Mining time dependency patterns in clinical pathways

Clinical pathways are widely adopted by many large hospitals around the world in order to provide high-quality patient treatment and to reduce the length of hospital stay of each patient. The development of clinical pathways is a lengthy process, and may require the collaboration among physicians, nurses and other staff in a hospital. However, individual differences cause great variance in the execution of clinical pathways. This calls for a more dynamic and adaptive process to improve the performance of clinical pathways. This paper proposes a data mining technique to discover the time-dependency patterns of clinical pathways for curing brain strokes. The purpose of mining time-dependency patterns is to discover patterns of process execution sequences and to identify the dependent relations between activities in a majority of cases. By obtaining the time-dependency patterns, we can predict the paths for new patients when they are admitted to a hospital, and, in turn, the health care procedure will then be more effective and efficient.

[1]  K. Aho,et al.  Cerebrovascular disease in the community: results of a WHO collaborative study. , 1980, Bulletin of the World Health Organization.

[2]  C. Ireson.  Critical pathways: effectiveness in achieving patient outcomes. , 1997, The Journal of nursing administration.

[3]  X.S. Wang,et al.  Discovering Frequent Event Patterns with Multiple Granularities in Time Sequences , 1998, IEEE Trans. Knowl. Data Eng..

[4]  Ramakrishnan Srikant,et al.  Mining sequential patterns , 1995, Proceedings of the Eleventh International Conference on Data Engineering.

[5]  F. Vanclay,et al.  Functional outcome measures in stroke rehabilitation. , 1991, Stroke.

[6]  R. Iorio,et al.  Impact of a clinical pathway and implant standardization on total hip arthroplasty: a clinical and economic study of short-term patient outcome. , 1998, The Journal of arthroplasty.

[7]  D C Kibbe,et al.  Applying clinical informatics to health care improvement: making progress is more difficult than we thought it would be. , 1997, The Joint Commission journal on quality improvement.

[8]  B Cooper,et al.  Stroke rehabilitation: Australian patient profile and functional outcome. , 1991, Journal of clinical epidemiology.

[9]  Dimitrios Gunopulos,et al.  Mining Process Models from Workflow Logs , 1998, EDBT.

[10]  Kazuo J. Ezawa,et al.  Constructing Bayesian Networks to Predict Uncollectible Telecommunications Accounts , 1996, IEEE Expert.

[11]  J. Nunamaker,et al.  Proceedings of the 32nd Hawaii International Conference on System Sciences , 1999 .

[12]  James A. Haley,et al.  Successful Experiences with Clinical Pathways in Rehabilitation , 1998 .

[13]  M. Dombovy,et al.  Rehabilitation for stroke: a review. , 1986, Stroke.

[14]  G. Ross,et al.  Evaluation of a critical pathway for stroke , 1997, The Journal of the American Osteopathic Association.

[15]  I R Odderson,et al.  A Model for Management of Patients With Stroke During the Acute Phase: Outcome and Economic Implications , 1993, Stroke.

[16]  Lawrence M. Fagan,et al.  Medical Informatics: Computer Applications in Health Care , 1991 .

[17]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[18]  A Pedersen.  A data-driven approach to work redesign in nursing units. , 1997, The Journal of nursing administration.

[19]  A H Rosenstein,et al.  Using information management to implement a clinical resource management program. , 1997, The Joint Commission journal on quality improvement.