Enhancing care services quality of nursing homes using data mining
By: CHENG, Bor-Wen.
Contributor(s): CHANG, Chun-Lang | LIU, I-Sheng.
Material type: ArticlePublisher: UK : Routledge, July 2005Subject(s): Nursing home | Customer relationship management | Data mining | Care services qualityTotal Quality Management & Business Excellence 16, 5, p. 575 - 596 Abstract: Taiwan has formally stepped into an ageing society since September 1993. As of April 2003, the elderly population nationwide has taken 9.09% of the total population, with nearly 2.05 million people. As the population structure is ageing, disease styles and family structures are changing, employment rate of women is increasing, human dignity and life quality is improving, and the number of the disabled is increasing, the needs for long-term care is evolving. Among various available resources, nursing homes that are equipped with professional care services are especially in demand. Therefore, the quality of their care services is an important agenda that deserves national emphasis. This research aims to understand the characteristics of the residents through data mining, the core technology of customer relationship management. Meanwhile, it explores the customized care service strategy for the residents by interviews with professionals to establish ongoing interactive relations between the institutes and the residents and their families. Hence, this research effectively divided the residents into four clusters, using data mining cluster analysis. Among all, there are 218 persons in the cluster whose residents have the most frequent acute ward stay, which takes 53.59% of the research subject. The cluster whose residents can simply maintain limited self-care has 131 persons, which takes 32.19%. The cluster whose residents have the most stable health conditions has 42 persons, which takes 10.32%. The cluster whose residents have the longest average residing period has 16 persons, which takes 3.9%. This research adopted interviews with professionals, focusing on the above four clusters to develop customized care service strategy, to provide an important referential foundation for nursing homes in their daily care services.Taiwan has formally stepped into an ageing society since September 1993. As of April 2003, the elderly population nationwide has taken 9.09% of the total population, with nearly 2.05 million people. As the population structure is ageing, disease styles and family structures are changing, employment rate of women is increasing, human dignity and life quality is improving, and the number of the disabled is increasing, the needs for long-term care is evolving. Among various available resources, nursing homes that are equipped with professional care services are especially in demand. Therefore, the quality of their care services is an important agenda that deserves national emphasis. This research aims to understand the characteristics of the residents through data mining, the core technology of customer relationship management. Meanwhile, it explores the customized care service strategy for the residents by interviews with professionals to establish ongoing interactive relations between the institutes and the residents and their families. Hence, this research effectively divided the residents into four clusters, using data mining cluster analysis. Among all, there are 218 persons in the cluster whose residents have the most frequent acute ward stay, which takes 53.59% of the research subject. The cluster whose residents can simply maintain limited self-care has 131 persons, which takes 32.19%. The cluster whose residents have the most stable health conditions has 42 persons, which takes 10.32%. The cluster whose residents have the longest average residing period has 16 persons, which takes 3.9%. This research adopted interviews with professionals, focusing on the above four clusters to develop customized care service strategy, to provide an important referential foundation for nursing homes in their daily care services.
There are no comments for this item.