronic healthcare records, it may not be a dream for each patient to benefit from their personal database with all the healthcare information. Recent advances in data mining will support this trend: analysis of such large scale databases enable us to visualize and capture what we have not seen only from clinical sites. However, it is notable that conventional computerized data are described by medical staff or measured by various kinds of medical instruments. They can be viewed as summaries of clinical processes, which remove background information behind the observations. Thus, analysis based on these data cannot overcome their limitations. One of the reasons why data mining is not successful for medical risk is that it takes a long time even for medical staff to interpret the results obtained and fill the gap between their knowledge and extracted patterns. If we want to go beyond these summaries and to get more information in order to capture the whole clinical actions or patients' behavior, we have to monitor and store their details through more sophisticated methods, such as sensor networks. For example, if we want to prevent medical incidents, in-hospital infections we have to monitor the behavior of medical staff, and if we want to prevent chronic diseases (metabolic syndromes) in an efficient way, we have to monitor the measurements of behavior of patients. Thus, although "On data" approaches are important for future medicine and healthcare, Ones of "Towards data" are more important for IT-oriented future development of these fields, which has been proposed by the organizer [1]. These data collection and their analysis will be new challenges for healthcare IT and thanks to the recent developments of sensors and devices: it will not be a dream or science fiction. This panel gives recent advances in IT technology for data collection, their problems and their future vision: not only hardware-based or sensor-based, but also human-oriented, or human-agent-interaction based will be discussed by the panelists who play important roles in building up these fields.