Stage Division and Pattern Discovery of Complex Patient Care Processes

This paper studies the design of a clinical pathway that defines medical service activities within each stage of a patient care process. Much prior research has developed clinicM process models that consider the trajectory of services occurring in a care process, by using data mining techniques on process execution logs. A novel approach that provides a more efficient way of clinical pathway design is introduced in this paper. Based on the strategy of TEI@I methodology, the proposed approach integrates statistical methods, optimization techniques and data mining. With the preprocessed data, a complex care process is subsequently divided into several medical stages, and then the patterns of each stage are identified, and thus a clinical pathway is developed. Finally, the proposed method is applied to the real world, using archival data derived from a hospital in Beijing, about three diseases that involve various departments, with an average of 300 samples for each disease. The results of real- world applications demonstrate that the proposed method can automatically and efficiently facilitate clinical pathways design. The main contributions to the field in this paper include （a） a new application of TEI@I methodology in healthcare domain, （b） a novel method for complex processes analysis, （c） tangible evidence of automatic clinical pathways design in the real world.