Knowledge Discovery from Multi-sources Healthcare Informatics

• Main Authors: KAM, Tin Seong, SHARMA, Juhi, WONG, Michael Tack Keong, LAVANYA, Asokan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2012
• Subjects: Healthcare Analytics; Data Mining; Interactive Visual Analytics; Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/1588
• Institution: Singapore Management University

The advances of healthcare informatics technologies and the rapid reduction of their costs provide healthcare service provides with a huge and continuously increasing amount of data about patients, hospital resources, disease diagnosis and electronic patient records. The use of these data, however, tends to confine to simple tabular or dashboard reports. There is a general lack of analysis to optimize the return of investment on the collecting and managing of these data. This explosive growth of healthcare related databases has far outpaced the analyst ability to interpret these data using conventional statistical techniques, creating an urgent need for new techniques to support the healthcare analyst in transforming the data into actionable information and knowledge. Using health screening, fitness challenge, and staff human resource datasets (i.e. medical claims and leaves), this paper demonstrates how actionable insights and knowledge can be discover from these datasets by integrating interactive Exploratory Data Analysis (EDA) and data mining techniques. We will also show the important of data integration as the key success factor in analysis mutli-sources datasets.