Summarizing clinical pathways from event logs

Clinical pathway analysis, as a pivotal issue in ensuring specialized, standardized, normalized and sophisticated therapy procedures, is receiving increasing attention in the field of medical informatics. Research in clinical pathway analysis has so far mostly focused on looking at aggregated data seen from an external perspective, and only provide very limited insight into the pathways. In some recent work, process mining techniques have been studied in discovering clinical pathway models from data. While it is interesting, discovered models may provide too much detail to give a comprehensive summary of the pathway. Moreover, the number of patterns discovered can be large. Alternatively, this article presents a new approach to build a concise and comprehensive summary that describes the entire structure of a clinical pathway, while revealing essential/critical medical behaviors in specific time intervals over the whole time period of the pathway.

The presented approach summarizes a clinical pathway from the collected clinical event log, which regularly records all kinds of patient therapy and treatment activities in clinical workflow by various hospital information systems. The proposed approach formally defines the clinical pathway summarization problem as an optimization problem that can be solved in polynomial time by using a dynamic-programming algorithm. More specifically, given an input event log, the presented approach summarizes the pathway by segmenting the observed time period of the pathway into continuous and overlapping time intervals, and discovering frequent medical behavior patterns in each specific time interval from the log.

The proposed approach is evaluated via real-world data-sets, which are extracted from Zhejiang Huzhou Central hospital of China with regard to four specific diseases, i.e., bronchial lung cancer, colon cancer, gastric cancer, and cerebral infarction, in two years (2007.08-2009.09). Although the medical behaviors contained in these logs are very diverse and heterogeneous, experimental results indicates that the presented approach is feasible to construct condensed clinical pathway summaries in polynomial time from the collected logs, and have a linear scalability against the increasing size of the logs.

Experiments on real data-sets illustrate that the presented approach is efficient and discovers high-quality results: the observed time period of a clinical pathway is correctly segmented into a set of continuous and overlapping time intervals, in which essential/critical medical behaviors are well discovered from the event log to form the backbone of a clinical pathway. The experimental results indicate that the generated clinical pathway summary not only reveals the global structure of a pathway, but also provides a thorough understanding of the way in which actual medical behaviors are practiced in specific time intervals, which might be essential from the perspectives of clinical pathway analysis and improvement.